commit 6845db4d2a867f488b8ecb282dda85cedd0af05a Author: aboelhamd Date: Fri Jul 26 23:44:10 2019 +0200 pyhthon script to load models and encoders, to predict new data diff --git a/loadmodels.ipynb b/loadmodels.ipynb new file mode 100644 index 0000000..0531b26 --- /dev/null +++ b/loadmodels.ipynb @@ -0,0 +1,15683 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "%matplotlib inline" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "\n", + "path='/home/aboelhamd/Downloads/sklearn-svm/sklearn-nobad'\n", + "files = {}\n", + "# r=root, d=directories, f=files\n", + "for r, d, f in os.walk(path):\n", + " for file in f:\n", + " files[file]=os.path.join(r, file)\n", + "\n", + "# os.mkdir('models')" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "file name : 40+68_63+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 276" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.5haberser
110.5haberser
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.5 haber ser\n", + "1 1 0.5 haber ser" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.45654482962107334\n", + "model : LinearSVM , score = 0.4637975614023888\n", + "model : RBFSVM , score = 0.31829418475530613\n", + "model : DecisionTree , score = 0.3836062964213818\n", + "model : RandomForest , score = 0.38350158147992314\n", + "model : AdaBoost , score = 0.3617831020952113\n", + "----------------------------------------------\n", + "\n", + "file name : 27+21_106_29+10_30_106_29+10_110_29_106_29+11_30_106_29+11_110_29_106_29+33_1_30_106_29+33_1_110_29_106_29+.csv\n", + "Rules(classes) number : 8\n", + "Words(features) number : 6\n", + "Records number : 120" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.137765unoaportaciónmuyclaroypositivo
110.128679unoaportaciónmuyclaroypositivo
220.119732unoaportaciónmuyclaroypositivo
330.119732unoaportaciónmuyclaroypositivo
440.127315unoaportaciónmuyclaroypositivo
550.127315unoaportaciónmuyclaroypositivo
660.119732unoaportaciónmuyclaroypositivo
770.119732unoaportaciónmuyclaroypositivo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.137765 uno aportación muy claro y positivo\n", + "1 1 0.128679 uno aportación muy claro y positivo\n", + "2 2 0.119732 uno aportación muy claro y positivo\n", + "3 3 0.119732 uno aportación muy claro y positivo\n", + "4 4 0.127315 uno aportación muy claro y positivo\n", + "5 5 0.127315 uno aportación muy claro y positivo\n", + "6 6 0.119732 uno aportación muy claro y positivo\n", + "7 7 0.119732 uno aportación muy claro y positivo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.06703474247602752\n", + "model : LinearSVM , score = 0.10093532974509636\n", + "model : RBFSVM , score = 0.11605573183596676\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.033775670441412345\n", + "----------------------------------------------\n", + "\n", + "file name : 13+37_12+37_113_1+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 117" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.352679hacer50año
110.323660hacer50año
220.323660hacer50año
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.352679 hacer 50 año\n", + "1 1 0.323660 hacer 50 año\n", + "2 2 0.323660 hacer 50 año" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.2942577385293566\n", + "model : LinearSVM , score = 0.3158541827161679\n", + "model : RBFSVM , score = 0.3532454955917427\n", + "model : DecisionTree , score = 0.17141174651482455\n", + "model : RandomForest , score = 0.1712896936630942\n", + "model : AdaBoost , score = 0.1694033114534203\n", + "----------------------------------------------\n", + "\n", + "file name : 76_64+76_91+76_108_68+75_67+75_63_64+75_63_91+75_63_108_68+100_40_64+100_40_91+100_40_108_68+100_37_67+100_37_63_64+100_37_63_91+100_37_63_108_68+.csv\n", + "Rules(classes) number : 14\n", + "Words(features) number : 5\n", + "Records number : 56" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.073716nohaberhablardeemplear
110.071830nohaberhablardeemplear
220.070473nohaberhablardeemplear
330.070710nohaberhablardeemplear
440.070710nohaberhablardeemplear
550.069735nohaberhablardeemplear
660.070710nohaberhablardeemplear
770.072360nohaberhablardeemplear
880.071338nohaberhablardeemplear
990.070000nohaberhablardeemplear
10100.072360nohaberhablardeemplear
11110.072360nohaberhablardeemplear
12120.071338nohaberhablardeemplear
13130.072360nohaberhablardeemplear
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.073716 no haber hablar de emplear\n", + "1 1 0.071830 no haber hablar de emplear\n", + "2 2 0.070473 no haber hablar de emplear\n", + "3 3 0.070710 no haber hablar de emplear\n", + "4 4 0.070710 no haber hablar de emplear\n", + "5 5 0.069735 no haber hablar de emplear\n", + "6 6 0.070710 no haber hablar de emplear\n", + "7 7 0.072360 no haber hablar de emplear\n", + "8 8 0.071338 no haber hablar de emplear\n", + "9 9 0.070000 no haber hablar de emplear\n", + "10 10 0.072360 no haber hablar de emplear\n", + "11 11 0.072360 no haber hablar de emplear\n", + "12 12 0.071338 no haber hablar de emplear\n", + "13 13 0.072360 no haber hablar de emplear" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.07381804243862623\n", + "model : RBFSVM , score = 0.07381804243862623\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 67+63_64+63_91+63_108_68+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 3\n", + "Records number : 116" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.254216encargardeelaborar
110.254216encargardeelaborar
220.247765encargardeelaborar
330.243803encargardeelaborar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.254216 encargar de elaborar\n", + "1 1 0.254216 encargar de elaborar\n", + "2 2 0.247765 encargar de elaborar\n", + "3 3 0.243803 encargar de elaborar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.13992349932223666\n", + "model : LinearSVM , score = 0.19246829395922085\n", + "model : RBFSVM , score = 0.237588422251646\n", + "model : DecisionTree , score = 0.07014294386464993\n", + "model : RandomForest , score = 0.051613671230843566\n", + "model : AdaBoost , score = 0.12037676753559738\n", + "----------------------------------------------\n", + "\n", + "file name : 65+64_63+108_40+108_68_63+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 3\n", + "Records number : 252" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.25472porhaberadoptar
110.25472porhaberadoptar
220.24528porhaberadoptar
330.24528porhaberadoptar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.25472 por haber adoptar\n", + "1 1 0.25472 por haber adoptar\n", + "2 2 0.24528 por haber adoptar\n", + "3 3 0.24528 por haber adoptar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.1854522284236849\n", + "model : LinearSVM , score = 0.20280748827570969\n", + "model : RBFSVM , score = 0.2596570585636813\n", + "model : DecisionTree , score = 0.12557739997430464\n", + "model : RandomForest , score = 0.09485241605291463\n", + "model : AdaBoost , score = 0.1167580398440067\n", + "----------------------------------------------\n", + "\n", + "file name : 7+8+9+10_108_1+11_108_1+33_1_108_1+.csv\n", + "Rules(classes) number : 6\n", + "Words(features) number : 4\n", + "Records number : 48480" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.150565elperiododesesión
110.201926elperiododesesión
220.206313elperiododesesión
330.150565elperiododesesión
440.140065elperiododesesión
550.150565elperiododesesión
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.150565 el periodo de sesión\n", + "1 1 0.201926 el periodo de sesión\n", + "2 2 0.206313 el periodo de sesión\n", + "3 3 0.150565 el periodo de sesión\n", + "4 4 0.140065 el periodo de sesión\n", + "5 5 0.150565 el periodo de sesión" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.16419735349154174\n", + "model : LinearSVM , score = 0.1661864935934602\n", + "model : RBFSVM , score = 0.1609621342969151\n", + "model : DecisionTree , score = 0.15462650678497822\n", + "model : RandomForest , score = 0.15304989039368436\n", + "model : AdaBoost , score = 0.14956443099905853\n", + "----------------------------------------------\n", + "\n", + "file name : 25+26_1+16_106_29_1+10_29_106_29_1+11_29_106_29_1+33_23+33_24_1+33_14_106_29_1+33_1_29_106_29_1+.csv\n", + "Rules(classes) number : 9\n", + "Words(features) number : 6\n", + "Records number : 72" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.118151elcomisióneuropeoyvarioestado
110.105356elcomisióneuropeoyvarioestado
220.118151elcomisióneuropeoyvarioestado
330.106344elcomisióneuropeoyvarioestado
440.103996elcomisióneuropeoyvarioestado
550.118151elcomisióneuropeoyvarioestado
660.105356elcomisióneuropeoyvarioestado
770.118151elcomisióneuropeoyvarioestado
880.106344elcomisióneuropeoyvarioestado
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.118151 el comisión europeo y vario estado\n", + "1 1 0.105356 el comisión europeo y vario estado\n", + "2 2 0.118151 el comisión europeo y vario estado\n", + "3 3 0.106344 el comisión europeo y vario estado\n", + "4 4 0.103996 el comisión europeo y vario estado\n", + "5 5 0.118151 el comisión europeo y vario estado\n", + "6 6 0.105356 el comisión europeo y vario estado\n", + "7 7 0.118151 el comisión europeo y vario estado\n", + "8 8 0.106344 el comisión europeo y vario estado" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.029696334364774767\n", + "model : LinearSVM , score = 0.11456630699260187\n", + "model : RBFSVM , score = 0.11456630699260187\n", + "model : DecisionTree , score = 0.029696334364774767\n", + "model : RandomForest , score = 0.029696334364774767\n", + "model : AdaBoost , score = 0.026728736800260753\n", + "----------------------------------------------\n", + "\n", + "file name : 79+84_63+100_42+100_47_63+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 4\n", + "Records number : 252" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.296603nolohaberhacer
110.224577nolohaberhacer
220.249630nolohaberhacer
330.229190nolohaberhacer
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.296603 no lo haber hacer\n", + "1 1 0.224577 no lo haber hacer\n", + "2 2 0.249630 no lo haber hacer\n", + "3 3 0.229190 no lo haber hacer" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.21821112734051148\n", + "model : LinearSVM , score = 0.2624706289668316\n", + "model : RBFSVM , score = 0.2703155070734252\n", + "model : DecisionTree , score = 0.18376902613505058\n", + "model : RandomForest , score = 0.13061732329930537\n", + "model : AdaBoost , score = 0.13723675459618487\n", + "----------------------------------------------\n", + "\n", + "file name : 21+10_30+10_110_29+11_30+11_110_29+33_1_30+33_1_110_29+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 4\n", + "Records number : 2625" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.153290unomedidamuyconcreto
110.139238unomedidamuyconcreto
220.139238unomedidamuyconcreto
330.144879unomedidamuyconcreto
440.144879unomedidamuyconcreto
550.139238unomedidamuyconcreto
660.139238unomedidamuyconcreto
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.153290 uno medida muy concreto\n", + "1 1 0.139238 uno medida muy concreto\n", + "2 2 0.139238 uno medida muy concreto\n", + "3 3 0.144879 uno medida muy concreto\n", + "4 4 0.144879 uno medida muy concreto\n", + "5 5 0.139238 uno medida muy concreto\n", + "6 6 0.139238 uno medida muy concreto" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.13412142502798866\n", + "model : LinearSVM , score = 0.1353239599793647\n", + "model : RBFSVM , score = 0.1511010967722058\n", + "model : DecisionTree , score = 0.12110940368235748\n", + "model : RandomForest , score = 0.09958795356372663\n", + "model : AdaBoost , score = 0.0963204974632738\n", + "----------------------------------------------\n", + "\n", + "file name : 30+110_29+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 2330" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.5muydiverso
110.5muydiverso
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.5 muy diverso\n", + "1 1 0.5 muy diverso" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.4861290996488517\n", + "model : LinearSVM , score = 0.4869539176571576\n", + "model : RBFSVM , score = 0.3770546423512336\n", + "model : DecisionTree , score = 0.45048994630836775\n", + "model : RandomForest , score = 0.44570368285343176\n", + "model : AdaBoost , score = 0.4438495914597549\n", + "----------------------------------------------\n", + "\n", + "file name : 64+91+108_68+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 2\n", + "Records number : 8310" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.333705deexaminar
110.334584deexaminar
220.331712deexaminar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.333705 de examinar\n", + "1 1 0.334584 de examinar\n", + "2 2 0.331712 de examinar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.33265543433716654\n", + "model : LinearSVM , score = 0.3397881270396379\n", + "model : RBFSVM , score = 0.24434363205564905\n", + "model : DecisionTree , score = 0.3232987533102557\n", + "model : RandomForest , score = 0.30205680231298204\n", + "model : AdaBoost , score = 0.3089100161490987\n", + "----------------------------------------------\n", + "\n", + "file name : 84+100_47+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 3\n", + "Records number : 478" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.5tambiénloponer
110.5tambiénloponer
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.5 también lo poner\n", + "1 1 0.5 también lo poner" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.5010828716535284\n", + "model : LinearSVM , score = 0.4840620915843279\n", + "model : RBFSVM , score = 0.34143532748351807\n", + "model : DecisionTree , score = 0.40254761567725456\n", + "model : RandomForest , score = 0.4106106872301484\n", + "model : AdaBoost , score = 0.4203780289178144\n", + "----------------------------------------------\n", + "\n", + "file name : 64_64+64_108_68+91_64+91_108_68+108_38+108_68_64+108_68_108_68+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 4\n", + "Records number : 14" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.141119dellegaracumplir
110.141119dellegaracumplir
220.142141dellegaracumplir
330.142141dellegaracumplir
440.151996dellegaracumplir
550.140742dellegaracumplir
660.140742dellegaracumplir
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.141119 de llegar a cumplir\n", + "1 1 0.141119 de llegar a cumplir\n", + "2 2 0.142141 de llegar a cumplir\n", + "3 3 0.142141 de llegar a cumplir\n", + "4 4 0.151996 de llegar a cumplir\n", + "5 5 0.140742 de llegar a cumplir\n", + "6 6 0.140742 de llegar a cumplir" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.141119\n", + "model : LinearSVM , score = 0.151996\n", + "model : RBFSVM , score = 0.151996\n", + "model : DecisionTree , score = 0.151996\n", + "model : RandomForest , score = 0.140742\n", + "model : AdaBoost , score = 0.151996\n", + "----------------------------------------------\n", + "\n", + "file name : 42+45_63+47_63+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 21" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.348117lohaberaprobar
110.315264lohaberaprobar
220.336619lohaberaprobar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.348117 lo haber aprobar\n", + "1 1 0.315264 lo haber aprobar\n", + "2 2 0.336619 lo haber aprobar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.16708374376704985\n", + "model : LinearSVM , score = 0.2792618308656347\n", + "model : RBFSVM , score = 0.2792618308656347\n", + "model : DecisionTree , score = 0.07951611775934861\n", + "model : RandomForest , score = 0.07951611775934861\n", + "model : AdaBoost , score = 0.07951611775934861\n", + "----------------------------------------------\n", + "\n", + "file name : 16+10_29+11_29+33_14+33_1_29+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 3\n", + "Records number : 114920" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.209393elserviciocompetente
110.194581elserviciocompetente
220.192052elserviciocompetente
330.209393elserviciocompetente
440.194581elserviciocompetente
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.209393 el servicio competente\n", + "1 1 0.194581 el servicio competente\n", + "2 2 0.192052 el servicio competente\n", + "3 3 0.209393 el servicio competente\n", + "4 4 0.194581 el servicio competente" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.20713068788495195\n", + "model : LinearSVM , score = 0.20767887864006607\n", + "model : RBFSVM , score = 0.19787543551643047\n", + "model : DecisionTree , score = 0.20371064322425628\n", + "model : RandomForest , score = 0.1997277746914184\n", + "model : AdaBoost , score = 0.20114442854828196\n", + "----------------------------------------------\n", + "\n", + "file name : 92+100_68+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 380" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.505715nocrear
110.494285nocrear
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.505715 no crear\n", + "1 1 0.494285 no crear" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.4600878205646209\n", + "model : LinearSVM , score = 0.46085152158880804\n", + "model : RBFSVM , score = 0.33494255798491407\n", + "model : DecisionTree , score = 0.41368250856415995\n", + "model : RandomForest , score = 0.37487519219381\n", + "model : AdaBoost , score = 0.4063428873583521\n", + "----------------------------------------------\n", + "\n", + "file name : 26+16_106_29+10_29_106_29+11_29_106_29+33_24+33_14_106_29+33_1_29_106_29+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 5\n", + "Records number : 4116" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.167642eldesarrollotécnicoyindustrial
110.138759eldesarrollotécnicoyindustrial
220.128489eldesarrollotécnicoyindustrial
330.130220eldesarrollotécnicoyindustrial
440.167642eldesarrollotécnicoyindustrial
550.138759eldesarrollotécnicoyindustrial
660.128489eldesarrollotécnicoyindustrial
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.167642 el desarrollo técnico y industrial\n", + "1 1 0.138759 el desarrollo técnico y industrial\n", + "2 2 0.128489 el desarrollo técnico y industrial\n", + "3 3 0.130220 el desarrollo técnico y industrial\n", + "4 4 0.167642 el desarrollo técnico y industrial\n", + "5 5 0.138759 el desarrollo técnico y industrial\n", + "6 6 0.128489 el desarrollo técnico y industrial" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.12281064387846821\n", + "model : LinearSVM , score = 0.12810103192443603\n", + "model : RBFSVM , score = 0.14976190134123576\n", + "model : DecisionTree , score = 0.1090782088471264\n", + "model : RandomForest , score = 0.0975205407192285\n", + "model : AdaBoost , score = 0.10507606742700715\n", + "----------------------------------------------\n", + "\n", + "file name : 76_64+76_108_68+75_38+75_67+75_63_64+75_63_108_68+100_39+100_40_64+100_40_108_68+100_37_38+100_37_67+100_37_63_64+100_37_63_108_68+.csv\n", + "Rules(classes) number : 13\n", + "Words(features) number : 5\n", + "Records number : 26" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.076446ni_siquierahaberllegaraemplear
110.076446ni_siquierahaberllegaraemplear
220.078513ni_siquierahaberllegaraemplear
330.076446ni_siquierahaberllegaraemplear
440.076446ni_siquierahaberllegaraemplear
550.076446ni_siquierahaberllegaraemplear
660.078513ni_siquierahaberllegaraemplear
770.076446ni_siquierahaberllegaraemplear
880.076446ni_siquierahaberllegaraemplear
990.078513ni_siquierahaberllegaraemplear
10100.076446ni_siquierahaberllegaraemplear
11110.076446ni_siquierahaberllegaraemplear
12120.076446ni_siquierahaberllegaraemplear
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.076446 ni_siquiera haber llegar a emplear\n", + "1 1 0.076446 ni_siquiera haber llegar a emplear\n", + "2 2 0.078513 ni_siquiera haber llegar a emplear\n", + "3 3 0.076446 ni_siquiera haber llegar a emplear\n", + "4 4 0.076446 ni_siquiera haber llegar a emplear\n", + "5 5 0.076446 ni_siquiera haber llegar a emplear\n", + "6 6 0.078513 ni_siquiera haber llegar a emplear\n", + "7 7 0.076446 ni_siquiera haber llegar a emplear\n", + "8 8 0.076446 ni_siquiera haber llegar a emplear\n", + "9 9 0.078513 ni_siquiera haber llegar a emplear\n", + "10 10 0.076446 ni_siquiera haber llegar a emplear\n", + "11 11 0.076446 ni_siquiera haber llegar a emplear\n", + "12 12 0.076446 ni_siquiera haber llegar a emplear" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.07707142653346746\n", + "model : RBFSVM , score = 0.07707142653346746\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 20_106+12_29_106+113_24+113_14_106+113_1_29_106+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 25" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.203738doscomentariosencilloy
110.196612doscomentariosencilloy
220.199300doscomentariosencilloy
330.203738doscomentariosencilloy
440.196612doscomentariosencilloy
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.203738 dos comentario sencillo y\n", + "1 1 0.196612 dos comentario sencillo y\n", + "2 2 0.199300 dos comentario sencillo y\n", + "3 3 0.203738 dos comentario sencillo y\n", + "4 4 0.196612 dos comentario sencillo y" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.07628991346706404\n", + "model : LinearSVM , score = 0.15087718345207474\n", + "model : RBFSVM , score = 0.15087718345207474\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 30_64+30_108_68+110_67+110_63_64+110_63_108_68+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 35" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.204084bieninformarparaevitar
110.193874bieninformarparaevitar
220.204084bieninformarparaevitar
330.204084bieninformarparaevitar
440.193874bieninformarparaevitar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.204084 bien informar para evitar\n", + "1 1 0.193874 bien informar para evitar\n", + "2 2 0.204084 bien informar para evitar\n", + "3 3 0.204084 bien informar para evitar\n", + "4 4 0.193874 bien informar para evitar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.1692041208560311\n", + "model : RBFSVM , score = 0.1692041208560311\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 80+108_92+108_100_68+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 63" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.340001paranovolver
110.334441paranovolver
220.325558paranovolver
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.340001 para no volver\n", + "1 1 0.334441 para no volver\n", + "2 2 0.325558 para no volver" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.21988317710465202\n", + "model : LinearSVM , score = 0.2792714064114462\n", + "model : RBFSVM , score = 0.3038233460112918\n", + "model : DecisionTree , score = 0.15838051390647628\n", + "model : RandomForest , score = 0.12615808996952854\n", + "model : AdaBoost , score = 0.12480093199720507\n", + "----------------------------------------------\n", + "\n", + "file name : 97+108_98+108_33_99+108_33_113_108_1+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 5\n", + "Records number : 264" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.257936antes_deel1deenero
110.251593antes_deel1deenero
220.251621antes_deel1deenero
330.238850antes_deel1deenero
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.257936 antes_de el 1 de enero\n", + "1 1 0.251593 antes_de el 1 de enero\n", + "2 2 0.251621 antes_de el 1 de enero\n", + "3 3 0.238850 antes_de el 1 de enero" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.18412234779307454\n", + "model : LinearSVM , score = 0.1712634434048582\n", + "model : RBFSVM , score = 0.2665445350564511\n", + "model : DecisionTree , score = 0.09966666528424266\n", + "model : RandomForest , score = 0.0893498872653412\n", + "model : AdaBoost , score = 0.12985147953020063\n", + "----------------------------------------------\n", + "\n", + "file name : 42_64+42_108_68+47_67+47_63_64+47_63_108_68+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 5\n", + "Records number : 15" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.202631lohaberhacersininformar
110.200782lohaberhacersininformar
220.199458lohaberhacersininformar
330.199458lohaberhacersininformar
440.197671lohaberhacersininformar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.202631 lo haber hacer sin informar\n", + "1 1 0.200782 lo haber hacer sin informar\n", + "2 2 0.199458 lo haber hacer sin informar\n", + "3 3 0.199458 lo haber hacer sin informar\n", + "4 4 0.197671 lo haber hacer sin informar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.13698720732322098\n", + "model : RBFSVM , score = 0.13698720732322098\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 30+110_63+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 484" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.5bienadaptar
110.5bienadaptar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.5 bien adaptar\n", + "1 1 0.5 bien adaptar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.4630506070154525\n", + "model : LinearSVM , score = 0.4630506070154525\n", + "model : RBFSVM , score = 0.32572428366113676\n", + "model : DecisionTree , score = 0.4001060386298835\n", + "model : RandomForest , score = 0.38451515996862545\n", + "model : AdaBoost , score = 0.3845365323262198\n", + "----------------------------------------------\n", + "\n", + "file name : 98_29+33_99_29+33_113_108_14+33_113_108_1_29+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 5\n", + "Records number : 12" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.288897el3demarzopasado
110.258390el3demarzopasado
220.227527el3demarzopasado
330.225187el3demarzopasado
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.288897 el 3 de marzo pasado\n", + "1 1 0.258390 el 3 de marzo pasado\n", + "2 2 0.227527 el 3 de marzo pasado\n", + "3 3 0.225187 el 3 de marzo pasado" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.15216143917608507\n", + "model : RBFSVM , score = 0.15216143917608507\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 35+37+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 1\n", + "Records number : 1222" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1
000.507778hay
110.492222hay
\n", + "
" + ], + "text/plain": [ + " rule weight word1\n", + "0 0 0.507778 hay\n", + "1 1 0.492222 hay" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.5081430489169222\n", + "model : LinearSVM , score = 0.5111208491983028\n", + "model : RBFSVM , score = 0.5111208491983028\n", + "model : DecisionTree , score = 0.5111208491983028\n", + "model : RandomForest , score = 0.5111208491983028\n", + "model : AdaBoost , score = 0.5111208491983028\n", + "----------------------------------------------\n", + "\n", + "file name : 17_63_29+31_15+31_1_63_29+33_29_15+33_29_1_63_29+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 5\n", + "Records number : 10" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.201255elnumerosodecisiónaprobarrelativo
110.198118elnumerosodecisiónaprobarrelativo
220.201255elnumerosodecisiónaprobarrelativo
330.198118elnumerosodecisiónaprobarrelativo
440.201255elnumerosodecisiónaprobarrelativo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.201255 el numeroso decisión aprobar relativo\n", + "1 1 0.198118 el numeroso decisión aprobar relativo\n", + "2 2 0.201255 el numeroso decisión aprobar relativo\n", + "3 3 0.198118 el numeroso decisión aprobar relativo\n", + "4 4 0.201255 el numeroso decisión aprobar relativo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.19984007429839853\n", + "model : RBFSVM , score = 0.19984007429839853\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 20+12_29+113_14+113_1_29+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 3\n", + "Records number : 1100" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.282894tresobjetivoprincipal
110.217106tresobjetivoprincipal
220.282894tresobjetivoprincipal
330.217106tresobjetivoprincipal
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.282894 tres objetivo principal\n", + "1 1 0.217106 tres objetivo principal\n", + "2 2 0.282894 tres objetivo principal\n", + "3 3 0.217106 tres objetivo principal" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.23407372214880567\n", + "model : LinearSVM , score = 0.24638366234420286\n", + "model : RBFSVM , score = 0.2604208440404019\n", + "model : DecisionTree , score = 0.21305397542331572\n", + "model : RandomForest , score = 0.12586922004458254\n", + "model : AdaBoost , score = 0.1717893312984715\n", + "----------------------------------------------\n", + "\n", + "file name : 65_64+65_108_68+64_67+64_63_64+64_63_108_68+108_40_64+108_40_108_68+108_68_67+108_68_63_64+108_68_63_108_68+.csv\n", + "Rules(classes) number : 10\n", + "Words(features) number : 5\n", + "Records number : 20" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.099691antes_dehaberaprenderaandar
110.099691antes_dehaberaprenderaandar
220.099691antes_dehaberaprenderaandar
330.099691antes_dehaberaprenderaandar
440.099691antes_dehaberaprenderaandar
550.100309antes_dehaberaprenderaandar
660.100309antes_dehaberaprenderaandar
770.100309antes_dehaberaprenderaandar
880.100309antes_dehaberaprenderaandar
990.100309antes_dehaberaprenderaandar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.099691 antes_de haber aprender a andar\n", + "1 1 0.099691 antes_de haber aprender a andar\n", + "2 2 0.099691 antes_de haber aprender a andar\n", + "3 3 0.099691 antes_de haber aprender a andar\n", + "4 4 0.099691 antes_de haber aprender a andar\n", + "5 5 0.100309 antes_de haber aprender a andar\n", + "6 6 0.100309 antes_de haber aprender a andar\n", + "7 7 0.100309 antes_de haber aprender a andar\n", + "8 8 0.100309 antes_de haber aprender a andar\n", + "9 9 0.100309 antes_de haber aprender a andar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.09969110030889967\n", + "model : LinearSVM , score = 0.10030889969110031\n", + "model : RBFSVM , score = 0.10030889969110031\n", + "model : DecisionTree , score = 0.10030889969110031\n", + "model : RandomForest , score = 0.09969110030889967\n", + "model : AdaBoost , score = 0.10030889969110031\n", + "----------------------------------------------\n", + "\n", + "file name : 74+75+100_35+100_37+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 2\n", + "Records number : 1836" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.287918nohay
110.221473nohay
220.261190nohay
330.229420nohay
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.287918 no hay\n", + "1 1 0.221473 no hay\n", + "2 2 0.261190 no hay\n", + "3 3 0.229420 no hay" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.222433076533358\n", + "model : LinearSVM , score = 0.24922576304028074\n", + "model : RBFSVM , score = 0.23637689663456252\n", + "model : DecisionTree , score = 0.22220220609108216\n", + "model : RandomForest , score = 0.21600669587384547\n", + "model : AdaBoost , score = 0.22307305648417208\n", + "----------------------------------------------\n", + "\n", + "file name : 40+35_63+37_63+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 2\n", + "Records number : 924" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.333450haberconvenir
110.333099haberconvenir
220.333450haberconvenir
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.333450 haber convenir\n", + "1 1 0.333099 haber convenir\n", + "2 2 0.333450 haber convenir" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.33343316386434263\n", + "model : LinearSVM , score = 0.346860081569324\n", + "model : RBFSVM , score = 0.22955782483687012\n", + "model : DecisionTree , score = 0.29952160210106243\n", + "model : RandomForest , score = 0.26062750522115874\n", + "model : AdaBoost , score = 0.2539933509453858\n", + "----------------------------------------------\n", + "\n", + "file name : 25_29+26_14+26_1_29+16_106_29_14+16_106_29_1_29+10_29_106_29_14+10_29_106_29_1_29+11_29_106_29_14+11_29_106_29_1_29+33_23_29+33_24_14+33_24_1_29+33_14_106_29_14+33_14_106_29_1_29+33_1_29_106_29_14+33_1_29_106_29_1_29+.csv\n", + "Rules(classes) number : 16\n", + "Words(features) number : 7\n", + "Records number : 32" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6word7
000.063607elderechohumanoyvarioacontecimientoreciente
110.061555elderechohumanoyvarioacontecimientoreciente
220.058596elderechohumanoyvarioacontecimientoreciente
330.066319elderechohumanoyvarioacontecimientoreciente
440.063607elderechohumanoyvarioacontecimientoreciente
550.063693elderechohumanoyvarioacontecimientoreciente
660.061188elderechohumanoyvarioacontecimientoreciente
770.062647elderechohumanoyvarioacontecimientoreciente
880.060222elderechohumanoyvarioacontecimientoreciente
990.063607elderechohumanoyvarioacontecimientoreciente
10100.061555elderechohumanoyvarioacontecimientoreciente
11110.058596elderechohumanoyvarioacontecimientoreciente
12120.066319elderechohumanoyvarioacontecimientoreciente
13130.063607elderechohumanoyvarioacontecimientoreciente
14140.063693elderechohumanoyvarioacontecimientoreciente
15150.061188elderechohumanoyvarioacontecimientoreciente
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6 \\\n", + "0 0 0.063607 el derecho humano y vario acontecimiento \n", + "1 1 0.061555 el derecho humano y vario acontecimiento \n", + "2 2 0.058596 el derecho humano y vario acontecimiento \n", + "3 3 0.066319 el derecho humano y vario acontecimiento \n", + "4 4 0.063607 el derecho humano y vario acontecimiento \n", + "5 5 0.063693 el derecho humano y vario acontecimiento \n", + "6 6 0.061188 el derecho humano y vario acontecimiento \n", + "7 7 0.062647 el derecho humano y vario acontecimiento \n", + "8 8 0.060222 el derecho humano y vario acontecimiento \n", + "9 9 0.063607 el derecho humano y vario acontecimiento \n", + "10 10 0.061555 el derecho humano y vario acontecimiento \n", + "11 11 0.058596 el derecho humano y vario acontecimiento \n", + "12 12 0.066319 el derecho humano y vario acontecimiento \n", + "13 13 0.063607 el derecho humano y vario acontecimiento \n", + "14 14 0.063693 el derecho humano y vario acontecimiento \n", + "15 15 0.061188 el derecho humano y vario acontecimiento \n", + "\n", + " word7 \n", + "0 reciente \n", + "1 reciente \n", + "2 reciente \n", + "3 reciente \n", + "4 reciente \n", + "5 reciente \n", + "6 reciente \n", + "7 reciente \n", + "8 reciente \n", + "9 reciente \n", + "10 reciente \n", + "11 reciente \n", + "12 reciente \n", + "13 reciente \n", + "14 reciente \n", + "15 reciente " + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.06659291686619512\n", + "model : RBFSVM , score = 0.06659291686619512\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 76+74_63+75_63+100_40+100_35_63+100_37_63+.csv\n", + "Rules(classes) number : 6\n", + "Words(features) number : 3\n", + "Records number : 618" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.17124quizáhaberllegar
110.15752quizáhaberllegar
220.17124quizáhaberllegar
330.17124quizáhaberllegar
440.15752quizáhaberllegar
550.17124quizáhaberllegar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.17124 quizá haber llegar\n", + "1 1 0.15752 quizá haber llegar\n", + "2 2 0.17124 quizá haber llegar\n", + "3 3 0.17124 quizá haber llegar\n", + "4 4 0.15752 quizá haber llegar\n", + "5 5 0.17124 quizá haber llegar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.15541247961251903\n", + "model : LinearSVM , score = 0.15642422260752123\n", + "model : RBFSVM , score = 0.1781171815647689\n", + "model : DecisionTree , score = 0.11920340132556226\n", + "model : RandomForest , score = 0.07302332395743687\n", + "model : AdaBoost , score = 0.08910207760680809\n", + "----------------------------------------------\n", + "\n", + "file name : 19+16_29+10_29_29+11_29_29+33_15+33_14_29+33_1_29_29+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 4\n", + "Records number : 6734" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.146545ningunoobstáculojurídicoreal
110.140010ningunoobstáculojurídicoreal
220.143535ningunoobstáculojurídicoreal
330.139819ningunoobstáculojurídicoreal
440.146545ningunoobstáculojurídicoreal
550.140010ningunoobstáculojurídicoreal
660.143535ningunoobstáculojurídicoreal
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.146545 ninguno obstáculo jurídico real\n", + "1 1 0.140010 ninguno obstáculo jurídico real\n", + "2 2 0.143535 ninguno obstáculo jurídico real\n", + "3 3 0.139819 ninguno obstáculo jurídico real\n", + "4 4 0.146545 ninguno obstáculo jurídico real\n", + "5 5 0.140010 ninguno obstáculo jurídico real\n", + "6 6 0.143535 ninguno obstáculo jurídico real" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.13357139094346357\n", + "model : LinearSVM , score = 0.14457829516012763\n", + "model : RBFSVM , score = 0.14829315087623948\n", + "model : DecisionTree , score = 0.1286554919938203\n", + "model : RandomForest , score = 0.09791982020184645\n", + "model : AdaBoost , score = 0.10583255654691229\n", + "----------------------------------------------\n", + "\n", + "file name : 93+100_69+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 14" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.503313nohacer
110.496687nohacer
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.503313 no hacer\n", + "1 1 0.496687 no hacer" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.28706249003625595\n", + "model : LinearSVM , score = 0.4242505909801415\n", + "model : RBFSVM , score = 0.4242505909801415\n", + "model : DecisionTree , score = 0.2855692474154155\n", + "model : RandomForest , score = 0.28331284259950834\n", + "model : AdaBoost , score = 0.2855692474154155\n", + "----------------------------------------------\n", + "\n", + "file name : 28+16_106_30+16_106_100_29+10_29_106_30+10_29_106_100_29+11_29_106_30+11_29_106_100_29+33_14_106_30+33_14_106_100_29+33_1_29_106_30+33_1_29_106_100_29+.csv\n", + "Rules(classes) number : 11\n", + "Words(features) number : 6\n", + "Records number : 242" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.091505unodebateabiertoymucho_másdinámico
110.092972unodebateabiertoymucho_másdinámico
220.092972unodebateabiertoymucho_másdinámico
330.089077unodebateabiertoymucho_másdinámico
440.089077unodebateabiertoymucho_másdinámico
550.090149unodebateabiertoymucho_másdinámico
660.090149unodebateabiertoymucho_másdinámico
770.092972unodebateabiertoymucho_másdinámico
880.092972unodebateabiertoymucho_másdinámico
990.089077unodebateabiertoymucho_másdinámico
10100.089077unodebateabiertoymucho_másdinámico
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.091505 uno debate abierto y mucho_más dinámico\n", + "1 1 0.092972 uno debate abierto y mucho_más dinámico\n", + "2 2 0.092972 uno debate abierto y mucho_más dinámico\n", + "3 3 0.089077 uno debate abierto y mucho_más dinámico\n", + "4 4 0.089077 uno debate abierto y mucho_más dinámico\n", + "5 5 0.090149 uno debate abierto y mucho_más dinámico\n", + "6 6 0.090149 uno debate abierto y mucho_más dinámico\n", + "7 7 0.092972 uno debate abierto y mucho_más dinámico\n", + "8 8 0.092972 uno debate abierto y mucho_más dinámico\n", + "9 9 0.089077 uno debate abierto y mucho_más dinámico\n", + "10 10 0.089077 uno debate abierto y mucho_más dinámico" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.02499643012919274\n", + "model : LinearSVM , score = 0.05853263185872462\n", + "model : RBFSVM , score = 0.09487956768291234\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.04976535493069682\n", + "----------------------------------------------\n", + "\n", + "file name : 40+63_63+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 4" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.486204haberrepetir
110.513796haberrepetir
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.486204 haber repetir\n", + "1 1 0.513796 haber repetir" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.48620399999999997\n", + "model : LinearSVM , score = 0.513796\n", + "model : RBFSVM , score = 0.513796\n", + "model : DecisionTree , score = 0.513796\n", + "model : RandomForest , score = 0.513796\n", + "model : AdaBoost , score = 0.513796\n", + "----------------------------------------------\n", + "\n", + "file name : 98+33_99+33_113_108_1+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 4\n", + "Records number : 213" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.336429el27demarzo
110.338076el27demarzo
220.325496el27demarzo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.336429 el 27 de marzo\n", + "1 1 0.338076 el 27 de marzo\n", + "2 2 0.325496 el 27 de marzo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.2851337068878107\n", + "model : LinearSVM , score = 0.26689440142665044\n", + "model : RBFSVM , score = 0.32354741596092174\n", + "model : DecisionTree , score = 0.130059015477188\n", + "model : RandomForest , score = 0.13016797136447059\n", + "model : AdaBoost , score = 0.17396683289488685\n", + "----------------------------------------------\n", + "\n", + "file name : 40+37_63+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 11700" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.5haberincluir
110.5haberincluir
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.5 haber incluir\n", + "1 1 0.5 haber incluir" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.4917035327565232\n", + "model : LinearSVM , score = 0.4933275214113945\n", + "model : RBFSVM , score = 0.43242836955937985\n", + "model : DecisionTree , score = 0.4761490467706863\n", + "model : RandomForest , score = 0.47036086996205184\n", + "model : AdaBoost , score = 0.46738221547011866\n", + "----------------------------------------------\n", + "\n", + "file name : 75+100_37+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 23248" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.515855norespetar
110.484145norespetar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.515855 no respetar\n", + "1 1 0.484145 no respetar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.5018283420998348\n", + "model : LinearSVM , score = 0.5043203550155587\n", + "model : RBFSVM , score = 0.41599039176105\n", + "model : DecisionTree , score = 0.49078794172529744\n", + "model : RandomForest , score = 0.4824725030459211\n", + "model : AdaBoost , score = 0.48468805774189694\n", + "----------------------------------------------\n", + "\n", + "file name : 20+12_29+113_15+113_14+113_1_29+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 3\n", + "Records number : 45" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.20011520.000actojurídico
110.20011520.000actojurídico
220.19954020.000actojurídico
330.20011520.000actojurídico
440.20011520.000actojurídico
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.200115 20.000 acto jurídico\n", + "1 1 0.200115 20.000 acto jurídico\n", + "2 2 0.199540 20.000 acto jurídico\n", + "3 3 0.200115 20.000 acto jurídico\n", + "4 4 0.200115 20.000 acto jurídico" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.1309606202361131\n", + "model : LinearSVM , score = 0.1751275346500531\n", + "model : RBFSVM , score = 0.1751275346500531\n", + "model : DecisionTree , score = 0.04407809457336834\n", + "model : RandomForest , score = 0.04407809457336834\n", + "model : AdaBoost , score = 0.04407809457336834\n", + "----------------------------------------------\n", + "\n", + "file name : 17+31_1+33_29_1+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 20829" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.333333unobuenofórmula
110.333333unobuenofórmula
220.333333unobuenofórmula
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.333333 uno bueno fórmula\n", + "1 1 0.333333 uno bueno fórmula\n", + "2 2 0.333333 uno bueno fórmula" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.3295921616760996\n", + "model : LinearSVM , score = 0.32920708495257434\n", + "model : RBFSVM , score = 0.14985848799535995\n", + "model : DecisionTree , score = 0.3181969882034842\n", + "model : RandomForest , score = 0.3066639449713755\n", + "model : AdaBoost , score = 0.30670845232364624\n", + "----------------------------------------------\n", + "\n", + "file name : 32+33_30+33_100_63+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 51" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.336110elmáspreocupar
110.331945elmáspreocupar
220.331945elmáspreocupar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.336110 el más preocupar\n", + "1 1 0.331945 el más preocupar\n", + "2 2 0.331945 el más preocupar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.2300763669196149\n", + "model : LinearSVM , score = 0.30457753516806924\n", + "model : RBFSVM , score = 0.30457753516806924\n", + "model : DecisionTree , score = 0.15145278645061538\n", + "model : RandomForest , score = 0.1906317271927346\n", + "model : AdaBoost , score = 0.18972779925884573\n", + "----------------------------------------------\n", + "\n", + "file name : 76_64+76_108_68+74_67+74_63_64+74_63_108_68+75_67+75_63_64+75_63_108_68+100_40_64+100_40_108_68+100_35_67+100_35_63_64+100_35_63_108_68+100_37_67+100_37_63_64+100_37_63_108_68+.csv\n", + "Rules(classes) number : 16\n", + "Words(features) number : 5\n", + "Records number : 32" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.066377ni_siquierahaberempezaratrabajar
110.066377ni_siquierahaberempezaratrabajar
220.056037ni_siquierahaberempezaratrabajar
330.056037ni_siquierahaberempezaratrabajar
440.056037ni_siquierahaberempezaratrabajar
550.066377ni_siquierahaberempezaratrabajar
660.066377ni_siquierahaberempezaratrabajar
770.066377ni_siquierahaberempezaratrabajar
880.066377ni_siquierahaberempezaratrabajar
990.066377ni_siquierahaberempezaratrabajar
10100.056037ni_siquierahaberempezaratrabajar
11110.056037ni_siquierahaberempezaratrabajar
12120.056037ni_siquierahaberempezaratrabajar
13130.066377ni_siquierahaberempezaratrabajar
14140.066377ni_siquierahaberempezaratrabajar
15150.066377ni_siquierahaberempezaratrabajar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.066377 ni_siquiera haber empezar a trabajar\n", + "1 1 0.066377 ni_siquiera haber empezar a trabajar\n", + "2 2 0.056037 ni_siquiera haber empezar a trabajar\n", + "3 3 0.056037 ni_siquiera haber empezar a trabajar\n", + "4 4 0.056037 ni_siquiera haber empezar a trabajar\n", + "5 5 0.066377 ni_siquiera haber empezar a trabajar\n", + "6 6 0.066377 ni_siquiera haber empezar a trabajar\n", + "7 7 0.066377 ni_siquiera haber empezar a trabajar\n", + "8 8 0.066377 ni_siquiera haber empezar a trabajar\n", + "9 9 0.066377 ni_siquiera haber empezar a trabajar\n", + "10 10 0.056037 ni_siquiera haber empezar a trabajar\n", + "11 11 0.056037 ni_siquiera haber empezar a trabajar\n", + "12 12 0.056037 ni_siquiera haber empezar a trabajar\n", + "13 13 0.066377 ni_siquiera haber empezar a trabajar\n", + "14 14 0.066377 ni_siquiera haber empezar a trabajar\n", + "15 15 0.066377 ni_siquiera haber empezar a trabajar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.06637753982652389\n", + "model : LinearSVM , score = 0.06637753982652389\n", + "model : RBFSVM , score = 0.06637753982652389\n", + "model : DecisionTree , score = 0.06637753982652389\n", + "model : RandomForest , score = 0.06637753982652389\n", + "model : AdaBoost , score = 0.06637753982652389\n", + "----------------------------------------------\n", + "\n", + "file name : 30_64+30_108_68+100_67+100_63_64+100_63_108_68+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 105" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.2realmentedisponeralibrar
110.2realmentedisponeralibrar
220.2realmentedisponeralibrar
330.2realmentedisponeralibrar
440.2realmentedisponeralibrar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.2 realmente disponer a librar\n", + "1 1 0.2 realmente disponer a librar\n", + "2 2 0.2 realmente disponer a librar\n", + "3 3 0.2 realmente disponer a librar\n", + "4 4 0.2 realmente disponer a librar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.1131868758808217\n", + "model : LinearSVM , score = 0.18936578010447513\n", + "model : RBFSVM , score = 0.18913502781145083\n", + "model : DecisionTree , score = 0.05658834573615122\n", + "model : RandomForest , score = 0.018868314183344823\n", + "model : AdaBoost , score = 0.07544836151255443\n", + "----------------------------------------------\n", + "\n", + "file name : 64+108_68+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 10714" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.516806porconsiderar
110.483194porconsiderar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.516806 por considerar\n", + "1 1 0.483194 por considerar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.4929621418967288\n", + "model : LinearSVM , score = 0.4942816164223336\n", + "model : RBFSVM , score = 0.37833582985460873\n", + "model : DecisionTree , score = 0.4755386350131668\n", + "model : RandomForest , score = 0.47136806950311533\n", + "model : AdaBoost , score = 0.4797982398098202\n", + "----------------------------------------------\n", + "\n", + "file name : 45+47+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 6" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.467616lohaber
110.532384lohaber
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.467616 lo haber\n", + "1 1 0.532384 lo haber" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.6510258814294746\n", + "model : LinearSVM , score = 0.3489741185705253\n", + "model : RBFSVM , score = 0.3489741185705253\n", + "model : DecisionTree , score = 0.3489741185705253\n", + "model : RandomForest , score = 0.3489741185705253\n", + "model : AdaBoost , score = 0.3489741185705253\n", + "----------------------------------------------\n", + "\n", + "file name : 38+69_64+69_108_68+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 6" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: divide by zero encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.349408llegaraser
110.325296llegaraser
220.325296llegaraser
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.349408 llegar a ser\n", + "1 1 0.325296 llegar a ser\n", + "2 2 0.325296 llegar a ser" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.349408\n", + "model : LinearSVM , score = 0.349408\n", + "model : RBFSVM , score = 0.349408\n", + "model : DecisionTree , score = 0.349408\n", + "model : RandomForest , score = 0.349408\n", + "model : AdaBoost , score = 0.349408\n", + "----------------------------------------------\n", + "\n", + "file name : 65+64_63+91_63+108_40+108_68_63+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 3\n", + "Records number : 90" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.198241dehaberser
110.201699dehaberser
220.202473dehaberser
330.198794dehaberser
440.198794dehaberser
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.198241 de haber ser\n", + "1 1 0.201699 de haber ser\n", + "2 2 0.202473 de haber ser\n", + "3 3 0.198794 de haber ser\n", + "4 4 0.198794 de haber ser" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.15721598781487842\n", + "model : LinearSVM , score = 0.13246373705958808\n", + "model : RBFSVM , score = 0.20180785092965567\n", + "model : DecisionTree , score = 0.04382684750214566\n", + "model : RandomForest , score = 0.021909366934298014\n", + "model : AdaBoost , score = 0.08857531485899726\n", + "----------------------------------------------\n", + "\n", + "file name : 40_64+40_108_68+35_67+35_63_64+35_63_108_68+37_67+37_63_64+37_63_108_68+.csv\n", + "Rules(classes) number : 8\n", + "Words(features) number : 4\n", + "Records number : 16" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.133838haberamenazarconrecurrir
110.130860haberamenazarconrecurrir
220.112964haberamenazarconrecurrir
330.112964haberamenazarconrecurrir
440.110838haberamenazarconrecurrir
550.133838haberamenazarconrecurrir
660.133838haberamenazarconrecurrir
770.130860haberamenazarconrecurrir
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.133838 haber amenazar con recurrir\n", + "1 1 0.130860 haber amenazar con recurrir\n", + "2 2 0.112964 haber amenazar con recurrir\n", + "3 3 0.112964 haber amenazar con recurrir\n", + "4 4 0.110838 haber amenazar con recurrir\n", + "5 5 0.133838 haber amenazar con recurrir\n", + "6 6 0.133838 haber amenazar con recurrir\n", + "7 7 0.130860 haber amenazar con recurrir" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.1264077214410737\n", + "model : RBFSVM , score = 0.1264077214410737\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 7_63_106_29+8_63_106_29+9_63_106_29+10_108_24+10_108_1_63_106_29+11_108_24+11_108_1_63_106_29+33_1_108_24+33_1_108_1_63_106_29+.csv\n", + "Rules(classes) number : 9\n", + "Words(features) number : 7\n", + "Records number : 45" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6word7
000.111574unodefinicióndeciudadanoampliaryconfuso
110.110444unodefinicióndeciudadanoampliaryconfuso
220.111013unodefinicióndeciudadanoampliaryconfuso
330.111046unodefinicióndeciudadanoampliaryconfuso
440.111574unodefinicióndeciudadanoampliaryconfuso
550.110600unodefinicióndeciudadanoampliaryconfuso
660.111129unodefinicióndeciudadanoampliaryconfuso
770.111046unodefinicióndeciudadanoampliaryconfuso
880.111574unodefinicióndeciudadanoampliaryconfuso
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6 word7\n", + "0 0 0.111574 uno definición de ciudadano ampliar y confuso\n", + "1 1 0.110444 uno definición de ciudadano ampliar y confuso\n", + "2 2 0.111013 uno definición de ciudadano ampliar y confuso\n", + "3 3 0.111046 uno definición de ciudadano ampliar y confuso\n", + "4 4 0.111574 uno definición de ciudadano ampliar y confuso\n", + "5 5 0.110600 uno definición de ciudadano ampliar y confuso\n", + "6 6 0.111129 uno definición de ciudadano ampliar y confuso\n", + "7 7 0.111046 uno definición de ciudadano ampliar y confuso\n", + "8 8 0.111574 uno definición de ciudadano ampliar y confuso" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.08862622990678397\n", + "model : RBFSVM , score = 0.08862622990678397\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 76+75_63+100_40+100_37_63+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 3\n", + "Records number : 5892" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.256020nohabermejorar
110.247588nohabermejorar
220.248196nohabermejorar
330.248196nohabermejorar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.256020 no haber mejorar\n", + "1 1 0.247588 no haber mejorar\n", + "2 2 0.248196 no haber mejorar\n", + "3 3 0.248196 no haber mejorar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.25182717265680205\n", + "model : LinearSVM , score = 0.248560018366495\n", + "model : RBFSVM , score = 0.2392588726742863\n", + "model : DecisionTree , score = 0.22779809088144265\n", + "model : RandomForest , score = 0.1955185463236218\n", + "model : AdaBoost , score = 0.21712035680478434\n", + "----------------------------------------------\n", + "\n", + "file name : 14+1_29+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 12718" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.512582formatransparente
110.487418formatransparente
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.512582 forma transparente\n", + "1 1 0.487418 forma transparente" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.5107458466229141\n", + "model : LinearSVM , score = 0.5118126996132488\n", + "model : RBFSVM , score = 0.3961875644243543\n", + "model : DecisionTree , score = 0.49368570571413434\n", + "model : RandomForest , score = 0.48852175500059875\n", + "model : AdaBoost , score = 0.4863975090871166\n", + "----------------------------------------------\n", + "\n", + "file name : 7_29_106_29+8_29_106_29+9_29_106_29+10_108_24+10_108_14_106_29+10_108_1_29_106_29+11_108_24+11_108_14_106_29+11_108_1_29_106_29+33_1_108_24+33_1_108_14_106_29+33_1_108_1_29_106_29+.csv\n", + "Rules(classes) number : 12\n", + "Words(features) number : 7\n", + "Records number : 960" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6word7
000.085027elcomisióndeasuntoeconómicoymonetario
110.084131elcomisióndeasuntoeconómicoymonetario
220.083727elcomisióndeasuntoeconómicoymonetario
330.086464elcomisióndeasuntoeconómicoymonetario
440.079889elcomisióndeasuntoeconómicoymonetario
550.085027elcomisióndeasuntoeconómicoymonetario
660.083974elcomisióndeasuntoeconómicoymonetario
770.077760elcomisióndeasuntoeconómicoymonetario
880.082619elcomisióndeasuntoeconómicoymonetario
990.086464elcomisióndeasuntoeconómicoymonetario
10100.079889elcomisióndeasuntoeconómicoymonetario
11110.085027elcomisióndeasuntoeconómicoymonetario
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6 word7\n", + "0 0 0.085027 el comisión de asunto económico y monetario\n", + "1 1 0.084131 el comisión de asunto económico y monetario\n", + "2 2 0.083727 el comisión de asunto económico y monetario\n", + "3 3 0.086464 el comisión de asunto económico y monetario\n", + "4 4 0.079889 el comisión de asunto económico y monetario\n", + "5 5 0.085027 el comisión de asunto económico y monetario\n", + "6 6 0.083974 el comisión de asunto económico y monetario\n", + "7 7 0.077760 el comisión de asunto económico y monetario\n", + "8 8 0.082619 el comisión de asunto económico y monetario\n", + "9 9 0.086464 el comisión de asunto económico y monetario\n", + "10 10 0.079889 el comisión de asunto económico y monetario\n", + "11 11 0.085027 el comisión de asunto económico y monetario" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.07544499220507477\n", + "model : LinearSVM , score = 0.052612650939349755\n", + "model : RBFSVM , score = 0.08680020851121312\n", + "model : DecisionTree , score = 0.017581560870878046\n", + "model : RandomForest , score = 0.01424467609890829\n", + "model : AdaBoost , score = 0.03310003280258349\n", + "----------------------------------------------\n", + "\n", + "file name : 18+17_29+31_15+31_14+31_1_29+33_29_15+33_29_14+33_29_1_29+.csv\n", + "Rules(classes) number : 8\n", + "Words(features) number : 4\n", + "Records number : 264" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.126349elnuevoiniciativacomunitario
110.126684elnuevoiniciativacomunitario
220.120451elnuevoiniciativacomunitario
330.126349elnuevoiniciativacomunitario
440.126684elnuevoiniciativacomunitario
550.120451elnuevoiniciativacomunitario
660.126349elnuevoiniciativacomunitario
770.126684elnuevoiniciativacomunitario
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.126349 el nuevo iniciativa comunitario\n", + "1 1 0.126684 el nuevo iniciativa comunitario\n", + "2 2 0.120451 el nuevo iniciativa comunitario\n", + "3 3 0.126349 el nuevo iniciativa comunitario\n", + "4 4 0.126684 el nuevo iniciativa comunitario\n", + "5 5 0.120451 el nuevo iniciativa comunitario\n", + "6 6 0.126349 el nuevo iniciativa comunitario\n", + "7 7 0.126684 el nuevo iniciativa comunitario" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.05998969026970071\n", + "model : LinearSVM , score = 0.10552628754472712\n", + "model : RBFSVM , score = 0.12329034588993983\n", + "model : DecisionTree , score = 0.00795886992053042\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.05331442712214913\n", + "----------------------------------------------\n", + "\n", + "file name : 67_63+63_65+63_64_63+63_108_40+63_108_68_63+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 10" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.205494culparporhaberpermitir
110.205494culparporhaberpermitir
220.205494culparporhaberpermitir
330.191759culparporhaberpermitir
440.191759culparporhaberpermitir
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.205494 culpar por haber permitir\n", + "1 1 0.205494 culpar por haber permitir\n", + "2 2 0.205494 culpar por haber permitir\n", + "3 3 0.191759 culpar por haber permitir\n", + "4 4 0.191759 culpar por haber permitir" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.205494\n", + "model : LinearSVM , score = 0.205494\n", + "model : RBFSVM , score = 0.205494\n", + "model : DecisionTree , score = 0.205494\n", + "model : RandomForest , score = 0.205494\n", + "model : AdaBoost , score = 0.205494\n", + "----------------------------------------------\n", + "\n", + "file name : 95+98_108_113+33_96+33_99_108_113+33_113_108_1_108_113+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 6\n", + "Records number : 310" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.213448el4denoviembrede1998
110.201655el4denoviembrede1998
220.205052el4denoviembrede1998
330.194317el4denoviembrede1998
440.185529el4denoviembrede1998
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.213448 el 4 de noviembre de 1998\n", + "1 1 0.201655 el 4 de noviembre de 1998\n", + "2 2 0.205052 el 4 de noviembre de 1998\n", + "3 3 0.194317 el 4 de noviembre de 1998\n", + "4 4 0.185529 el 4 de noviembre de 1998" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.14465495993573385\n", + "model : LinearSVM , score = 0.17372084213541714\n", + "model : RBFSVM , score = 0.22295327450479063\n", + "model : DecisionTree , score = 0.06054547157295547\n", + "model : RandomForest , score = 0.028428275938724212\n", + "model : AdaBoost , score = 0.12970190060199288\n", + "----------------------------------------------\n", + "\n", + "file name : 30+100_29+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 5240" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.5a_escalalocal
110.5a_escalalocal
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.5 a_escala local\n", + "1 1 0.5 a_escala local" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.48398804800554773\n", + "model : LinearSVM , score = 0.4862776422770272\n", + "model : RBFSVM , score = 0.3250500585555513\n", + "model : DecisionTree , score = 0.465989043359402\n", + "model : RandomForest , score = 0.4394429154941928\n", + "model : AdaBoost , score = 0.45410508837298397\n", + "----------------------------------------------\n", + "\n", + "file name : 28+16_106_30+16_106_110_29+10_29_106_30+10_29_106_110_29+11_29_106_30+11_29_106_110_29+33_14_106_30+33_14_106_110_29+33_1_29_106_30+33_1_29_106_110_29+.csv\n", + "Rules(classes) number : 11\n", + "Words(features) number : 6\n", + "Records number : 88" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.096350unopuntoconcretoperomuysensible
110.092374unopuntoconcretoperomuysensible
220.092374unopuntoconcretoperomuysensible
330.087653unopuntoconcretoperomuysensible
440.087653unopuntoconcretoperomuysensible
550.091771unopuntoconcretoperomuysensible
660.091771unopuntoconcretoperomuysensible
770.092374unopuntoconcretoperomuysensible
880.092374unopuntoconcretoperomuysensible
990.087653unopuntoconcretoperomuysensible
10100.087653unopuntoconcretoperomuysensible
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.096350 uno punto concreto pero muy sensible\n", + "1 1 0.092374 uno punto concreto pero muy sensible\n", + "2 2 0.092374 uno punto concreto pero muy sensible\n", + "3 3 0.087653 uno punto concreto pero muy sensible\n", + "4 4 0.087653 uno punto concreto pero muy sensible\n", + "5 5 0.091771 uno punto concreto pero muy sensible\n", + "6 6 0.091771 uno punto concreto pero muy sensible\n", + "7 7 0.092374 uno punto concreto pero muy sensible\n", + "8 8 0.092374 uno punto concreto pero muy sensible\n", + "9 9 0.087653 uno punto concreto pero muy sensible\n", + "10 10 0.087653 uno punto concreto pero muy sensible" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.09517323380336981\n", + "model : RBFSVM , score = 0.09517323380336981\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 10_63_106_29+11_63_106_29+33_24+33_1_63_106_29+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 5\n", + "Records number : 48" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.248919unomodoplanificarysistemático
110.252398unomodoplanificarysistemático
220.249763unomodoplanificarysistemático
330.248919unomodoplanificarysistemático
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.248919 uno modo planificar y sistemático\n", + "1 1 0.252398 uno modo planificar y sistemático\n", + "2 2 0.249763 uno modo planificar y sistemático\n", + "3 3 0.248919 uno modo planificar y sistemático" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.12742105727778924\n", + "model : LinearSVM , score = 0.2592056410137905\n", + "model : RBFSVM , score = 0.2592056410137905\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.04150894525417662\n", + "----------------------------------------------\n", + "\n", + "file name : 40_65+40_64_63+40_91_63+40_108_40+40_108_68_63+35_67_63+35_63_65+35_63_64_63+35_63_91_63+35_63_108_40+35_63_108_68_63+37_67_63+37_63_65+37_63_64_63+37_63_91_63+37_63_108_40+37_63_108_68_63+.csv\n", + "Rules(classes) number : 17\n", + "Words(features) number : 5\n", + "Records number : 34" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.058557haberdecirdehaberadoptar
110.059888haberdecirdehaberadoptar
220.058393haberdecirdehaberadoptar
330.057981haberdecirdehaberadoptar
440.057981haberdecirdehaberadoptar
550.058962haberdecirdehaberadoptar
660.057254haberdecirdehaberadoptar
770.058962haberdecirdehaberadoptar
880.057597haberdecirdehaberadoptar
990.058962haberdecirdehaberadoptar
10100.058962haberdecirdehaberadoptar
11110.059888haberdecirdehaberadoptar
12120.058557haberdecirdehaberadoptar
13130.059888haberdecirdehaberadoptar
14140.058393haberdecirdehaberadoptar
15150.059888haberdecirdehaberadoptar
16160.059888haberdecirdehaberadoptar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.058557 haber decir de haber adoptar\n", + "1 1 0.059888 haber decir de haber adoptar\n", + "2 2 0.058393 haber decir de haber adoptar\n", + "3 3 0.057981 haber decir de haber adoptar\n", + "4 4 0.057981 haber decir de haber adoptar\n", + "5 5 0.058962 haber decir de haber adoptar\n", + "6 6 0.057254 haber decir de haber adoptar\n", + "7 7 0.058962 haber decir de haber adoptar\n", + "8 8 0.057597 haber decir de haber adoptar\n", + "9 9 0.058962 haber decir de haber adoptar\n", + "10 10 0.058962 haber decir de haber adoptar\n", + "11 11 0.059888 haber decir de haber adoptar\n", + "12 12 0.058557 haber decir de haber adoptar\n", + "13 13 0.059888 haber decir de haber adoptar\n", + "14 14 0.058393 haber decir de haber adoptar\n", + "15 15 0.059888 haber decir de haber adoptar\n", + "16 16 0.059888 haber decir de haber adoptar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.05855728243281527\n", + "model : LinearSVM , score = 0.0598877820336654\n", + "model : RBFSVM , score = 0.0598877820336654\n", + "model : DecisionTree , score = 0.0598877820336654\n", + "model : RandomForest , score = 0.05839268248219526\n", + "model : AdaBoost , score = 0.0598877820336654\n", + "----------------------------------------------\n", + "\n", + "file name : 23_29+24_14+24_1_29+14_106_29_14+14_106_29_1_29+1_29_106_29_14+1_29_106_29_1_29+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 6\n", + "Records number : 14" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.143889reducciónobligatorioyopcionalpropuestarelativo
110.144008reducciónobligatorioyopcionalpropuestarelativo
220.143889reducciónobligatorioyopcionalpropuestarelativo
330.141088reducciónobligatorioyopcionalpropuestarelativo
440.140978reducciónobligatorioyopcionalpropuestarelativo
550.143134reducciónobligatorioyopcionalpropuestarelativo
660.143015reducciónobligatorioyopcionalpropuestarelativo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.143889 reducción obligatorio y opcional propuesta relativo\n", + "1 1 0.144008 reducción obligatorio y opcional propuesta relativo\n", + "2 2 0.143889 reducción obligatorio y opcional propuesta relativo\n", + "3 3 0.141088 reducción obligatorio y opcional propuesta relativo\n", + "4 4 0.140978 reducción obligatorio y opcional propuesta relativo\n", + "5 5 0.143134 reducción obligatorio y opcional propuesta relativo\n", + "6 6 0.143015 reducción obligatorio y opcional propuesta relativo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.1438888561111439\n", + "model : LinearSVM , score = 0.14400785599214402\n", + "model : RBFSVM , score = 0.14400785599214402\n", + "model : DecisionTree , score = 0.14400785599214402\n", + "model : RandomForest , score = 0.14400785599214402\n", + "model : AdaBoost , score = 0.14400785599214402\n", + "----------------------------------------------\n", + "\n", + "file name : 10+11+33_1+.csv\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Rules(classes) number : 3\n", + "Words(features) number : 2\n", + "Records number : 269157" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.331459elescalera
110.337082elescalera
220.331459elescalera
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.331459 el escalera\n", + "1 1 0.337082 el escalera\n", + "2 2 0.331459 el escalera" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.3333842516772396\n", + "model : LinearSVM , score = 0.3335066744992964\n", + "model : RBFSVM , score = 0.2821422374759117\n", + "model : DecisionTree , score = 0.33131072497438363\n", + "model : RandomForest , score = 0.3289805767186921\n", + "model : AdaBoost , score = 0.3321084830109897\n", + "----------------------------------------------\n", + "\n", + "file name : 76_108_52+75_63_108_52+100_40_108_52+100_37_63_108_52+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 6\n", + "Records number : 8" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.25yahaberempezarahacerlo
110.25yahaberempezarahacerlo
220.25yahaberempezarahacerlo
330.25yahaberempezarahacerlo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.25 ya haber empezar a hacer lo\n", + "1 1 0.25 ya haber empezar a hacer lo\n", + "2 2 0.25 ya haber empezar a hacer lo\n", + "3 3 0.25 ya haber empezar a hacer lo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.25\n", + "model : LinearSVM , score = 0.25\n", + "model : RBFSVM , score = 0.25\n", + "model : DecisionTree , score = 0.25\n", + "model : RandomForest , score = 0.25\n", + "model : AdaBoost , score = 0.25\n", + "----------------------------------------------\n", + "\n", + "file name : 23+24_1+14_106_29_1+1_29_106_29_1+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 5\n", + "Records number : 28" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.252352consecuenciaeconómicoyincalculabledaño
110.252352consecuenciaeconómicoyincalculabledaño
220.251366consecuenciaeconómicoyincalculabledaño
330.243930consecuenciaeconómicoyincalculabledaño
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.252352 consecuencia económico y incalculable daño\n", + "1 1 0.252352 consecuencia económico y incalculable daño\n", + "2 2 0.251366 consecuencia económico y incalculable daño\n", + "3 3 0.243930 consecuencia económico y incalculable daño" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.06864049718985643\n", + "model : LinearSVM , score = 0.2204557855078027\n", + "model : RBFSVM , score = 0.2204557855078027\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.06763873369214851\n", + "----------------------------------------------\n", + "\n", + "file name : 75_69+100_70+100_37_69+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 552" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.316646actualmenteestarllevar
110.366708actualmenteestarllevar
220.316646actualmenteestarllevar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.316646 actualmente estar llevar\n", + "1 1 0.366708 actualmente estar llevar\n", + "2 2 0.316646 actualmente estar llevar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.3127688216070106\n", + "model : LinearSVM , score = 0.3452572891939757\n", + "model : RBFSVM , score = 0.3377194914074114\n", + "model : DecisionTree , score = 0.23282676815502515\n", + "model : RandomForest , score = 0.2048260357129543\n", + "model : AdaBoost , score = 0.21022800798163122\n", + "----------------------------------------------\n", + "\n", + "file name : 40+35_36+35_63+37_36+37_63+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 2\n", + "Records number : 10" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.220455haberhaber_que
110.178101haberhaber_que
220.185300haberhaber_que
330.195689haberhaber_que
440.220455haberhaber_que
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.220455 haber haber_que\n", + "1 1 0.178101 haber haber_que\n", + "2 2 0.185300 haber haber_que\n", + "3 3 0.195689 haber haber_que\n", + "4 4 0.220455 haber haber_que" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.220455\n", + "model : LinearSVM , score = 0.220455\n", + "model : RBFSVM , score = 0.220455\n", + "model : DecisionTree , score = 0.220455\n", + "model : RandomForest , score = 0.220455\n", + "model : AdaBoost , score = 0.220455\n", + "----------------------------------------------\n", + "\n", + "file name : 7_29+8_29+9_29+10_108_14+10_108_1_29+11_108_14+11_108_1_29+33_1_108_14+33_1_108_1_29+.csv\n", + "Rules(classes) number : 9\n", + "Words(features) number : 5\n", + "Records number : 15057" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.110232elprogramadefondoestructural
110.113624elprogramadefondoestructural
220.112062elprogramadefondoestructural
330.110865elprogramadefondoestructural
440.110232elprogramadefondoestructural
550.111261elprogramadefondoestructural
660.110628elprogramadefondoestructural
770.110865elprogramadefondoestructural
880.110232elprogramadefondoestructural
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.110232 el programa de fondo estructural\n", + "1 1 0.113624 el programa de fondo estructural\n", + "2 2 0.112062 el programa de fondo estructural\n", + "3 3 0.110865 el programa de fondo estructural\n", + "4 4 0.110232 el programa de fondo estructural\n", + "5 5 0.111261 el programa de fondo estructural\n", + "6 6 0.110628 el programa de fondo estructural\n", + "7 7 0.110865 el programa de fondo estructural\n", + "8 8 0.110232 el programa de fondo estructural" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.10341161383475868\n", + "model : LinearSVM , score = 0.10728662965308675\n", + "model : RBFSVM , score = 0.11419949384647897\n", + "model : DecisionTree , score = 0.09967279951894004\n", + "model : RandomForest , score = 0.08666607275524917\n", + "model : AdaBoost , score = 0.0893746415611208\n", + "----------------------------------------------\n", + "\n", + "file name : 7_63_29+8_63_29+9_63_29+10_108_15+10_108_1_63_29+11_108_15+11_108_1_63_29+33_1_108_15+33_1_108_1_63_29+.csv\n", + "Rules(classes) number : 9\n", + "Words(features) number : 6\n", + "Records number : 18" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.113506eltribunaldecuentatitularpolítico
110.107992eltribunaldecuentatitularpolítico
220.108196eltribunaldecuentatitularpolítico
330.110663eltribunaldecuentatitularpolítico
440.113506eltribunaldecuentatitularpolítico
550.110113eltribunaldecuentatitularpolítico
660.111856eltribunaldecuentatitularpolítico
770.110663eltribunaldecuentatitularpolítico
880.113506eltribunaldecuentatitularpolítico
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.113506 el tribunal de cuenta titular político\n", + "1 1 0.107992 el tribunal de cuenta titular político\n", + "2 2 0.108196 el tribunal de cuenta titular político\n", + "3 3 0.110663 el tribunal de cuenta titular político\n", + "4 4 0.113506 el tribunal de cuenta titular político\n", + "5 5 0.110113 el tribunal de cuenta titular político\n", + "6 6 0.111856 el tribunal de cuenta titular político\n", + "7 7 0.110663 el tribunal de cuenta titular político\n", + "8 8 0.113506 el tribunal de cuenta titular político" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.11350588649411349\n", + "model : LinearSVM , score = 0.11350588649411349\n", + "model : RBFSVM , score = 0.11350588649411349\n", + "model : DecisionTree , score = 0.11350588649411349\n", + "model : RandomForest , score = 0.11066288933711066\n", + "model : AdaBoost , score = 0.11350588649411349\n", + "----------------------------------------------\n", + "\n", + "file name : 40_108_52+37_63_108_52+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 5\n", + "Records number : 6" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.5haberesforzarporlograrlo
110.5haberesforzarporlograrlo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.5 haber esforzar por lograr lo\n", + "1 1 0.5 haber esforzar por lograr lo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.3333333333333333\n", + "model : LinearSVM , score = 0.3333333333333333\n", + "model : RBFSVM , score = 0.3333333333333333\n", + "model : DecisionTree , score = 0.3333333333333333\n", + "model : RandomForest , score = 0.3333333333333333\n", + "model : AdaBoost , score = 0.3333333333333333\n", + "----------------------------------------------\n", + "\n", + "file name : 75_108_52+100_37_108_52+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 5\n", + "Records number : 4" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.524038nollegarahacerlo
110.475962nollegarahacerlo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.524038 no llegar a hacer lo\n", + "1 1 0.475962 no llegar a hacer lo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.524038\n", + "model : LinearSVM , score = 0.524038\n", + "model : RBFSVM , score = 0.524038\n", + "model : DecisionTree , score = 0.524038\n", + "model : RandomForest , score = 0.524038\n", + "model : AdaBoost , score = 0.524038\n", + "----------------------------------------------\n", + "\n", + "file name : 22+12_30+12_110_29+113_1_30+113_1_110_29+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 55" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.196140trespreguntamuyamplio
110.200965trespreguntamuyamplio
220.200965trespreguntamuyamplio
330.200965trespreguntamuyamplio
440.200965trespreguntamuyamplio
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.196140 tres pregunta muy amplio\n", + "1 1 0.200965 tres pregunta muy amplio\n", + "2 2 0.200965 tres pregunta muy amplio\n", + "3 3 0.200965 tres pregunta muy amplio\n", + "4 4 0.200965 tres pregunta muy amplio" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.18761920526265205\n", + "model : RBFSVM , score = 0.18761920526265205\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.10754406011611722\n", + "----------------------------------------------\n", + "\n", + "file name : 21+10_30+10_100_29+11_30+11_100_29+33_1_30+33_1_100_29+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 4\n", + "Records number : 6314" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.139609ningunoresponsableclaramentedefinido
110.139571ningunoresponsableclaramentedefinido
220.139571ningunoresponsableclaramentedefinido
330.151054ningunoresponsableclaramentedefinido
440.151054ningunoresponsableclaramentedefinido
550.139571ningunoresponsableclaramentedefinido
660.139571ningunoresponsableclaramentedefinido
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.139609 ninguno responsable claramente definido\n", + "1 1 0.139571 ninguno responsable claramente definido\n", + "2 2 0.139571 ninguno responsable claramente definido\n", + "3 3 0.151054 ninguno responsable claramente definido\n", + "4 4 0.151054 ninguno responsable claramente definido\n", + "5 5 0.139571 ninguno responsable claramente definido\n", + "6 6 0.139571 ninguno responsable claramente definido" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.13484570998686124\n", + "model : LinearSVM , score = 0.1491420531697449\n", + "model : RBFSVM , score = 0.1491420531697449\n", + "model : DecisionTree , score = 0.1357829061167114\n", + "model : RandomForest , score = 0.1049334948840881\n", + "model : AdaBoost , score = 0.11366428395684831\n", + "----------------------------------------------\n", + "\n", + "file name : 30_64+30_91+30_108_68+100_67+100_63_64+100_63_91+100_63_108_68+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 4\n", + "Records number : 14" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.144291sólohacerdeostentar
110.142893sólohacerdeostentar
220.140671sólohacerdeostentar
330.144291sólohacerdeostentar
440.144291sólohacerdeostentar
550.142893sólohacerdeostentar
660.140671sólohacerdeostentar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.144291 sólo hacer de ostentar\n", + "1 1 0.142893 sólo hacer de ostentar\n", + "2 2 0.140671 sólo hacer de ostentar\n", + "3 3 0.144291 sólo hacer de ostentar\n", + "4 4 0.144291 sólo hacer de ostentar\n", + "5 5 0.142893 sólo hacer de ostentar\n", + "6 6 0.140671 sólo hacer de ostentar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.1442908557091443\n", + "model : LinearSVM , score = 0.1442908557091443\n", + "model : RBFSVM , score = 0.1442908557091443\n", + "model : DecisionTree , score = 0.1442908557091443\n", + "model : RandomForest , score = 0.14067085932914067\n", + "model : AdaBoost , score = 0.1442908557091443\n", + "----------------------------------------------\n", + "\n", + "file name : 107+106_114+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 22" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.492222por_ello?
110.507778por_ello?
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.492222 por_ello ?\n", + "1 1 0.507778 por_ello ?" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.5162341376179551\n", + "model : LinearSVM , score = 0.4837658623820448\n", + "model : RBFSVM , score = 0.4837658623820448\n", + "model : DecisionTree , score = 0.4837658623820448\n", + "model : RandomForest , score = 0.4837658623820448\n", + "model : AdaBoost , score = 0.4837658623820448\n", + "----------------------------------------------\n", + "\n", + "file name : 66_63+108_33_40+108_33_68_63+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 4\n", + "Records number : 12" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: divide by zero encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.332287aelhaberser
110.333856aelhaberser
220.333856aelhaberser
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.332287 a el haber ser\n", + "1 1 0.333856 a el haber ser\n", + "2 2 0.333856 a el haber ser" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.168756715514194\n", + "model : LinearSVM , score = 0.3317720257615749\n", + "model : RBFSVM , score = 0.3317720257615749\n", + "model : DecisionTree , score = 0.168756715514194\n", + "model : RandomForest , score = 0.168756715514194\n", + "model : AdaBoost , score = 0.168756715514194\n", + "----------------------------------------------\n", + "\n", + "file name : 73+47_69+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 3\n", + "Records number : 20" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.516462loestarconsiderar
110.483538loestarconsiderar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.516462 lo estar considerar\n", + "1 1 0.483538 lo estar considerar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.2885738316797356\n", + "model : LinearSVM , score = 0.5246475627579833\n", + "model : RBFSVM , score = 0.5246475627579833\n", + "model : DecisionTree , score = 0.2885738316797356\n", + "model : RandomForest , score = 0.2885738316797356\n", + "model : AdaBoost , score = 0.2885738316797356\n", + "----------------------------------------------\n", + "\n", + "file name : 76+92_63+100_40+100_68_63+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 3\n", + "Records number : 52" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.254160nohaberdar
110.251783nohaberdar
220.247029nohaberdar
330.247029nohaberdar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.254160 no haber dar\n", + "1 1 0.251783 no haber dar\n", + "2 2 0.247029 no haber dar\n", + "3 3 0.247029 no haber dar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.15103283830142405\n", + "model : LinearSVM , score = 0.22423955793981423\n", + "model : RBFSVM , score = 0.22423955793981423\n", + "model : DecisionTree , score = 0.03948810955170136\n", + "model : RandomForest , score = 0.037898620798693966\n", + "model : AdaBoost , score = 0.03948810955170136\n", + "----------------------------------------------\n", + "\n", + "file name : 67+63_64+63_108_68+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 1440" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.333333encaminaracolmar
110.333333encaminaracolmar
220.333333encaminaracolmar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.333333 encaminar a colmar\n", + "1 1 0.333333 encaminar a colmar\n", + "2 2 0.333333 encaminar a colmar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.3036674273824966\n", + "model : LinearSVM , score = 0.30277620674779554\n", + "model : RBFSVM , score = 0.2817275907721134\n", + "model : DecisionTree , score = 0.2409576074269052\n", + "model : RandomForest , score = 0.2251987337310944\n", + "model : AdaBoost , score = 0.2475688472396243\n", + "----------------------------------------------\n", + "\n", + "file name : 108_85+108_100_52+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 4\n", + "Records number : 6" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.504829paranohacerlo
110.495171paranohacerlo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.504829 para no hacer lo\n", + "1 1 0.495171 para no hacer lo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.6778889827349154\n", + "model : LinearSVM , score = 0.3221110172650846\n", + "model : RBFSVM , score = 0.3221110172650846\n", + "model : DecisionTree , score = 0.3221110172650846\n", + "model : RandomForest , score = 0.3221110172650846\n", + "model : AdaBoost , score = 0.3221110172650846\n", + "----------------------------------------------\n", + "\n", + "file name : 75_12+75_113_1+100_13+100_37_12+100_37_113_1+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 20" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.191526allíhacerdosaño
110.191526allíhacerdosaño
220.233895allíhacerdosaño
330.191526allíhacerdosaño
440.191526allíhacerdosaño
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.191526 allí hacer dos año\n", + "1 1 0.191526 allí hacer dos año\n", + "2 2 0.233895 allí hacer dos año\n", + "3 3 0.191526 allí hacer dos año\n", + "4 4 0.191526 allí hacer dos año" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.20502695568933266\n", + "model : RBFSVM , score = 0.20502695568933266\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 38+68_64+68_108_68+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 48" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.342926llegarallevar
110.328537llegarallevar
220.328537llegarallevar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.342926 llegar a llevar\n", + "1 1 0.328537 llegar a llevar\n", + "2 2 0.328537 llegar a llevar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.2800503298865964\n", + "model : LinearSVM , score = 0.35847536180810363\n", + "model : RBFSVM , score = 0.35847536180810363\n", + "model : DecisionTree , score = 0.11863372226489452\n", + "model : RandomForest , score = 0.11863372226489452\n", + "model : AdaBoost , score = 0.15941830265683726\n", + "----------------------------------------------\n", + "\n", + "file name : 94_1+97_108_12+97_108_113_1+108_95_1+108_98_108_12+108_98_108_113_1+108_33_96_1+108_33_99_108_12+108_33_99_108_113_1+108_33_113_108_1_108_12+108_33_113_108_1_108_113_1+.csv\n", + "Rules(classes) number : 11\n", + "Words(features) number : 8\n", + "Records number : 22" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6word7word8
000.099314hastael3dejuliode2008artículo
110.093227hastael3dejuliode2008artículo
220.093227hastael3dejuliode2008artículo
330.093704hastael3dejuliode2008artículo
440.088948hastael3dejuliode2008artículo
550.088948hastael3dejuliode2008artículo
660.093521hastael3dejuliode2008artículo
770.088774hastael3dejuliode2008artículo
880.088774hastael3dejuliode2008artículo
990.085781hastael3dejuliode2008artículo
10100.085781hastael3dejuliode2008artículo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6 word7 word8\n", + "0 0 0.099314 hasta el 3 de julio de 2008 artículo\n", + "1 1 0.093227 hasta el 3 de julio de 2008 artículo\n", + "2 2 0.093227 hasta el 3 de julio de 2008 artículo\n", + "3 3 0.093704 hasta el 3 de julio de 2008 artículo\n", + "4 4 0.088948 hasta el 3 de julio de 2008 artículo\n", + "5 5 0.088948 hasta el 3 de julio de 2008 artículo\n", + "6 6 0.093521 hasta el 3 de julio de 2008 artículo\n", + "7 7 0.088774 hasta el 3 de julio de 2008 artículo\n", + "8 8 0.088774 hasta el 3 de julio de 2008 artículo\n", + "9 9 0.085781 hasta el 3 de julio de 2008 artículo\n", + "10 10 0.085781 hasta el 3 de julio de 2008 artículo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0993142\n", + "model : LinearSVM , score = 0.0993142\n", + "model : RBFSVM , score = 0.0993142\n", + "model : DecisionTree , score = 0.0993142\n", + "model : RandomForest , score = 0.08894850000000001\n", + "model : AdaBoost , score = 0.0993142\n", + "----------------------------------------------\n", + "\n", + "file name : 40_64+40_108_68+37_67+37_63_64+37_63_108_68+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 445" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.2haberentraraformar
110.2haberentraraformar
220.2haberentraraformar
330.2haberentraraformar
440.2haberentraraformar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.2 haber entrar a formar\n", + "1 1 0.2 haber entrar a formar\n", + "2 2 0.2 haber entrar a formar\n", + "3 3 0.2 haber entrar a formar\n", + "4 4 0.2 haber entrar a formar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.15753374623659042\n", + "model : LinearSVM , score = 0.17511385970256155\n", + "model : RBFSVM , score = 0.19861279595487677\n", + "model : DecisionTree , score = 0.053446455252070986\n", + "model : RandomForest , score = 0.05822788654192368\n", + "model : AdaBoost , score = 0.07641758281833691\n", + "----------------------------------------------\n", + "\n", + "file name : 7_29_29+8_29_29+9_29_29+10_108_15+10_108_14_29+10_108_1_29_29+11_108_15+11_108_14_29+11_108_1_29_29+33_1_108_15+33_1_108_14_29+33_1_108_1_29_29+.csv\n", + "Rules(classes) number : 12\n", + "Words(features) number : 6\n", + "Records number : 708" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.081911elconveniodeginebraderechohumanitario
110.087933elconveniodeginebraderechohumanitario
220.085374elconveniodeginebraderechohumanitario
330.083864elconveniodeginebraderechohumanitario
440.083349elconveniodeginebraderechohumanitario
550.081911elconveniodeginebraderechohumanitario
660.082985elconveniodeginebraderechohumanitario
770.082480elconveniodeginebraderechohumanitario
880.081071elconveniodeginebraderechohumanitario
990.083864elconveniodeginebraderechohumanitario
10100.083349elconveniodeginebraderechohumanitario
11110.081911elconveniodeginebraderechohumanitario
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.081911 el convenio de ginebra derecho humanitario\n", + "1 1 0.087933 el convenio de ginebra derecho humanitario\n", + "2 2 0.085374 el convenio de ginebra derecho humanitario\n", + "3 3 0.083864 el convenio de ginebra derecho humanitario\n", + "4 4 0.083349 el convenio de ginebra derecho humanitario\n", + "5 5 0.081911 el convenio de ginebra derecho humanitario\n", + "6 6 0.082985 el convenio de ginebra derecho humanitario\n", + "7 7 0.082480 el convenio de ginebra derecho humanitario\n", + "8 8 0.081071 el convenio de ginebra derecho humanitario\n", + "9 9 0.083864 el convenio de ginebra derecho humanitario\n", + "10 10 0.083349 el convenio de ginebra derecho humanitario\n", + "11 11 0.081911 el convenio de ginebra derecho humanitario" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.04779147271034485\n", + "model : LinearSVM , score = 0.058570542697414935\n", + "model : RBFSVM , score = 0.0854309586301861\n", + "model : DecisionTree , score = 0.02643110905790252\n", + "model : RandomForest , score = 0.008685935557837875\n", + "model : AdaBoost , score = 0.019361885843466525\n", + "----------------------------------------------\n", + "\n", + "file name : 27+21_106_29+10_30_106_29+10_100_29_106_29+11_30_106_29+11_100_29_106_29+33_1_30_106_29+33_1_100_29_106_29+.csv\n", + "Rules(classes) number : 8\n", + "Words(features) number : 6\n", + "Records number : 264" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.127872unopapelmásactivoyindependiente
110.121875unopapelmásactivoyindependiente
220.124957unopapelmásactivoyindependiente
330.124957unopapelmásactivoyindependiente
440.125213unopapelmásactivoyindependiente
550.125213unopapelmásactivoyindependiente
660.124957unopapelmásactivoyindependiente
770.124957unopapelmásactivoyindependiente
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.127872 uno papel más activo y independiente\n", + "1 1 0.121875 uno papel más activo y independiente\n", + "2 2 0.124957 uno papel más activo y independiente\n", + "3 3 0.124957 uno papel más activo y independiente\n", + "4 4 0.125213 uno papel más activo y independiente\n", + "5 5 0.125213 uno papel más activo y independiente\n", + "6 6 0.124957 uno papel más activo y independiente\n", + "7 7 0.124957 uno papel más activo y independiente" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0542559900037661\n", + "model : LinearSVM , score = 0.08926087280201091\n", + "model : RBFSVM , score = 0.12326377231319587\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0769822895774275\n", + "----------------------------------------------\n", + "\n", + "file name : 20_106_29+12_29_106_29+113_23+113_24+113_14_106_29+113_1_29_106_29+.csv\n", + "Rules(classes) number : 6\n", + "Words(features) number : 5\n", + "Records number : 12" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.168775seisobjetivodiferenteydiverso
110.165523seisobjetivodiferenteydiverso
220.162509seisobjetivodiferenteydiverso
330.168894seisobjetivodiferenteydiverso
440.168775seisobjetivodiferenteydiverso
550.165523seisobjetivodiferenteydiverso
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.168775 seis objetivo diferente y diverso\n", + "1 1 0.165523 seis objetivo diferente y diverso\n", + "2 2 0.162509 seis objetivo diferente y diverso\n", + "3 3 0.168894 seis objetivo diferente y diverso\n", + "4 4 0.168775 seis objetivo diferente y diverso\n", + "5 5 0.165523 seis objetivo diferente y diverso" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.1687751687751688\n", + "model : LinearSVM , score = 0.16889416889416892\n", + "model : RBFSVM , score = 0.16889416889416892\n", + "model : DecisionTree , score = 0.16889416889416892\n", + "model : RandomForest , score = 0.1687751687751688\n", + "model : AdaBoost , score = 0.16889416889416892\n", + "----------------------------------------------\n", + "\n", + "file name : 24+1_63_106_29+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 4\n", + "Records number : 6" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.505526inmigraciónequilibrarycoherente
110.494474inmigraciónequilibrarycoherente
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.505526 inmigración equilibrar y coherente\n", + "1 1 0.494474 inmigración equilibrar y coherente" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.3298335598322446\n", + "model : LinearSVM , score = 0.3298335598322446\n", + "model : RBFSVM , score = 0.3298335598322446\n", + "model : DecisionTree , score = 0.3298335598322446\n", + "model : RandomForest , score = 0.3298335598322446\n", + "model : AdaBoost , score = 0.3298335598322446\n", + "----------------------------------------------\n", + "\n", + "file name : 96+99_108_113+113_108_1_108_113+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 5\n", + "Records number : 255" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.3769281deenerode2003
110.3297941deenerode2003
220.2932781deenerode2003
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.376928 1 de enero de 2003\n", + "1 1 0.329794 1 de enero de 2003\n", + "2 2 0.293278 1 de enero de 2003" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.28492173347494804\n", + "model : LinearSVM , score = 0.3367974223858633\n", + "model : RBFSVM , score = 0.39453017910222304\n", + "model : DecisionTree , score = 0.17837654888961102\n", + "model : RandomForest , score = 0.1659894936543952\n", + "model : AdaBoost , score = 0.2195843182352461\n", + "----------------------------------------------\n", + "\n", + "file name : 30+100_63+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 1076" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.5de_alguna_maneraocultar
110.5de_alguna_maneraocultar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.5 de_alguna_manera ocultar\n", + "1 1 0.5 de_alguna_manera ocultar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.4572205314900661\n", + "model : LinearSVM , score = 0.4647990828862173\n", + "model : RBFSVM , score = 0.2732230548762148\n", + "model : DecisionTree , score = 0.4237193577408349\n", + "model : RandomForest , score = 0.38300158878767293\n", + "model : AdaBoost , score = 0.3903416770705051\n", + "----------------------------------------------\n", + "\n", + "file name : 84_69+100_73+100_47_69+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 4\n", + "Records number : 15" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.296842hoyloestardebatir
110.406315hoyloestardebatir
220.296842hoyloestardebatir
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.296842 hoy lo estar debatir\n", + "1 1 0.406315 hoy lo estar debatir\n", + "2 2 0.296842 hoy lo estar debatir" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.11115762827378055\n", + "model : LinearSVM , score = 0.2336983141481243\n", + "model : RBFSVM , score = 0.2336983141481243\n", + "model : DecisionTree , score = 0.11115762827378055\n", + "model : RandomForest , score = 0.11115762827378055\n", + "model : AdaBoost , score = 0.11115762827378055\n", + "----------------------------------------------\n", + "\n", + "file name : 10_63_29+11_63_29+33_15+33_1_63_29+.csv\n", + "Rules(classes) number : 4\n", + "Words(features) number : 4\n", + "Records number : 84" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.247563unosistemainformatizareficaz
110.247210unosistemainformatizareficaz
220.257664unosistemainformatizareficaz
330.247563unosistemainformatizareficaz
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.247563 uno sistema informatizar eficaz\n", + "1 1 0.247210 uno sistema informatizar eficaz\n", + "2 2 0.257664 uno sistema informatizar eficaz\n", + "3 3 0.247563 uno sistema informatizar eficaz" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.11849355553125353\n", + "model : LinearSVM , score = 0.19053970371076076\n", + "model : RBFSVM , score = 0.23823980418499188\n", + "model : DecisionTree , score = 0.0694058122852295\n", + "model : RandomForest , score = 0.046491304325740085\n", + "model : AdaBoost , score = 0.11843892392606487\n", + "----------------------------------------------\n", + "\n", + "file name : 64_64+64_108_68+108_38+108_68_64+108_68_108_68+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 25" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.202745parallegaraconseguir
110.202745parallegaraconseguir
220.204575parallegaraconseguir
330.194967parallegaraconseguir
440.194967parallegaraconseguir
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.202745 para llegar a conseguir\n", + "1 1 0.202745 para llegar a conseguir\n", + "2 2 0.204575 para llegar a conseguir\n", + "3 3 0.194967 para llegar a conseguir\n", + "4 4 0.194967 para llegar a conseguir" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.1535092359942748\n", + "model : LinearSVM , score = 0.15974950555717687\n", + "model : RBFSVM , score = 0.15974950555717687\n", + "model : DecisionTree , score = 0.07794581534522631\n", + "model : RandomForest , score = 0.07560799123470986\n", + "model : AdaBoost , score = 0.15974950555717687\n", + "----------------------------------------------\n", + "\n", + "file name : 60+47_68+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 3\n", + "Records number : 16" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.5lopoderconstatar
110.5lopoderconstatar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.5 lo poder constatar\n", + "1 1 0.5 lo poder constatar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.3907131479265588\n", + "model : LinearSVM , score = 0.5187070811770713\n", + "model : RBFSVM , score = 0.5187070811770713\n", + "model : DecisionTree , score = 0.3907131479265588\n", + "model : RandomForest , score = 0.3907131479265588\n", + "model : AdaBoost , score = 0.3907131479265588\n", + "----------------------------------------------\n", + "\n", + "file name : 38+37_64+37_108_68+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 51" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.354531llegaraser
110.322735llegaraser
220.322735llegaraser
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.354531 llegar a ser\n", + "1 1 0.322735 llegar a ser\n", + "2 2 0.322735 llegar a ser" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.23554661057521825\n", + "model : LinearSVM , score = 0.2961067303875821\n", + "model : RBFSVM , score = 0.18448152174300372\n", + "model : DecisionTree , score = 0.1981366276139268\n", + "model : RandomForest , score = 0.19869171041483163\n", + "model : AdaBoost , score = 0.1981366276139268\n", + "----------------------------------------------\n", + "\n", + "file name : 32+33_30+33_100_29+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 456" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.340749elmásmoderno
110.329626elmásmoderno
220.329626elmásmoderno
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.340749 el más moderno\n", + "1 1 0.329626 el más moderno\n", + "2 2 0.329626 el más moderno" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.31015551879539377\n", + "model : LinearSVM , score = 0.3302076467085666\n", + "model : RBFSVM , score = 0.33077810202475727\n", + "model : DecisionTree , score = 0.27999006952059113\n", + "model : RandomForest , score = 0.2324501225530451\n", + "model : AdaBoost , score = 0.23169006359161295\n", + "----------------------------------------------\n", + "\n", + "file name : 40+69_63+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 8" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.5haberescuchar
110.5haberescuchar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.5 haber escuchar\n", + "1 1 0.5 haber escuchar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.25\n", + "model : LinearSVM , score = 0.25\n", + "model : RBFSVM , score = 0.25\n", + "model : DecisionTree , score = 0.25\n", + "model : RandomForest , score = 0.25\n", + "model : AdaBoost , score = 0.25\n", + "----------------------------------------------\n", + "\n", + "file name : 18_106_63+17_29_106_63+31_23+31_14_106_63+31_1_29_106_63+33_29_23+33_29_14_106_63+33_29_1_29_106_63+.csv\n", + "Rules(classes) number : 8\n", + "Words(features) number : 6\n", + "Records number : 16" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.130386elactualestructurapresupuestarioydeterminar
110.121098elactualestructurapresupuestarioydeterminar
220.122773elactualestructurapresupuestarioydeterminar
330.130386elactualestructurapresupuestarioydeterminar
440.121098elactualestructurapresupuestarioydeterminar
550.122773elactualestructurapresupuestarioydeterminar
660.130386elactualestructurapresupuestarioydeterminar
770.121098elactualestructurapresupuestarioydeterminar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.130386 el actual estructura presupuestario y determinar\n", + "1 1 0.121098 el actual estructura presupuestario y determinar\n", + "2 2 0.122773 el actual estructura presupuestario y determinar\n", + "3 3 0.130386 el actual estructura presupuestario y determinar\n", + "4 4 0.121098 el actual estructura presupuestario y determinar\n", + "5 5 0.122773 el actual estructura presupuestario y determinar\n", + "6 6 0.130386 el actual estructura presupuestario y determinar\n", + "7 7 0.121098 el actual estructura presupuestario y determinar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.13038626077252155\n", + "model : LinearSVM , score = 0.13038626077252155\n", + "model : RBFSVM , score = 0.13038626077252155\n", + "model : DecisionTree , score = 0.13038626077252155\n", + "model : RandomForest , score = 0.13038626077252155\n", + "model : AdaBoost , score = 0.13038626077252155\n", + "----------------------------------------------\n", + "\n", + "file name : 75+100_36+100_37+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 2\n", + "Records number : 312" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.328514nohaber_que
110.335654nohaber_que
220.335831nohaber_que
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.328514 no haber_que\n", + "1 1 0.335654 no haber_que\n", + "2 2 0.335831 no haber_que" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.297156053940856\n", + "model : LinearSVM , score = 0.30364650810851324\n", + "model : RBFSVM , score = 0.27833199568512473\n", + "model : DecisionTree , score = 0.29661452526235416\n", + "model : RandomForest , score = 0.27751982744798837\n", + "model : AdaBoost , score = 0.25890578456830055\n", + "----------------------------------------------\n", + "\n", + "file name : 31+33_29+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 3450" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.5elúltimo
110.5elúltimo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.5 el último\n", + "1 1 0.5 el último" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.489499313017107\n", + "model : LinearSVM , score = 0.500640208963022\n", + "model : RBFSVM , score = 0.40714635803619653\n", + "model : DecisionTree , score = 0.4665642676145503\n", + "model : RandomForest , score = 0.45032754557246746\n", + "model : AdaBoost , score = 0.4576052390901414\n", + "----------------------------------------------\n", + "\n", + "file name : 39+40_64+40_108_68+37_38+37_67+37_63_64+37_63_108_68+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 4\n", + "Records number : 28" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.159656haberllegaraalcanzar
110.136138haberllegaraalcanzar
220.136138haberllegaraalcanzar
330.159656haberllegaraalcanzar
440.136138haberllegaraalcanzar
550.136138haberllegaraalcanzar
660.136138haberllegaraalcanzar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.159656 haber llegar a alcanzar\n", + "1 1 0.136138 haber llegar a alcanzar\n", + "2 2 0.136138 haber llegar a alcanzar\n", + "3 3 0.159656 haber llegar a alcanzar\n", + "4 4 0.136138 haber llegar a alcanzar\n", + "5 5 0.136138 haber llegar a alcanzar\n", + "6 6 0.136138 haber llegar a alcanzar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.15303900968914755\n", + "model : RBFSVM , score = 0.15303900968914755\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 32_64+32_108_68+33_30_64+33_30_108_68+33_100_67+33_100_63_64+33_100_63_108_68+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 5\n", + "Records number : 14" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.148288elmáscualificarparaorganizar
110.140989elmáscualificarparaorganizar
220.145447elmáscualificarparaorganizar
330.137192elmáscualificarparaorganizar
440.145447elmáscualificarparaorganizar
550.145447elmáscualificarparaorganizar
660.137192elmáscualificarparaorganizar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.148288 el más cualificar para organizar\n", + "1 1 0.140989 el más cualificar para organizar\n", + "2 2 0.145447 el más cualificar para organizar\n", + "3 3 0.137192 el más cualificar para organizar\n", + "4 4 0.145447 el más cualificar para organizar\n", + "5 5 0.145447 el más cualificar para organizar\n", + "6 6 0.137192 el más cualificar para organizar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.14828770342459316\n", + "model : LinearSVM , score = 0.14828770342459316\n", + "model : RBFSVM , score = 0.14828770342459316\n", + "model : DecisionTree , score = 0.14828770342459316\n", + "model : RandomForest , score = 0.14828770342459316\n", + "model : AdaBoost , score = 0.14828770342459316\n", + "----------------------------------------------\n", + "\n", + "file name : 76+100_40+100_69_63+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 6" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.335418nohaberpresentar
110.317747nohaberpresentar
220.346834nohaberpresentar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.335418 no haber presentar\n", + "1 1 0.317747 no haber presentar\n", + "2 2 0.346834 no haber presentar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.3354183354183354\n", + "model : LinearSVM , score = 0.34683434683434683\n", + "model : RBFSVM , score = 0.34683434683434683\n", + "model : DecisionTree , score = 0.34683434683434683\n", + "model : RandomForest , score = 0.31774731774731774\n", + "model : AdaBoost , score = 0.34683434683434683\n", + "----------------------------------------------\n", + "\n", + "file name : 40_64+40_108_68+68_67+68_63_64+68_63_108_68+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 10" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.2haberlimitararealizar
110.2haberlimitararealizar
220.2haberlimitararealizar
330.2haberlimitararealizar
440.2haberlimitararealizar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.2 haber limitar a realizar\n", + "1 1 0.2 haber limitar a realizar\n", + "2 2 0.2 haber limitar a realizar\n", + "3 3 0.2 haber limitar a realizar\n", + "4 4 0.2 haber limitar a realizar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.20244410771241195\n", + "model : RBFSVM , score = 0.20244410771241195\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 99_29+113_108_14+113_108_1_29+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 4\n", + "Records number : 6" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.33689021deseptiembrepróximo
110.33798221deseptiembrepróximo
220.32512921deseptiembrepróximo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.336890 21 de septiembre próximo\n", + "1 1 0.337982 21 de septiembre próximo\n", + "2 2 0.325129 21 de septiembre próximo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.33688966311033686\n", + "model : LinearSVM , score = 0.33798166201833796\n", + "model : RBFSVM , score = 0.33798166201833796\n", + "model : DecisionTree , score = 0.33798166201833796\n", + "model : RandomForest , score = 0.33688966311033686\n", + "model : AdaBoost ," + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + " score = 0.33798166201833796\n", + "----------------------------------------------\n", + "\n", + "file name : 22+12_30+12_110_63+113_1_30+113_1_110_63+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 10" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.208152doscolegatanexperimentar
110.197962doscolegatanexperimentar
220.197962doscolegatanexperimentar
330.197962doscolegatanexperimentar
440.197962doscolegatanexperimentar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.208152 dos colega tan experimentar\n", + "1 1 0.197962 dos colega tan experimentar\n", + "2 2 0.197962 dos colega tan experimentar\n", + "3 3 0.197962 dos colega tan experimentar\n", + "4 4 0.197962 dos colega tan experimentar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.208152\n", + "model : LinearSVM , score = 0.208152\n", + "model : RBFSVM , score = 0.208152\n", + "model : DecisionTree , score = 0.208152\n", + "model : RandomForest , score = 0.208152\n", + "model : AdaBoost , score = 0.208152\n", + "----------------------------------------------\n", + "\n", + "file name : 36+37+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 1\n", + "Records number : 836" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1
000.506138haber_que
110.493862haber_que
\n", + "
" + ], + "text/plain": [ + " rule weight word1\n", + "0 0 0.506138 haber_que\n", + "1 1 0.493862 haber_que" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.5010786051719591\n", + "model : LinearSVM , score = 0.5010786051719591\n", + "model : RBFSVM , score = 0.5010786051719591\n", + "model : DecisionTree , score = 0.5010786051719591\n", + "model : RandomForest , score = 0.5010786051719591\n", + "model : AdaBoost , score = 0.5010786051719591\n", + "----------------------------------------------\n", + "\n", + "file name : 18_106+17_29_106+31_24+31_14_106+31_1_29_106+33_29_24+33_29_14_106+33_29_1_29_106+.csv\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Rules(classes) number : 8\n", + "Words(features) number : 5\n", + "Records number : 216" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.125313eldistintocondicióngeográficoy
110.123135eldistintocondicióngeográficoy
220.127328eldistintocondicióngeográficoy
330.125313eldistintocondicióngeográficoy
440.123135eldistintocondicióngeográficoy
550.127328eldistintocondicióngeográficoy
660.125313eldistintocondicióngeográficoy
770.123135eldistintocondicióngeográficoy
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.125313 el distinto condición geográfico y\n", + "1 1 0.123135 el distinto condición geográfico y\n", + "2 2 0.127328 el distinto condición geográfico y\n", + "3 3 0.125313 el distinto condición geográfico y\n", + "4 4 0.123135 el distinto condición geográfico y\n", + "5 5 0.127328 el distinto condición geográfico y\n", + "6 6 0.125313 el distinto condición geográfico y\n", + "7 7 0.123135 el distinto condición geográfico y" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.08375096177689977\n", + "model : LinearSVM , score = 0.06595154882580584\n", + "model : RBFSVM , score = 0.12189498544976621\n", + "model : DecisionTree , score = 0.009444793672452916\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.04690395659934957\n", + "----------------------------------------------\n", + "\n", + "file name : 67_63+63_65+63_64_63+63_91_63+63_108_40+63_108_68_63+.csv\n", + "Rules(classes) number : 6\n", + "Words(features) number : 4\n", + "Records number : 12" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.164068acusardehaberencargar
110.153241acusardehaberencargar
220.164068acusardehaberencargar
330.190487acusardehaberencargar
440.164068acusardehaberencargar
550.164068acusardehaberencargar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.164068 acusar de haber encargar\n", + "1 1 0.153241 acusar de haber encargar\n", + "2 2 0.164068 acusar de haber encargar\n", + "3 3 0.190487 acusar de haber encargar\n", + "4 4 0.164068 acusar de haber encargar\n", + "5 5 0.164068 acusar de haber encargar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.16406800000000002\n", + "model : LinearSVM , score = 0.190487\n", + "model : RBFSVM , score = 0.190487\n", + "model : DecisionTree , score = 0.190487\n", + "model : RandomForest , score = 0.16406800000000002\n", + "model : AdaBoost ," + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + " score = 0.190487\n", + "----------------------------------------------\n", + "\n", + "file name : 18+17_29+31_14+31_1_29+33_29_14+33_29_1_29+.csv\n", + "Rules(classes) number : 6\n", + "Words(features) number : 4\n", + "Records number : 5040" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.169627suyopropioanálisispolítico
110.163536suyopropioanálisispolítico
220.169627suyopropioanálisispolítico
330.163792suyopropioanálisispolítico
440.169627suyopropioanálisispolítico
550.163792suyopropioanálisispolítico
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.169627 suyo propio análisis político\n", + "1 1 0.163536 suyo propio análisis político\n", + "2 2 0.169627 suyo propio análisis político\n", + "3 3 0.163792 suyo propio análisis político\n", + "4 4 0.169627 suyo propio análisis político\n", + "5 5 0.163792 suyo propio análisis político" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.15442273131374676\n", + "model : LinearSVM , score = 0.16483321148477884\n", + "model : RBFSVM , score = 0.17021238841374622\n", + "model : DecisionTree , score = 0.12652932765832817\n", + "model : RandomForest , score = 0.10259509639472521\n", + "model : AdaBoost , score = 0.1258932983112584\n", + "----------------------------------------------\n", + "\n", + "file name : 75_64+75_108_68+100_38+100_37_64+100_37_108_68+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 40" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.197488inclusollegaraponer
110.197488inclusollegaraponer
220.210048inclusollegaraponer
330.197488inclusollegaraponer
440.197488inclusollegaraponer
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.197488 incluso llegar a poner\n", + "1 1 0.197488 incluso llegar a poner\n", + "2 2 0.210048 incluso llegar a poner\n", + "3 3 0.197488 incluso llegar a poner\n", + "4 4 0.197488 incluso llegar a poner" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.04963963207633959\n", + "model : LinearSVM , score = 0.2079680095233451\n", + "model : RBFSVM , score = 0.2079680095233451\n", + "model : DecisionTree , score = 0.052796653155487816\n", + "model : RandomForest , score = 0.052796653155487816\n", + "model : AdaBoost , score = 0.052796653155487816\n", + "----------------------------------------------\n", + "\n", + "file name : 40_64+40_91+40_108_68+37_67+37_63_64+37_63_91+37_63_108_68+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 4\n", + "Records number : 91" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.144200habertratardemejorar
110.141673habertratardemejorar
220.139854habertratardemejorar
330.144200habertratardemejorar
440.144200habertratardemejorar
550.141673habertratardemejorar
660.144200habertratardemejorar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.144200 haber tratar de mejorar\n", + "1 1 0.141673 haber tratar de mejorar\n", + "2 2 0.139854 haber tratar de mejorar\n", + "3 3 0.144200 haber tratar de mejorar\n", + "4 4 0.144200 haber tratar de mejorar\n", + "5 5 0.141673 haber tratar de mejorar\n", + "6 6 0.144200 haber tratar de mejorar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.04232042772474502\n", + "model : LinearSVM , score = 0.13311660024331154\n", + "model : RBFSVM , score = 0.13311660024331154\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.02119754231305326\n", + "model : AdaBoost , score = 0.0653773982389182\n", + "----------------------------------------------\n", + "\n", + "file name : 76_64+76_108_68+75_67+75_63_64+75_63_108_68+100_40_64+100_40_108_68+100_37_67+100_37_63_64+100_37_63_108_68+.csv\n", + "Rules(classes) number : 10\n", + "Words(features) number : 5\n", + "Records number : 140" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.1ahorahabervolveraser
110.1ahorahabervolveraser
220.1ahorahabervolveraser
330.1ahorahabervolveraser
440.1ahorahabervolveraser
550.1ahorahabervolveraser
660.1ahorahabervolveraser
770.1ahorahabervolveraser
880.1ahorahabervolveraser
990.1ahorahabervolveraser
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.1 ahora haber volver a ser\n", + "1 1 0.1 ahora haber volver a ser\n", + "2 2 0.1 ahora haber volver a ser\n", + "3 3 0.1 ahora haber volver a ser\n", + "4 4 0.1 ahora haber volver a ser\n", + "5 5 0.1 ahora haber volver a ser\n", + "6 6 0.1 ahora haber volver a ser\n", + "7 7 0.1 ahora haber volver a ser\n", + "8 8 0.1 ahora haber volver a ser\n", + "9 9 0.1 ahora haber volver a ser" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.029109801540275218\n", + "model : LinearSVM , score = 0.10136400242342919\n", + "model : RBFSVM , score = 0.10136400242342919\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.05738313227876574\n", + "----------------------------------------------\n", + "\n", + "file name : 99+113_108_1+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 3\n", + "Records number : 110" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.52336918denoviembre
110.47663118denoviembre
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.523369 18 de noviembre\n", + "1 1 0.476631 18 de noviembre" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.46647297102853236\n", + "model : LinearSVM , score = 0.4616156736822202\n", + "model : RBFSVM , score = 0.4927045780339101\n", + "model : DecisionTree , score = 0.3703357021742049\n", + "model : RandomForest , score = 0.29095544220379604\n", + "model : AdaBoost , score = 0.3344475953181826\n", + "----------------------------------------------\n", + "\n", + "file name : 15+1_63_29+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 3\n", + "Records number : 12" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.522456normaarmonizarcomún
110.477544normaarmonizarcomún
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.522456 norma armonizar común\n", + "1 1 0.477544 norma armonizar común" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.17453341368671002\n", + "model : LinearSVM , score = 0.5096781499837646\n", + "model : RBFSVM , score = 0.5096781499837646\n", + "model : DecisionTree , score = 0.17453341368671002\n", + "model : RandomForest , score = 0.17453341368671002\n", + "model : AdaBoost , score = 0.17453341368671002\n", + "----------------------------------------------\n", + "\n", + "file name : 79+84_63+100_42+100_45_63+100_47_63+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 15" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.227411nolohaberser
110.194775nolohaberser
220.210592nolohaberser
330.178748nolohaberser
440.188474nolohaberser
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.227411 no lo haber ser\n", + "1 1 0.194775 no lo haber ser\n", + "2 2 0.210592 no lo haber ser\n", + "3 3 0.178748 no lo haber ser\n", + "4 4 0.188474 no lo haber ser" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.12847496543948675\n", + "model : RBFSVM , score = 0.12847496543948675\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 22+12_30+12_100_63+113_1_30+113_1_100_63+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 30" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.203416trestemaestrechamenteinterrelacionar
110.199146trestemaestrechamenteinterrelacionar
220.199146trestemaestrechamenteinterrelacionar
330.199146trestemaestrechamenteinterrelacionar
440.199146trestemaestrechamenteinterrelacionar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.203416 tres tema estrechamente interrelacionar\n", + "1 1 0.199146 tres tema estrechamente interrelacionar\n", + "2 2 0.199146 tres tema estrechamente interrelacionar\n", + "3 3 0.199146 tres tema estrechamente interrelacionar\n", + "4 4 0.199146 tres tema estrechamente interrelacionar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.1325296415453355\n", + "model : LinearSVM , score = 0.19959612235054666\n", + "model : RBFSVM , score = 0.19959612235054666\n", + "model : DecisionTree , score = 0.06596999538879848\n", + "model : RandomForest , score = 0.06596999538879848\n", + "model : AdaBoost , score = 0.06596999538879848\n", + "----------------------------------------------\n", + "\n", + "file name : 21_64+21_108_68+10_30_64+10_30_108_68+10_100_67+10_100_63_64+10_100_63_108_68+11_30_64+11_30_108_68+11_100_67+11_100_63_64+11_100_63_108_68+33_1_30_64+33_1_30_108_68+33_1_100_67+33_1_100_63_64+33_1_100_63_108_68+.csv\n", + "Rules(classes) number : 17\n", + "Words(features) number : 6\n", + "Records number : 34" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.061179nuestrodiputadomásacostumbraraintervenir
110.057171nuestrodiputadomásacostumbraraintervenir
220.057728nuestrodiputadomásacostumbraraintervenir
330.057728nuestrodiputadomásacostumbraraintervenir
440.057728nuestrodiputadomásacostumbraraintervenir
550.057728nuestrodiputadomásacostumbraraintervenir
660.057728nuestrodiputadomásacostumbraraintervenir
770.060875nuestrodiputadomásacostumbraraintervenir
880.060875nuestrodiputadomásacostumbraraintervenir
990.060875nuestrodiputadomásacostumbraraintervenir
10100.060875nuestrodiputadomásacostumbraraintervenir
11110.060875nuestrodiputadomásacostumbraraintervenir
12120.057728nuestrodiputadomásacostumbraraintervenir
13130.057728nuestrodiputadomásacostumbraraintervenir
14140.057728nuestrodiputadomásacostumbraraintervenir
15150.057728nuestrodiputadomásacostumbraraintervenir
16160.057728nuestrodiputadomásacostumbraraintervenir
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.061179 nuestro diputado más acostumbrar a intervenir\n", + "1 1 0.057171 nuestro diputado más acostumbrar a intervenir\n", + "2 2 0.057728 nuestro diputado más acostumbrar a intervenir\n", + "3 3 0.057728 nuestro diputado más acostumbrar a intervenir\n", + "4 4 0.057728 nuestro diputado más acostumbrar a intervenir\n", + "5 5 0.057728 nuestro diputado más acostumbrar a intervenir\n", + "6 6 0.057728 nuestro diputado más acostumbrar a intervenir\n", + "7 7 0.060875 nuestro diputado más acostumbrar a intervenir\n", + "8 8 0.060875 nuestro diputado más acostumbrar a intervenir\n", + "9 9 0.060875 nuestro diputado más acostumbrar a intervenir\n", + "10 10 0.060875 nuestro diputado más acostumbrar a intervenir\n", + "11 11 0.060875 nuestro diputado más acostumbrar a intervenir\n", + "12 12 0.057728 nuestro diputado más acostumbrar a intervenir\n", + "13 13 0.057728 nuestro diputado más acostumbrar a intervenir\n", + "14 14 0.057728 nuestro diputado más acostumbrar a intervenir\n", + "15 15 0.057728 nuestro diputado más acostumbrar a intervenir\n", + "16 16 0.057728 nuestro diputado más acostumbrar a intervenir" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.061179375528249785\n", + "model : LinearSVM , score = 0.061179375528249785\n", + "model : RBFSVM , score = 0.061179375528249785\n", + "model : DecisionTree , score = 0.061179375528249785\n", + "model : RandomForest , score = 0.05772767690892923\n", + "model : AdaBoost , score = 0.061179375528249785\n", + "----------------------------------------------\n", + "\n", + "file name : 30_108_52+100_63_108_52+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 5\n", + "Records number : 4" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5
000.5demasiadoasustarparahacerlo
110.5demasiadoasustarparahacerlo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5\n", + "0 0 0.5 demasiado asustar para hacer lo\n", + "1 1 0.5 demasiado asustar para hacer lo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.0\n", + "model : RBFSVM , score = 0.0\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 85+100_52+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 3\n", + "Records number : 18" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.499061noutilizarlo
110.500939noutilizarlo
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.499061 no utilizar lo\n", + "1 1 0.500939 no utilizar lo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.2236238975351392\n", + "model : LinearSVM , score = 0.44156793810892925\n", + "model : RBFSVM , score = 0.44156793810892925\n", + "model : DecisionTree , score = 0.2236238975351392\n", + "model : RandomForest , score = 0.2236238975351392\n", + "model : AdaBoost , score = 0.2236238975351392\n", + "----------------------------------------------\n", + "\n", + "file name : 66+108_33_68+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 3\n", + "Records number : 308" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.492659aelseñalar
110.507341aelseñalar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.492659 a el señalar\n", + "1 1 0.507341 a el señalar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.461297191301524\n", + "model : LinearSVM , score = 0.46970196445060763\n", + "model : RBFSVM , score = 0.28830592251804876\n", + "model : DecisionTree , score = 0.4122573664704467\n", + "model : RandomForest , score = 0.36884414076967253\n", + "model : AdaBoost , score = 0.37300673572156284\n", + "----------------------------------------------\n", + "\n", + "file name : 42+47_63+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 3\n", + "Records number : 244" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.499704lohaberser
110.500296lohaberser
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.499704 lo haber ser\n", + "1 1 0.500296 lo haber ser" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.38677502238711753\n", + "model : LinearSVM , score = 0.4636285737988887\n", + "model : RBFSVM , score = 0.3184207452419576\n", + "model : DecisionTree , score = 0.3351521422881191\n", + "model : RandomForest , score = 0.35993603057560336\n", + "model : AdaBoost , score = 0.3624322759665186\n", + "----------------------------------------------\n", + "\n", + "file name : 21+10_30+10_100_63+11_30+11_100_63+33_1_30+33_1_100_63+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 4\n", + "Records number : 1120" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.144982unosistematotalmentedescentralizar
110.142143unosistematotalmentedescentralizar
220.142143unosistematotalmentedescentralizar
330.143223unosistematotalmentedescentralizar
440.143223unosistematotalmentedescentralizar
550.142143unosistematotalmentedescentralizar
660.142143unosistematotalmentedescentralizar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.144982 uno sistema totalmente descentralizar\n", + "1 1 0.142143 uno sistema totalmente descentralizar\n", + "2 2 0.142143 uno sistema totalmente descentralizar\n", + "3 3 0.143223 uno sistema totalmente descentralizar\n", + "4 4 0.143223 uno sistema totalmente descentralizar\n", + "5 5 0.142143 uno sistema totalmente descentralizar\n", + "6 6 0.142143 uno sistema totalmente descentralizar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.1177903737614213\n", + "model : LinearSVM , score = 0.1120123893124631\n", + "model : RBFSVM , score = 0.1436045515362441\n", + "model : DecisionTree , score = 0.05609071186648488\n", + "model : RandomForest , score = 0.04315566291476371\n", + "model : AdaBoost , score = 0.08045588756829092\n", + "----------------------------------------------\n", + "\n", + "file name : 96_1+99_108_12+99_108_113_1+113_108_1_108_12+113_108_1_108_113_1+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 6\n", + "Records number : 20" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6
000.24152415dediciembrede2006continuación
110.20130415dediciembrede2006continuación
220.20130415dediciembrede2006continuación
330.17793415dediciembrede2006continuación
440.17793415dediciembrede2006continuación
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6\n", + "0 0 0.241524 15 de diciembre de 2006 continuación\n", + "1 1 0.201304 15 de diciembre de 2006 continuación\n", + "2 2 0.201304 15 de diciembre de 2006 continuación\n", + "3 3 0.177934 15 de diciembre de 2006 continuación\n", + "4 4 0.177934 15 de diciembre de 2006 continuación" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.0\n", + "model : LinearSVM , score = 0.2413839808040335\n", + "model : RBFSVM , score = 0.2413839808040335\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.0\n", + "----------------------------------------------\n", + "\n", + "file name : 47_64+47_108_68+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 4\n", + "Records number : 4" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.5lollegarasaber
110.5lollegarasaber
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.5 lo llegar a saber\n", + "1 1 0.5 lo llegar a saber" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.5\n", + "model : LinearSVM , score = 0.5\n", + "model : RBFSVM , score = 0.5\n", + "model : DecisionTree , score = 0.5\n", + "model : RandomForest , score = 0.5\n", + "model : AdaBoost , score = 0.5\n", + "----------------------------------------------\n", + "\n", + "file name : 21+10_30+10_110_63+11_30+11_110_63+33_1_30+33_1_110_63+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 4\n", + "Records number : 287" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.132379suyoactuacióntandecidir
110.142428suyoactuacióntandecidir
220.142428suyoactuacióntandecidir
330.148955suyoactuacióntandecidir
440.148955suyoactuacióntandecidir
550.142428suyoactuacióntandecidir
660.142428suyoactuacióntandecidir
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.132379 suyo actuación tan decidir\n", + "1 1 0.142428 suyo actuación tan decidir\n", + "2 2 0.142428 suyo actuación tan decidir\n", + "3 3 0.148955 suyo actuación tan decidir\n", + "4 4 0.148955 suyo actuación tan decidir\n", + "5 5 0.142428 suyo actuación tan decidir\n", + "6 6 0.142428 suyo actuación tan decidir" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.12117854955889858\n", + "model : LinearSVM , score = 0.11058929905981565\n", + "model : RBFSVM , score = 0.13765637162946023\n", + "model : DecisionTree , score = 0.05708629776372969\n", + "model : RandomForest , score = 0.013768958717064288\n", + "model : AdaBoost , score = 0.048194050630391144\n", + "----------------------------------------------\n", + "\n", + "file name : 70+37_69+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 1756" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.514636estarexaminar
110.485364estarexaminar
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.514636 estar examinar\n", + "1 1 0.485364 estar examinar" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.5092376080873654\n", + "model : LinearSVM , score = 0.5155477821955644\n", + "model : RBFSVM , score = 0.4142580693139405\n", + "model : DecisionTree , score = 0.47187299992698806\n", + "model : RandomForest , score = 0.4381772239282214\n", + "model : AdaBoost , score = 0.4576496467893957\n", + "----------------------------------------------\n", + "\n", + "file name : 12+113_1+.csv\n", + "Rules(classes) number : 2\n", + "Words(features) number : 2\n", + "Records number : 6242" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2
000.5seismes
110.5seismes
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2\n", + "0 0 0.5 seis mes\n", + "1 1 0.5 seis mes" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.5023250356357817\n", + "model : LinearSVM , score = 0.49487183011875113\n", + "model : RBFSVM , score = 0.3587189323620225\n", + "model : DecisionTree , score = 0.4876632082487883\n", + "model : RandomForest , score = 0.4593944237711818\n", + "model : AdaBoost , score = 0.4652437067509656\n", + "----------------------------------------------\n", + "\n", + "file name : 22+12_30+12_100_29+113_1_30+113_1_100_29+.csv\n", + "Rules(classes) number : 5\n", + "Words(features) number : 4\n", + "Records number : 60" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.20855250paísmáspobre
110.20176750paísmáspobre
220.19395750paísmáspobre
330.20176750paísmáspobre
440.19395750paísmáspobre
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.208552 50 país más pobre\n", + "1 1 0.201767 50 país más pobre\n", + "2 2 0.193957 50 país más pobre\n", + "3 3 0.201767 50 país más pobre\n", + "4 4 0.193957 50 país más pobre" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.03243725296195384\n", + "model : LinearSVM , score = 0.20664318571254572\n", + "model : RBFSVM , score = 0.20664318571254572\n", + "model : DecisionTree , score = 0.0\n", + "model : RandomForest , score = 0.0\n", + "model : AdaBoost , score = 0.03312666534301269\n", + "----------------------------------------------\n", + "\n", + "file name : 15+14_29+1_29_29+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 777" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.336066conceptojurídicoindeterminado
110.331967conceptojurídicoindeterminado
220.331967conceptojurídicoindeterminado
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.336066 concepto jurídico indeterminado\n", + "1 1 0.331967 concepto jurídico indeterminado\n", + "2 2 0.331967 concepto jurídico indeterminado" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.2936050137852968\n", + "model : LinearSVM , score = 0.29726552361270925\n", + "model : RBFSVM , score = 0.33627700140717914\n", + "model : DecisionTree , score = 0.2752638365628531\n", + "model : RandomForest , score = 0.16709213403780793\n", + "model : AdaBoost , score = 0.1985863322341775\n", + "----------------------------------------------\n", + "\n", + "file name : 84+100_60+100_47+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 3\n", + "Records number : 12" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3
000.328663nolopoder
110.345980nolopoder
220.325357nolopoder
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3\n", + "0 0 0.328663 no lo poder\n", + "1 1 0.345980 no lo poder\n", + "2 2 0.325357 no lo poder" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.16665342755583534\n", + "model : LinearSVM , score = 0.3344504145340458\n", + "model : RBFSVM , score = 0.3344504145340458\n", + "model : DecisionTree , score = 0.16665342755583534\n", + "model : RandomForest , score = 0.1655003759407887\n", + "model : AdaBoost , score = 0.16665342755583534\n", + "----------------------------------------------\n", + "\n", + "file name : 94+97_108_113+108_95+108_98_108_113+108_33_96+108_33_99_108_113+108_33_113_108_1_108_113+.csv\n", + "Rules(classes) number : 7\n", + "Words(features) number : 7\n", + "Records number : 273" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4word5word6word7
000.162927ael27deabrilde2000
110.136174ael27deabrilde2000
220.154397ael27deabrilde2000
330.130163ael27deabrilde2000
440.160826ael27deabrilde2000
550.134703ael27deabrilde2000
660.120809ael27deabrilde2000
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4 word5 word6 word7\n", + "0 0 0.162927 a el 27 de abril de 2000\n", + "1 1 0.136174 a el 27 de abril de 2000\n", + "2 2 0.154397 a el 27 de abril de 2000\n", + "3 3 0.130163 a el 27 de abril de 2000\n", + "4 4 0.160826 a el 27 de abril de 2000\n", + "5 5 0.134703 a el 27 de abril de 2000\n", + "6 6 0.120809 a el 27 de abril de 2000" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.07477421659088763\n", + "model : LinearSVM , score = 0.10496404562553276\n", + "model : RBFSVM , score = 0.15827958403992717\n", + "model : DecisionTree , score = 0.00769779337779194\n", + "model : RandomForest , score = 0.02123447408436888\n", + "model : AdaBoost , score = 0.06372186683106934\n", + "----------------------------------------------\n", + "\n", + "file name : 24+14_106_29+1_29_106_29+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 4\n", + "Records number : 789" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.335496normaclaroycompleto
110.331636normaclaroycompleto
220.332868normaclaroycompleto
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.335496 norma claro y completo\n", + "1 1 0.331636 norma claro y completo\n", + "2 2 0.332868 norma claro y completo" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.32481851581061016\n", + "model : LinearSVM , score = 0.3165909792196462\n", + "model : RBFSVM , score = 0.3488859231380752\n", + "model : DecisionTree , score = 0.2606002301328052\n", + "model : RandomForest , score = 0.20003356990093957\n", + "model : AdaBoost , score = 0.22003922441900595\n", + "----------------------------------------------\n", + "\n", + "file name : 60_63+47_40+47_68_63+.csv\n", + "Rules(classes) number : 3\n", + "Words(features) number : 4\n", + "Records number : 6" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ruleweightword1word2word3word4
000.314649lopoderhaberser
110.342676lopoderhaberser
220.342676lopoderhaberser
\n", + "
" + ], + "text/plain": [ + " rule weight word1 word2 word3 word4\n", + "0 0 0.314649 lo poder haber ser\n", + "1 1 0.342676 lo poder haber ser\n", + "2 2 0.342676 lo poder haber ser" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "model : NaiveBayes , score = 0.3146486853513146\n", + "model : LinearSVM , score = 0.34267565732434274\n", + "model : RBFSVM , score = 0.34267565732434274\n", + "model : DecisionTree , score = 0.34267565732434274\n", + "model : RandomForest , score = 0.3146486853513146\n", + "model : AdaBoost , score = 0.34267565732434274\n", + "----------------------------------------------\n", + "\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:436: RuntimeWarning: divide by zero encountered in log\n", + " n_ij = - 0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i, :]))\n", + "/home/aboelhamd/anaconda3/lib/python3.7/site-packages/sklearn/naive_bayes.py:438: RuntimeWarning: invalid value encountered in true_divide\n", + " (self.sigma_[i, :]), 1)\n" + ] + } + ], + "source": [ + "### import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n", + "import numpy as np\n", + "from matplotlib.colors import ListedColormap\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.svm import SVC\n", + "from sklearn.tree import DecisionTreeClassifier\n", + "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier\n", + "from sklearn.naive_bayes import GaussianNB\n", + "from sklearn.externals import joblib\n", + "from sklearn.preprocessing import OrdinalEncoder\n", + "\n", + "\n", + "for file in files:\n", + " # These are the classifiers that permit training data with sample weights!\n", + " names = [\"NaiveBayes\", \"LinearSVM\", \"RBFSVM\", \"DecisionTree\",\n", + " \"RandomForest\", \"AdaBoost\"]\n", + " \n", + " print(\"file name :\", file)\n", + " data = pd.read_csv(files[file], delimiter=r\"\\s+\", header=None).dropna()\n", + " \n", + " # words (features) encoding\n", + " # load the encoder\n", + " enc = joblib.load('models/'+'encoder'+'-'+file[:-4])\n", + " # remove records with unseen word, will return always 0 for that record\n", + " # this will be solved later\n", + " \n", + " \n", + " features = enc.fit_transform(data.iloc[:,2:])\n", + "# display(enc.categories_)\n", + "# display(data.iloc[:,2:],features)\n", + " # target and weights\n", + " target = data.iloc[:,0]\n", + " weights = data.iloc[:,1].values\n", + " \n", + "# print(\"file name :\", file)\n", + " print(\"Rules(classes) number :\",target.nunique())\n", + " print(\"Words(features) number :\",features.shape[1])\n", + " print(\"Records number :\",features.shape[0], end = '')\n", + " display(data.iloc[:target.nunique(),:])\n", + " \n", + " # split to train and test\n", + " X_train, X_test, y_train, y_test, w_train, w_test = \\\n", + " train_test_split(features, target, weights, test_size=.5, random_state=0, stratify=target)\n", + "# display(features, target, weights)\n", + "# display(X_train, X_test, y_train, y_test, w_train, w_test)\n", + " \n", + " # train models and print their scores\n", + " for name in names:\n", + " print(\"model :\", name, \",\", end = '')\n", + " modelname = 'sklearn-models/'+name+'-'+file[:-4]+'.model'\n", + " loaded_model = joblib.load(modelname)\n", + " score = loaded_model.score(X=X_test, y=y_test, sample_weight=w_test)\n", + " print(\" score =\", score)\n", + " \n", + " # save models\n", + "# name+'-'+file[:-4]+'.model'\n", + "# modelname = 'sklearn-models/'+name+'-'+file[:-4]+'.model'\n", + "# joblib.dump(clf, filename)\n", + " print(\"----------------------------------------------\\n\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[0, 0],\n", + " [1, 1]], dtype=int32)" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# enc = OrdinalEncoder(dtype=np.int32)\n", + "# features = enc.fit_transform(data.iloc[:,2:])\n", + "enc.fit_transform([['a','b'],['c','d']])" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 58, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "set(['a','b']).issubset(enc.categories_[0])\n", + "# enc.transform([['lo','poder']])" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012345
0ruleweightword1word2word3word4
100.314649lopoderhaberser
210.342676lopoderhaberser
320.342676lopoderhaberser
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4 5\n", + "0 rule weight word1 word2 word3 word4\n", + "1 0 0.314649 lo poder haber ser\n", + "2 1 0.342676 lo poder haber ser\n", + "3 2 0.342676 lo poder haber ser" + ] + }, + "execution_count": 49, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data = pd.read_csv(files[file], delimiter=r\"\\s+\", header=None).dropna()\n", + "data" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": {}, + "outputs": [], + "source": [ + "file='60_63+47_40+47_68_63+.csv'" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.7.1" + } + }, + "nbformat": 4, + "nbformat_minor": 1 +}