Created
May 4, 2016 04:45
-
-
Save ricalanis/d6dd3665ed90544190ffcccbf04d89a8 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"import os\n", | |
"import requests\n", | |
"from nltk import FreqDist" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 9, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"def token():\n", | |
" r = requests.get('https://graph.facebook.com/oauth/access_token?grant_type=client_credentials&client_id='+client_id+'&client_secret='+client_secret)\n", | |
" access_token = r.text.split('=')[1]\n", | |
" return access_token\n", | |
"\n", | |
"client_id = os.environ[\"client_id\"]\n", | |
"client_secret = os.environ[\"client_secret\"]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 10, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"def base_url(facebook_id,object_type, token, comment_adder = \"\"):\n", | |
" if object_type == \"comments\": comment_adder = \"&fields=comments,id,created_time,message,from\"\n", | |
" url_base = 'https://graph.facebook.com/v2.5/'+facebook_id+'/'+object_type+'/?limit=100&access_token='+ token + comment_adder\n", | |
" print(url_base)\n", | |
" return url_base\n", | |
"\n", | |
"\n", | |
"def facebook_data(facebook_id, object_type, token):\n", | |
" #when object type = \"posts\", gets posts, when \"comments\", gets comments.\n", | |
" url_base = base_url(facebook_id,object_type, token)\n", | |
" next_page, data = next_page_data(url_base,url_base)\n", | |
" posts = []\n", | |
" while next_page is not None:\n", | |
" posts = posts + data\n", | |
" next_page,data = next_page_data(next_page,url_base)\n", | |
" return posts\n", | |
"\n", | |
"\n", | |
"def next_url(r, url_base):\n", | |
" try:\n", | |
" next_cursor = r.json()['paging']['cursors']['after']\n", | |
" next_page = url_base + \"&after=\"+ next_cursor\n", | |
" data = r.json()[\"data\"]\n", | |
" except:\n", | |
" next_page = None\n", | |
" data = None\n", | |
" return next_page,data\n", | |
"\n", | |
"\n", | |
"def next_page_data(pagination_token,url_base):\n", | |
" r = requests.get(pagination_token)\n", | |
" try:\n", | |
" next_page = r.json()[\"paging\"][\"next\"]\n", | |
" data = r.json()[\"data\"]\n", | |
" except:\n", | |
" next_page, data = next_url(r, url_base)\n", | |
" return next_page, data" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 11, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"post_id = \"1037553166317439_1052734731465949\"\n", | |
"post_type = \"comments\"" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 12, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"https://graph.facebook.com/v2.5/1037553166317439_1052734731465949/comments/?limit=100&access_token=1694781514134125|lDRvOGNP3v_IQxI68Legs9j9QWw&fields=comments,id,created_time,message,from\n" | |
] | |
} | |
], | |
"source": [ | |
"comments_post = facebook_data(post_id, post_type,token())" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 13, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"561" | |
] | |
}, | |
"execution_count": 13, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"len(comments_post)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 15, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"{'created_time': '2016-04-19T22:10:23+0000',\n", | |
" 'from': {'id': '1129125517119186', 'name': 'Javier Lecter'},\n", | |
" 'id': '1052734731465949_1052775478128541',\n", | |
" 'message': 'igual que en Tamaulipas ya van para afuera por destruir el estado !!!'}" | |
] | |
}, | |
"execution_count": 15, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_post[0]" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"### Aplanar dataset para poder accesarlo fácil." | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 16, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"comments_post_plano = [{\"id\": comment[\"id\"],\"message\":comment[\"message\"],\"created_time\":comment[\"created_time\"], \"from_id\":comment[\"from\"][\"id\"],\"from_name\":comment[\"from\"][\"name\"]} for comment in comments_post]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 17, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"{'created_time': '2016-04-19T22:10:23+0000',\n", | |
" 'from_id': '1129125517119186',\n", | |
" 'from_name': 'Javier Lecter',\n", | |
" 'id': '1052734731465949_1052775478128541',\n", | |
" 'message': 'igual que en Tamaulipas ya van para afuera por destruir el estado !!!'}" | |
] | |
}, | |
"execution_count": 17, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_post_plano[0]" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"### Empieza la parte de pandas" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 374, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"import pandas" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 375, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"comments_df = pandas.DataFrame(comments_post_plano)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 376, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/html": [ | |
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n", | |
"<table border=\"1\" class=\"dataframe\">\n", | |
" <thead>\n", | |
" <tr style=\"text-align: right;\">\n", | |
" <th></th>\n", | |
" <th>created_time</th>\n", | |
" <th>from_id</th>\n", | |
" <th>from_name</th>\n", | |
" <th>id</th>\n", | |
" <th>message</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>2016-04-19T22:10:23+0000</td>\n", | |
" <td>1129125517119186</td>\n", | |
" <td>Javier Lecter</td>\n", | |
" <td>1052734731465949_1052775478128541</td>\n", | |
" <td>igual que en Tamaulipas ya van para afuera por...</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>2016-04-19T22:20:31+0000</td>\n", | |
" <td>563927170436016</td>\n", | |
" <td>Ivan Jist</td>\n", | |
" <td>1052734731465949_1052779208128168</td>\n", | |
" <td>Y el pri por robar todo el dinero a la Uv y ci...</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>2016-04-19T22:27:06+0000</td>\n", | |
" <td>716106398532421</td>\n", | |
" <td>Pequeño Corazonsito Cruz</td>\n", | |
" <td>1052734731465949_1052781654794590</td>\n", | |
" <td>Yo</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>2016-04-19T22:30:10+0000</td>\n", | |
" <td>1169546603088411</td>\n", | |
" <td>Carlos F Vazquez</td>\n", | |
" <td>1052734731465949_1052782811461141</td>\n", | |
" <td>Nadie vote por el pri por tenemos que correrlo...</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>2016-04-19T22:32:14+0000</td>\n", | |
" <td>232046980484475</td>\n", | |
" <td>David Camacho</td>\n", | |
" <td>1052734731465949_1052783438127745</td>\n", | |
" <td>El pri está dando patadas de hogado, ya no pue...</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" created_time from_id from_name \\\n", | |
"0 2016-04-19T22:10:23+0000 1129125517119186 Javier Lecter \n", | |
"1 2016-04-19T22:20:31+0000 563927170436016 Ivan Jist \n", | |
"2 2016-04-19T22:27:06+0000 716106398532421 Pequeño Corazonsito Cruz \n", | |
"3 2016-04-19T22:30:10+0000 1169546603088411 Carlos F Vazquez \n", | |
"4 2016-04-19T22:32:14+0000 232046980484475 David Camacho \n", | |
"\n", | |
" id \\\n", | |
"0 1052734731465949_1052775478128541 \n", | |
"1 1052734731465949_1052779208128168 \n", | |
"2 1052734731465949_1052781654794590 \n", | |
"3 1052734731465949_1052782811461141 \n", | |
"4 1052734731465949_1052783438127745 \n", | |
"\n", | |
" message \n", | |
"0 igual que en Tamaulipas ya van para afuera por... \n", | |
"1 Y el pri por robar todo el dinero a la Uv y ci... \n", | |
"2 Yo \n", | |
"3 Nadie vote por el pri por tenemos que correrlo... \n", | |
"4 El pri está dando patadas de hogado, ya no pue... " | |
] | |
}, | |
"execution_count": 376, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_df[0:5]" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"### Empieza tokenización" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 377, | |
"metadata": { | |
"collapsed": false, | |
"scrolled": true | |
}, | |
"outputs": [], | |
"source": [ | |
"comments_df[\"message_clean\"]=comments_df[\"message\"].apply(sentence_cleaner)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 378, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"STOPWORDS=set([\" el\",\"esta\",\"estas\",\"q\",\"ma\",\"este\",\"estos\",\"ultima\",\"ultimas\",\"ultimo\",\"ultimos\",\"a\",\"añadio\",\"aun\",\"actualmente\",\"ademas\",\"afirmo\",\"agrego\",\"ahi\",\"ahora\",\"al\",\"algun\",\"algo\",\"alguna\",\"algunas\",\"alguno\",\"algunos\",\"alrededor\",\"ambos\",\"ante\",\"anterior\",\"antes\",\"apenas\",\"aproximadamente\",\"aqui\",\"asi\",\"aseguro\",\"aunque\",\"ayer\",\"bajo\",\"bien\",\"buen\",\"buena\",\"buenas\",\"bueno\",\"buenos\",\"como\",\"cada\",\"casi\",\"cerca\",\"cierto\",\"cinco\",\"comento\",\"como\",\"con\",\"conocer\",\"considero\",\"considera\",\"contra\",\"cosas\",\"creo\",\"cual\",\"cuales\",\"cualquier\",\"cuando\",\"cuanto\",\"cuatro\",\"cuenta\",\"da\",\"dado\",\"dan\",\"dar\",\"de\",\"debe\",\"deben\",\"debido\",\"decir\",\"dejo\",\"del\",\"demas\",\"dentro\",\"desde\",\"despues\",\"dice\",\"dicen\",\"dicho\",\"dieron\",\"diferente\",\"diferentes\",\"dijeron\",\"dijo\",\"dio\",\"donde\",\"dos\",\"durante\",\"e\",\"ejemplo\",\"el\",\"ella\",\"ellas\",\"ello\",\"ellos\",\"embargo\",\"en\",\"encuentra\",\"entonces\",\"entre\",\"era\",\"eran\",\"es\",\"esa\",\"esas\",\"ese\",\"eso\",\"esos\",\"esta\",\"estan\",\"esta\",\"estaba\",\"estaban\",\"estamos\",\"estar\",\"estara\",\"estas\",\"este\",\"esto\",\"estos\",\"estoy\",\"estuvo\",\"ex\",\"existe\",\"existen\",\"explico\",\"expreso\",\"fin\",\"fue\",\"fueron\",\"gran\",\"grandes\",\"ha\",\"habia\",\"habian\",\"haber\",\"habra\",\"hace\",\"hacen\",\"hacer\",\"hacerlo\",\"hacia\",\"haciendo\",\"han\",\"hasta\",\"hay\",\"haya\",\"he\",\"hecho\",\"hemos\",\"hicieron\",\"hizo\",\"hoy\",\"hubo\",\"incluso\",\"indico\",\"informo\",\"junto\",\"la\",\"lado\",\"las\",\"le\",\"les\",\"llego\",\"lleva\",\"llevar\",\"lo\",\"los\",\"luego\",\"mas\",\"manera\",\"manifesto\",\"mayor\",\"me\",\"mediante\",\"mejor\",\"menciono\",\"menos\",\"mi\",\"mientras\",\"misma\",\"mismas\",\"mismo\",\"mismos\",\"momento\",\"mucha\",\"muchas\",\"mucho\",\"muchos\",\"muy\",\"nada\",\"nadie\",\"ni\",\"ningun\",\"ninguna\",\"ningunas\",\"ninguno\",\"ningunos\",\"no\",\"nos\",\"nosotras\",\"nosotros\",\"nuestra\",\"nuestras\",\"nuestro\",\"nuestros\",\"nueva\",\"nuevas\",\"nuevo\",\"nuevos\",\"nunca\",\"o\",\"ocho\",\"otra\",\"otras\",\"otro\",\"otros\",\"para\",\"parece\",\"parte\",\"partir\",\"pasada\",\"pasado\",\"pero\",\"pesar\",\"poca\",\"pocas\",\"poco\",\"pocos\",\"podemos\",\"podra\",\"podran\",\"podria\",\"podrian\",\"poner\",\"por\",\"porque\",\"posible\",\"proximo\",\"proximos\",\"principalmente\",\"propia\",\"propias\",\"propio\",\"propios\",\"pudo\",\"pueda\",\"puede\",\"pueden\",\"pues\",\"que\",\"que\",\"quedo\",\"queremos\",\"quien\",\"quien\",\"quienes\",\"quiere\",\"realizo\",\"realizado\",\"realizar\",\"respecto\",\"si\",\"solo\",\"se\",\"señalo\",\"sea\",\"sean\",\"segun\",\"seis\",\"ser\",\"sera\",\"seran\",\"seria\",\"si\",\"sido\",\"siempre\",\"siendo\",\"siete\",\"sigue\",\"siguiente\",\"sin\",\"sino\",\"sobre\",\"sola\",\"solamente\",\"solas\",\"solo\",\"solos\",\"son\",\"su\",\"sus\",\"tal\",\"tambien\",\"tampoco\",\"tan\",\"tanto\",\"tenia\",\"tendra\",\"tendran\",\"tenemos\",\"tener\",\"tenga\",\"tengo\",\"tenido\",\"tiene\",\"tienen\",\"toda\",\"todas\",\"todavia\",\"todo\",\"todos\",\"total\",\"tras\",\"trata\",\"traves\",\"tres\",\"tuvo\",\"un\",\"una\",\"unas\",\"uno\",\"unos\",\"usted\",\"va\",\"vamos\",\"van\",\"varias\",\"varios\",\"veces\",\"ver\",\"vez\",\"y\",\"ya\",\"yo\",\"ke\",\"komo\",\"aki\",\"aunke\"])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 379, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"REMOVECHARS= set([\"'\",'\"',\",\",\".\",\";\",\"¿\",\"?\",\"...\",\"#\", \"!\", \"¡\",\":\",\"\\n\",\"*\",\")\",\"(\"])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 380, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"REPLACECHARS = {\"á\":\"a\", \"é\":\"e\", \"í\":\"i\",\"ó\":\"o\",\"ú\":\"u\"}" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 381, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"def char_cleaner(word):\n", | |
" output =\"\"\n", | |
" for letter in word:\n", | |
" if letter in REPLACECHARS:\n", | |
" append =REPLACECHARS[letter]\n", | |
" elif letter in REMOVECHARS:\n", | |
" append = \" \"\n", | |
" else:\n", | |
" append = letter\n", | |
" output = output + append\n", | |
" return(output)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 382, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"def sentence_cleaner(sentence):\n", | |
" sentence = sentence.lower()\n", | |
" sentence_string = char_cleaner(sentence)\n", | |
" output = stopword_remover_tokenizer(sentence_string)\n", | |
" return(output)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 383, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"def stopword_remover_tokenizer(sentence):\n", | |
" sentence_token = sentence.split(\" \")\n", | |
" output = []\n", | |
" for token in sentence_token:\n", | |
" if len(token)>2:\n", | |
" output.append(token)\n", | |
" return(output)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 384, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"0 [igual, que, tamaulipas, van, para, afuera, po...\n", | |
"1 [pri, por, robar, todo, dinero, cierto, robo, ...\n", | |
"2 []\n", | |
"3 [nadie, vote, por, pri, por, tenemos, que, cor...\n", | |
"4 [pri, esta, dando, patadas, hogado, puede, man...\n", | |
"5 [pasa, nada, eso, dice, nuestro, gobernador, p...\n", | |
"6 [vio, que, gente, estado, esta, hasta, madre, ...\n", | |
"7 [voto, para, pri, ratassssssss]\n", | |
"8 [pan]\n", | |
"9 [por, haber, golpeado, los, viejos, pensionado...\n", | |
"10 [fuera]\n", | |
"11 [pri, deberia, siquiera, estar, las, encuestas...\n", | |
"12 [eso, esperaba, maquinaria, roja, pero, aun, c...\n", | |
"13 [quien, este, durmiendo, que, por, una, despen...\n", | |
"14 []\n", | |
"15 [todos, son, coructos, pri, ocupa, primer, lug...\n", | |
"16 []\n", | |
"17 []\n", | |
"18 [sigan, votando, por, pri, que, les, miserias,...\n", | |
"19 [creo, que, miguel, angel, con, todo, conformo...\n", | |
"20 [siempre, mismo, con, pri, carvallo, donde, an...\n", | |
"21 [nos, engañen, otra, ves, una, monos, hagamos,...\n", | |
"22 []\n", | |
"23 [increible, pri, este, segundo, lugar, encuesta]\n", | |
"24 [voto, priiu]\n", | |
"25 [chingar, asu, madre, pri, del, estado, mas, pri]\n", | |
"26 [jacobo, ceron]\n", | |
"27 [fuera, fuera, pri, jajajajajajjaja]\n", | |
"28 [34%, hace, demasiado, jajajajjaja, pri, hay, ...\n", | |
"29 [hay, que, darle, voto, yunes, linares, para, ...\n", | |
" ... \n", | |
"70 []\n", | |
"71 [soy, gay]\n", | |
"72 [pri, una, dictaduria, nose, porq, abren, las,...\n", | |
"73 [miedo, tiene, paralisado, pueblo, sean, pende...\n", | |
"74 [pinches, pri, por, eso, estamos, como, estamos]\n", | |
"75 [santanas, tevoy, destruir, poder, cristo]\n", | |
"76 [para, fuera, pri, esta, dejando, mas, pobres,...\n", | |
"77 [pri, perdio, veracruz, gracias, duarte]\n", | |
"78 [chinge, sptm, hector, yunes]\n", | |
"79 [todos, roban, pero, saquemos, pri, peor]\n", | |
"80 [pinche, marrana, parada]\n", | |
"81 [pri, ala, verga, jamas, regresa, poder]\n", | |
"82 [olvidare, todas, las, fotos, todos, los, recu...\n", | |
"83 [distractor, duarte, quien, realmente, apoya, ...\n", | |
"84 [pinche, partido, esta, peor, que, los, drenaj...\n", | |
"85 [vamos, vamos, yunes, linares, estan, desesper...\n", | |
"86 [verdad, son, pesimas, las, gestiones, pristas...\n", | |
"87 [como, agarran, pendeja, ala, jente, poca, mad...\n", | |
"88 [todos, con, miguel, angel, yunes, linares]\n", | |
"89 [jajajaja, quien, quieren, engañar]\n", | |
"90 [partido, del, pri, vale, para, una, madre, te...\n", | |
"91 [fuerte, abrazo, lenis]\n", | |
"92 [duarte, pri, ban, fuera, culeros]\n", | |
"93 [tlacuache, tlacuaches]\n", | |
"94 [ver, dice, ine, instituto, nacional, estafado...\n", | |
"95 [adios, pri]\n", | |
"96 [estaran, preocupados]\n", | |
"97 [era, esperarse, pri, utilizando, maquinaria, ...\n", | |
"98 [jajaja, van, pelar, miyuli]\n", | |
"99 [chingue, madre, marrana, ine]\n", | |
"Name: message_clean, dtype: object" | |
] | |
}, | |
"execution_count": 384, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"#comments_df.iloc[\"mess\"]\n", | |
"comments_df[\"message_clean\"][0:100]" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## ¿Qué tanto funciona una clasificación directa por matching?" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 114, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"['pri',\n", | |
" 'esta',\n", | |
" 'dando',\n", | |
" 'patadas',\n", | |
" 'hogado',\n", | |
" 'puede',\n", | |
" 'manipular',\n", | |
" 'los',\n", | |
" 'veracruzanos']" | |
] | |
}, | |
"execution_count": 114, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_df.iloc[4][\"message_clean\"]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 86, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"morena_class = comments_df.iloc[4][\"message_clean\"]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 88, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"def is_morena(tokens):\n", | |
" for morena_word in morena_class:\n", | |
" if morena_word in tokens:\n", | |
" class_message = \"anti-pri\"\n", | |
" else:\n", | |
" class_message = \"none\"\n", | |
" return class_message" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 89, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"comments_df_morenazo = comments_df" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 90, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"comments_df_morenazo[\"morenazo\"]=comments_df_morenazo[\"message_clean\"].apply(is_morena)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 93, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/html": [ | |
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n", | |
"<table border=\"1\" class=\"dataframe\">\n", | |
" <thead>\n", | |
" <tr style=\"text-align: right;\">\n", | |
" <th></th>\n", | |
" <th>created_time</th>\n", | |
" <th>from_id</th>\n", | |
" <th>from_name</th>\n", | |
" <th>id</th>\n", | |
" <th>message</th>\n", | |
" <th>message_clean</th>\n", | |
" <th>morenazo</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>2016-04-19T22:32:14+0000</td>\n", | |
" <td>232046980484475</td>\n", | |
" <td>David Camacho</td>\n", | |
" <td>1052734731465949_1052783438127745</td>\n", | |
" <td>El pri está dando patadas de hogado, ya no pue...</td>\n", | |
" <td>[pri, esta, dando, patadas, hogado, puede, man...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>183</th>\n", | |
" <td>2016-04-20T21:58:29+0000</td>\n", | |
" <td>1167084456675195</td>\n", | |
" <td>Marcos Roke</td>\n", | |
" <td>1052734731465949_1053393964733359</td>\n", | |
" <td>Que se coman entre los dos! Como la gente ya n...</td>\n", | |
" <td>[que, coman, entre, los, dos, como, gente, qui...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>236</th>\n", | |
" <td>2016-04-21T02:46:55+0000</td>\n", | |
" <td>1081985265191562</td>\n", | |
" <td>Javier Garsil</td>\n", | |
" <td>1052734731465949_1053524434720312</td>\n", | |
" <td>Cual guerra sucia yo no soy de ningún partido ...</td>\n", | |
" <td>[cual, guerra, sucia, soy, ningun, partido, qu...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>270</th>\n", | |
" <td>2016-04-21T13:52:43+0000</td>\n", | |
" <td>1785182975046569</td>\n", | |
" <td>Christian De Jesus Martinez Gonzalez</td>\n", | |
" <td>1052734731465949_1053813388024750</td>\n", | |
" <td>Este 5 de junio nadie detendra el triunfo de l...</td>\n", | |
" <td>[este, junio, nadie, detendra, triunfo, los, v...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>333</th>\n", | |
" <td>2016-04-22T14:33:34+0000</td>\n", | |
" <td>259169027768104</td>\n", | |
" <td>Reynaldo Arredondo</td>\n", | |
" <td>1052734731465949_1054546891284733</td>\n", | |
" <td>La porqueria del PRI quieren desviar la atenci...</td>\n", | |
" <td>[porqueria, del, pri, quieren, desviar, atenci...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>494</th>\n", | |
" <td>2016-04-25T03:04:43+0000</td>\n", | |
" <td>262839304069539</td>\n", | |
" <td>Chuliss Gamas</td>\n", | |
" <td>1052734731465949_1165779210123647</td>\n", | |
" <td>Todavia habrá veracruzanos que piensen votar p...</td>\n", | |
" <td>[todavia, habra, veracruzanos, que, piensen, v...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>522</th>\n", | |
" <td>2016-04-26T18:16:09+0000</td>\n", | |
" <td>273199159680407</td>\n", | |
" <td>Javier Perez</td>\n", | |
" <td>1052734731465949_1011234278924962</td>\n", | |
" <td>No nos harán cambiar de opinión los Veracruzan...</td>\n", | |
" <td>[nos, haran, cambiar, opinion, los, veracruzan...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" created_time from_id \\\n", | |
"4 2016-04-19T22:32:14+0000 232046980484475 \n", | |
"183 2016-04-20T21:58:29+0000 1167084456675195 \n", | |
"236 2016-04-21T02:46:55+0000 1081985265191562 \n", | |
"270 2016-04-21T13:52:43+0000 1785182975046569 \n", | |
"333 2016-04-22T14:33:34+0000 259169027768104 \n", | |
"494 2016-04-25T03:04:43+0000 262839304069539 \n", | |
"522 2016-04-26T18:16:09+0000 273199159680407 \n", | |
"\n", | |
" from_name id \\\n", | |
"4 David Camacho 1052734731465949_1052783438127745 \n", | |
"183 Marcos Roke 1052734731465949_1053393964733359 \n", | |
"236 Javier Garsil 1052734731465949_1053524434720312 \n", | |
"270 Christian De Jesus Martinez Gonzalez 1052734731465949_1053813388024750 \n", | |
"333 Reynaldo Arredondo 1052734731465949_1054546891284733 \n", | |
"494 Chuliss Gamas 1052734731465949_1165779210123647 \n", | |
"522 Javier Perez 1052734731465949_1011234278924962 \n", | |
"\n", | |
" message \\\n", | |
"4 El pri está dando patadas de hogado, ya no pue... \n", | |
"183 Que se coman entre los dos! Como la gente ya n... \n", | |
"236 Cual guerra sucia yo no soy de ningún partido ... \n", | |
"270 Este 5 de junio nadie detendra el triunfo de l... \n", | |
"333 La porqueria del PRI quieren desviar la atenci... \n", | |
"494 Todavia habrá veracruzanos que piensen votar p... \n", | |
"522 No nos harán cambiar de opinión los Veracruzan... \n", | |
"\n", | |
" message_clean morenazo \n", | |
"4 [pri, esta, dando, patadas, hogado, puede, man... anti-pri \n", | |
"183 [que, coman, entre, los, dos, como, gente, qui... anti-pri \n", | |
"236 [cual, guerra, sucia, soy, ningun, partido, qu... anti-pri \n", | |
"270 [este, junio, nadie, detendra, triunfo, los, v... anti-pri \n", | |
"333 [porqueria, del, pri, quieren, desviar, atenci... anti-pri \n", | |
"494 [todavia, habra, veracruzanos, que, piensen, v... anti-pri \n", | |
"522 [nos, haran, cambiar, opinion, los, veracruzan... anti-pri " | |
] | |
}, | |
"execution_count": 93, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_df_morenazo[comments_df_morenazo[\"morenazo\"] == \"anti-pri\"]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 92, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"'Cual guerra sucia yo no soy de ningún partido y lo que veo es un pinche ratero con licencia desvergonzado que quiere seguir robando. Si de verdad quiere hacer algo por Veracruz que lo haga sin estar en ningún cargo público con lo robado le alcanza para ayudar a muchísimos veracruzanos. Pinches rateros no tienen llenadera'" | |
] | |
}, | |
"execution_count": 92, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_df.iloc[236][\"message\"]" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"### Obtención de las palabras más mencionadas" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Esto sirve como un norte para el humano: Puede dar un tip sobre categorías a investigar" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 95, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"concat_messages = []\n", | |
"for row in comments_df.iterrows():\n", | |
" for word in row[1][\"message_clean\"]:\n", | |
" if word not in STOPWORDS:\n", | |
" concat_messages = concat_messages + [word]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 96, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"freq_list_messages = list(FreqDist(concat_messages).items())\n", | |
"sorted_freq_list = sorted(freq_list_messages , key=lambda pair: pair[1], reverse=True)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 97, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"[('pri', 262),\n", | |
" ('yunes', 57),\n", | |
" ('duarte', 57),\n", | |
" ('veracruz', 51),\n", | |
" ('miguel', 42),\n", | |
" ('fuera', 41),\n", | |
" ('voto', 39),\n", | |
" ('ratas', 38),\n", | |
" ('gente', 37),\n", | |
" ('angel', 36),\n", | |
" ('pan', 36),\n", | |
" ('pueblo', 33),\n", | |
" ('madre', 30),\n", | |
" ('linares', 28),\n", | |
" ('gobierno', 28),\n", | |
" ('estado', 26),\n", | |
" ('pinche', 22),\n", | |
" ('partido', 20),\n", | |
" ('votar', 19),\n", | |
" ('morena', 18),\n", | |
" ('guerra', 17),\n", | |
" ('sucia', 16),\n", | |
" ('dinero', 16),\n", | |
" ('carcel', 16),\n", | |
" ('poder', 16),\n", | |
" ('rata', 15),\n", | |
" ('quieren', 15),\n", | |
" ('marrana', 15),\n", | |
" ('hector', 15),\n", | |
" ('priistas', 14),\n", | |
" ('pinches', 14),\n", | |
" ('gobernador', 14),\n", | |
" ('patadas', 14),\n", | |
" ('bola', 14),\n", | |
" ('pendejos', 13),\n", | |
" ('rateros', 13),\n", | |
" ('partidos', 13),\n", | |
" ('ganar', 13),\n", | |
" ('porqueria', 13),\n", | |
" ('basta', 12),\n", | |
" ('arriba', 12),\n", | |
" ('ala', 11),\n", | |
" ('corruptos', 11),\n", | |
" ('chingar', 11),\n", | |
" ('miedo', 10),\n", | |
" ('gane', 10),\n", | |
" ('voten', 10),\n", | |
" ('cambio', 10),\n", | |
" ('dejen', 10),\n", | |
" ('verdad', 10),\n", | |
" ('perder', 10),\n", | |
" ('mierda', 10),\n", | |
" ('ahogado', 10),\n", | |
" ('sacar', 9),\n", | |
" ('sabe', 9),\n", | |
" ('peor', 9),\n", | |
" ('pendejo', 9),\n", | |
" ('cambiar', 8),\n", | |
" ('años', 8),\n", | |
" ('robar', 8),\n", | |
" ('mal', 8),\n", | |
" ('puto', 8),\n", | |
" ('dios', 8),\n", | |
" ('etc', 8),\n", | |
" ('robo', 8),\n", | |
" ('perro', 8),\n", | |
" ('seguir', 8),\n", | |
" ('lugar', 7),\n", | |
" ('corrupto', 7),\n", | |
" ('pais', 7),\n", | |
" ('votando', 7),\n", | |
" ('basura', 7),\n", | |
" ('votemos', 7),\n", | |
" ('vida', 7),\n", | |
" ('saben', 7),\n", | |
" ('tiempo', 7),\n", | |
" ('unico', 7),\n", | |
" ('puta', 7),\n", | |
" ('robado', 7),\n", | |
" ('elecciones', 7),\n", | |
" ('veracruzanos', 7),\n", | |
" ('ustedes', 7),\n", | |
" ('hijos', 7),\n", | |
" ('despensa', 6),\n", | |
" ('queda', 6),\n", | |
" ('pesos', 6),\n", | |
" ('mexico', 6),\n", | |
" ('ojala', 6),\n", | |
" ('javier', 6),\n", | |
" ('mamadas', 6),\n", | |
" ('maldito', 6),\n", | |
" ('ojos', 6),\n", | |
" ('politica', 6),\n", | |
" ('hagan', 6),\n", | |
" ('fidel', 6),\n", | |
" ('engañar', 6),\n", | |
" ('politicos', 6),\n", | |
" ('asta', 6),\n", | |
" ('verga', 6),\n", | |
" ('jajaja', 6),\n", | |
" ('favor', 6),\n", | |
" ('eres', 5),\n", | |
" ('jajajajaja', 5),\n", | |
" ('señores', 5),\n", | |
" ('veracruzano', 5),\n", | |
" ('quiero', 5),\n", | |
" ('vaya', 5),\n", | |
" ('peje', 5),\n", | |
" ('iguales', 5),\n", | |
" ('peña', 5),\n", | |
" ('limpio', 5),\n", | |
" ('sigan', 5),\n", | |
" ('dando', 5),\n", | |
" ('cree', 5),\n", | |
" ('televisa', 5),\n", | |
" ('primero', 5),\n", | |
" ('quieran', 5),\n", | |
" ('encuestas', 5),\n", | |
" ('pobres', 5),\n", | |
" ('primer', 5),\n", | |
" ('corrupcion', 5),\n", | |
" ('sabemos', 5),\n", | |
" ('jente', 5),\n", | |
" ('nieto', 5),\n", | |
" ('inseguridad', 5),\n", | |
" ('gracias', 5),\n", | |
" ('jajajaja', 5),\n", | |
" ('gordo', 5),\n", | |
" ('igual', 5),\n", | |
" ('meter', 5),\n", | |
" ('seguira', 5),\n", | |
" ('gana', 5),\n", | |
" ('malos', 5),\n", | |
" ('boca', 5),\n", | |
" ('pobre', 5),\n", | |
" ('tanta', 4),\n", | |
" ('tapar', 4),\n", | |
" ('priista', 4),\n", | |
" ('gorda', 4),\n", | |
" ('violencia', 4),\n", | |
" ('familia', 4),\n", | |
" ('historia', 4),\n", | |
" ('azul', 4),\n", | |
" ('paso', 4),\n", | |
" ('votare', 4),\n", | |
" ('roban', 4),\n", | |
" ('delincuencia', 4),\n", | |
" ('cargo', 4),\n", | |
" ('aya', 4),\n", | |
" ('dejar', 4),\n", | |
" ('dejense', 4),\n", | |
" ('asu', 4),\n", | |
" ('jamas', 4),\n", | |
" ('muera', 4),\n", | |
" ('quiebra', 4),\n", | |
" ('culpa', 4),\n", | |
" ('sucio', 4),\n", | |
" ('llama', 4),\n", | |
" ('soy', 4),\n", | |
" ('adelante', 4),\n", | |
" ('doriga', 4),\n", | |
" ('quieres', 4),\n", | |
" ('den', 4),\n", | |
" ('pura', 4),\n", | |
" ('lopez', 4),\n", | |
" ('hablan', 4),\n", | |
" ('vote', 4),\n", | |
" ('creen', 4),\n", | |
" ('pendeja', 4),\n", | |
" ('diferencia', 4),\n", | |
" ('alos', 4),\n", | |
" ('mexicanos', 4),\n", | |
" ('perros', 4),\n", | |
" ('chinguen', 4),\n", | |
" ('huevos', 4),\n", | |
" ('landa', 4),\n", | |
" ('andan', 4),\n", | |
" ('chinge', 4),\n", | |
" ('somos', 4),\n", | |
" ('claro', 3),\n", | |
" ('deja', 3),\n", | |
" ('ine', 3),\n", | |
" ('diputados', 3),\n", | |
" ('seguiremos', 3),\n", | |
" ('mayoria', 3),\n", | |
" ('directo', 3),\n", | |
" ('kien', 3),\n", | |
" ('marrano', 3),\n", | |
" ('año', 3),\n", | |
" ('madres', 3),\n", | |
" ('ves', 3),\n", | |
" ('saquen', 3),\n", | |
" ('ganaran', 3),\n", | |
" ('ahogados', 3),\n", | |
" ('punto', 3),\n", | |
" ('verde', 3),\n", | |
" ('hagamos', 3),\n", | |
" ('hueso', 3),\n", | |
" ('agarro', 3),\n", | |
" ('oportunidades', 3),\n", | |
" ('siga', 3),\n", | |
" ('apoyar', 3),\n", | |
" ('ami', 3),\n", | |
" ('mil', 3),\n", | |
" ('saca', 3),\n", | |
" ('deuda', 3),\n", | |
" ('asesino', 3),\n", | |
" ('despierten', 3),\n", | |
" ('candidato', 3),\n", | |
" ('memoria', 3),\n", | |
" ('prd', 3),\n", | |
" ('afuera', 3),\n", | |
" ('manos', 3),\n", | |
" ('confianza', 3),\n", | |
" ('dejara', 3),\n", | |
" ('nadien', 3),\n", | |
" ('apoyando', 3),\n", | |
" ('deberia', 3),\n", | |
" ('aser', 3),\n", | |
" ('amlo', 3),\n", | |
" ('miyuli', 3),\n", | |
" ('quemados', 3),\n", | |
" ('mafia', 3),\n", | |
" ('hagas', 3),\n", | |
" ('ladrones', 3),\n", | |
" ('puras', 3),\n", | |
" ('ganara', 3),\n", | |
" ('personas', 3),\n", | |
" ('recursos', 3),\n", | |
" ('señor', 3),\n", | |
" ('puercos', 3),\n", | |
" ('dejaron', 3),\n", | |
" ('diran', 3),\n", | |
" ('destruir', 3),\n", | |
" ('come', 3),\n", | |
" ('falta', 3),\n", | |
" ('creer', 3),\n", | |
" ('obrador', 3),\n", | |
" ('vde', 3),\n", | |
" ('bonito', 3),\n", | |
" ('vale', 3),\n", | |
" ('puro', 3),\n", | |
" ('adios', 3),\n", | |
" ('mala', 3),\n", | |
" ('cerdo', 3),\n", | |
" ('https', 3),\n", | |
" ('lic', 3),\n", | |
" ('juntos', 3),\n", | |
" ('junio', 3),\n", | |
" ('robaron', 3),\n", | |
" ('pensionados', 3),\n", | |
" ('mandar', 3),\n", | |
" ('votos', 3),\n", | |
" ('entiendan', 3),\n", | |
" ('nombre', 3),\n", | |
" ('pandilla', 3),\n", | |
" ('risa', 3),\n", | |
" ('digan', 3),\n", | |
" ('alianza', 3),\n", | |
" ('importante', 3),\n", | |
" ('facebook', 3),\n", | |
" ('robando', 3),\n", | |
" ('vean', 3),\n", | |
" ('acuerdo', 3),\n", | |
" ('rratas', 3),\n", | |
" ('empezando', 3),\n", | |
" ('complices', 2),\n", | |
" ('dedo', 2),\n", | |
" ('xalapa', 2),\n", | |
" ('limpiar', 2),\n", | |
" ('justicia', 2),\n", | |
" ('sale', 2),\n", | |
" ('vergüenza', 2),\n", | |
" ('culeros', 2),\n", | |
" ('votaran', 2),\n", | |
" ('confie', 2),\n", | |
" ('alcanza', 2),\n", | |
" ('yunez', 2),\n", | |
" ('recuperar', 2),\n", | |
" ('gusta', 2),\n", | |
" ('piensan', 2),\n", | |
" ('votaron', 2),\n", | |
" ('fotos', 2),\n", | |
" ('social', 2),\n", | |
" ('nomas', 2),\n", | |
" ('llevo', 2),\n", | |
" ('ratero', 2),\n", | |
" ('garras', 2),\n", | |
" ('palabras', 2),\n", | |
" ('metiendo', 2),\n", | |
" ('tragar', 2),\n", | |
" ('promesas', 2),\n", | |
" ('gorra', 2),\n", | |
" ('kieren', 2),\n", | |
" ('opinion', 2),\n", | |
" ('objetivo', 2),\n", | |
" ('pelea', 2),\n", | |
" ('des', 2),\n", | |
" ('darle', 2),\n", | |
" ('ganado', 2),\n", | |
" ('pregunto', 2),\n", | |
" ('miserias', 2),\n", | |
" ('opinar', 2),\n", | |
" ('culo', 2),\n", | |
" ('lana', 2),\n", | |
" ('gastando', 2),\n", | |
" ('detendra', 2),\n", | |
" ('sector', 2),\n", | |
" ('migel', 2),\n", | |
" ('esperaba', 2),\n", | |
" ('finanzas', 2),\n", | |
" ('limpios', 2),\n", | |
" ('siente', 2),\n", | |
" ('segundo', 2),\n", | |
" ('acabar', 2),\n", | |
" ('regala', 2),\n", | |
" ('punta', 2),\n", | |
" ('crean', 2),\n", | |
" ('estaran', 2),\n", | |
" ('paz', 2),\n", | |
" ('mis', 2),\n", | |
" ('cochino', 2),\n", | |
" ('muerto', 2),\n", | |
" ('diciendo', 2),\n", | |
" ('pendejadas', 2),\n", | |
" ('humo', 2),\n", | |
" ('desesperada', 2),\n", | |
" ('crimen', 2),\n", | |
" ('opciones', 2),\n", | |
" ('ñaka', 2),\n", | |
" ('cuentos', 2),\n", | |
" ('save', 2),\n", | |
" ('grande', 2),\n", | |
" ('comer', 2),\n", | |
" ('idiota', 2),\n", | |
" ('impunidad', 2),\n", | |
" ('aganar', 2),\n", | |
" ('lodo', 2),\n", | |
" ('idiotas', 2),\n", | |
" ('voy', 2),\n", | |
" ('mamada', 2),\n", | |
" ('seguro', 2),\n", | |
" ('veo', 2),\n", | |
" ('alguien', 2),\n", | |
" ('trabajar', 2),\n", | |
" ('iba', 2),\n", | |
" ('perdido', 2),\n", | |
" ('anda', 2),\n", | |
" ('com/story', 2),\n", | |
" ('siguen', 2),\n", | |
" ('persecucion', 2),\n", | |
" ('seguridad', 2),\n", | |
" ('conforman', 2),\n", | |
" ('tamaulipas', 2),\n", | |
" ('tapo', 2),\n", | |
" ('eleccion', 2),\n", | |
" ('mueran', 2),\n", | |
" ('bastante', 2),\n", | |
" ('querer', 2),\n", | |
" ('chingando', 2),\n", | |
" ('patria', 2),\n", | |
" ('descarado', 2),\n", | |
" ('disque', 2),\n", | |
" ('pidiendo', 2),\n", | |
" ('trabajando', 2),\n", | |
" ('metio', 2),\n", | |
" ('carlos', 2),\n", | |
" ('españa', 2),\n", | |
" ('aliados', 2),\n", | |
" ('depende', 2),\n", | |
" ('vemos', 2),\n", | |
" ('sptm', 2),\n", | |
" ('primaria', 2),\n", | |
" ('espero', 2),\n", | |
" ('metan', 2),\n", | |
" ('ntro', 2),\n", | |
" ('cochinos', 2),\n", | |
" ('robos', 2),\n", | |
" ('desesperados', 2),\n", | |
" ('nose', 2),\n", | |
" ('vuelva', 2),\n", | |
" ('saber', 2),\n", | |
" ('morir', 2),\n", | |
" ('triunfo', 2),\n", | |
" ('cabrones', 2),\n", | |
" ('situacion', 2),\n", | |
" ('medicamentos', 2),\n", | |
" ('epn', 2),\n", | |
" ('jugar', 2),\n", | |
" ('sige', 2),\n", | |
" ('mama', 2),\n", | |
" ('infierno', 2),\n", | |
" ('delincuentes', 2),\n", | |
" ('jajajajajaoye', 2),\n", | |
" ('gobernatura', 2),\n", | |
" ('nefastos', 2),\n", | |
" ('pristas', 2),\n", | |
" ('burro', 2),\n", | |
" ('pagar', 2),\n", | |
" ('mandan', 2),\n", | |
" ('nacional', 2),\n", | |
" ('siganle', 2),\n", | |
" ('santo', 2),\n", | |
" ('puntos', 2),\n", | |
" ('gustaria', 2),\n", | |
" ('amigos', 2),\n", | |
" ('porquerias', 2),\n", | |
" ('pobrecito', 2),\n", | |
" ('apoya', 2),\n", | |
" ('cabeza', 2),\n", | |
" ('namas', 2),\n", | |
" ('dejemos', 2),\n", | |
" ('abajo', 2),\n", | |
" ('robarle', 2),\n", | |
" ('satelites', 2),\n", | |
" ('nido', 2),\n", | |
" ('pie', 2),\n", | |
" ('escuchados', 2),\n", | |
" ('federal', 2),\n", | |
" ('coatzacoalcos', 2),\n", | |
" ('calderon', 2),\n", | |
" ('das', 2),\n", | |
" ('claves', 2),\n", | |
" ('bandido', 2),\n", | |
" ('esten', 2),\n", | |
" ('quieras', 2),\n", | |
" ('porq', 2),\n", | |
" ('investiguen', 2),\n", | |
" ('jugando', 2),\n", | |
" ('abusos', 2),\n", | |
" ('ven', 2),\n", | |
" ('palabra', 2),\n", | |
" ('yuni', 2),\n", | |
" ('serian', 2),\n", | |
" ('vos', 2),\n", | |
" ('secuestros', 2),\n", | |
" ('comiendo', 2),\n", | |
" ('eyos', 2),\n", | |
" ('pipo', 2),\n", | |
" ('hora', 2),\n", | |
" ('campaña', 2),\n", | |
" ('engañan', 2),\n", | |
" ('simplemente', 2),\n", | |
" ('haga', 2),\n", | |
" ('ganaba', 2),\n", | |
" ('apoyo', 2),\n", | |
" ('realmente', 2),\n", | |
" ('tambo', 2),\n", | |
" ('chingue', 2),\n", | |
" ('andres', 2),\n", | |
" ('ciudadania', 2),\n", | |
" ('maquinaria', 2),\n", | |
" ('faltan', 2),\n", | |
" ('razon', 2),\n", | |
" ('riko', 2),\n", | |
" ('comunicacion', 2),\n", | |
" ('maestra', 2),\n", | |
" ('aber', 2),\n", | |
" ('porkeria', 2),\n", | |
" ('poo', 2),\n", | |
" ('esperaban', 2),\n", | |
" ('trabajo', 2),\n", | |
" ('ciudadanos', 2),\n", | |
" ('pague', 2),\n", | |
" ('saquemos', 2),\n", | |
" ('opcion', 2),\n", | |
" ('conozco', 2),\n", | |
" ('fuerte', 2),\n", | |
" ('presidente', 2),\n", | |
" ('tus', 2),\n", | |
" ('foto', 2),\n", | |
" ('salir', 2),\n", | |
" ('comentario', 2),\n", | |
" ('siquiera', 2),\n", | |
" ('joto', 2),\n", | |
" ('rrateros', 2),\n", | |
" ('ayuda', 2),\n", | |
" ('boto', 2),\n", | |
" ('vieja', 2),\n", | |
" ('pareciera', 2),\n", | |
" ('abran', 2),\n", | |
" ('boten', 2),\n", | |
" ('tricolor', 2),\n", | |
" ('mantecoso', 2),\n", | |
" ('mundo', 2),\n", | |
" ('botar', 2),\n", | |
" ('asquerosas', 2),\n", | |
" ('ayudar', 2),\n", | |
" ('gato', 2),\n", | |
" ('sol', 2),\n", | |
" ('creyendo', 2),\n", | |
" ('cuello', 2),\n", | |
" ('malo', 2),\n", | |
" ('salio', 2),\n", | |
" ('venga', 2),\n", | |
" ('calzones', 2),\n", | |
" ('votamos', 2),\n", | |
" ('chingada', 2),\n", | |
" ('ignorantes', 2),\n", | |
" ('esperarse', 2),\n", | |
" ('manuel', 2),\n", | |
" ('suficiente', 2),\n", | |
" ('increible', 2),\n", | |
" ('andar', 2),\n", | |
" ('enjuicien', 2),\n", | |
" ('millones', 2),\n", | |
" ('php', 2),\n", | |
" ('elector', 2),\n", | |
" ('miseria', 2),\n", | |
" ('ganan', 2),\n", | |
" ('//m', 2),\n", | |
" ('vendido', 2),\n", | |
" ('medios', 2),\n", | |
" ('cara', 2),\n", | |
" ('malditos', 2),\n", | |
" ('creible', 2),\n", | |
" ('saludes', 1),\n", | |
" ('diske', 1),\n", | |
" ('conformista', 1),\n", | |
" ('quejandose', 1),\n", | |
" ('pescado', 1),\n", | |
" ('chin', 1),\n", | |
" ('aleman', 1),\n", | |
" ('brambilla', 1),\n", | |
" ('pola', 1),\n", | |
" ('dividir', 1),\n", | |
" ('regordete', 1),\n", | |
" ('disfrutando', 1),\n", | |
" ('levantones', 1),\n", | |
" ('murio', 1),\n", | |
" ('abrir', 1),\n", | |
" ('desmadre', 1),\n", | |
" ('ver´', 1),\n", | |
" ('vaja', 1),\n", | |
" ('choro', 1),\n", | |
" ('comadres', 1),\n", | |
" ('presupuesto', 1),\n", | |
" ('internda', 1),\n", | |
" ('gracia', 1),\n", | |
" ('roja', 1),\n", | |
" ('adar', 1),\n", | |
" ('meme', 1),\n", | |
" ('perritos', 1),\n", | |
" ('transas', 1),\n", | |
" ('estupido', 1),\n", | |
" ('vea', 1),\n", | |
" ('vidas', 1),\n", | |
" ('costa', 1),\n", | |
" ('vueltas', 1),\n", | |
" ('sienpre', 1),\n", | |
" ('coca', 1),\n", | |
" ('merescan', 1),\n", | |
" ('razonemos', 1),\n", | |
" ('orgullo', 1),\n", | |
" ('circo', 1),\n", | |
" ('ducho', 1),\n", | |
" ('parasitos', 1),\n", | |
" ('jajajajajajjaja', 1),\n", | |
" ('ferras', 1),\n", | |
" ('cargos', 1),\n", | |
" ('llenar', 1),\n", | |
" ('caseta', 1),\n", | |
" ('complice', 1),\n", | |
" ('definido', 1),\n", | |
" ('asil', 1),\n", | |
" ('iso', 1),\n", | |
" ('verdades', 1),\n", | |
" ('operacion', 1),\n", | |
" ('habromos', 1),\n", | |
" ('coruccion', 1),\n", | |
" ('sinvergüenzas', 1),\n", | |
" ('pederasta', 1),\n", | |
" ('pedacito', 1),\n", | |
" ('duda', 1),\n", | |
" ('defendiendo', 1),\n", | |
" ('echen', 1),\n", | |
" ('loteria', 1),\n", | |
" ('nacer', 1),\n", | |
" ('pensaron', 1),\n", | |
" ('extranjera', 1),\n", | |
" ('apri', 1),\n", | |
" ('contiendas', 1),\n", | |
" ('hayan', 1),\n", | |
" ('carsel', 1),\n", | |
" ('peores', 1),\n", | |
" ('explosiones', 1),\n", | |
" ('robarnos', 1),\n", | |
" ('gasta', 1),\n", | |
" ('salinas', 1),\n", | |
" ('ahuevo', 1),\n", | |
" ('recibidos', 1),\n", | |
" ('obvio', 1),\n", | |
" ('estratagema', 1),\n", | |
" ('gacha', 1),\n", | |
" ('tlacuache', 1),\n", | |
" ('acatlan', 1),\n", | |
" ('figura', 1),\n", | |
" ('pasando', 1),\n", | |
" ('huela', 1),\n", | |
" ('paralisado', 1),\n", | |
" ('quejan', 1),\n", | |
" ('sintiendo', 1),\n", | |
" ('datos', 1),\n", | |
" ('deve', 1),\n", | |
" ('kitar', 1),\n", | |
" ('aliado', 1),\n", | |
" ('barrio', 1),\n", | |
" ('gandallas', 1),\n", | |
" ('destrocense', 1),\n", | |
" ('infladas', 1),\n", | |
" ('tragando', 1),\n", | |
" ('buscar', 1),\n", | |
" ('coludas', 1),\n", | |
" ('agamos', 1),\n", | |
" ('demonios', 1),\n", | |
" ('dejes', 1),\n", | |
" ('ojetes', 1),\n", | |
" ('blanquiazules', 1),\n", | |
" ('coahuila', 1),\n", | |
" ('empezndo', 1),\n", | |
" ('traia', 1),\n", | |
" ('definitivamente', 1),\n", | |
" ('pertenecen', 1),\n", | |
" ('votacion', 1),\n", | |
" ('querian', 1),\n", | |
" ('ppr', 1),\n", | |
" ('serà', 1),\n", | |
" ('aůn', 1),\n", | |
" ('podido', 1),\n", | |
" ('soga', 1),\n", | |
" ('postor', 1),\n", | |
" ('piiiiii', 1),\n", | |
" ('mueble', 1),\n", | |
" ('rivas', 1),\n", | |
" ('amigo', 1),\n", | |
" ('dije', 1),\n", | |
" ('peleando', 1),\n", | |
" ('cuchara', 1),\n", | |
" ('traicionado', 1),\n", | |
" ('homicida', 1),\n", | |
" ('hospitales', 1),\n", | |
" ('pelar', 1),\n", | |
" ('pensar', 1),\n", | |
" ('pajarito', 1),\n", | |
" ('cumplan', 1),\n", | |
" ('quedar', 1),\n", | |
" ('pisen', 1),\n", | |
" ('descanse', 1),\n", | |
" ('nni', 1),\n", | |
" ('corrias', 1),\n", | |
" ('dudosos', 1),\n", | |
" ('muestra', 1),\n", | |
" ('escuchado', 1),\n", | |
" ('olvidare', 1),\n", | |
" ('beltran', 1),\n", | |
" ('obligando', 1),\n", | |
" ('real', 1),\n", | |
" ('correrlos', 1),\n", | |
" ('durmiendo', 1),\n", | |
" ('agarran', 1),\n", | |
" ('tomaron', 1),\n", | |
" ('seguirse', 1),\n", | |
" ('gar', 1),\n", | |
" ('estuvieron', 1),\n", | |
" ('importa', 1),\n", | |
" ('gordonadora', 1),\n", | |
" ('acanbio', 1),\n", | |
" ('fracasados', 1),\n", | |
" ('garces', 1),\n", | |
" ('gobernados', 1),\n", | |
" ('asen', 1),\n", | |
" ('niño', 1),\n", | |
" ('targeta', 1),\n", | |
" ('rendon', 1),\n", | |
" ('faltos', 1),\n", | |
" ('tasa', 1),\n", | |
" ('cambie', 1),\n", | |
" ('llegue', 1),\n", | |
" ('camada', 1),\n", | |
" ('bonita', 1),\n", | |
" ('botin', 1),\n", | |
" ('otaolaurruchi', 1),\n", | |
" ('silencio', 1),\n", | |
" ('desviar', 1),\n", | |
" ('señoras', 1),\n", | |
" ('iniciar', 1),\n", | |
" ('votas', 1),\n", | |
" ('pagados', 1),\n", | |
" ('viene', 1),\n", | |
" ('pidieron', 1),\n", | |
" ('traga', 1),\n", | |
" ('debemos', 1),\n", | |
" ('canpaña', 1),\n", | |
" ('hecto', 1),\n", | |
" ('militantes', 1),\n", | |
" ('tratemos', 1),\n", | |
" ('cafe', 1),\n", | |
" ('manipular', 1),\n", | |
" ('honrades', 1),\n", | |
" ('luis', 1),\n", | |
" ('armemosla', 1),\n", | |
" ('ciudadano', 1),\n", | |
" ('esperanza', 1),\n", | |
" ('chismes', 1),\n", | |
" ('rrata', 1),\n", | |
" ('estuve', 1),\n", | |
" ('cnc', 1),\n", | |
" ('perderlo', 1),\n", | |
" ('debo', 1),\n", | |
" ('sienta', 1),\n", | |
" ('comentando', 1),\n", | |
" ('fuerzas', 1),\n", | |
" ('ceron', 1),\n", | |
" ('aceptar', 1),\n", | |
" ('kambiar', 1),\n", | |
" ('gastar', 1),\n", | |
" ('super', 1),\n", | |
" ('aprecia', 1),\n", | |
" ('eras', 1),\n", | |
" ('revolcada', 1),\n", | |
" ('informate', 1),\n", | |
" ('lad', 1),\n", | |
" ('mėxico', 1),\n", | |
" ('muertes', 1),\n", | |
" ('trankilidad', 1),\n", | |
" ('decimos', 1),\n", | |
" ('promete', 1),\n", | |
" ('escondo', 1),\n", | |
" ('numero', 1),\n", | |
" ('pichemarrana', 1),\n", | |
" ('maje', 1),\n", | |
" ('pongance', 1),\n", | |
" ('//lopezobrador', 1),\n", | |
" ('hambre', 1),\n", | |
" ('cobardes', 1),\n", | |
" ('jarochos', 1),\n", | |
" ('taca', 1),\n", | |
" ('lista', 1),\n", | |
" ('recuerdo', 1),\n", | |
" ('licenciada', 1),\n", | |
" ('ciega', 1),\n", | |
" ('jajajaka', 1),\n", | |
" ('decirle', 1),\n", | |
" ('gobierna', 1),\n", | |
" ('une', 1),\n", | |
" ('dignidad', 1),\n", | |
" ('gandero', 1),\n", | |
" ('narcos', 1),\n", | |
" ('rescatemos', 1),\n", | |
" ('echan', 1),\n", | |
" ('dee', 1),\n", | |
" ('chavo', 1),\n", | |
" ('precidente', 1),\n", | |
" ('politico', 1),\n", | |
" ('roba', 1),\n", | |
" ('avento', 1),\n", | |
" ('aviones', 1),\n", | |
" ('ejercito', 1),\n", | |
" ('robe', 1),\n", | |
" ('claudiquemos', 1),\n", | |
" ('mendigos', 1),\n", | |
" ('difamando', 1),\n", | |
" ('condenan', 1),\n", | |
" ('buey', 1),\n", | |
" ('dejas', 1),\n", | |
" ('camas', 1),\n", | |
" ('recuerden', 1),\n", | |
" ('vaa', 1),\n", | |
" ('chance', 1),\n", | |
" ('usar', 1),\n", | |
" ('ganando', 1),\n", | |
" ('pagina', 1),\n", | |
" ('juego', 1),\n", | |
" ('abrazo', 1),\n", | |
" ('intereses', 1),\n", | |
" ('quietes', 1),\n", | |
" ('ordeñando', 1),\n", | |
" ('ban', 1),\n", | |
" ('qieren', 1),\n", | |
" ('maneras', 1),\n", | |
" ('boleta', 1),\n", | |
" ('pena', 1),\n", | |
" ('encabrona', 1),\n", | |
" ('azteca', 1),\n", | |
" ('poreso', 1),\n", | |
" ('diario', 1),\n", | |
" ('llenan', 1),\n", | |
" ('fui', 1),\n", | |
" ('gaudy', 1),\n", | |
" ('hermoso', 1),\n", | |
" ('dijieron', 1),\n", | |
" ('echarles', 1),\n", | |
" ('ocupa', 1),\n", | |
" ('saquean', 1),\n", | |
" ('enemigo', 1),\n", | |
" ('cruel', 1),\n", | |
" ('coman', 1),\n", | |
" ('trabaje', 1),\n", | |
" ('alver', 1),\n", | |
" ('kiere', 1),\n", | |
" ('bendiciones', 1),\n", | |
" ('chicharrones', 1),\n", | |
" ('confirmo', 1),\n", | |
" ('tamaleros', 1),\n", | |
" ('tinoco', 1),\n", | |
" ('decepcionada', 1),\n", | |
" ('marina', 1),\n", | |
" ('achigar', 1),\n", | |
" ('encarcel', 1),\n", | |
" ('mediocres', 1),\n", | |
" ('hadta', 1),\n", | |
" ('agua', 1),\n", | |
" ('kuleros', 1),\n", | |
" ('dedican', 1),\n", | |
" ('tantito', 1),\n", | |
" ('pense', 1),\n", | |
" ('seras', 1),\n", | |
" ('sabroso', 1),\n", | |
" ('lefalta', 1),\n", | |
" ('vio', 1),\n", | |
" ('municipio', 1),\n", | |
" ('votan', 1),\n", | |
" ('ambre', 1),\n", | |
" ('humanos', 1),\n", | |
" ('mayates', 1),\n", | |
" ('enriqui', 1),\n", | |
" ('pondra', 1),\n", | |
" ('cierren', 1),\n", | |
" ('dejarnos', 1),\n", | |
" ('estimado', 1),\n", | |
" ('lacayos', 1),\n", | |
" ('acaba', 1),\n", | |
" ('peligrosos', 1),\n", | |
" ('loq', 1),\n", | |
" ('pemex', 1),\n", | |
" ('👎\\U0001f3fc😂', 1),\n", | |
" ('piedra', 1),\n", | |
" ('estaye', 1),\n", | |
" ('drenajes', 1),\n", | |
" ('rroben', 1),\n", | |
" ('cargar', 1),\n", | |
" ('sakeadores', 1),\n", | |
" ('trniendo', 1),\n", | |
" ('marcaran', 1),\n", | |
" ('fantasias', 1),\n", | |
" ('clasico', 1),\n", | |
" ('asumadre', 1),\n", | |
" ('lideres', 1),\n", | |
" ('orejas', 1),\n", | |
" ('quisiera', 1),\n", | |
" ('materia', 1),\n", | |
" ('cuerda', 1),\n", | |
" ('agarraron', 1),\n", | |
" ('vacias', 1),\n", | |
" ('ande', 1),\n", | |
" ('aceptan', 1),\n", | |
" ('cre', 1),\n", | |
" ('rescatamos', 1),\n", | |
" ('llevado', 1),\n", | |
" ('vecina', 1),\n", | |
" ('sit', 1),\n", | |
" ('mero', 1),\n", | |
" ('golpe', 1),\n", | |
" ('amor', 1),\n", | |
" ('obras', 1),\n", | |
" ('hdtsrp', 1),\n", | |
" ('tratan', 1),\n", | |
" ('insulto', 1),\n", | |
" ('tremenda', 1),\n", | |
" ('prii', 1),\n", | |
" ('perjudicar', 1),\n", | |
" ('cumplen', 1),\n", | |
" ('perdera', 1),\n", | |
" ('desperto', 1),\n", | |
" ('engorda', 1),\n", | |
" ('novedad', 1),\n", | |
" ('universitarios', 1),\n", | |
" ('papapa', 1),\n", | |
" ('arde', 1),\n", | |
" ('titere', 1),\n", | |
" ('sel', 1),\n", | |
" ('broncas', 1),\n", | |
" ('tlacuaches', 1),\n", | |
" ('mellooooo', 1),\n", | |
" ('deberian', 1),\n", | |
" ('dictaduria', 1),\n", | |
" ('org', 1),\n", | |
" ('pasara', 1),\n", | |
" ('angeles', 1),\n", | |
" ('cochina', 1),\n", | |
" ('credencial', 1),\n", | |
" ('bosca', 1),\n", | |
" ('omporta', 1),\n", | |
" ('occico', 1),\n", | |
" ('dimara', 1),\n", | |
" ('cerdonador', 1),\n", | |
" ('acabe', 1),\n", | |
" ('avian', 1),\n", | |
" ('ase', 1),\n", | |
" ('partes', 1),\n", | |
" ('ropa', 1),\n", | |
" ('demora', 1),\n", | |
" ('compromiso', 1),\n", | |
" ('viviendo', 1),\n", | |
" ('manipulando', 1),\n", | |
" ('fiesta', 1),\n", | |
" ('tema', 1),\n", | |
" ('bistek', 1),\n", | |
" ('acabado', 1),\n", | |
" ('junta', 1),\n", | |
" ('juguen', 1),\n", | |
" ('conformo', 1),\n", | |
" ('prospera', 1),\n", | |
" ('encerrar', 1),\n", | |
" ('mensos', 1),\n", | |
" ('ratassssssss', 1),\n", | |
" ('govierno', 1),\n", | |
" ('carecemos', 1),\n", | |
" ('solicito', 1),\n", | |
" ('qedar', 1),\n", | |
" ('mina', 1),\n", | |
" ('nadamas', 1),\n", | |
" ('100%', 1),\n", | |
" ('madriguera', 1),\n", | |
" ('seas', 1),\n", | |
" ('cinico', 1),\n", | |
" ('sembrado', 1),\n", | |
" ('putos', 1),\n", | |
" ('bastaria', 1),\n", | |
" ('continuen', 1),\n", | |
" ('duela', 1),\n", | |
" ('efectivamente', 1),\n", | |
" ('pobresa', 1),\n", | |
" ('desaparecer', 1),\n", | |
" ('alcaldia', 1),\n", | |
" ('aviente', 1),\n", | |
" ('invertir', 1),\n", | |
" ('capaz', 1),\n", | |
" ('analizen', 1),\n", | |
" ('incendio', 1),\n", | |
" ('defiende', 1),\n", | |
" ('rratero', 1),\n", | |
" ('santanas', 1),\n", | |
" ('maravillosos', 1),\n", | |
" ('atencion', 1),\n", | |
" ('nietos', 1),\n", | |
" ('cmo', 1),\n", | |
" ('jejejejeje', 1),\n", | |
" ('trallendo', 1),\n", | |
" ('mentiras', 1),\n", | |
" ('demente', 1),\n", | |
" ('corajes', 1),\n", | |
" ('laban', 1),\n", | |
" ('difisil', 1),\n", | |
" ('iotrospadeciendo', 1),\n", | |
" ('ablan', 1),\n", | |
" ('ague', 1),\n", | |
" ('cambiemos', 1),\n", | |
" ('sistema', 1),\n", | |
" ('logramos', 1),\n", | |
" ('ancianos', 1),\n", | |
" ('derrumbe', 1),\n", | |
" ('angelica', 1),\n", | |
" ('descubran', 1),\n", | |
" ('pri-meramente', 1),\n", | |
" ('anoche', 1),\n", | |
" ('linare', 1),\n", | |
" ('inocente', 1),\n", | |
" ('tipico', 1),\n", | |
" ('lis', 1),\n", | |
" ('comentarios', 1),\n", | |
" ('mayuli', 1),\n", | |
" ('prineros', 1),\n", | |
" ('hara', 1),\n", | |
" ('amo', 1),\n", | |
" ('llunes', 1),\n", | |
" ('contrario', 1),\n", | |
" ('albarado', 1),\n", | |
" ('pensamiento', 1),\n", | |
" ('priiu', 1),\n", | |
" ('querido', 1),\n", | |
" ('limpias', 1),\n", | |
" ('jodidos', 1),\n", | |
" ('sanas', 1),\n", | |
" ('pantalla', 1),\n", | |
" ('gobernar', 1),\n", | |
" ('amenaza', 1),\n", | |
" ('sinonimos', 1),\n", | |
" ('prison', 1),\n", | |
" ('desaparecidos', 1),\n", | |
" ('doctor', 1),\n", | |
" ('tendremos', 1),\n", | |
" ('perteneser', 1),\n", | |
" ('delicuantazo', 1),\n", | |
" ('clase', 1),\n", | |
" ('asecinos', 1),\n", | |
" ('perdieron', 1),\n", | |
" ('suceder', 1),\n", | |
" ('divertirse', 1),\n", | |
" ('rancho', 1),\n", | |
" ...]" | |
] | |
}, | |
"execution_count": 97, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"sorted_freq_list" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 98, | |
"metadata": { | |
"collapsed": false, | |
"scrolled": true | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"[('pri', 262), ('yunes', 57), ('duarte', 57), ('veracruz', 51), ('miguel', 42), ('fuera', 41), ('voto', 39), ('ratas', 38), ('gente', 37), ('angel', 36), ('pan', 36), ('pueblo', 33), ('madre', 30), ('linares', 28), ('gobierno', 28), ('estado', 26), ('pinche', 22), ('partido', 20), ('votar', 19), ('morena', 18), ('guerra', 17), ('sucia', 16), ('dinero', 16), ('carcel', 16), ('poder', 16), ('rata', 15), ('quieren', 15), ('marrana', 15), ('hector', 15), ('priistas', 14), ('pinches', 14), ('gobernador', 14), ('patadas', 14), ('bola', 14), ('pendejos', 13), ('rateros', 13), ('partidos', 13), ('ganar', 13), ('porqueria', 13), ('basta', 12), ('arriba', 12), ('ala', 11), ('corruptos', 11), ('chingar', 11), ('miedo', 10), ('gane', 10), ('voten', 10), ('cambio', 10), ('dejen', 10), ('verdad', 10)]\n" | |
] | |
} | |
], | |
"source": [ | |
"top_50 =sorted_freq_list[0:50]\n", | |
"print(top_50)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 45, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"word_vectors = {}\n", | |
"i = 0\n", | |
"for row in comments_df.iterrows():\n", | |
" current_line_vector = row[1][\"message_clean\"]\n", | |
" \n", | |
" current_vector = []\n", | |
" for word_current in current_line_vector:\n", | |
" if word_current not in STOPWORDS:\n", | |
" current_vector = current_vector + [word_current]\n", | |
" \n", | |
" for word in top_50:\n", | |
" if word[0] in current_vector:\n", | |
" append_vector = current_vector\n", | |
" append_vector.remove(word[0])\n", | |
" if word[0] in word_vectors:\n", | |
" word_vectors[word[0]] = word_vectors[word[0]] + append_vector\n", | |
" else:\n", | |
" word_vectors[word[0]] = append_vector" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 204, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"sorted_dict_keys = {}\n", | |
"for key in word_vectors:\n", | |
" freq_list_messages_word = list(FreqDist(word_vectors[key]).items())\n", | |
" sorted_freq_list_word = sorted(freq_list_messages_word, key=lambda pair: pair[1], reverse=True)\n", | |
" sorted_dict_keys[key] = sorted_freq_list_word" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 205, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"dict_keys(['ratas', 'quieren', 'estado', 'morena', 'porqueria', 'ala', 'voten', 'chingar', 'ganar', 'marrana', 'pinche', 'pan', 'pri', 'angel', 'bola', 'madre', 'arriba', 'pendejos', 'veracruz', 'verdad', 'votar', 'gente', 'miedo', 'partidos', 'gobernador', 'poder', 'dejen', 'carcel', 'duarte', 'sucia', 'dinero', 'partido', 'priistas', 'guerra', 'patadas', 'yunes', 'miguel', 'voto', 'rata', 'cambio', 'pinches', 'corruptos', 'hector', 'fuera', 'gane', 'basta', 'linares', 'pueblo', 'rateros', 'gobierno'])" | |
] | |
}, | |
"execution_count": 205, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"word_vectors.keys()" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"### Palabras que se mencionan cuando se toman los tokens más mencionados" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 206, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"[('pri', 37),\n", | |
" ('veracruz', 36),\n", | |
" ('fuera', 35),\n", | |
" ('voto', 30),\n", | |
" ('duarte', 29),\n", | |
" ('yunes', 22),\n", | |
" ('pan', 21),\n", | |
" ('gente', 20),\n", | |
" ('madre', 18),\n", | |
" ('miguel', 18),\n", | |
" ('ratas', 16),\n", | |
" ('estado', 15),\n", | |
" ('angel', 13),\n", | |
" ('morena', 13),\n", | |
" ('pueblo', 13),\n", | |
" ('linares', 12),\n", | |
" ('gobierno', 12),\n", | |
" ('votar', 11),\n", | |
" ('basta', 10),\n", | |
" ('poder', 10),\n", | |
" ('partido', 9),\n", | |
" ('carcel', 9),\n", | |
" ('perder', 8),\n", | |
" ('ganar', 8),\n", | |
" ('rateros', 8),\n", | |
" ('mierda', 8),\n", | |
" ('partidos', 8),\n", | |
" ('hector', 8),\n", | |
" ('voten', 8),\n", | |
" ('sacar', 7),\n", | |
" ('chingar', 7),\n", | |
" ('bola', 7),\n", | |
" ('cambio', 7),\n", | |
" ('despensa', 6),\n", | |
" ('pinches', 6),\n", | |
" ('pendejos', 6),\n", | |
" ('lugar', 6),\n", | |
" ('ala', 6),\n", | |
" ('porqueria', 6),\n", | |
" ('patadas', 6),\n", | |
" ('rata', 6),\n", | |
" ('verdad', 6),\n", | |
" ('sabe', 6),\n", | |
" ('marrana', 6),\n", | |
" ('hagan', 5),\n", | |
" ('ahogado', 5),\n", | |
" ('gobernador', 5),\n", | |
" ('votando', 5),\n", | |
" ('basura', 5),\n", | |
" ('mexico', 5),\n", | |
" ('gane', 5),\n", | |
" ('votemos', 5),\n", | |
" ('dinero', 5),\n", | |
" ('elecciones', 5),\n", | |
" ('robo', 5),\n", | |
" ('mal', 5),\n", | |
" ('puto', 4),\n", | |
" ('puta', 4),\n", | |
" ('pinche', 4),\n", | |
" ('priistas', 4),\n", | |
" ('pesos', 4),\n", | |
" ('dios', 4),\n", | |
" ('pais', 4),\n", | |
" ('quieren', 4),\n", | |
" ('veracruzano', 4),\n", | |
" ('arriba', 4),\n", | |
" ('jente', 4),\n", | |
" ('den', 4),\n", | |
" ('roban', 4),\n", | |
" ('gracias', 4),\n", | |
" ('vote', 4),\n", | |
" ('verga', 4),\n", | |
" ('veracruzanos', 4),\n", | |
" ('javier', 4),\n", | |
" ('guerra', 4),\n", | |
" ('gana', 4),\n", | |
" ('muera', 4),\n", | |
" ('encuestas', 4),\n", | |
" ('favor', 4),\n", | |
" ('claro', 3),\n", | |
" ('pobres', 3),\n", | |
" ('inseguridad', 3),\n", | |
" ('tapar', 3),\n", | |
" ('kien', 3),\n", | |
" ('corruptos', 3),\n", | |
" ('doriga', 3),\n", | |
" ('jajajajaja', 3),\n", | |
" ('peje', 3),\n", | |
" ('gorda', 3),\n", | |
" ('recursos', 3),\n", | |
" ('quiebra', 3),\n", | |
" ('engañar', 3),\n", | |
" ('etc', 3),\n", | |
" ('cambiar', 3),\n", | |
" ('sabemos', 3),\n", | |
" ('pendejo', 3),\n", | |
" ('años', 3),\n", | |
" ('obrador', 3),\n", | |
" ('robado', 3),\n", | |
" ('vde', 3),\n", | |
" ('punto', 3),\n", | |
" ('verde', 3),\n", | |
" ('alos', 3),\n", | |
" ('lopez', 3),\n", | |
" ('ojos', 3),\n", | |
" ('hagas', 3),\n", | |
" ('mil', 3),\n", | |
" ('asta', 3),\n", | |
" ('robar', 3),\n", | |
" ('peña', 3),\n", | |
" ('candidato', 3),\n", | |
" ('mexicanos', 3),\n", | |
" ('deberia', 3),\n", | |
" ('asu', 3),\n", | |
" ('jamas', 3),\n", | |
" ('sigan', 3),\n", | |
" ('dando', 3),\n", | |
" ('importante', 3),\n", | |
" ('meter', 3),\n", | |
" ('chinguen', 3),\n", | |
" ('peor', 3),\n", | |
" ('malos', 3),\n", | |
" ('pensionados', 3),\n", | |
" ('cree', 3),\n", | |
" ('culpa', 3),\n", | |
" ('oportunidades', 3),\n", | |
" ('boca', 3),\n", | |
" ('saben', 3),\n", | |
" ('ustedes', 3),\n", | |
" ('quieran', 3),\n", | |
" ('diferencia', 3),\n", | |
" ('somos', 3),\n", | |
" ('pura', 3),\n", | |
" ('miedo', 2),\n", | |
" ('xalapa', 2),\n", | |
" ('sale', 2),\n", | |
" ('tiempo', 2),\n", | |
" ('unico', 2),\n", | |
" ('mayoria', 2),\n", | |
" ('abajo', 2),\n", | |
" ('mafia', 2),\n", | |
" ('soy', 2),\n", | |
" ('directo', 2),\n", | |
" ('satelites', 2),\n", | |
" ('eres', 2),\n", | |
" ('ladrones', 2),\n", | |
" ('televisa', 2),\n", | |
" ('segundo', 2),\n", | |
" ('descarado', 2),\n", | |
" ('adelante', 2),\n", | |
" ('dedo', 2),\n", | |
" ('calderon', 2),\n", | |
" ('des', 2),\n", | |
" ('saquen', 2),\n", | |
" ('fidel', 2),\n", | |
" ('puras', 2),\n", | |
" ('sucio', 2),\n", | |
" ('personas', 2),\n", | |
" ('palabras', 2),\n", | |
" ('metiendo', 2),\n", | |
" ('promesas', 2),\n", | |
" ('primer', 2),\n", | |
" ('corrupcion', 2),\n", | |
" ('corrupto', 2),\n", | |
" ('madres', 2),\n", | |
" ('señor', 2),\n", | |
" ('kieren', 2),\n", | |
" ('cochino', 2),\n", | |
" ('pelea', 2),\n", | |
" ('lana', 2),\n", | |
" ('darle', 2),\n", | |
" ('historia', 2),\n", | |
" ('ven', 2),\n", | |
" ('yuni', 2),\n", | |
" ('señores', 2),\n", | |
" ('nieto', 2),\n", | |
" ('seguiremos', 2),\n", | |
" ('digan', 2),\n", | |
" ('dejaron', 2),\n", | |
" ('sige', 2),\n", | |
" ('campaña', 2),\n", | |
" ('diputados', 2),\n", | |
" ('gastando', 2),\n", | |
" ('ves', 2),\n", | |
" ('votos', 2),\n", | |
" ('sector', 2),\n", | |
" ('vean', 2),\n", | |
" ('finanzas', 2),\n", | |
" ('quiero', 2),\n", | |
" ('andan', 2),\n", | |
" ('siente', 2),\n", | |
" ('marrano', 2),\n", | |
" ('acabar', 2),\n", | |
" ('regala', 2),\n", | |
" ('riko', 2),\n", | |
" ('mamada', 2),\n", | |
" ('esperaban', 2),\n", | |
" ('crean', 2),\n", | |
" ('hueso', 2),\n", | |
" ('pendejadas', 2),\n", | |
" ('muerto', 2),\n", | |
" ('diciendo', 2),\n", | |
" ('agarro', 2),\n", | |
" ('vale', 2),\n", | |
" ('votaran', 2),\n", | |
" ('seguro', 2),\n", | |
" ('diran', 2),\n", | |
" ('delincuencia', 2),\n", | |
" ('crimen', 2),\n", | |
" ('mandar', 2),\n", | |
" ('opciones', 2),\n", | |
" ('vaya', 2),\n", | |
" ('saquemos', 2),\n", | |
" ('seguira', 2),\n", | |
" ('votaron', 2),\n", | |
" ('paso', 2),\n", | |
" ('opcion', 2),\n", | |
" ('idiota', 2),\n", | |
" ('miseria', 2),\n", | |
" ('pendeja', 2),\n", | |
" ('aya', 2),\n", | |
" ('amlo', 2),\n", | |
" ('siquiera', 2),\n", | |
" ('saca', 2),\n", | |
" ('iba', 2),\n", | |
" ('boto', 2),\n", | |
" ('perdido', 2),\n", | |
" ('robaron', 2),\n", | |
" ('despierten', 2),\n", | |
" ('igual', 2),\n", | |
" ('pareciera', 2),\n", | |
" ('cabeza', 2),\n", | |
" ('landa', 2),\n", | |
" ('limpio', 2),\n", | |
" ('año', 2),\n", | |
" ('simplemente', 2),\n", | |
" ('patria', 2),\n", | |
" ('votare', 2),\n", | |
" ('seguir', 2),\n", | |
" ('tanta', 2),\n", | |
" ('metio', 2),\n", | |
" ('dejar', 2),\n", | |
" ('aliados', 2),\n", | |
" ('perros', 2),\n", | |
" ('salio', 2),\n", | |
" ('afuera', 2),\n", | |
" ('venga', 2),\n", | |
" ('nombre', 2),\n", | |
" ('ntro', 2),\n", | |
" ('vida', 2),\n", | |
" ('cochinos', 2),\n", | |
" ('seguridad', 2),\n", | |
" ('nose', 2),\n", | |
" ('ignorantes', 2),\n", | |
" ('esperarse', 2),\n", | |
" ('manos', 2),\n", | |
" ('alianza', 2),\n", | |
" ('increible', 2),\n", | |
" ('asesino', 2),\n", | |
" ('apoyando', 2),\n", | |
" ('maldito', 2),\n", | |
" ('mamadas', 2),\n", | |
" ('millones', 2),\n", | |
" ('gobernatura', 2),\n", | |
" ('elector', 2),\n", | |
" ('creen', 2),\n", | |
" ('vendido', 2),\n", | |
" ('junio', 2),\n", | |
" ('mandan', 2),\n", | |
" ('hijos', 2),\n", | |
" ('rratas', 2),\n", | |
" ('cara', 2),\n", | |
" ('aser', 2),\n", | |
" ('siganle', 2),\n", | |
" ('sucia', 2),\n", | |
" ('dejen', 2),\n", | |
" ('puntos', 2),\n", | |
" ('siga', 2),\n", | |
" ('entiendan', 2),\n", | |
" ('pobre', 2),\n", | |
" ('chinge', 2),\n", | |
" ('diske', 1),\n", | |
" ('conformista', 1),\n", | |
" ('cono', 1),\n", | |
" ('maquinaria', 1),\n", | |
" ('apoya', 1),\n", | |
" ('pescado', 1),\n", | |
" ('chorrillo', 1),\n", | |
" ('aleman', 1),\n", | |
" ('namas', 1),\n", | |
" ('complices', 1),\n", | |
" ('perdedores', 1),\n", | |
" ('lacara', 1),\n", | |
" ('pola', 1),\n", | |
" ('empleos', 1),\n", | |
" ('dividir', 1),\n", | |
" ('regordete', 1),\n", | |
" ('colores', 1),\n", | |
" ('hablar', 1),\n", | |
" ('apollarte', 1),\n", | |
" ('metan', 1),\n", | |
" ('descanse', 1),\n", | |
" ('falsas', 1),\n", | |
" ('levantones', 1),\n", | |
" ('orarios', 1),\n", | |
" ('murio', 1),\n", | |
" ('abrir', 1),\n", | |
" ('quemados', 1),\n", | |
" ('ver´', 1),\n", | |
" ('limpiar', 1),\n", | |
" ('vaja', 1),\n", | |
" ('justicia', 1),\n", | |
" ('porkeria', 1),\n", | |
" ('presupuesto', 1),\n", | |
" ('gracia', 1),\n", | |
" ('empleados', 1),\n", | |
" ('andas', 1),\n", | |
" ('dejemos', 1),\n", | |
" ('adar', 1),\n", | |
" ('huesito', 1),\n", | |
" ('callarle', 1),\n", | |
" ('ofrecer', 1),\n", | |
" ('soga', 1),\n", | |
" ('culeros', 1),\n", | |
" ('objetivo', 1),\n", | |
" ('alcanza', 1),\n", | |
" ('yunez', 1),\n", | |
" ('decirle', 1),\n", | |
" ('perdieron', 1),\n", | |
" ('robarle', 1),\n", | |
" ('sienpre', 1),\n", | |
" ('aile', 1),\n", | |
" ('coca', 1),\n", | |
" ('fslsos', 1),\n", | |
" ('razonemos', 1),\n", | |
" ('madrrados', 1),\n", | |
" ('manches', 1),\n", | |
" ('llenan', 1),\n", | |
" ('meta', 1),\n", | |
" ('jajajajajajjaja', 1),\n", | |
" ('kiere', 1),\n", | |
" ('nido', 1),\n", | |
" ('rateriad', 1),\n", | |
" ('llenar', 1),\n", | |
" ('achigar', 1),\n", | |
" ('secuaces', 1),\n", | |
" ('definido', 1),\n", | |
" ('asil', 1),\n", | |
" ('recuperar', 1),\n", | |
" ('cerdo', 1),\n", | |
" ('coruccion', 1),\n", | |
" ('gusta', 1),\n", | |
" ('umilde', 1),\n", | |
" ('pedacito', 1),\n", | |
" ('cojer', 1),\n", | |
" ('continuar', 1),\n", | |
" ('siega', 1),\n", | |
" ('casas', 1),\n", | |
" ('fotos', 1),\n", | |
" ('escuchados', 1),\n", | |
" ('traisiono', 1),\n", | |
" ('social', 1),\n", | |
" ('puerco', 1),\n", | |
" ('pensaron', 1),\n", | |
" ('cuentos', 1),\n", | |
" ('extranjera', 1),\n", | |
" ('cobrar', 1),\n", | |
" ('noticias', 1),\n", | |
" ('contiendas', 1),\n", | |
" ('pagina', 1),\n", | |
" ('carsel', 1),\n", | |
" ('peores', 1),\n", | |
" ('cambiemos', 1),\n", | |
" ('robarnos', 1),\n", | |
" ('ochoa', 1),\n", | |
" ('federal', 1),\n", | |
" ('gandero', 1),\n", | |
" ('obvio', 1),\n", | |
" ('llevo', 1),\n", | |
" ('saber', 1),\n", | |
" ('utilizando', 1),\n", | |
" ('gacha', 1),\n", | |
" ('huela', 1),\n", | |
" ('perteneser', 1),\n", | |
" ('quejan', 1),\n", | |
" ('datos', 1),\n", | |
" ('analiticos', 1),\n", | |
" ('cortina', 1),\n", | |
" ('valio', 1),\n", | |
" ('ching', 1),\n", | |
" ('ganara', 1),\n", | |
" ('ponerte', 1),\n", | |
" ('aliado', 1),\n", | |
" ('barrio', 1),\n", | |
" ('jugando', 1),\n", | |
" ('gandallas', 1),\n", | |
" ('bandido', 1),\n", | |
" ('foto', 1),\n", | |
" ('correrlos', 1),\n", | |
" ('jajakael', 1),\n", | |
" ('haces', 1),\n", | |
" ('buscar', 1),\n", | |
" ('pansona', 1),\n", | |
" ('desesperados', 1),\n", | |
" ('dejando', 1),\n", | |
" ('coahuila', 1),\n", | |
" ('confianza', 1),\n", | |
" ('traia', 1),\n", | |
" ('definitivamente', 1),\n", | |
" ('nadien', 1),\n", | |
" ('votacion', 1),\n", | |
" ('miserable', 1),\n", | |
" ('delicuencia', 1),\n", | |
" ('pongan', 1),\n", | |
" ('respeto', 1),\n", | |
" ('piiiiii', 1),\n", | |
" ('asesinatos', 1),\n", | |
" ('criterio', 1),\n", | |
" ('criterios', 1),\n", | |
" ('sacarlos', 1),\n", | |
" ('sube', 1),\n", | |
" ('violencia', 1),\n", | |
" ('quieras', 1),\n", | |
" ('cinico', 1),\n", | |
" ('cuchara', 1),\n", | |
" ('porq', 1),\n", | |
" ('traicionado', 1),\n", | |
" ('tiro', 1),\n", | |
" ('nefasto', 1),\n", | |
" ('limpios', 1),\n", | |
" ('ganador', 1),\n", | |
" ('pajarito', 1),\n", | |
" ('beneficiar', 1),\n", | |
" ('nni', 1),\n", | |
" ('gusto', 1),\n", | |
" ('importa', 1),\n", | |
" ('mosle', 1),\n", | |
" ('vota', 1),\n", | |
" ('hasen', 1),\n", | |
" ('carvallo', 1),\n", | |
" ('escuchado', 1),\n", | |
" ('beltran', 1),\n", | |
" ('mendingando', 1),\n", | |
" ('acanbio', 1),\n", | |
" ('converse', 1),\n", | |
" ('durmiendo', 1),\n", | |
" ('spero', 1),\n", | |
" ('pierda', 1),\n", | |
" ('abusos', 1),\n", | |
" ('ganado', 1),\n", | |
" ('seguirse', 1),\n", | |
" ('motivo', 1),\n", | |
" ('estuvieron', 1),\n", | |
" ('alio', 1),\n", | |
" ('garces', 1),\n", | |
" ('extorsiones', 1),\n", | |
" ('niño', 1),\n", | |
" ('ebrio', 1),\n", | |
" ('targeta', 1),\n", | |
" ('diarte', 1),\n", | |
" ('venido', 1),\n", | |
" ('cochinada', 1),\n", | |
" ('pequeños', 1),\n", | |
" ('prd', 1),\n", | |
" ('despedida', 1),\n", | |
" ('carros', 1),\n", | |
" ('voluntad', 1),\n", | |
" ('camada', 1),\n", | |
" ('tumba', 1),\n", | |
" ('arrastrado', 1),\n", | |
" ('olvidaro', 1),\n", | |
" ('sienten', 1),\n", | |
" ('tuyas', 1),\n", | |
" ('sinvergüenza', 1),\n", | |
" ('desviar', 1),\n", | |
" ('wevos', 1),\n", | |
" ('cartel', 1),\n", | |
" ('ignorante', 1),\n", | |
" ('señoras', 1),\n", | |
" ('papa', 1),\n", | |
" ('ensucian', 1),\n", | |
" ('votas', 1),\n", | |
" ('miserias', 1),\n", | |
" ('politiko', 1),\n", | |
" ('aber', 1),\n", | |
" ('aora', 1),\n", | |
" ('pague', 1),\n", | |
" ('secuestros', 1),\n", | |
" ('3000', 1),\n", | |
" ('canpaña', 1),\n", | |
" ('hecto', 1),\n", | |
" ('poo', 1),\n", | |
" ('apoyara', 1),\n", | |
" ('http', 1),\n", | |
" ('manipular', 1),\n", | |
" ('vino', 1),\n", | |
" ('titulares', 1),\n", | |
" ('aclaran', 1),\n", | |
" ('ayuda', 1),\n", | |
" ('politicos', 1),\n", | |
" ('espaeramos', 1),\n", | |
" ('trayectoria', 1),\n", | |
" ('pipo', 1),\n", | |
" ('rrata', 1),\n", | |
" ('cnc', 1),\n", | |
" ('confirma', 1),\n", | |
" ('lados', 1),\n", | |
" ('digas', 1),\n", | |
" ('presentan', 1),\n", | |
" ('comentando', 1),\n", | |
" ('documentacion', 1),\n", | |
" ('culo', 1),\n", | |
" ('asco', 1),\n", | |
" ('kambiar', 1),\n", | |
" ('gastar', 1),\n", | |
" ('aprecia', 1),\n", | |
" ('perderlo', 1),\n", | |
" ('informate', 1),\n", | |
" ('lad', 1),\n", | |
" ('presidentes', 1),\n", | |
" ('haga', 1),\n", | |
" ('muertes', 1),\n", | |
" ('soborno', 1),\n", | |
" ('vuelta', 1),\n", | |
" ('podido', 1),\n", | |
" ('apoyar', 1),\n", | |
" ('ganaba', 1),\n", | |
" ('malditas', 1),\n", | |
" ('sufriendo', 1),\n", | |
" ('puerca', 1),\n", | |
" ('monos', 1),\n", | |
" ('trato', 1),\n", | |
" ('chingarse', 1),\n", | |
" ('tus', 1),\n", | |
" ('//lopezobrador', 1),\n", | |
" ('impuso', 1),\n", | |
" ('cobardes', 1),\n", | |
" ('vendiendo', 1),\n", | |
" ('taca', 1),\n", | |
" ('ahuihui', 1),\n", | |
" ('chile', 1),\n", | |
" ('ciega', 1),\n", | |
" ('creer', 1),\n", | |
" ('gobierna', 1),\n", | |
" ('realmente', 1),\n", | |
" ('trepan', 1),\n", | |
" ('escribio', 1),\n", | |
" ('misera', 1),\n", | |
" ('bolsa', 1),\n", | |
" ('informarse', 1),\n", | |
" ('tambo', 1),\n", | |
" ('gestiones', 1),\n", | |
" ('muucha', 1),\n", | |
" ('vasta', 1),\n", | |
" ('dee', 1),\n", | |
" ('rojos', 1),\n", | |
" ('alver', 1),\n", | |
" ('precidente', 1),\n", | |
" ('rratero', 1),\n", | |
" ('rancho', 1),\n", | |
" ('realidad', 1),\n", | |
" ('avento', 1),\n", | |
" ('sionismo', 1),\n", | |
" ('vendan', 1),\n", | |
" ('aviones', 1),\n", | |
" ('mamen', 1),\n", | |
" ('ayudando', 1),\n", | |
" ('hermoso', 1),\n", | |
" ('dejas', 1),\n", | |
" ('astrosidad', 1),\n", | |
" ('diga', 1),\n", | |
" ('recuerden', 1),\n", | |
" ('destrozadas', 1),\n", | |
" ('vaa', 1),\n", | |
" ('decian', 1),\n", | |
" ('chance', 1),\n", | |
" ('ganando', 1),\n", | |
" ('permitamos', 1),\n", | |
" ('planeo', 1),\n", | |
" ('pajaritos', 1),\n", | |
" ('quietes', 1),\n", | |
" ('ban', 1),\n", | |
" ('piense', 1),\n", | |
" ('maneras', 1),\n", | |
" ('familia', 1),\n", | |
" ('querian', 1),\n", | |
" ('pena', 1),\n", | |
" ('poreso', 1),\n", | |
" ('igualitos', 1),\n", | |
" ('muestra', 1),\n", | |
" ('mayuli', 1),\n", | |
" ('hagamos', 1),\n", | |
" ('fui', 1),\n", | |
" ('analiza', 1),\n", | |
" ('dijieron', 1),\n", | |
" ('inepto', 1),\n", | |
" ('entro', 1),\n", | |
" ('cuitlahuac', 1),\n", | |
" ('largo', 1),\n", | |
" ('estaran', 1),\n", | |
" ('miren', 1),\n", | |
" ('saquean', 1),\n", | |
" ('compañeros', 1),\n", | |
" ('deberle', 1),\n", | |
" ('miguelon', 1),\n", | |
" ('familias', 1),\n", | |
" ('enemigo', 1),\n", | |
" ('coman', 1),\n", | |
" ('hagase', 1),\n", | |
" ('trataran', 1),\n", | |
" ('universitarios', 1),\n", | |
" ('chicharrones', 1),\n", | |
" ('paz', 1),\n", | |
" ('confirmo', 1),\n", | |
" ('putos', 1),\n", | |
" ('cantar', 1),\n", | |
" ('boleta', 1),\n", | |
" ('dictador', 1),\n", | |
" ('autopista', 1),\n", | |
" ('decepcionada', 1),\n", | |
" ('desaparecer', 1),\n", | |
" ('mis', 1),\n", | |
" ('aparezca', 1),\n", | |
" ('tantito', 1),\n", | |
" ('palisa', 1),\n", | |
" ('humo', 1),\n", | |
" ('esque', 1),\n", | |
" ('complice', 1),\n", | |
" ('hadta', 1),\n", | |
" ('kuleros', 1),\n", | |
" ('traidor', 1),\n", | |
" ('dedican', 1),\n", | |
" ('votarcpor', 1),\n", | |
" ('recuerda', 1),\n", | |
" ('seras', 1),\n", | |
" ('andar', 1),\n", | |
" ('hermanos', 1),\n", | |
" ('lefalta', 1),\n", | |
" ('vio', 1),\n", | |
" ('ase', 1),\n", | |
" ('votan', 1),\n", | |
" ('harta', 1),\n", | |
" ('gobernados', 1),\n", | |
" ('xfavor', 1),\n", | |
" ('mayates', 1),\n", | |
" ('enriqui', 1),\n", | |
" ('tienes', 1),\n", | |
" ('confio', 1),\n", | |
" ('mansiones', 1),\n", | |
" ('ablan', 1),\n", | |
" ('adios', 1),\n", | |
" ('estimado', 1),\n", | |
" ('imparticion', 1),\n", | |
" ('loq', 1),\n", | |
" ('llunes', 1),\n", | |
" ('regalar', 1),\n", | |
" ('estaye', 1),\n", | |
" ('panistas', 1),\n", | |
" ('salario', 1),\n", | |
" ('asesinos', 1),\n", | |
" ('sakeadores', 1),\n", | |
" ('desesperada', 1),\n", | |
" ('trniendo', 1),\n", | |
" ('muestran', 1),\n", | |
" ('vimos', 1),\n", | |
" ('fantasias', 1),\n", | |
" ('opinion', 1),\n", | |
" ('lic', 1),\n", | |
" ('novenario', 1),\n", | |
" ('mala', 1),\n", | |
" ('trabajo', 1),\n", | |
" ('orejas', 1),\n", | |
" ('juege', 1),\n", | |
" ('cocninos', 1),\n", | |
" ('pidiendo', 1),\n", | |
" ('agarraron', 1),\n", | |
" ('entienden', 1),\n", | |
" ('ganen', 1),\n", | |
" ('disen', 1),\n", | |
" ('aceptan', 1),\n", | |
" ('cre', 1),\n", | |
" ('rescatamos', 1),\n", | |
" ('piensan', 1),\n", | |
" ('llevado', 1),\n", | |
" ('vecina', 1),\n", | |
" ('sit', 1),\n", | |
" ('mero', 1),\n", | |
" ('sirves', 1),\n", | |
" ('golpe', 1),\n", | |
" ('obras', 1),\n", | |
" ('organisado', 1),\n", | |
" ('derecha', 1),\n", | |
" ('podridas', 1),\n", | |
" ('save', 1),\n", | |
" ('perjudicar', 1),\n", | |
" ('cumplen', 1),\n", | |
" ('oposicion', 1),\n", | |
" ('lacras', 1),\n", | |
" ('alianzas', 1),\n", | |
" ('ria', 1),\n", | |
" ('desperto', 1),\n", | |
" ('ciudadania', 1),\n", | |
" ('desesperadisimos', 1),\n", | |
" ('patrimordial', 1),\n", | |
" ('grande', 1),\n", | |
" ('cargo', 1),\n", | |
" ('comer', 1),\n", | |
" ('engañando', 1),\n", | |
" ('sel', 1),\n", | |
" ('aparescan', 1),\n", | |
" ('pidamosle', 1),\n", | |
" ('amenasan', 1),\n", | |
" ('dictaduria', 1),\n", | |
" ('org', 1),\n", | |
" ('esperanza', 1),\n", | |
" ('chingao', 1),\n", | |
" ('angeles', 1),\n", | |
" ('credencial', 1),\n", | |
" ('bosca', 1),\n", | |
" ('omporta', 1),\n", | |
" ('porkerias', 1),\n", | |
" ('laa', 1),\n", | |
" ('amigo', 1),\n", | |
" ('dimara', 1),\n", | |
" ('acabe', 1),\n", | |
" ('uacion', 1),\n", | |
" ('puros', 1),\n", | |
" ('partes', 1),\n", | |
" ('bajara', 1),\n", | |
" ('ira', 1),\n", | |
" ('visitas', 1),\n", | |
" ('viviendo', 1),\n", | |
" ('quiten', 1),\n", | |
" ('perdida', 1),\n", | |
" ('central', 1),\n", | |
" ('tapir', 1),\n", | |
" ('bistek', 1),\n", | |
" ('acabado', 1),\n", | |
" ('carnicas', 1),\n", | |
" ('junta', 1),\n", | |
" ('juguen', 1),\n", | |
" ('prospera', 1),\n", | |
" ('despojados', 1),\n", | |
" ('largan', 1),\n", | |
" ('correcta', 1),\n", | |
" ('acabaron', 1),\n", | |
" ('mensos', 1),\n", | |
" ('ratassssssss', 1),\n", | |
" ('fuerte', 1),\n", | |
" ('govierno', 1),\n", | |
" ('carecemos', 1),\n", | |
" ('enel', 1),\n", | |
" ('presidente', 1),\n", | |
" ('goto', 1),\n", | |
" ('solicito', 1),\n", | |
" ('estupida', 1),\n", | |
" ('lujosos', 1),\n", | |
" ('elegir', 1),\n", | |
" ('vueltas', 1),\n", | |
" ('drogados', 1),\n", | |
" ('gobernar', 1),\n", | |
" ('depositan', 1),\n", | |
" ('ypeña', 1),\n", | |
" ('aplicar', 1),\n", | |
" ('torio', 1),\n", | |
" ('epn', 1),\n", | |
" ('mamando', 1),\n", | |
" ('chifla', 1),\n", | |
" ('protegen', 1),\n", | |
" ('bomba', 1),\n", | |
" ('isidro', 1),\n", | |
" ('bastaria', 1),\n", | |
" ('continuen', 1),\n", | |
" ('duela', 1),\n", | |
" ('efectivamente', 1),\n", | |
" ('pobresa', 1),\n", | |
" ('maestros', 1),\n", | |
" ('alcaldia', 1),\n", | |
" ('vayan', 1),\n", | |
" ('logotipo', 1),\n", | |
" ('jajajajjaja', 1),\n", | |
" ('alimentado', 1),\n", | |
" ('perdio', 1),\n", | |
" ('iguales', 1),\n", | |
" ('apoyo', 1),\n", | |
" ('analizen', 1),\n", | |
" ('violencias', 1),\n", | |
" ('bote', 1),\n", | |
" ('ami', 1),\n", | |
" ('formas', 1),\n", | |
" ('salir', 1),\n", | |
" ('hayan', 1),\n", | |
" ('enviaron', 1),\n", | |
" ('corajes', 1),\n", | |
" ('manejos', 1),\n", | |
" ('difaman', 1),\n", | |
" ('union', 1),\n", | |
" ('atencion', 1),\n", | |
" ('muertos', 1),\n", | |
" ('nietos', 1),\n", | |
" ('durar', 1),\n", | |
" ('conocemos', 1),\n", | |
" ('trallendo', 1),\n", | |
" ('ganso', 1),\n", | |
" ('demente', 1),\n", | |
" ('alguien', 1),\n", | |
" ('independiente', 1),\n", | |
" ('hambre', 1),\n", | |
" ('arribistas', 1),\n", | |
" ('dejarnos', 1),\n", | |
" ('soltar', 1),\n", | |
" ('ague', 1),\n", | |
" ('ecologista', 1),\n", | |
" ('joto', 1),\n", | |
" ('saludos', 1),\n", | |
" ('afan', 1),\n", | |
" ('candidatura', 1),\n", | |
" ('complises', 1),\n", | |
" ('valen', 1),\n", | |
" ('rrateros', 1),\n", | |
" ('logramos', 1),\n", | |
" ('ancianos', 1),\n", | |
" ('electorado', 1),\n", | |
" ('descubran', 1),\n", | |
" ('ojala', 1),\n", | |
" ('mautzer', 1),\n", | |
" ('tapando', 1),\n", | |
" ('pri-meramente', 1),\n", | |
" ('anoche', 1),\n", | |
" ('akeyos', 1),\n", | |
" ('vivo', 1),\n", | |
" ('mugre', 1),\n", | |
" ('dispuesto', 1),\n", | |
" ('nomas', 1),\n", | |
" ('hara', 1),\n", | |
" ('salinas', 1),\n", | |
" ('parientes', 1),\n", | |
" ('sacarlo', 1),\n", | |
" ('resultado', 1),\n", | |
" ('albarado', 1),\n", | |
" ('siguen', 1),\n", | |
" ('querido', 1),\n", | |
" ('limpias', 1),\n", | |
" ('ocupa', 1),\n", | |
" ('gey', 1),\n", | |
" ('aguas', 1),\n", | |
" ('desaparecidos', 1),\n", | |
" ('militante', 1),\n", | |
" ('pendejas', 1),\n", | |
" ('doctor', 1),\n", | |
" ('microcefalia', 1),\n", | |
" ('muriendo', 1),\n", | |
" ('promesa', 1),\n", | |
" ('opresoras', 1),\n", | |
" ('botin', 1),\n", | |
" ('quede', 1),\n", | |
" ('fijar', 1),\n", | |
" ('conforman', 1),\n", | |
" ('trepadores', 1),\n", | |
" ('hora', 1),\n", | |
" ('tubo', 1),\n", | |
" ('pagar', 1),\n", | |
" ('apoco', 1),\n", | |
" ('derecho', 1),\n", | |
" ('tapo', 1),\n", | |
" ('taxis', 1),\n", | |
" ('lema', 1),\n", | |
" ('abran', 1),\n", | |
" ('cinismo', 1),\n", | |
" ('mina', 1),\n", | |
" ('ocultar', 1),\n", | |
" ('publicacion', 1),\n", | |
" ('boten', 1),\n", | |
" ('vendio', 1),\n", | |
" ('dinosaurios', 1),\n", | |
" ('tricolor', 1),\n", | |
" ('salarios', 1),\n", | |
" ('temerosos', 1),\n", | |
" ('encarga', 1),\n", | |
" ('herrera', 1),\n", | |
" ('sanas', 1),\n", | |
" ('golpeado', 1),\n", | |
" ('montoya', 1),\n", | |
" ('mella', 1),\n", | |
" ('salud', 1),\n", | |
" ('bastante', 1),\n", | |
" ('acatlan', 1),\n", | |
" ('mundo', 1),\n", | |
" ('puedo', 1),\n", | |
" ('roben', 1),\n", | |
" ('botar', 1),\n", | |
" ('llamada', 1),\n", | |
" ('figura', 1),\n", | |
" ('trankilidad', 1),\n", | |
" ('regresa', 1),\n", | |
" ('desgracia', 1),\n", | |
" ('tortas', 1),\n", | |
" ('congreso', 1),\n", | |
" ('decimos', 1),\n", | |
" ('flota', 1),\n", | |
" ('recordar', 1),\n", | |
" ('despierta', 1),\n", | |
" ('heroe', 1),\n", | |
" ('sorprende', 1),\n", | |
" ('hacemos', 1),\n", | |
" ('mataron', 1),\n", | |
" ('priista', 1),\n", | |
" ('pertido', 1),\n", | |
" ('seguidores', 1),\n", | |
" ('aso', 1),\n", | |
" ('floristeros', 1),\n", | |
" ('cuentas', 1),\n", | |
" ('mentira', 1),\n", | |
" ('tratemos', 1),\n", | |
" ('caso', 1),\n", | |
" ('toman', 1),\n", | |
" ('ayudar', 1),\n", | |
" ('credenciales', 1),\n", | |
" ('omosexual', 1),\n", | |
" ('mejorar', 1),\n", | |
" ('permitiremos', 1),\n", | |
" ('lumbre', 1),\n", | |
" ('dure', 1),\n", | |
" ('debemos', 1),\n", | |
" ('sol', 1),\n", | |
" ('trabajando', 1),\n", | |
" ('axiones', 1),\n", | |
" ('montajes', 1),\n", | |
" ('votara', 1),\n", | |
" ('quremos', 1),\n", | |
" ('carlos', 1),\n", | |
" ('podrida', 1),\n", | |
" ('une', 1),\n", | |
" ('carne', 1),\n", | |
" ('ande', 1),\n", | |
" ('palacio', 1),\n", | |
" ('dominado', 1),\n", | |
" ('creyendo', 1),\n", | |
" ('dejense', 1),\n", | |
" ('cuello', 1),\n", | |
" ('aliannas', 1),\n", | |
" ('serian', 1),\n", | |
" ('sinvergüenzadas', 1),\n", | |
" ('ricos', 1),\n", | |
" ('34%', 1),\n", | |
" ('jugar', 1),\n", | |
" ('declaraciones', 1),\n", | |
" ('explocion', 1),\n", | |
" ('das', 1),\n", | |
" ('frutas', 1),\n", | |
" ('asistir', 1),\n", | |
" ('nacion', 1),\n", | |
" ('2do', 1),\n", | |
" ('aliarse', 1),\n", | |
" ('vinieron', 1),\n", | |
" ('malo', 1),\n", | |
" ('depende', 1),\n", | |
" ('carajo', 1),\n", | |
" ('empaña', 1),\n", | |
" ('vandido', 1),\n", | |
" ('haz', 1),\n", | |
" ('omar', 1),\n", | |
" ('cansa', 1),\n", | |
" ('yase', 1),\n", | |
" ('resigna', 1),\n", | |
" ('obtener', 1),\n", | |
" ('queda', 1),\n", | |
" ('comprobar', 1),\n", | |
" ('hiran', 1),\n", | |
" ('alegria', 1),\n", | |
" ('expot', 1),\n", | |
" ('cuanta', 1),\n", | |
" ('vemos', 1),\n", | |
" ('increiblemente', 1),\n", | |
" ('micerable', 1),\n", | |
" ('linare', 1),\n", | |
" ('real', 1),\n", | |
" ('votes', 1),\n", | |
" ('matar', 1),\n", | |
" ('escena', 1),\n", | |
" ('andemos', 1),\n", | |
" ('cagadas', 1),\n", | |
" ('neta', 1),\n", | |
" ('gañar', 1),\n", | |
" ('hollo', 1),\n", | |
" ('agamos', 1),\n", | |
" ('fracaso', 1),\n", | |
" ('gobernante', 1),\n", | |
" ('preguntenle', 1),\n", | |
" ('ciudadanos', 1),\n", | |
" ('mesa', 1),\n", | |
" ('pandilla', 1),\n", | |
" ('sii', 1),\n", | |
" ('lastima', 1),\n", | |
" ('derrocar', 1),\n", | |
" ('chingada', 1),\n", | |
" ('cafe', 1),\n", | |
" ('creados', 1),\n", | |
" ('verdaderos', 1),\n", | |
" ('espantan', 1),\n", | |
" ...]" | |
] | |
}, | |
"execution_count": 206, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"sorted_dict_keys[\"pri\"]" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"collapsed": false | |
}, | |
"source": [ | |
"## Empieza trabajo de clasificación supervisada" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 207, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/html": [ | |
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n", | |
"<table border=\"1\" class=\"dataframe\">\n", | |
" <thead>\n", | |
" <tr style=\"text-align: right;\">\n", | |
" <th></th>\n", | |
" <th>created_time</th>\n", | |
" <th>from_id</th>\n", | |
" <th>from_name</th>\n", | |
" <th>id</th>\n", | |
" <th>message</th>\n", | |
" <th>message_clean</th>\n", | |
" <th>categoria</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>2016-04-19T22:10:23+0000</td>\n", | |
" <td>1129125517119186</td>\n", | |
" <td>Javier Lecter</td>\n", | |
" <td>1052734731465949_1052775478128541</td>\n", | |
" <td>igual que en Tamaulipas ya van para afuera por...</td>\n", | |
" <td>[igual, que, tamaulipas, van, para, afuera, po...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>2016-04-19T22:20:31+0000</td>\n", | |
" <td>563927170436016</td>\n", | |
" <td>Ivan Jist</td>\n", | |
" <td>1052734731465949_1052779208128168</td>\n", | |
" <td>Y el pri por robar todo el dinero a la Uv y ci...</td>\n", | |
" <td>[pri, por, robar, todo, dinero, cierto, robo, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>2016-04-19T22:27:06+0000</td>\n", | |
" <td>716106398532421</td>\n", | |
" <td>Pequeño Corazonsito Cruz</td>\n", | |
" <td>1052734731465949_1052781654794590</td>\n", | |
" <td>Yo</td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>2016-04-19T22:30:10+0000</td>\n", | |
" <td>1169546603088411</td>\n", | |
" <td>Carlos F Vazquez</td>\n", | |
" <td>1052734731465949_1052782811461141</td>\n", | |
" <td>Nadie vote por el pri por tenemos que correrlo...</td>\n", | |
" <td>[nadie, vote, por, pri, por, tenemos, que, cor...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>2016-04-19T22:32:14+0000</td>\n", | |
" <td>232046980484475</td>\n", | |
" <td>David Camacho</td>\n", | |
" <td>1052734731465949_1052783438127745</td>\n", | |
" <td>El pri está dando patadas de hogado, ya no pue...</td>\n", | |
" <td>[pri, esta, dando, patadas, hogado, puede, man...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" created_time from_id from_name \\\n", | |
"0 2016-04-19T22:10:23+0000 1129125517119186 Javier Lecter \n", | |
"1 2016-04-19T22:20:31+0000 563927170436016 Ivan Jist \n", | |
"2 2016-04-19T22:27:06+0000 716106398532421 Pequeño Corazonsito Cruz \n", | |
"3 2016-04-19T22:30:10+0000 1169546603088411 Carlos F Vazquez \n", | |
"4 2016-04-19T22:32:14+0000 232046980484475 David Camacho \n", | |
"\n", | |
" id \\\n", | |
"0 1052734731465949_1052775478128541 \n", | |
"1 1052734731465949_1052779208128168 \n", | |
"2 1052734731465949_1052781654794590 \n", | |
"3 1052734731465949_1052782811461141 \n", | |
"4 1052734731465949_1052783438127745 \n", | |
"\n", | |
" message \\\n", | |
"0 igual que en Tamaulipas ya van para afuera por... \n", | |
"1 Y el pri por robar todo el dinero a la Uv y ci... \n", | |
"2 Yo \n", | |
"3 Nadie vote por el pri por tenemos que correrlo... \n", | |
"4 El pri está dando patadas de hogado, ya no pue... \n", | |
"\n", | |
" message_clean categoria \n", | |
"0 [igual, que, tamaulipas, van, para, afuera, po... none \n", | |
"1 [pri, por, robar, todo, dinero, cierto, robo, ... none \n", | |
"2 [] none \n", | |
"3 [nadie, vote, por, pri, por, tenemos, que, cor... none \n", | |
"4 [pri, esta, dando, patadas, hogado, puede, man... none " | |
] | |
}, | |
"execution_count": 207, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_df[0:5]" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"#### Al correr clasificar, sin ninguna categoría, basicamente nos arrojará la sugerencia de los tokens más mencionados,que se enlistan arriba" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Arranquemos la clasificación. Partamos de un dataframe sin categorías" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 385, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"comments_df_categorización = comments_df" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 386, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"comments_df_categorización[\"categoria\"] = \"none\"" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"La busqueda de palabras más mencionadas es el PRI, con subpalabras bastante negativas: El comentario 3 sigue esta norma, partamos de ese para taggear más posts anti-pri, por medio de solo verificar los tokens que tienen en común" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 387, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"['nadie', 'vote', 'por', 'pri', 'por', 'tenemos', 'que', 'correrlos', 'veracruz', 'esos', 'priistas']\n" | |
] | |
} | |
], | |
"source": [ | |
"anti_pri_post = comments_df_categorización.iloc[3][\"message_clean\"]\n", | |
"print(anti_pri_post)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 388, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"def is_antipri(tokens):\n", | |
" for anti_pri_word in anti_pri_post:\n", | |
" if anti_pri_word in tokens:\n", | |
" class_message = \"anti-pri\"\n", | |
" else:\n", | |
" class_message = \"none\"\n", | |
" return class_message" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 389, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"## Ahora categorizar\n", | |
"comments_df_categorización[\"categoria\"]=comments_df_categorización[\"message_clean\"].apply(is_antipri)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 390, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/html": [ | |
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n", | |
"<table border=\"1\" class=\"dataframe\">\n", | |
" <thead>\n", | |
" <tr style=\"text-align: right;\">\n", | |
" <th></th>\n", | |
" <th>created_time</th>\n", | |
" <th>from_id</th>\n", | |
" <th>from_name</th>\n", | |
" <th>id</th>\n", | |
" <th>message</th>\n", | |
" <th>message_clean</th>\n", | |
" <th>categoria</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>3</th>\n", | |
" <td>2016-04-19T22:30:10+0000</td>\n", | |
" <td>1169546603088411</td>\n", | |
" <td>Carlos F Vazquez</td>\n", | |
" <td>1052734731465949_1052782811461141</td>\n", | |
" <td>Nadie vote por el pri por tenemos que correrlo...</td>\n", | |
" <td>[nadie, vote, por, pri, por, tenemos, que, cor...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>85</th>\n", | |
" <td>2016-04-20T05:26:17+0000</td>\n", | |
" <td>10209112224939960</td>\n", | |
" <td>Huerta Bejar</td>\n", | |
" <td>1052734731465949_1052947714777984</td>\n", | |
" <td>Vamos, vamos, Yunes Linares, .....están desesp...</td>\n", | |
" <td>[vamos, vamos, yunes, linares, estan, desesper...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>123</th>\n", | |
" <td>2016-04-20T16:48:54+0000</td>\n", | |
" <td>1707815296141890</td>\n", | |
" <td>Liby Marini Manica</td>\n", | |
" <td>1052734731465949_1053245991414823</td>\n", | |
" <td>Ya parenle con esa herramienta sucia contra mi...</td>\n", | |
" <td>[parenle, con, esa, herramienta, sucia, contra...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>162</th>\n", | |
" <td>2016-04-20T19:39:57+0000</td>\n", | |
" <td>10206558105015263</td>\n", | |
" <td>Gustavo Jiménez</td>\n", | |
" <td>1052734731465949_1053334778072611</td>\n", | |
" <td>Si no hace todo como gobernador para encerrar ...</td>\n", | |
" <td>[hace, todo, como, gobernador, para, encerrar,...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>167</th>\n", | |
" <td>2016-04-20T20:10:51+0000</td>\n", | |
" <td>10207524219761808</td>\n", | |
" <td>Moisés Santiago</td>\n", | |
" <td>1052734731465949_1053354084737347</td>\n", | |
" <td>Arriba Miguel la historia de los priistas ya s...</td>\n", | |
" <td>[arriba, miguel, historia, los, priistas, escr...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>169</th>\n", | |
" <td>2016-04-20T20:16:39+0000</td>\n", | |
" <td>10206031848094912</td>\n", | |
" <td>Cartur FerPoch</td>\n", | |
" <td>1052734731465949_1053357538070335</td>\n", | |
" <td>Son unos sucios los priistas, empezando con Du...</td>\n", | |
" <td>[son, unos, sucios, los, priistas, empezando, ...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>232</th>\n", | |
" <td>2016-04-21T01:58:01+0000</td>\n", | |
" <td>10156828527775652</td>\n", | |
" <td>Elías Castillo Romero</td>\n", | |
" <td>1052734731465949_1053505471388875</td>\n", | |
" <td>Ni a morena le está funcionando aliarse con el...</td>\n", | |
" <td>[morena, esta, funcionando, aliarse, con, pri,...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>287</th>\n", | |
" <td>2016-04-21T18:27:16+0000</td>\n", | |
" <td>1048538801886247</td>\n", | |
" <td>Mar Elen Mendoza Diaz</td>\n", | |
" <td>1052734731465949_1053952194677536</td>\n", | |
" <td>Todos sabemos que Veracruz es azul.. Lo único ...</td>\n", | |
" <td>[todos, sabemos, que, veracruz, azul, unico, q...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>433</th>\n", | |
" <td>2016-04-23T21:17:10+0000</td>\n", | |
" <td>236653660029830</td>\n", | |
" <td>Rossi Canelita</td>\n", | |
" <td>1052734731465949_1164963606871874</td>\n", | |
" <td>Lloren mendigos priistas jejejejeje</td>\n", | |
" <td>[lloren, mendigos, priistas, jejejejeje]</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>452</th>\n", | |
" <td>2016-04-24T01:36:08+0000</td>\n", | |
" <td>1150043911706791</td>\n", | |
" <td>Laura Cordova</td>\n", | |
" <td>1052734731465949_1009610072420716</td>\n", | |
" <td>No me extraña que estén nerviosos esos priista...</td>\n", | |
" <td>[extraña, que, esten, nerviosos, esos, priista...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>464</th>\n", | |
" <td>2016-04-24T05:07:36+0000</td>\n", | |
" <td>1703943466526760</td>\n", | |
" <td>Henry Ramirez</td>\n", | |
" <td>1052734731465949_1165143550187213</td>\n", | |
" <td>Maldito. PRIISTA héctor. Mentiroso. Los. Priii...</td>\n", | |
" <td>[maldito, priista, hector, mentiroso, los, pri...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>499</th>\n", | |
" <td>2016-04-25T13:29:50+0000</td>\n", | |
" <td>1738621133018242</td>\n", | |
" <td>Luis Jose Dominguez Zantos</td>\n", | |
" <td>1052734731465949_1010425872339136</td>\n", | |
" <td>Todos en el estado conocemos a los priistas na...</td>\n", | |
" <td>[todos, estado, conocemos, los, priistas, nada...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>507</th>\n", | |
" <td>2016-04-25T23:55:35+0000</td>\n", | |
" <td>979389295489638</td>\n", | |
" <td>Urit Guillermo Romero</td>\n", | |
" <td>1052734731465949_1010770425638014</td>\n", | |
" <td>Disque yunes el bueno, bueno pero para robar...</td>\n", | |
" <td>[disque, yunes, bueno, bueno, pero, para, roba...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>517</th>\n", | |
" <td>2016-04-26T03:16:56+0000</td>\n", | |
" <td>1541115712857667</td>\n", | |
" <td>Teo FloMe</td>\n", | |
" <td>1052734731465949_1010863958961994</td>\n", | |
" <td>Televisa es un bandido k c vende al mejor post...</td>\n", | |
" <td>[televisa, bandido, vende, mejor, postor, pien...</td>\n", | |
" <td>anti-pri</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" created_time from_id from_name \\\n", | |
"3 2016-04-19T22:30:10+0000 1169546603088411 Carlos F Vazquez \n", | |
"85 2016-04-20T05:26:17+0000 10209112224939960 Huerta Bejar \n", | |
"123 2016-04-20T16:48:54+0000 1707815296141890 Liby Marini Manica \n", | |
"162 2016-04-20T19:39:57+0000 10206558105015263 Gustavo Jiménez \n", | |
"167 2016-04-20T20:10:51+0000 10207524219761808 Moisés Santiago \n", | |
"169 2016-04-20T20:16:39+0000 10206031848094912 Cartur FerPoch \n", | |
"232 2016-04-21T01:58:01+0000 10156828527775652 Elías Castillo Romero \n", | |
"287 2016-04-21T18:27:16+0000 1048538801886247 Mar Elen Mendoza Diaz \n", | |
"433 2016-04-23T21:17:10+0000 236653660029830 Rossi Canelita \n", | |
"452 2016-04-24T01:36:08+0000 1150043911706791 Laura Cordova \n", | |
"464 2016-04-24T05:07:36+0000 1703943466526760 Henry Ramirez \n", | |
"499 2016-04-25T13:29:50+0000 1738621133018242 Luis Jose Dominguez Zantos \n", | |
"507 2016-04-25T23:55:35+0000 979389295489638 Urit Guillermo Romero \n", | |
"517 2016-04-26T03:16:56+0000 1541115712857667 Teo FloMe \n", | |
"\n", | |
" id \\\n", | |
"3 1052734731465949_1052782811461141 \n", | |
"85 1052734731465949_1052947714777984 \n", | |
"123 1052734731465949_1053245991414823 \n", | |
"162 1052734731465949_1053334778072611 \n", | |
"167 1052734731465949_1053354084737347 \n", | |
"169 1052734731465949_1053357538070335 \n", | |
"232 1052734731465949_1053505471388875 \n", | |
"287 1052734731465949_1053952194677536 \n", | |
"433 1052734731465949_1164963606871874 \n", | |
"452 1052734731465949_1009610072420716 \n", | |
"464 1052734731465949_1165143550187213 \n", | |
"499 1052734731465949_1010425872339136 \n", | |
"507 1052734731465949_1010770425638014 \n", | |
"517 1052734731465949_1010863958961994 \n", | |
"\n", | |
" message \\\n", | |
"3 Nadie vote por el pri por tenemos que correrlo... \n", | |
"85 Vamos, vamos, Yunes Linares, .....están desesp... \n", | |
"123 Ya parenle con esa herramienta sucia contra mi... \n", | |
"162 Si no hace todo como gobernador para encerrar ... \n", | |
"167 Arriba Miguel la historia de los priistas ya s... \n", | |
"169 Son unos sucios los priistas, empezando con Du... \n", | |
"232 Ni a morena le está funcionando aliarse con el... \n", | |
"287 Todos sabemos que Veracruz es azul.. Lo único ... \n", | |
"433 Lloren mendigos priistas jejejejeje \n", | |
"452 No me extraña que estén nerviosos esos priista... \n", | |
"464 Maldito. PRIISTA héctor. Mentiroso. Los. Priii... \n", | |
"499 Todos en el estado conocemos a los priistas na... \n", | |
"507 Disque yunes el bueno, bueno pero para robar... \n", | |
"517 Televisa es un bandido k c vende al mejor post... \n", | |
"\n", | |
" message_clean categoria \n", | |
"3 [nadie, vote, por, pri, por, tenemos, que, cor... anti-pri \n", | |
"85 [vamos, vamos, yunes, linares, estan, desesper... anti-pri \n", | |
"123 [parenle, con, esa, herramienta, sucia, contra... anti-pri \n", | |
"162 [hace, todo, como, gobernador, para, encerrar,... anti-pri \n", | |
"167 [arriba, miguel, historia, los, priistas, escr... anti-pri \n", | |
"169 [son, unos, sucios, los, priistas, empezando, ... anti-pri \n", | |
"232 [morena, esta, funcionando, aliarse, con, pri,... anti-pri \n", | |
"287 [todos, sabemos, que, veracruz, azul, unico, q... anti-pri \n", | |
"433 [lloren, mendigos, priistas, jejejejeje] anti-pri \n", | |
"452 [extraña, que, esten, nerviosos, esos, priista... anti-pri \n", | |
"464 [maldito, priista, hector, mentiroso, los, pri... anti-pri \n", | |
"499 [todos, estado, conocemos, los, priistas, nada... anti-pri \n", | |
"507 [disque, yunes, bueno, bueno, pero, para, roba... anti-pri \n", | |
"517 [televisa, bandido, vende, mejor, postor, pien... anti-pri " | |
] | |
}, | |
"execution_count": 390, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_df_categorización[comments_df_categorización[\"categoria\"] == \"anti-pri\"]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 391, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array(['anti-pri', 'none'], dtype=object)" | |
] | |
}, | |
"execution_count": 391, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"import numpy as np\n", | |
"np.unique(comments_df_categorización[\"categoria\"])" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"### Se categorizaron (bastante buenos, pero afectados por el bias de los posts que se quedan abiertos) bien algunos posts. No se recomienda mantenerse con un solo post categorizado. " | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Pasamos a implementar bag of words. Para esto, encontremos una segunda categoría para empezar el proceso" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 392, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/html": [ | |
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n", | |
"<table border=\"1\" class=\"dataframe\">\n", | |
" <thead>\n", | |
" <tr style=\"text-align: right;\">\n", | |
" <th></th>\n", | |
" <th>created_time</th>\n", | |
" <th>from_id</th>\n", | |
" <th>from_name</th>\n", | |
" <th>id</th>\n", | |
" <th>message</th>\n", | |
" <th>message_clean</th>\n", | |
" <th>categoria</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>2016-04-19T22:10:23+0000</td>\n", | |
" <td>1129125517119186</td>\n", | |
" <td>Javier Lecter</td>\n", | |
" <td>1052734731465949_1052775478128541</td>\n", | |
" <td>igual que en Tamaulipas ya van para afuera por...</td>\n", | |
" <td>[igual, que, tamaulipas, van, para, afuera, po...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>2016-04-19T22:20:31+0000</td>\n", | |
" <td>563927170436016</td>\n", | |
" <td>Ivan Jist</td>\n", | |
" <td>1052734731465949_1052779208128168</td>\n", | |
" <td>Y el pri por robar todo el dinero a la Uv y ci...</td>\n", | |
" <td>[pri, por, robar, todo, dinero, cierto, robo, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>2016-04-19T22:27:06+0000</td>\n", | |
" <td>716106398532421</td>\n", | |
" <td>Pequeño Corazonsito Cruz</td>\n", | |
" <td>1052734731465949_1052781654794590</td>\n", | |
" <td>Yo</td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>2016-04-19T22:32:14+0000</td>\n", | |
" <td>232046980484475</td>\n", | |
" <td>David Camacho</td>\n", | |
" <td>1052734731465949_1052783438127745</td>\n", | |
" <td>El pri está dando patadas de hogado, ya no pue...</td>\n", | |
" <td>[pri, esta, dando, patadas, hogado, puede, man...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>5</th>\n", | |
" <td>2016-04-19T22:38:29+0000</td>\n", | |
" <td>1005519999541281</td>\n", | |
" <td>Raymundo Gomez</td>\n", | |
" <td>1052734731465949_1052785638127525</td>\n", | |
" <td>No pasa nada eso dice nuestro gobernador puñal...</td>\n", | |
" <td>[pasa, nada, eso, dice, nuestro, gobernador, p...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>6</th>\n", | |
" <td>2016-04-19T22:39:48+0000</td>\n", | |
" <td>1161542603879742</td>\n", | |
" <td>Carlos Lopez</td>\n", | |
" <td>1052734731465949_1052785974794158</td>\n", | |
" <td>Ya vio que la gente de estado está hasta la ma...</td>\n", | |
" <td>[vio, que, gente, estado, esta, hasta, madre, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>7</th>\n", | |
" <td>2016-04-19T22:51:22+0000</td>\n", | |
" <td>1008574712554591</td>\n", | |
" <td>Basi Poet Hernandez</td>\n", | |
" <td>1052734731465949_1052790111460411</td>\n", | |
" <td>NI UN VOTO PARA EL PRI. RATASSSSSSSS</td>\n", | |
" <td>[voto, para, pri, ratassssssss]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>8</th>\n", | |
" <td>2016-04-19T22:51:40+0000</td>\n", | |
" <td>10209072954923008</td>\n", | |
" <td>Trigos Estrellix</td>\n", | |
" <td>1052734731465949_1052790221460400</td>\n", | |
" <td>PAN*</td>\n", | |
" <td>[pan]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>9</th>\n", | |
" <td>2016-04-19T22:53:56+0000</td>\n", | |
" <td>640669849416464</td>\n", | |
" <td>Eduardo Alfonso Ruiz</td>\n", | |
" <td>1052734731465949_1052790738127015</td>\n", | |
" <td>POR HABER GOLPEADO A LOS VIEJOS PENSIONADOS\\nP...</td>\n", | |
" <td>[por, haber, golpeado, los, viejos, pensionado...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>10</th>\n", | |
" <td>2016-04-19T22:56:29+0000</td>\n", | |
" <td>1051815134886799</td>\n", | |
" <td>Jose Luis Martinez Lara</td>\n", | |
" <td>1052734731465949_1052791428126946</td>\n", | |
" <td>Fuera!!!</td>\n", | |
" <td>[fuera]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>11</th>\n", | |
" <td>2016-04-19T23:03:16+0000</td>\n", | |
" <td>10206410155160328</td>\n", | |
" <td>Rikrdo Lopz</td>\n", | |
" <td>1052734731465949_1052793558126733</td>\n", | |
" <td>El pri no debería ni siquiera estar en las enc...</td>\n", | |
" <td>[pri, deberia, siquiera, estar, las, encuestas...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>12</th>\n", | |
" <td>2016-04-19T23:04:13+0000</td>\n", | |
" <td>1150097811688100</td>\n", | |
" <td>Angel Vasquez Vera</td>\n", | |
" <td>1052734731465949_1052793991460023</td>\n", | |
" <td>Eso, ya se esperaba de la maquinaria roja. Per...</td>\n", | |
" <td>[eso, esperaba, maquinaria, roja, pero, aun, c...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>13</th>\n", | |
" <td>2016-04-19T23:04:26+0000</td>\n", | |
" <td>1020323774729225</td>\n", | |
" <td>Carmen Salazar Mora</td>\n", | |
" <td>1052734731465949_1052794061460016</td>\n", | |
" <td>Quien este durmiendo y que por una despensa qu...</td>\n", | |
" <td>[quien, este, durmiendo, que, por, una, despen...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>14</th>\n", | |
" <td>2016-04-19T23:06:58+0000</td>\n", | |
" <td>1710921779175951</td>\n", | |
" <td>Liliana Del Carmen García Zárate</td>\n", | |
" <td>1052734731465949_1052794981459924</td>\n", | |
" <td></td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>15</th>\n", | |
" <td>2016-04-19T23:08:22+0000</td>\n", | |
" <td>1619483091707011</td>\n", | |
" <td>Noe Juarez</td>\n", | |
" <td>1052734731465949_1052795288126560</td>\n", | |
" <td>Todos son coructos y el pri ocupa el primer lu...</td>\n", | |
" <td>[todos, son, coructos, pri, ocupa, primer, lug...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>16</th>\n", | |
" <td>2016-04-19T23:10:19+0000</td>\n", | |
" <td>10206247953030159</td>\n", | |
" <td>Elsi Hernandez Lopez</td>\n", | |
" <td>1052734731465949_1052796388126450</td>\n", | |
" <td></td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>17</th>\n", | |
" <td>2016-04-19T23:10:23+0000</td>\n", | |
" <td>10206247953030159</td>\n", | |
" <td>Elsi Hernandez Lopez</td>\n", | |
" <td>1052734731465949_1052796404793115</td>\n", | |
" <td></td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>18</th>\n", | |
" <td>2016-04-19T23:10:35+0000</td>\n", | |
" <td>10209410945889904</td>\n", | |
" <td>Gray Fox Die</td>\n", | |
" <td>1052734731465949_1052796481459774</td>\n", | |
" <td>Sigan votando por el pri que les da miserias a...</td>\n", | |
" <td>[sigan, votando, por, pri, que, les, miserias,...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>19</th>\n", | |
" <td>2016-04-19T23:12:39+0000</td>\n", | |
" <td>1059514784122092</td>\n", | |
" <td>Peter Infante Cruz</td>\n", | |
" <td>1052734731465949_1052797171459705</td>\n", | |
" <td>Yo creo que el sr Miguel ángel va con todo y m...</td>\n", | |
" <td>[creo, que, miguel, angel, con, todo, conformo...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>20</th>\n", | |
" <td>2016-04-19T23:14:48+0000</td>\n", | |
" <td>224509774594310</td>\n", | |
" <td>Erik Cruz</td>\n", | |
" <td>1052734731465949_1052797721459650</td>\n", | |
" <td>Siempre es lo mismo con el pri carvallo donde ...</td>\n", | |
" <td>[siempre, mismo, con, pri, carvallo, donde, an...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>21</th>\n", | |
" <td>2016-04-19T23:20:18+0000</td>\n", | |
" <td>214934918887206</td>\n", | |
" <td>Axel Gabino San Juan Bautizta</td>\n", | |
" <td>1052734731465949_1052799821459440</td>\n", | |
" <td>Q nos engañen otra ves una monos y hagamos la ...</td>\n", | |
" <td>[nos, engañen, otra, ves, una, monos, hagamos,...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>22</th>\n", | |
" <td>2016-04-19T23:21:21+0000</td>\n", | |
" <td>214934918887206</td>\n", | |
" <td>Axel Gabino San Juan Bautizta</td>\n", | |
" <td>1052734731465949_1052800151459407</td>\n", | |
" <td></td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>23</th>\n", | |
" <td>2016-04-19T23:22:52+0000</td>\n", | |
" <td>1171739079525238</td>\n", | |
" <td>Omar Suriano Calles</td>\n", | |
" <td>1052734731465949_1052800621459360</td>\n", | |
" <td>Es increíble k el pri este en segundo lugar en...</td>\n", | |
" <td>[increible, pri, este, segundo, lugar, encuesta]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>24</th>\n", | |
" <td>2016-04-19T23:24:27+0000</td>\n", | |
" <td>1551872245115511</td>\n", | |
" <td>Concepcion Zamora</td>\n", | |
" <td>1052734731465949_1052800978125991</td>\n", | |
" <td>Ni un voto a el priiu</td>\n", | |
" <td>[voto, priiu]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>25</th>\n", | |
" <td>2016-04-19T23:28:01+0000</td>\n", | |
" <td>1792764180944470</td>\n", | |
" <td>Jose Luis Serrano Lagunes</td>\n", | |
" <td>1052734731465949_1052802578125831</td>\n", | |
" <td>A chingar asu madre el pri del estado no mas pri</td>\n", | |
" <td>[chingar, asu, madre, pri, del, estado, mas, pri]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>26</th>\n", | |
" <td>2016-04-19T23:30:16+0000</td>\n", | |
" <td>1029174180509737</td>\n", | |
" <td>Gonzalo Kaphwan</td>\n", | |
" <td>1052734731465949_1052803254792430</td>\n", | |
" <td>Jacobo Ceron ,</td>\n", | |
" <td>[jacobo, ceron]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>27</th>\n", | |
" <td>2016-04-19T23:30:42+0000</td>\n", | |
" <td>1754337714825307</td>\n", | |
" <td>Roger Rivas</td>\n", | |
" <td>1052734731465949_1052803408125748</td>\n", | |
" <td>FUERA FUERA EL PRI..JAJAJAJAJAJJAJA</td>\n", | |
" <td>[fuera, fuera, pri, jajajajajajjaja]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>28</th>\n", | |
" <td>2016-04-19T23:34:52+0000</td>\n", | |
" <td>10208954940047997</td>\n", | |
" <td>Marck Anthony</td>\n", | |
" <td>1052734731465949_1052804934792262</td>\n", | |
" <td>Y 34% se me hace demasiado Jajajajjaja al Pri ...</td>\n", | |
" <td>[34%, hace, demasiado, jajajajjaja, pri, hay, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>29</th>\n", | |
" <td>2016-04-19T23:37:40+0000</td>\n", | |
" <td>224744787882164</td>\n", | |
" <td>Alfredo Alvarado</td>\n", | |
" <td>1052734731465949_1052805834792172</td>\n", | |
" <td>Hay que darle el voto a yunes Linares,para sac...</td>\n", | |
" <td>[hay, que, darle, voto, yunes, linares, para, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>30</th>\n", | |
" <td>2016-04-19T23:38:42+0000</td>\n", | |
" <td>1717243161856281</td>\n", | |
" <td>Valentina Posadas</td>\n", | |
" <td>1052734731465949_1052806238125465</td>\n", | |
" <td></td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>...</th>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>531</th>\n", | |
" <td>2016-04-27T00:10:38+0000</td>\n", | |
" <td>967327370055232</td>\n", | |
" <td>Leonardo Rojas H</td>\n", | |
" <td>1052734731465949_1167015786666656</td>\n", | |
" <td>Chismosos!! Como inventan!!.</td>\n", | |
" <td>[chismosos, como, inventan]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>532</th>\n", | |
" <td>2016-04-27T00:27:49+0000</td>\n", | |
" <td>233495237006715</td>\n", | |
" <td>Israel Bautista</td>\n", | |
" <td>1052734731465949_1011402615574795</td>\n", | |
" <td>Arriba el peje entre ellos se tiran flores par...</td>\n", | |
" <td>[arriba, peje, entre, ellos, tiran, flores, pa...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>533</th>\n", | |
" <td>2016-04-27T00:29:47+0000</td>\n", | |
" <td>232703960433073</td>\n", | |
" <td>Lupi Rubio</td>\n", | |
" <td>1052734731465949_1011403168908073</td>\n", | |
" <td>Saludes. Disfruten paseo las s. Quiero</td>\n", | |
" <td>[saludes, disfruten, paseo, las, quiero]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>534</th>\n", | |
" <td>2016-04-27T00:59:52+0000</td>\n", | |
" <td>1706548062935044</td>\n", | |
" <td>Margarito Ramirez Mendoza</td>\n", | |
" <td>1052734731465949_1011412155573841</td>\n", | |
" <td>No se dejen engañar son patadas de ahogado que...</td>\n", | |
" <td>[dejen, engañar, son, patadas, ahogado, que, e...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>535</th>\n", | |
" <td>2016-04-27T01:35:16+0000</td>\n", | |
" <td>1750965218482905</td>\n", | |
" <td>Manuel Martinez Garcia</td>\n", | |
" <td>1052734731465949_1011422658906124</td>\n", | |
" <td>C corruptohico niñote</td>\n", | |
" <td>[corruptohico, niñote]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>536</th>\n", | |
" <td>2016-04-27T01:45:42+0000</td>\n", | |
" <td>586079581556228</td>\n", | |
" <td>Fork Bautista</td>\n", | |
" <td>1052734731465949_1167052893329612</td>\n", | |
" <td>son puras mamadas la polita ya k le toke al pa...</td>\n", | |
" <td>[son, puras, mamadas, polita, toke, pan, tambi...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>537</th>\n", | |
" <td>2016-04-27T01:48:31+0000</td>\n", | |
" <td>641439986021125</td>\n", | |
" <td>Irene Hernandez</td>\n", | |
" <td>1052734731465949_1167053903329511</td>\n", | |
" <td>sinvergüenzas no k moy limpios. Sus mapaches. ...</td>\n", | |
" <td>[sinvergüenzas, moy, limpios, sus, mapaches, l...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>538</th>\n", | |
" <td>2016-04-27T01:56:53+0000</td>\n", | |
" <td>1585790621733381</td>\n", | |
" <td>Raul Malaga Cruz</td>\n", | |
" <td>1052734731465949_1011429478905442</td>\n", | |
" <td>El pri no gana almenos qué juege sucio como ya...</td>\n", | |
" <td>[pri, gana, almenos, que, juege, sucio, como, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>539</th>\n", | |
" <td>2016-04-27T02:07:33+0000</td>\n", | |
" <td>804647173001125</td>\n", | |
" <td>Amelia Cuellar</td>\n", | |
" <td>1052734731465949_1011434012238322</td>\n", | |
" <td>Gobierno corrupto junto con todos los que se a...</td>\n", | |
" <td>[gobierno, corrupto, junto, con, todos, los, q...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>540</th>\n", | |
" <td>2016-04-27T02:10:56+0000</td>\n", | |
" <td>1682535325342955</td>\n", | |
" <td>Hilda Rojas</td>\n", | |
" <td>1052734731465949_1167062729995295</td>\n", | |
" <td>Ni a cual ir todos lis partidos por política s...</td>\n", | |
" <td>[cual, todos, lis, partidos, por, politica, so...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>541</th>\n", | |
" <td>2016-04-27T02:24:09+0000</td>\n", | |
" <td>1300648329949876</td>\n", | |
" <td>Javier Alva Rex</td>\n", | |
" <td>1052734731465949_1011439922237731</td>\n", | |
" <td>Yunes Linares ganará aún con la lluvia de lodo.</td>\n", | |
" <td>[yunes, linares, ganara, aun, con, lluvia, lodo]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>542</th>\n", | |
" <td>2016-04-27T04:10:03+0000</td>\n", | |
" <td>1331456030202694</td>\n", | |
" <td>Elisa Rosendo Castillo</td>\n", | |
" <td>1052734731465949_1167105313324370</td>\n", | |
" <td>#están desesperados y somos 7millones de votos...</td>\n", | |
" <td>[estan, desesperados, somos, 7millones, votos,...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>543</th>\n", | |
" <td>2016-04-27T04:47:12+0000</td>\n", | |
" <td>525312784322250</td>\n", | |
" <td>Hortencia Galindo</td>\n", | |
" <td>1052734731465949_1167120353322866</td>\n", | |
" <td>Y la marrana sigue comiendo !!!!!</td>\n", | |
" <td>[marrana, sigue, comiendo]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>544</th>\n", | |
" <td>2016-04-27T08:21:44+0000</td>\n", | |
" <td>994158437337758</td>\n", | |
" <td>Alfred Garcia</td>\n", | |
" <td>1052734731465949_1011583748890015</td>\n", | |
" <td>eso ya no es novedad</td>\n", | |
" <td>[eso, novedad]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>545</th>\n", | |
" <td>2016-04-27T22:07:11+0000</td>\n", | |
" <td>1792976970923203</td>\n", | |
" <td>Ana Gabriela Estrada</td>\n", | |
" <td>1052734731465949_1011956045519452</td>\n", | |
" <td>Todos los del pri son una bola de rrateros es ...</td>\n", | |
" <td>[todos, los, del, pri, son, una, bola, rratero...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>546</th>\n", | |
" <td>2016-04-27T23:54:24+0000</td>\n", | |
" <td>241101932917101</td>\n", | |
" <td>Ale Zamudio Cruz</td>\n", | |
" <td>1052734731465949_1167634389938129</td>\n", | |
" <td>y pinche rata del Duarte muy tranquilo contod...</td>\n", | |
" <td>[pinche, rata, del, duarte, muy, tranquilo, co...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>547</th>\n", | |
" <td>2016-04-27T23:55:22+0000</td>\n", | |
" <td>241101932917101</td>\n", | |
" <td>Ale Zamudio Cruz</td>\n", | |
" <td>1052734731465949_1167634623271439</td>\n", | |
" <td>con su risa burlona para que vea</td>\n", | |
" <td>[con, risa, burlona, para, que, vea]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>548</th>\n", | |
" <td>2016-04-28T00:05:19+0000</td>\n", | |
" <td>272612976407755</td>\n", | |
" <td>Mario Moreno</td>\n", | |
" <td>1052734731465949_1167637853271116</td>\n", | |
" <td>Ahora es cuando hay que darle con todo al PRI ...</td>\n", | |
" <td>[ahora, cuando, hay, que, darle, con, todo, pr...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>549</th>\n", | |
" <td>2016-04-28T01:58:18+0000</td>\n", | |
" <td>240210256369371</td>\n", | |
" <td>Arturo Estudillo</td>\n", | |
" <td>1052734731465949_1167695349932033</td>\n", | |
" <td>Es una madriguera de ratas andan diario aca en...</td>\n", | |
" <td>[una, madriguera, ratas, andan, diario, aca, f...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>550</th>\n", | |
" <td>2016-04-28T02:29:23+0000</td>\n", | |
" <td>1760048690881980</td>\n", | |
" <td>Rafael Aguilar García</td>\n", | |
" <td>1052734731465949_1167706059930962</td>\n", | |
" <td>Ya se lo cargo el payaso. Gracias a Fidel y La...</td>\n", | |
" <td>[cargo, payaso, gracias, fidel, gorda, duarte]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>551</th>\n", | |
" <td>2016-04-28T03:27:53+0000</td>\n", | |
" <td>1619054318419436</td>\n", | |
" <td>Hernandez Vallejo</td>\n", | |
" <td>1052734731465949_1167730699928498</td>\n", | |
" <td>Solo dios puede ayudarnos</td>\n", | |
" <td>[solo, dios, puede, ayudarnos]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>552</th>\n", | |
" <td>2016-04-28T03:58:19+0000</td>\n", | |
" <td>1604808463179358</td>\n", | |
" <td>Carlos Daniel Espinoza</td>\n", | |
" <td>1052734731465949_1012102398838150</td>\n", | |
" <td>Por esos hijos de sptm este estado esta asi ya...</td>\n", | |
" <td>[por, esos, hijos, sptm, este, estado, esta, a...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>553</th>\n", | |
" <td>2016-04-28T03:59:18+0000</td>\n", | |
" <td>1117966451575523</td>\n", | |
" <td>Landy Castillo Sierra</td>\n", | |
" <td>1052734731465949_1167743733260528</td>\n", | |
" <td>LLa desesperada guerra sucia del PRI contra e...</td>\n", | |
" <td>[lla, desesperada, guerra, sucia, del, pri, co...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>554</th>\n", | |
" <td>2016-04-28T13:21:45+0000</td>\n", | |
" <td>251456561874663</td>\n", | |
" <td>Joseph Tauroasesino</td>\n", | |
" <td>1052734731465949_1167964776571757</td>\n", | |
" <td>Ese puto del gobernador que pague lo que debe ...</td>\n", | |
" <td>[ese, puto, del, gobernador, que, pague, que, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>555</th>\n", | |
" <td>2016-04-28T17:40:11+0000</td>\n", | |
" <td>572881672892104</td>\n", | |
" <td>Ceci Sanchez</td>\n", | |
" <td>1052734731465949_1168072516560983</td>\n", | |
" <td>Traga pinche gordo..mientras al estado lo unde...</td>\n", | |
" <td>[traga, pinche, gordo, mientras, estado, undes...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>556</th>\n", | |
" <td>2016-04-28T19:07:07+0000</td>\n", | |
" <td>1674866359441422</td>\n", | |
" <td>Isabel Alfaro</td>\n", | |
" <td>1052734731465949_1012459905469066</td>\n", | |
" <td>Muy cierto</td>\n", | |
" <td>[muy, cierto]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>557</th>\n", | |
" <td>2016-04-28T20:11:55+0000</td>\n", | |
" <td>854116821361102</td>\n", | |
" <td>Ricardo Hernandez</td>\n", | |
" <td>1052734731465949_1168143303220571</td>\n", | |
" <td>Pobres pendejos quieren seguir ordeñando la vaca.</td>\n", | |
" <td>[pobres, pendejos, quieren, seguir, ordeñando,...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>558</th>\n", | |
" <td>2016-04-28T21:43:10+0000</td>\n", | |
" <td>599039010260924</td>\n", | |
" <td>Samm Sourdon</td>\n", | |
" <td>1052734731465949_1012526615462395</td>\n", | |
" <td>a huevo no se imaginan estar en la cárcel y es...</td>\n", | |
" <td>[huevo, imaginan, estar, carcel, estar, comien...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>559</th>\n", | |
" <td>2016-04-28T22:18:51+0000</td>\n", | |
" <td>1056358417752313</td>\n", | |
" <td>Macario Lopez</td>\n", | |
" <td>1052734731465949_1168198759881692</td>\n", | |
" <td>Q gane el q el pueblo elija sin corrupción sin...</td>\n", | |
" <td>[gane, pueblo, elija, sin, corrupcion, sin, pl...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>560</th>\n", | |
" <td>2016-04-28T23:45:12+0000</td>\n", | |
" <td>207245306334552</td>\n", | |
" <td>Joel Quevedo</td>\n", | |
" <td>1052734731465949_1012575425457514</td>\n", | |
" <td>ay se esta tragando nuetros ipuestos concomida...</td>\n", | |
" <td>[esta, tragando, nuetros, ipuestos, concomidas...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"<p>547 rows × 7 columns</p>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" created_time from_id \\\n", | |
"0 2016-04-19T22:10:23+0000 1129125517119186 \n", | |
"1 2016-04-19T22:20:31+0000 563927170436016 \n", | |
"2 2016-04-19T22:27:06+0000 716106398532421 \n", | |
"4 2016-04-19T22:32:14+0000 232046980484475 \n", | |
"5 2016-04-19T22:38:29+0000 1005519999541281 \n", | |
"6 2016-04-19T22:39:48+0000 1161542603879742 \n", | |
"7 2016-04-19T22:51:22+0000 1008574712554591 \n", | |
"8 2016-04-19T22:51:40+0000 10209072954923008 \n", | |
"9 2016-04-19T22:53:56+0000 640669849416464 \n", | |
"10 2016-04-19T22:56:29+0000 1051815134886799 \n", | |
"11 2016-04-19T23:03:16+0000 10206410155160328 \n", | |
"12 2016-04-19T23:04:13+0000 1150097811688100 \n", | |
"13 2016-04-19T23:04:26+0000 1020323774729225 \n", | |
"14 2016-04-19T23:06:58+0000 1710921779175951 \n", | |
"15 2016-04-19T23:08:22+0000 1619483091707011 \n", | |
"16 2016-04-19T23:10:19+0000 10206247953030159 \n", | |
"17 2016-04-19T23:10:23+0000 10206247953030159 \n", | |
"18 2016-04-19T23:10:35+0000 10209410945889904 \n", | |
"19 2016-04-19T23:12:39+0000 1059514784122092 \n", | |
"20 2016-04-19T23:14:48+0000 224509774594310 \n", | |
"21 2016-04-19T23:20:18+0000 214934918887206 \n", | |
"22 2016-04-19T23:21:21+0000 214934918887206 \n", | |
"23 2016-04-19T23:22:52+0000 1171739079525238 \n", | |
"24 2016-04-19T23:24:27+0000 1551872245115511 \n", | |
"25 2016-04-19T23:28:01+0000 1792764180944470 \n", | |
"26 2016-04-19T23:30:16+0000 1029174180509737 \n", | |
"27 2016-04-19T23:30:42+0000 1754337714825307 \n", | |
"28 2016-04-19T23:34:52+0000 10208954940047997 \n", | |
"29 2016-04-19T23:37:40+0000 224744787882164 \n", | |
"30 2016-04-19T23:38:42+0000 1717243161856281 \n", | |
".. ... ... \n", | |
"531 2016-04-27T00:10:38+0000 967327370055232 \n", | |
"532 2016-04-27T00:27:49+0000 233495237006715 \n", | |
"533 2016-04-27T00:29:47+0000 232703960433073 \n", | |
"534 2016-04-27T00:59:52+0000 1706548062935044 \n", | |
"535 2016-04-27T01:35:16+0000 1750965218482905 \n", | |
"536 2016-04-27T01:45:42+0000 586079581556228 \n", | |
"537 2016-04-27T01:48:31+0000 641439986021125 \n", | |
"538 2016-04-27T01:56:53+0000 1585790621733381 \n", | |
"539 2016-04-27T02:07:33+0000 804647173001125 \n", | |
"540 2016-04-27T02:10:56+0000 1682535325342955 \n", | |
"541 2016-04-27T02:24:09+0000 1300648329949876 \n", | |
"542 2016-04-27T04:10:03+0000 1331456030202694 \n", | |
"543 2016-04-27T04:47:12+0000 525312784322250 \n", | |
"544 2016-04-27T08:21:44+0000 994158437337758 \n", | |
"545 2016-04-27T22:07:11+0000 1792976970923203 \n", | |
"546 2016-04-27T23:54:24+0000 241101932917101 \n", | |
"547 2016-04-27T23:55:22+0000 241101932917101 \n", | |
"548 2016-04-28T00:05:19+0000 272612976407755 \n", | |
"549 2016-04-28T01:58:18+0000 240210256369371 \n", | |
"550 2016-04-28T02:29:23+0000 1760048690881980 \n", | |
"551 2016-04-28T03:27:53+0000 1619054318419436 \n", | |
"552 2016-04-28T03:58:19+0000 1604808463179358 \n", | |
"553 2016-04-28T03:59:18+0000 1117966451575523 \n", | |
"554 2016-04-28T13:21:45+0000 251456561874663 \n", | |
"555 2016-04-28T17:40:11+0000 572881672892104 \n", | |
"556 2016-04-28T19:07:07+0000 1674866359441422 \n", | |
"557 2016-04-28T20:11:55+0000 854116821361102 \n", | |
"558 2016-04-28T21:43:10+0000 599039010260924 \n", | |
"559 2016-04-28T22:18:51+0000 1056358417752313 \n", | |
"560 2016-04-28T23:45:12+0000 207245306334552 \n", | |
"\n", | |
" from_name id \\\n", | |
"0 Javier Lecter 1052734731465949_1052775478128541 \n", | |
"1 Ivan Jist 1052734731465949_1052779208128168 \n", | |
"2 Pequeño Corazonsito Cruz 1052734731465949_1052781654794590 \n", | |
"4 David Camacho 1052734731465949_1052783438127745 \n", | |
"5 Raymundo Gomez 1052734731465949_1052785638127525 \n", | |
"6 Carlos Lopez 1052734731465949_1052785974794158 \n", | |
"7 Basi Poet Hernandez 1052734731465949_1052790111460411 \n", | |
"8 Trigos Estrellix 1052734731465949_1052790221460400 \n", | |
"9 Eduardo Alfonso Ruiz 1052734731465949_1052790738127015 \n", | |
"10 Jose Luis Martinez Lara 1052734731465949_1052791428126946 \n", | |
"11 Rikrdo Lopz 1052734731465949_1052793558126733 \n", | |
"12 Angel Vasquez Vera 1052734731465949_1052793991460023 \n", | |
"13 Carmen Salazar Mora 1052734731465949_1052794061460016 \n", | |
"14 Liliana Del Carmen García Zárate 1052734731465949_1052794981459924 \n", | |
"15 Noe Juarez 1052734731465949_1052795288126560 \n", | |
"16 Elsi Hernandez Lopez 1052734731465949_1052796388126450 \n", | |
"17 Elsi Hernandez Lopez 1052734731465949_1052796404793115 \n", | |
"18 Gray Fox Die 1052734731465949_1052796481459774 \n", | |
"19 Peter Infante Cruz 1052734731465949_1052797171459705 \n", | |
"20 Erik Cruz 1052734731465949_1052797721459650 \n", | |
"21 Axel Gabino San Juan Bautizta 1052734731465949_1052799821459440 \n", | |
"22 Axel Gabino San Juan Bautizta 1052734731465949_1052800151459407 \n", | |
"23 Omar Suriano Calles 1052734731465949_1052800621459360 \n", | |
"24 Concepcion Zamora 1052734731465949_1052800978125991 \n", | |
"25 Jose Luis Serrano Lagunes 1052734731465949_1052802578125831 \n", | |
"26 Gonzalo Kaphwan 1052734731465949_1052803254792430 \n", | |
"27 Roger Rivas 1052734731465949_1052803408125748 \n", | |
"28 Marck Anthony 1052734731465949_1052804934792262 \n", | |
"29 Alfredo Alvarado 1052734731465949_1052805834792172 \n", | |
"30 Valentina Posadas 1052734731465949_1052806238125465 \n", | |
".. ... ... \n", | |
"531 Leonardo Rojas H 1052734731465949_1167015786666656 \n", | |
"532 Israel Bautista 1052734731465949_1011402615574795 \n", | |
"533 Lupi Rubio 1052734731465949_1011403168908073 \n", | |
"534 Margarito Ramirez Mendoza 1052734731465949_1011412155573841 \n", | |
"535 Manuel Martinez Garcia 1052734731465949_1011422658906124 \n", | |
"536 Fork Bautista 1052734731465949_1167052893329612 \n", | |
"537 Irene Hernandez 1052734731465949_1167053903329511 \n", | |
"538 Raul Malaga Cruz 1052734731465949_1011429478905442 \n", | |
"539 Amelia Cuellar 1052734731465949_1011434012238322 \n", | |
"540 Hilda Rojas 1052734731465949_1167062729995295 \n", | |
"541 Javier Alva Rex 1052734731465949_1011439922237731 \n", | |
"542 Elisa Rosendo Castillo 1052734731465949_1167105313324370 \n", | |
"543 Hortencia Galindo 1052734731465949_1167120353322866 \n", | |
"544 Alfred Garcia 1052734731465949_1011583748890015 \n", | |
"545 Ana Gabriela Estrada 1052734731465949_1011956045519452 \n", | |
"546 Ale Zamudio Cruz 1052734731465949_1167634389938129 \n", | |
"547 Ale Zamudio Cruz 1052734731465949_1167634623271439 \n", | |
"548 Mario Moreno 1052734731465949_1167637853271116 \n", | |
"549 Arturo Estudillo 1052734731465949_1167695349932033 \n", | |
"550 Rafael Aguilar García 1052734731465949_1167706059930962 \n", | |
"551 Hernandez Vallejo 1052734731465949_1167730699928498 \n", | |
"552 Carlos Daniel Espinoza 1052734731465949_1012102398838150 \n", | |
"553 Landy Castillo Sierra 1052734731465949_1167743733260528 \n", | |
"554 Joseph Tauroasesino 1052734731465949_1167964776571757 \n", | |
"555 Ceci Sanchez 1052734731465949_1168072516560983 \n", | |
"556 Isabel Alfaro 1052734731465949_1012459905469066 \n", | |
"557 Ricardo Hernandez 1052734731465949_1168143303220571 \n", | |
"558 Samm Sourdon 1052734731465949_1012526615462395 \n", | |
"559 Macario Lopez 1052734731465949_1168198759881692 \n", | |
"560 Joel Quevedo 1052734731465949_1012575425457514 \n", | |
"\n", | |
" message \\\n", | |
"0 igual que en Tamaulipas ya van para afuera por... \n", | |
"1 Y el pri por robar todo el dinero a la Uv y ci... \n", | |
"2 Yo \n", | |
"4 El pri está dando patadas de hogado, ya no pue... \n", | |
"5 No pasa nada eso dice nuestro gobernador puñal... \n", | |
"6 Ya vio que la gente de estado está hasta la ma... \n", | |
"7 NI UN VOTO PARA EL PRI. RATASSSSSSSS \n", | |
"8 PAN* \n", | |
"9 POR HABER GOLPEADO A LOS VIEJOS PENSIONADOS\\nP... \n", | |
"10 Fuera!!! \n", | |
"11 El pri no debería ni siquiera estar en las enc... \n", | |
"12 Eso, ya se esperaba de la maquinaria roja. Per... \n", | |
"13 Quien este durmiendo y que por una despensa qu... \n", | |
"14 \n", | |
"15 Todos son coructos y el pri ocupa el primer lu... \n", | |
"16 \n", | |
"17 \n", | |
"18 Sigan votando por el pri que les da miserias a... \n", | |
"19 Yo creo que el sr Miguel ángel va con todo y m... \n", | |
"20 Siempre es lo mismo con el pri carvallo donde ... \n", | |
"21 Q nos engañen otra ves una monos y hagamos la ... \n", | |
"22 \n", | |
"23 Es increíble k el pri este en segundo lugar en... \n", | |
"24 Ni un voto a el priiu \n", | |
"25 A chingar asu madre el pri del estado no mas pri \n", | |
"26 Jacobo Ceron , \n", | |
"27 FUERA FUERA EL PRI..JAJAJAJAJAJJAJA \n", | |
"28 Y 34% se me hace demasiado Jajajajjaja al Pri ... \n", | |
"29 Hay que darle el voto a yunes Linares,para sac... \n", | |
"30 \n", | |
".. ... \n", | |
"531 Chismosos!! Como inventan!!. \n", | |
"532 Arriba el peje entre ellos se tiran flores par... \n", | |
"533 Saludes. Disfruten paseo las s. Quiero \n", | |
"534 No se dejen engañar son patadas de ahogado que... \n", | |
"535 C corruptohico niñote \n", | |
"536 son puras mamadas la polita ya k le toke al pa... \n", | |
"537 sinvergüenzas no k moy limpios. Sus mapaches. ... \n", | |
"538 El pri no gana almenos qué juege sucio como ya... \n", | |
"539 Gobierno corrupto junto con todos los que se a... \n", | |
"540 Ni a cual ir todos lis partidos por política s... \n", | |
"541 Yunes Linares ganará aún con la lluvia de lodo. \n", | |
"542 #están desesperados y somos 7millones de votos... \n", | |
"543 Y la marrana sigue comiendo !!!!! \n", | |
"544 eso ya no es novedad \n", | |
"545 Todos los del pri son una bola de rrateros es ... \n", | |
"546 y pinche rata del Duarte muy tranquilo contod... \n", | |
"547 con su risa burlona para que vea \n", | |
"548 Ahora es cuando hay que darle con todo al PRI ... \n", | |
"549 Es una madriguera de ratas andan diario aca en... \n", | |
"550 Ya se lo cargo el payaso. Gracias a Fidel y La... \n", | |
"551 Solo dios puede ayudarnos \n", | |
"552 Por esos hijos de sptm este estado esta asi ya... \n", | |
"553 LLa desesperada guerra sucia del PRI contra e... \n", | |
"554 Ese puto del gobernador que pague lo que debe ... \n", | |
"555 Traga pinche gordo..mientras al estado lo unde... \n", | |
"556 Muy cierto \n", | |
"557 Pobres pendejos quieren seguir ordeñando la vaca. \n", | |
"558 a huevo no se imaginan estar en la cárcel y es... \n", | |
"559 Q gane el q el pueblo elija sin corrupción sin... \n", | |
"560 ay se esta tragando nuetros ipuestos concomida... \n", | |
"\n", | |
" message_clean categoria \n", | |
"0 [igual, que, tamaulipas, van, para, afuera, po... none \n", | |
"1 [pri, por, robar, todo, dinero, cierto, robo, ... none \n", | |
"2 [] none \n", | |
"4 [pri, esta, dando, patadas, hogado, puede, man... none \n", | |
"5 [pasa, nada, eso, dice, nuestro, gobernador, p... none \n", | |
"6 [vio, que, gente, estado, esta, hasta, madre, ... none \n", | |
"7 [voto, para, pri, ratassssssss] none \n", | |
"8 [pan] none \n", | |
"9 [por, haber, golpeado, los, viejos, pensionado... none \n", | |
"10 [fuera] none \n", | |
"11 [pri, deberia, siquiera, estar, las, encuestas... none \n", | |
"12 [eso, esperaba, maquinaria, roja, pero, aun, c... none \n", | |
"13 [quien, este, durmiendo, que, por, una, despen... none \n", | |
"14 [] none \n", | |
"15 [todos, son, coructos, pri, ocupa, primer, lug... none \n", | |
"16 [] none \n", | |
"17 [] none \n", | |
"18 [sigan, votando, por, pri, que, les, miserias,... none \n", | |
"19 [creo, que, miguel, angel, con, todo, conformo... none \n", | |
"20 [siempre, mismo, con, pri, carvallo, donde, an... none \n", | |
"21 [nos, engañen, otra, ves, una, monos, hagamos,... none \n", | |
"22 [] none \n", | |
"23 [increible, pri, este, segundo, lugar, encuesta] none \n", | |
"24 [voto, priiu] none \n", | |
"25 [chingar, asu, madre, pri, del, estado, mas, pri] none \n", | |
"26 [jacobo, ceron] none \n", | |
"27 [fuera, fuera, pri, jajajajajajjaja] none \n", | |
"28 [34%, hace, demasiado, jajajajjaja, pri, hay, ... none \n", | |
"29 [hay, que, darle, voto, yunes, linares, para, ... none \n", | |
"30 [] none \n", | |
".. ... ... \n", | |
"531 [chismosos, como, inventan] none \n", | |
"532 [arriba, peje, entre, ellos, tiran, flores, pa... none \n", | |
"533 [saludes, disfruten, paseo, las, quiero] none \n", | |
"534 [dejen, engañar, son, patadas, ahogado, que, e... none \n", | |
"535 [corruptohico, niñote] none \n", | |
"536 [son, puras, mamadas, polita, toke, pan, tambi... none \n", | |
"537 [sinvergüenzas, moy, limpios, sus, mapaches, l... none \n", | |
"538 [pri, gana, almenos, que, juege, sucio, como, ... none \n", | |
"539 [gobierno, corrupto, junto, con, todos, los, q... none \n", | |
"540 [cual, todos, lis, partidos, por, politica, so... none \n", | |
"541 [yunes, linares, ganara, aun, con, lluvia, lodo] none \n", | |
"542 [estan, desesperados, somos, 7millones, votos,... none \n", | |
"543 [marrana, sigue, comiendo] none \n", | |
"544 [eso, novedad] none \n", | |
"545 [todos, los, del, pri, son, una, bola, rratero... none \n", | |
"546 [pinche, rata, del, duarte, muy, tranquilo, co... none \n", | |
"547 [con, risa, burlona, para, que, vea] none \n", | |
"548 [ahora, cuando, hay, que, darle, con, todo, pr... none \n", | |
"549 [una, madriguera, ratas, andan, diario, aca, f... none \n", | |
"550 [cargo, payaso, gracias, fidel, gorda, duarte] none \n", | |
"551 [solo, dios, puede, ayudarnos] none \n", | |
"552 [por, esos, hijos, sptm, este, estado, esta, a... none \n", | |
"553 [lla, desesperada, guerra, sucia, del, pri, co... none \n", | |
"554 [ese, puto, del, gobernador, que, pague, que, ... none \n", | |
"555 [traga, pinche, gordo, mientras, estado, undes... none \n", | |
"556 [muy, cierto] none \n", | |
"557 [pobres, pendejos, quieren, seguir, ordeñando,... none \n", | |
"558 [huevo, imaginan, estar, carcel, estar, comien... none \n", | |
"559 [gane, pueblo, elija, sin, corrupcion, sin, pl... none \n", | |
"560 [esta, tragando, nuetros, ipuestos, concomidas... none \n", | |
"\n", | |
"[547 rows x 7 columns]" | |
] | |
}, | |
"execution_count": 392, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_df_categorización[comments_df_categorización[\"categoria\"] == \"none\"]" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Otra palabra que llama la atención, es morena. Encontremos un post que lo trate" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 393, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"created_time 2016-04-19T22:53:56+0000\n", | |
"from_id 640669849416464\n", | |
"from_name Eduardo Alfonso Ruiz\n", | |
"id 1052734731465949_1052790738127015\n", | |
"message POR HABER GOLPEADO A LOS VIEJOS PENSIONADOS\\nP...\n", | |
"message_clean [por, haber, golpeado, los, viejos, pensionado...\n", | |
"categoria none\n", | |
"Name: 9, dtype: object\n", | |
"created_time 2016-04-20T00:08:54+0000\n", | |
"from_id 10208256468305273\n", | |
"from_name Pupis RoAl\n", | |
"id 1052734731465949_1052817844790971\n", | |
"message Tiene uno que hacer que su voto sea útil para ...\n", | |
"message_clean [tiene, uno, que, hacer, que, voto, sea, util,...\n", | |
"categoria none\n", | |
"Name: 38, dtype: object\n", | |
"created_time 2016-04-20T01:16:45+0000\n", | |
"from_id 10201607172698574\n", | |
"from_name José Israel HG\n", | |
"id 1052734731465949_1052846468121442\n", | |
"message Aguas, MORENA es aliado del PRI, el mismo AMLO...\n", | |
"message_clean [aguas, morena, aliado, del, pri, mismo, amlo,...\n", | |
"categoria none\n", | |
"Name: 50, dtype: object\n", | |
"created_time 2016-04-20T05:14:15+0000\n", | |
"from_id 1739876516256063\n", | |
"from_name Leo Mendiola\n", | |
"id 1052734731465949_1052943314778424\n", | |
"message Es un distractor de duarte quien realmente apo...\n", | |
"message_clean [distractor, duarte, quien, realmente, apoya, ...\n", | |
"categoria none\n", | |
"Name: 83, dtype: object\n", | |
"created_time 2016-04-20T16:18:27+0000\n", | |
"from_id 10206027870963469\n", | |
"from_name Miguel Angel\n", | |
"id 1052734731465949_1053233514749404\n", | |
"message Morena no se presentó al debate por los coment...\n", | |
"message_clean [morena, presento, debate, por, los, comentari...\n", | |
"categoria none\n", | |
"Name: 118, dtype: object\n", | |
"created_time 2016-04-20T21:58:29+0000\n", | |
"from_id 1167084456675195\n", | |
"from_name Marcos Roke\n", | |
"id 1052734731465949_1053393964733359\n", | |
"message Que se coman entre los dos! Como la gente ya n...\n", | |
"message_clean [que, coman, entre, los, dos, como, gente, qui...\n", | |
"categoria none\n", | |
"Name: 183, dtype: object\n", | |
"created_time 2016-04-20T22:19:14+0000\n", | |
"from_id 1717249001866289\n", | |
"from_name Bella Leo\n", | |
"id 1052734731465949_1053409941398428\n", | |
"message Kieren hacerle creer al pueblo k van ganando p...\n", | |
"message_clean [kieren, hacerle, creer, pueblo, van, ganando,...\n", | |
"categoria none\n", | |
"Name: 191, dtype: object\n", | |
"created_time 2016-04-20T23:03:04+0000\n", | |
"from_id 968141139940174\n", | |
"from_name Jose Luis Sanchez Lara\n", | |
"id 1052734731465949_1053433861396036\n", | |
"message sale la pelea por la gobernatura de veracruz d...\n", | |
"message_clean [sale, pelea, por, gobernatura, veracruz, debe...\n", | |
"categoria none\n", | |
"Name: 202, dtype: object\n", | |
"created_time 2016-04-21T01:58:01+0000\n", | |
"from_id 10156828527775652\n", | |
"from_name Elías Castillo Romero\n", | |
"id 1052734731465949_1053505471388875\n", | |
"message Ni a morena le está funcionando aliarse con el...\n", | |
"message_clean [morena, esta, funcionando, aliarse, con, pri,...\n", | |
"categoria anti-pri\n", | |
"Name: 232, dtype: object\n", | |
"created_time 2016-04-21T03:30:15+0000\n", | |
"from_id 567285890121584\n", | |
"from_name Jose Alfonso Lerista\n", | |
"id 1052734731465949_1053542114718544\n", | |
"message Morena (peje)se alio con pri y sus partidos l...\n", | |
"message_clean [morena, peje, alio, con, pri, sus, partidos, ...\n", | |
"categoria none\n", | |
"Name: 245, dtype: object\n", | |
"created_time 2016-04-21T04:29:02+0000\n", | |
"from_id 111845025887237\n", | |
"from_name Omar Garces\n", | |
"id 1052734731465949_1053560578050031\n", | |
"message Para aquellos que creen en Morena les aviso qu...\n", | |
"message_clean [para, aquellos, que, creen, morena, les, avis...\n", | |
"categoria none\n", | |
"Name: 253, dtype: object\n", | |
"created_time 2016-04-22T03:33:30+0000\n", | |
"from_id 228141764222711\n", | |
"from_name Pili Grajales\n", | |
"id 1052734731465949_1054220271317395\n", | |
"message Morena ya hizo alianza con el PRI AMLO lo dijo...\n", | |
"message_clean [morena, hizo, alianza, con, pri, amlo, dijo, ...\n", | |
"categoria none\n", | |
"Name: 323, dtype: object\n", | |
"created_time 2016-04-22T14:37:14+0000\n", | |
"from_id 987295711377273\n", | |
"from_name Luis Manuel Duran Ibarra\n", | |
"id 1052734731465949_1054548714617884\n", | |
"message Ahora para los perros ya les van adar yase ven...\n", | |
"message_clean [ahora, para, los, perros, les, van, adar, yas...\n", | |
"categoria none\n", | |
"Name: 334, dtype: object\n", | |
"created_time 2016-04-23T02:54:41+0000\n", | |
"from_id 229762630725895\n", | |
"from_name Emeterio Hernandez Escalante\n", | |
"id 1052734731465949_1054906061248816\n", | |
"message El pri y el pan son lo mismo nomas qu uno es r...\n", | |
"message_clean [pri, pan, son, mismo, nomas, uno, rrata, otro...\n", | |
"categoria none\n", | |
"Name: 388, dtype: object\n", | |
"created_time 2016-04-25T03:06:33+0000\n", | |
"from_id 262839304069539\n", | |
"from_name Chuliss Gamas\n", | |
"id 1052734731465949_1010200435695013\n", | |
"message Amigo infórmate bien morena y pri son lo mismo...\n", | |
"message_clean [amigo, informate, bien, morena, pri, son, mis...\n", | |
"categoria none\n", | |
"Name: 495, dtype: object\n", | |
"created_time 2016-04-27T00:27:49+0000\n", | |
"from_id 233495237006715\n", | |
"from_name Israel Bautista\n", | |
"id 1052734731465949_1011402615574795\n", | |
"message Arriba el peje entre ellos se tiran flores par...\n", | |
"message_clean [arriba, peje, entre, ellos, tiran, flores, pa...\n", | |
"categoria none\n", | |
"Name: 532, dtype: object\n" | |
] | |
} | |
], | |
"source": [ | |
"for row in comments_df_categorización.iterrows():\n", | |
" if \"morena\" in row[1][\"message_clean\"]:\n", | |
" print(row[1])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 394, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"morena_class = comments_df_categorización.iloc[232]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 395, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"created_time 2016-04-21T01:58:01+0000\n", | |
"from_id 10156828527775652\n", | |
"from_name Elías Castillo Romero\n", | |
"id 1052734731465949_1053505471388875\n", | |
"message Ni a morena le está funcionando aliarse con el...\n", | |
"message_clean [morena, esta, funcionando, aliarse, con, pri,...\n", | |
"categoria anti-pri\n", | |
"Name: 232, dtype: object" | |
] | |
}, | |
"execution_count": 395, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"morena_class" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"La categoría es: contra morena" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 402, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"comments_df_categorización[\"categoria\"][232]=\"anti-morena\"" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 413, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"created_time 2016-04-21T01:58:01+0000\n", | |
"from_id 10156828527775652\n", | |
"from_name Elías Castillo Romero\n", | |
"id 1052734731465949_1053505471388875\n", | |
"message Ni a morena le está funcionando aliarse con el...\n", | |
"message_clean [morena, esta, funcionando, aliarse, con, pri,...\n", | |
"categoria anti-morena\n", | |
"Name: 232, dtype: object" | |
] | |
}, | |
"execution_count": 413, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_df_categorización.iloc[232]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 414, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"comments_df_premorena = comments_df_categorización" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 415, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array(['anti-morena', 'anti-pri', 'none'], dtype=object)" | |
] | |
}, | |
"execution_count": 415, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"np.unique(comments_df_premorena[\"categoria\"])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 426, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"def df_bag_of_words(dataframe_in):\n", | |
" bag_of_words = {}\n", | |
" #Se trae los datos que estan categorizados\n", | |
" dataframe_concategoria = dataframe_in[dataframe_in[\"categoria\"]!=\"none\"]\n", | |
" size, vocabulary = get_uniques(dataframe_concategoria)\n", | |
" bag_of_words[\"vocabulary\"]= size\n", | |
" bag_of_words[\"class\"] = {}\n", | |
" whole_df_size = float(len(dataframe_concategoria))\n", | |
" for unique_class in np.unique(dataframe_concategoria[\"categoria\"]):\n", | |
" dataframe_class = dataframe_concategoria[dataframe_concategoria[\"categoria\"]==unique_class]\n", | |
" class_words_size, class_vocabulary, class_word_count = get_uniques_class(dataframe_class)\n", | |
" bag_of_words[\"class\"][unique_class] = {}\n", | |
" bag_of_words[\"class\"][unique_class][\"word_prior\"] = float(len(dataframe_class))/whole_df_size\n", | |
" bag_of_words[\"class\"][unique_class][\"unique_words\"] = class_words_size\n", | |
" bag_of_words[\"class\"][unique_class][\"word_count\"] = class_word_count\n", | |
" return(bag_of_words)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 427, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"def get_uniques(dataframe_in):\n", | |
" word_list = []\n", | |
" for row in dataframe_in.iterrows():\n", | |
" word_list = word_list + row[1][\"message_clean\"]\n", | |
" uniques = np.unique(word_list)\n", | |
" size = len(uniques)\n", | |
" return size,uniques" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 428, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"def get_uniques_class(dataframe_in):\n", | |
" word_list = []\n", | |
" for row in dataframe_in.iterrows():\n", | |
" word_list = word_list + row[1][\"message_clean\"]\n", | |
" uniques = np.unique(word_list)\n", | |
" size = len(uniques)\n", | |
" class_word_count = {}\n", | |
" for unique in uniques:\n", | |
" class_word_count[unique]=word_list.count(unique)\n", | |
" return size,uniques, class_word_count" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 431, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"case_bag_of_words =df_bag_of_words(comments_df_premorena)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 432, | |
"metadata": { | |
"collapsed": false, | |
"scrolled": true | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"{'class': {'anti-morena': {'unique_words': 25,\n", | |
" 'word_count': {'aliarse': 1,\n", | |
" 'beneficiar': 1,\n", | |
" 'bueno': 1,\n", | |
" 'con': 1,\n", | |
" 'del': 1,\n", | |
" 'esta': 1,\n", | |
" 'funcionando': 1,\n", | |
" 'hace': 1,\n", | |
" 'hayan': 1,\n", | |
" 'incluso': 1,\n", | |
" 'mella': 1,\n", | |
" 'morena': 1,\n", | |
" 'obtener': 1,\n", | |
" 'pan': 2,\n", | |
" 'para': 2,\n", | |
" 'parientes': 1,\n", | |
" 'pipo': 1,\n", | |
" 'pri': 1,\n", | |
" 'priistas': 1,\n", | |
" 'provenientes': 1,\n", | |
" 'que': 1,\n", | |
" 'siquiera': 1,\n", | |
" 'torio': 1,\n", | |
" 'traicionado': 1,\n", | |
" 'votos': 1},\n", | |
" 'word_prior': 0.07142857142857142},\n", | |
" 'anti-pri': {'unique_words': 139,\n", | |
" 'word_count': {'acaba': 1,\n", | |
" 'alegria': 1,\n", | |
" 'angel': 1,\n", | |
" 'arriba': 1,\n", | |
" 'asesino': 1,\n", | |
" 'avian': 1,\n", | |
" 'azul': 1,\n", | |
" 'bandido': 1,\n", | |
" 'basura': 1,\n", | |
" 'bueno': 2,\n", | |
" 'cambiar': 1,\n", | |
" 'cambiemos': 1,\n", | |
" 'cantar': 1,\n", | |
" 'casi': 1,\n", | |
" 'ciegos': 1,\n", | |
" 'coludas': 1,\n", | |
" 'como': 2,\n", | |
" 'comprando': 1,\n", | |
" 'comprar': 1,\n", | |
" 'con': 2,\n", | |
" 'conocemos': 1,\n", | |
" 'contra': 1,\n", | |
" 'correrlos': 1,\n", | |
" 'corrupcion': 1,\n", | |
" 'corrupto': 1,\n", | |
" 'credibilidad': 1,\n", | |
" 'creen': 1,\n", | |
" 'dejense': 1,\n", | |
" 'den': 1,\n", | |
" 'desesperada': 1,\n", | |
" 'desgracia': 1,\n", | |
" 'digan': 1,\n", | |
" 'dinero': 1,\n", | |
" 'disque': 1,\n", | |
" 'duarte': 3,\n", | |
" 'ellos': 1,\n", | |
" 'empezando': 1,\n", | |
" 'empezndo': 1,\n", | |
" 'encerrar': 1,\n", | |
" 'entonces': 1,\n", | |
" 'esa': 1,\n", | |
" 'escribio': 1,\n", | |
" 'ese': 1,\n", | |
" 'esos': 3,\n", | |
" 'estado': 1,\n", | |
" 'estan': 3,\n", | |
" 'esten': 1,\n", | |
" 'extraña': 1,\n", | |
" 'farmacias': 1,\n", | |
" 'fuera': 1,\n", | |
" 'ganar': 1,\n", | |
" 'gente': 1,\n", | |
" 'gobernador': 1,\n", | |
" 'gobierno': 1,\n", | |
" 'gracias': 1,\n", | |
" 'hace': 1,\n", | |
" 'hagan': 1,\n", | |
" 'hara': 1,\n", | |
" 'hector': 1,\n", | |
" 'herramienta': 1,\n", | |
" 'historia': 1,\n", | |
" 'hospitales': 1,\n", | |
" 'ignorantes': 1,\n", | |
" 'invertir': 1,\n", | |
" 'jejejejeje': 1,\n", | |
" 'jugar': 1,\n", | |
" 'las': 2,\n", | |
" 'lema': 1,\n", | |
" 'les': 2,\n", | |
" 'limpio': 1,\n", | |
" 'linares': 2,\n", | |
" 'lloren': 1,\n", | |
" 'los': 11,\n", | |
" 'maldigo': 1,\n", | |
" 'maldito': 1,\n", | |
" 'medicamentos': 1,\n", | |
" 'mejor': 1,\n", | |
" 'mendigos': 1,\n", | |
" 'mentiroso': 1,\n", | |
" 'migel': 1,\n", | |
" 'miguel': 1,\n", | |
" 'nada': 1,\n", | |
" 'nadie': 1,\n", | |
" 'nerviosos': 1,\n", | |
" 'nos': 1,\n", | |
" 'nuestro': 1,\n", | |
" 'opinion': 1,\n", | |
" 'para': 4,\n", | |
" 'parenle': 1,\n", | |
" 'patria': 1,\n", | |
" 'pedacito': 1,\n", | |
" 'perdera': 1,\n", | |
" 'periodistas': 1,\n", | |
" 'pero': 1,\n", | |
" 'perras': 1,\n", | |
" 'piensan': 1,\n", | |
" 'poder': 1,\n", | |
" 'por': 3,\n", | |
" 'porque': 1,\n", | |
" 'postor': 1,\n", | |
" 'pregunto': 1,\n", | |
" 'pri': 3,\n", | |
" 'priiistas': 1,\n", | |
" 'priista': 1,\n", | |
" 'priistas': 13,\n", | |
" 'pueblo': 2,\n", | |
" 'puede': 1,\n", | |
" 'qieren': 1,\n", | |
" 'que': 11,\n", | |
" 'quiere': 1,\n", | |
" 'ratas': 4,\n", | |
" 'rateros': 1,\n", | |
" 'robar': 2,\n", | |
" 'sabemos': 1,\n", | |
" 'siempre': 1,\n", | |
" 'solo': 3,\n", | |
" 'son': 3,\n", | |
" 'sucia': 1,\n", | |
" 'sucios': 1,\n", | |
" 'sufrir': 1,\n", | |
" 'televisa': 1,\n", | |
" 'tenemos': 1,\n", | |
" 'tiempo': 1,\n", | |
" 'todo': 1,\n", | |
" 'todos': 5,\n", | |
" 'totalmente': 1,\n", | |
" 'unas': 1,\n", | |
" 'unico': 1,\n", | |
" 'unos': 1,\n", | |
" 'vacias': 1,\n", | |
" 'vamos': 2,\n", | |
" 'van': 1,\n", | |
" 'ven': 1,\n", | |
" 'vende': 1,\n", | |
" 'veracruz': 3,\n", | |
" 'vidas': 1,\n", | |
" 'vote': 1,\n", | |
" 'vsmos': 1,\n", | |
" 'yunes': 3},\n", | |
" 'word_prior': 0.9285714285714286}},\n", | |
" 'vocabulary': 157}" | |
] | |
}, | |
"execution_count": 432, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"case_bag_of_words" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 552, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"def classify_message(text):\n", | |
" #limpia la\n", | |
" text_clean = sentence_cleaner(text)\n", | |
" text_clean = stopword_cleaner(text_clean)\n", | |
" output_probabilities = []\n", | |
" class_probability_dict = {}\n", | |
" #Va, categoria por categoria, verificando si las palabras estan en el diccionario, y si si, prueba la categoria.\n", | |
" for category in case_bag_of_words['class']:\n", | |
" class_probability = 0\n", | |
" #iterar por palabra de la oracion\n", | |
" for word in text_clean:\n", | |
" if word in case_bag_of_words['class'][category][\"word_count\"]:\n", | |
" probability = (float(case_bag_of_words['class'][category][\"word_count\"][word])+1.0)/(float(case_bag_of_words['class'][category][\"unique_words\"])+case_bag_of_words[\"vocabulary\"])\n", | |
" else:\n", | |
" probability = 1.0/(float(case_bag_of_words['class'][category][\"unique_words\"])+case_bag_of_words[\"vocabulary\"])\n", | |
" #inicializa la probabilidad de la clase \n", | |
" if class_probability == 0:\n", | |
" class_probability = probability\n", | |
" else:\n", | |
" class_probability = class_probability * probability\n", | |
" final_probability = float(case_bag_of_words['class'][category][\"word_prior\"])*class_probability\n", | |
" #Fill directory\n", | |
" class_probability_dict[category] = final_probability\n", | |
" output_probabilities.append(final_probability)\n", | |
" return(output_probabilities,class_probability_dict)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 482, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"def stopword_cleaner(in_list):\n", | |
" out = []\n", | |
" for token in in_list:\n", | |
" if token not in STOPWORDS:\n", | |
" out = out + [token]\n", | |
" return out" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 531, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/html": [ | |
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n", | |
"<table border=\"1\" class=\"dataframe\">\n", | |
" <thead>\n", | |
" <tr style=\"text-align: right;\">\n", | |
" <th></th>\n", | |
" <th>created_time</th>\n", | |
" <th>from_id</th>\n", | |
" <th>from_name</th>\n", | |
" <th>id</th>\n", | |
" <th>message</th>\n", | |
" <th>message_clean</th>\n", | |
" <th>categoria</th>\n", | |
" </tr>\n", | |
" </thead>\n", | |
" <tbody>\n", | |
" <tr>\n", | |
" <th>0</th>\n", | |
" <td>2016-04-19T22:10:23+0000</td>\n", | |
" <td>1129125517119186</td>\n", | |
" <td>Javier Lecter</td>\n", | |
" <td>1052734731465949_1052775478128541</td>\n", | |
" <td>igual que en Tamaulipas ya van para afuera por...</td>\n", | |
" <td>[igual, que, tamaulipas, van, para, afuera, po...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>1</th>\n", | |
" <td>2016-04-19T22:20:31+0000</td>\n", | |
" <td>563927170436016</td>\n", | |
" <td>Ivan Jist</td>\n", | |
" <td>1052734731465949_1052779208128168</td>\n", | |
" <td>Y el pri por robar todo el dinero a la Uv y ci...</td>\n", | |
" <td>[pri, por, robar, todo, dinero, cierto, robo, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>2</th>\n", | |
" <td>2016-04-19T22:27:06+0000</td>\n", | |
" <td>716106398532421</td>\n", | |
" <td>Pequeño Corazonsito Cruz</td>\n", | |
" <td>1052734731465949_1052781654794590</td>\n", | |
" <td>Yo</td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>4</th>\n", | |
" <td>2016-04-19T22:32:14+0000</td>\n", | |
" <td>232046980484475</td>\n", | |
" <td>David Camacho</td>\n", | |
" <td>1052734731465949_1052783438127745</td>\n", | |
" <td>El pri está dando patadas de hogado, ya no pue...</td>\n", | |
" <td>[pri, esta, dando, patadas, hogado, puede, man...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>5</th>\n", | |
" <td>2016-04-19T22:38:29+0000</td>\n", | |
" <td>1005519999541281</td>\n", | |
" <td>Raymundo Gomez</td>\n", | |
" <td>1052734731465949_1052785638127525</td>\n", | |
" <td>No pasa nada eso dice nuestro gobernador puñal...</td>\n", | |
" <td>[pasa, nada, eso, dice, nuestro, gobernador, p...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>6</th>\n", | |
" <td>2016-04-19T22:39:48+0000</td>\n", | |
" <td>1161542603879742</td>\n", | |
" <td>Carlos Lopez</td>\n", | |
" <td>1052734731465949_1052785974794158</td>\n", | |
" <td>Ya vio que la gente de estado está hasta la ma...</td>\n", | |
" <td>[vio, que, gente, estado, esta, hasta, madre, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>7</th>\n", | |
" <td>2016-04-19T22:51:22+0000</td>\n", | |
" <td>1008574712554591</td>\n", | |
" <td>Basi Poet Hernandez</td>\n", | |
" <td>1052734731465949_1052790111460411</td>\n", | |
" <td>NI UN VOTO PARA EL PRI. RATASSSSSSSS</td>\n", | |
" <td>[voto, para, pri, ratassssssss]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>8</th>\n", | |
" <td>2016-04-19T22:51:40+0000</td>\n", | |
" <td>10209072954923008</td>\n", | |
" <td>Trigos Estrellix</td>\n", | |
" <td>1052734731465949_1052790221460400</td>\n", | |
" <td>PAN*</td>\n", | |
" <td>[pan]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>9</th>\n", | |
" <td>2016-04-19T22:53:56+0000</td>\n", | |
" <td>640669849416464</td>\n", | |
" <td>Eduardo Alfonso Ruiz</td>\n", | |
" <td>1052734731465949_1052790738127015</td>\n", | |
" <td>POR HABER GOLPEADO A LOS VIEJOS PENSIONADOS\\nP...</td>\n", | |
" <td>[por, haber, golpeado, los, viejos, pensionado...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>10</th>\n", | |
" <td>2016-04-19T22:56:29+0000</td>\n", | |
" <td>1051815134886799</td>\n", | |
" <td>Jose Luis Martinez Lara</td>\n", | |
" <td>1052734731465949_1052791428126946</td>\n", | |
" <td>Fuera!!!</td>\n", | |
" <td>[fuera]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>11</th>\n", | |
" <td>2016-04-19T23:03:16+0000</td>\n", | |
" <td>10206410155160328</td>\n", | |
" <td>Rikrdo Lopz</td>\n", | |
" <td>1052734731465949_1052793558126733</td>\n", | |
" <td>El pri no debería ni siquiera estar en las enc...</td>\n", | |
" <td>[pri, deberia, siquiera, estar, las, encuestas...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>12</th>\n", | |
" <td>2016-04-19T23:04:13+0000</td>\n", | |
" <td>1150097811688100</td>\n", | |
" <td>Angel Vasquez Vera</td>\n", | |
" <td>1052734731465949_1052793991460023</td>\n", | |
" <td>Eso, ya se esperaba de la maquinaria roja. Per...</td>\n", | |
" <td>[eso, esperaba, maquinaria, roja, pero, aun, c...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>13</th>\n", | |
" <td>2016-04-19T23:04:26+0000</td>\n", | |
" <td>1020323774729225</td>\n", | |
" <td>Carmen Salazar Mora</td>\n", | |
" <td>1052734731465949_1052794061460016</td>\n", | |
" <td>Quien este durmiendo y que por una despensa qu...</td>\n", | |
" <td>[quien, este, durmiendo, que, por, una, despen...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>14</th>\n", | |
" <td>2016-04-19T23:06:58+0000</td>\n", | |
" <td>1710921779175951</td>\n", | |
" <td>Liliana Del Carmen García Zárate</td>\n", | |
" <td>1052734731465949_1052794981459924</td>\n", | |
" <td></td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>15</th>\n", | |
" <td>2016-04-19T23:08:22+0000</td>\n", | |
" <td>1619483091707011</td>\n", | |
" <td>Noe Juarez</td>\n", | |
" <td>1052734731465949_1052795288126560</td>\n", | |
" <td>Todos son coructos y el pri ocupa el primer lu...</td>\n", | |
" <td>[todos, son, coructos, pri, ocupa, primer, lug...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>16</th>\n", | |
" <td>2016-04-19T23:10:19+0000</td>\n", | |
" <td>10206247953030159</td>\n", | |
" <td>Elsi Hernandez Lopez</td>\n", | |
" <td>1052734731465949_1052796388126450</td>\n", | |
" <td></td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>17</th>\n", | |
" <td>2016-04-19T23:10:23+0000</td>\n", | |
" <td>10206247953030159</td>\n", | |
" <td>Elsi Hernandez Lopez</td>\n", | |
" <td>1052734731465949_1052796404793115</td>\n", | |
" <td></td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>18</th>\n", | |
" <td>2016-04-19T23:10:35+0000</td>\n", | |
" <td>10209410945889904</td>\n", | |
" <td>Gray Fox Die</td>\n", | |
" <td>1052734731465949_1052796481459774</td>\n", | |
" <td>Sigan votando por el pri que les da miserias a...</td>\n", | |
" <td>[sigan, votando, por, pri, que, les, miserias,...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>19</th>\n", | |
" <td>2016-04-19T23:12:39+0000</td>\n", | |
" <td>1059514784122092</td>\n", | |
" <td>Peter Infante Cruz</td>\n", | |
" <td>1052734731465949_1052797171459705</td>\n", | |
" <td>Yo creo que el sr Miguel ángel va con todo y m...</td>\n", | |
" <td>[creo, que, miguel, angel, con, todo, conformo...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>20</th>\n", | |
" <td>2016-04-19T23:14:48+0000</td>\n", | |
" <td>224509774594310</td>\n", | |
" <td>Erik Cruz</td>\n", | |
" <td>1052734731465949_1052797721459650</td>\n", | |
" <td>Siempre es lo mismo con el pri carvallo donde ...</td>\n", | |
" <td>[siempre, mismo, con, pri, carvallo, donde, an...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>21</th>\n", | |
" <td>2016-04-19T23:20:18+0000</td>\n", | |
" <td>214934918887206</td>\n", | |
" <td>Axel Gabino San Juan Bautizta</td>\n", | |
" <td>1052734731465949_1052799821459440</td>\n", | |
" <td>Q nos engañen otra ves una monos y hagamos la ...</td>\n", | |
" <td>[nos, engañen, otra, ves, una, monos, hagamos,...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>22</th>\n", | |
" <td>2016-04-19T23:21:21+0000</td>\n", | |
" <td>214934918887206</td>\n", | |
" <td>Axel Gabino San Juan Bautizta</td>\n", | |
" <td>1052734731465949_1052800151459407</td>\n", | |
" <td></td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>23</th>\n", | |
" <td>2016-04-19T23:22:52+0000</td>\n", | |
" <td>1171739079525238</td>\n", | |
" <td>Omar Suriano Calles</td>\n", | |
" <td>1052734731465949_1052800621459360</td>\n", | |
" <td>Es increíble k el pri este en segundo lugar en...</td>\n", | |
" <td>[increible, pri, este, segundo, lugar, encuesta]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>24</th>\n", | |
" <td>2016-04-19T23:24:27+0000</td>\n", | |
" <td>1551872245115511</td>\n", | |
" <td>Concepcion Zamora</td>\n", | |
" <td>1052734731465949_1052800978125991</td>\n", | |
" <td>Ni un voto a el priiu</td>\n", | |
" <td>[voto, priiu]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>25</th>\n", | |
" <td>2016-04-19T23:28:01+0000</td>\n", | |
" <td>1792764180944470</td>\n", | |
" <td>Jose Luis Serrano Lagunes</td>\n", | |
" <td>1052734731465949_1052802578125831</td>\n", | |
" <td>A chingar asu madre el pri del estado no mas pri</td>\n", | |
" <td>[chingar, asu, madre, pri, del, estado, mas, pri]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>26</th>\n", | |
" <td>2016-04-19T23:30:16+0000</td>\n", | |
" <td>1029174180509737</td>\n", | |
" <td>Gonzalo Kaphwan</td>\n", | |
" <td>1052734731465949_1052803254792430</td>\n", | |
" <td>Jacobo Ceron ,</td>\n", | |
" <td>[jacobo, ceron]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>27</th>\n", | |
" <td>2016-04-19T23:30:42+0000</td>\n", | |
" <td>1754337714825307</td>\n", | |
" <td>Roger Rivas</td>\n", | |
" <td>1052734731465949_1052803408125748</td>\n", | |
" <td>FUERA FUERA EL PRI..JAJAJAJAJAJJAJA</td>\n", | |
" <td>[fuera, fuera, pri, jajajajajajjaja]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>28</th>\n", | |
" <td>2016-04-19T23:34:52+0000</td>\n", | |
" <td>10208954940047997</td>\n", | |
" <td>Marck Anthony</td>\n", | |
" <td>1052734731465949_1052804934792262</td>\n", | |
" <td>Y 34% se me hace demasiado Jajajajjaja al Pri ...</td>\n", | |
" <td>[34%, hace, demasiado, jajajajjaja, pri, hay, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>29</th>\n", | |
" <td>2016-04-19T23:37:40+0000</td>\n", | |
" <td>224744787882164</td>\n", | |
" <td>Alfredo Alvarado</td>\n", | |
" <td>1052734731465949_1052805834792172</td>\n", | |
" <td>Hay que darle el voto a yunes Linares,para sac...</td>\n", | |
" <td>[hay, que, darle, voto, yunes, linares, para, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>30</th>\n", | |
" <td>2016-04-19T23:38:42+0000</td>\n", | |
" <td>1717243161856281</td>\n", | |
" <td>Valentina Posadas</td>\n", | |
" <td>1052734731465949_1052806238125465</td>\n", | |
" <td></td>\n", | |
" <td>[]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>...</th>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" <td>...</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>531</th>\n", | |
" <td>2016-04-27T00:10:38+0000</td>\n", | |
" <td>967327370055232</td>\n", | |
" <td>Leonardo Rojas H</td>\n", | |
" <td>1052734731465949_1167015786666656</td>\n", | |
" <td>Chismosos!! Como inventan!!.</td>\n", | |
" <td>[chismosos, como, inventan]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>532</th>\n", | |
" <td>2016-04-27T00:27:49+0000</td>\n", | |
" <td>233495237006715</td>\n", | |
" <td>Israel Bautista</td>\n", | |
" <td>1052734731465949_1011402615574795</td>\n", | |
" <td>Arriba el peje entre ellos se tiran flores par...</td>\n", | |
" <td>[arriba, peje, entre, ellos, tiran, flores, pa...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>533</th>\n", | |
" <td>2016-04-27T00:29:47+0000</td>\n", | |
" <td>232703960433073</td>\n", | |
" <td>Lupi Rubio</td>\n", | |
" <td>1052734731465949_1011403168908073</td>\n", | |
" <td>Saludes. Disfruten paseo las s. Quiero</td>\n", | |
" <td>[saludes, disfruten, paseo, las, quiero]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>534</th>\n", | |
" <td>2016-04-27T00:59:52+0000</td>\n", | |
" <td>1706548062935044</td>\n", | |
" <td>Margarito Ramirez Mendoza</td>\n", | |
" <td>1052734731465949_1011412155573841</td>\n", | |
" <td>No se dejen engañar son patadas de ahogado que...</td>\n", | |
" <td>[dejen, engañar, son, patadas, ahogado, que, e...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>535</th>\n", | |
" <td>2016-04-27T01:35:16+0000</td>\n", | |
" <td>1750965218482905</td>\n", | |
" <td>Manuel Martinez Garcia</td>\n", | |
" <td>1052734731465949_1011422658906124</td>\n", | |
" <td>C corruptohico niñote</td>\n", | |
" <td>[corruptohico, niñote]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>536</th>\n", | |
" <td>2016-04-27T01:45:42+0000</td>\n", | |
" <td>586079581556228</td>\n", | |
" <td>Fork Bautista</td>\n", | |
" <td>1052734731465949_1167052893329612</td>\n", | |
" <td>son puras mamadas la polita ya k le toke al pa...</td>\n", | |
" <td>[son, puras, mamadas, polita, toke, pan, tambi...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>537</th>\n", | |
" <td>2016-04-27T01:48:31+0000</td>\n", | |
" <td>641439986021125</td>\n", | |
" <td>Irene Hernandez</td>\n", | |
" <td>1052734731465949_1167053903329511</td>\n", | |
" <td>sinvergüenzas no k moy limpios. Sus mapaches. ...</td>\n", | |
" <td>[sinvergüenzas, moy, limpios, sus, mapaches, l...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>538</th>\n", | |
" <td>2016-04-27T01:56:53+0000</td>\n", | |
" <td>1585790621733381</td>\n", | |
" <td>Raul Malaga Cruz</td>\n", | |
" <td>1052734731465949_1011429478905442</td>\n", | |
" <td>El pri no gana almenos qué juege sucio como ya...</td>\n", | |
" <td>[pri, gana, almenos, que, juege, sucio, como, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>539</th>\n", | |
" <td>2016-04-27T02:07:33+0000</td>\n", | |
" <td>804647173001125</td>\n", | |
" <td>Amelia Cuellar</td>\n", | |
" <td>1052734731465949_1011434012238322</td>\n", | |
" <td>Gobierno corrupto junto con todos los que se a...</td>\n", | |
" <td>[gobierno, corrupto, junto, con, todos, los, q...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>540</th>\n", | |
" <td>2016-04-27T02:10:56+0000</td>\n", | |
" <td>1682535325342955</td>\n", | |
" <td>Hilda Rojas</td>\n", | |
" <td>1052734731465949_1167062729995295</td>\n", | |
" <td>Ni a cual ir todos lis partidos por política s...</td>\n", | |
" <td>[cual, todos, lis, partidos, por, politica, so...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>541</th>\n", | |
" <td>2016-04-27T02:24:09+0000</td>\n", | |
" <td>1300648329949876</td>\n", | |
" <td>Javier Alva Rex</td>\n", | |
" <td>1052734731465949_1011439922237731</td>\n", | |
" <td>Yunes Linares ganará aún con la lluvia de lodo.</td>\n", | |
" <td>[yunes, linares, ganara, aun, con, lluvia, lodo]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>542</th>\n", | |
" <td>2016-04-27T04:10:03+0000</td>\n", | |
" <td>1331456030202694</td>\n", | |
" <td>Elisa Rosendo Castillo</td>\n", | |
" <td>1052734731465949_1167105313324370</td>\n", | |
" <td>#están desesperados y somos 7millones de votos...</td>\n", | |
" <td>[estan, desesperados, somos, 7millones, votos,...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>543</th>\n", | |
" <td>2016-04-27T04:47:12+0000</td>\n", | |
" <td>525312784322250</td>\n", | |
" <td>Hortencia Galindo</td>\n", | |
" <td>1052734731465949_1167120353322866</td>\n", | |
" <td>Y la marrana sigue comiendo !!!!!</td>\n", | |
" <td>[marrana, sigue, comiendo]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>544</th>\n", | |
" <td>2016-04-27T08:21:44+0000</td>\n", | |
" <td>994158437337758</td>\n", | |
" <td>Alfred Garcia</td>\n", | |
" <td>1052734731465949_1011583748890015</td>\n", | |
" <td>eso ya no es novedad</td>\n", | |
" <td>[eso, novedad]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>545</th>\n", | |
" <td>2016-04-27T22:07:11+0000</td>\n", | |
" <td>1792976970923203</td>\n", | |
" <td>Ana Gabriela Estrada</td>\n", | |
" <td>1052734731465949_1011956045519452</td>\n", | |
" <td>Todos los del pri son una bola de rrateros es ...</td>\n", | |
" <td>[todos, los, del, pri, son, una, bola, rratero...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>546</th>\n", | |
" <td>2016-04-27T23:54:24+0000</td>\n", | |
" <td>241101932917101</td>\n", | |
" <td>Ale Zamudio Cruz</td>\n", | |
" <td>1052734731465949_1167634389938129</td>\n", | |
" <td>y pinche rata del Duarte muy tranquilo contod...</td>\n", | |
" <td>[pinche, rata, del, duarte, muy, tranquilo, co...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>547</th>\n", | |
" <td>2016-04-27T23:55:22+0000</td>\n", | |
" <td>241101932917101</td>\n", | |
" <td>Ale Zamudio Cruz</td>\n", | |
" <td>1052734731465949_1167634623271439</td>\n", | |
" <td>con su risa burlona para que vea</td>\n", | |
" <td>[con, risa, burlona, para, que, vea]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>548</th>\n", | |
" <td>2016-04-28T00:05:19+0000</td>\n", | |
" <td>272612976407755</td>\n", | |
" <td>Mario Moreno</td>\n", | |
" <td>1052734731465949_1167637853271116</td>\n", | |
" <td>Ahora es cuando hay que darle con todo al PRI ...</td>\n", | |
" <td>[ahora, cuando, hay, que, darle, con, todo, pr...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>549</th>\n", | |
" <td>2016-04-28T01:58:18+0000</td>\n", | |
" <td>240210256369371</td>\n", | |
" <td>Arturo Estudillo</td>\n", | |
" <td>1052734731465949_1167695349932033</td>\n", | |
" <td>Es una madriguera de ratas andan diario aca en...</td>\n", | |
" <td>[una, madriguera, ratas, andan, diario, aca, f...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>550</th>\n", | |
" <td>2016-04-28T02:29:23+0000</td>\n", | |
" <td>1760048690881980</td>\n", | |
" <td>Rafael Aguilar García</td>\n", | |
" <td>1052734731465949_1167706059930962</td>\n", | |
" <td>Ya se lo cargo el payaso. Gracias a Fidel y La...</td>\n", | |
" <td>[cargo, payaso, gracias, fidel, gorda, duarte]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>551</th>\n", | |
" <td>2016-04-28T03:27:53+0000</td>\n", | |
" <td>1619054318419436</td>\n", | |
" <td>Hernandez Vallejo</td>\n", | |
" <td>1052734731465949_1167730699928498</td>\n", | |
" <td>Solo dios puede ayudarnos</td>\n", | |
" <td>[solo, dios, puede, ayudarnos]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>552</th>\n", | |
" <td>2016-04-28T03:58:19+0000</td>\n", | |
" <td>1604808463179358</td>\n", | |
" <td>Carlos Daniel Espinoza</td>\n", | |
" <td>1052734731465949_1012102398838150</td>\n", | |
" <td>Por esos hijos de sptm este estado esta asi ya...</td>\n", | |
" <td>[por, esos, hijos, sptm, este, estado, esta, a...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>553</th>\n", | |
" <td>2016-04-28T03:59:18+0000</td>\n", | |
" <td>1117966451575523</td>\n", | |
" <td>Landy Castillo Sierra</td>\n", | |
" <td>1052734731465949_1167743733260528</td>\n", | |
" <td>LLa desesperada guerra sucia del PRI contra e...</td>\n", | |
" <td>[lla, desesperada, guerra, sucia, del, pri, co...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>554</th>\n", | |
" <td>2016-04-28T13:21:45+0000</td>\n", | |
" <td>251456561874663</td>\n", | |
" <td>Joseph Tauroasesino</td>\n", | |
" <td>1052734731465949_1167964776571757</td>\n", | |
" <td>Ese puto del gobernador que pague lo que debe ...</td>\n", | |
" <td>[ese, puto, del, gobernador, que, pague, que, ...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>555</th>\n", | |
" <td>2016-04-28T17:40:11+0000</td>\n", | |
" <td>572881672892104</td>\n", | |
" <td>Ceci Sanchez</td>\n", | |
" <td>1052734731465949_1168072516560983</td>\n", | |
" <td>Traga pinche gordo..mientras al estado lo unde...</td>\n", | |
" <td>[traga, pinche, gordo, mientras, estado, undes...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>556</th>\n", | |
" <td>2016-04-28T19:07:07+0000</td>\n", | |
" <td>1674866359441422</td>\n", | |
" <td>Isabel Alfaro</td>\n", | |
" <td>1052734731465949_1012459905469066</td>\n", | |
" <td>Muy cierto</td>\n", | |
" <td>[muy, cierto]</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>557</th>\n", | |
" <td>2016-04-28T20:11:55+0000</td>\n", | |
" <td>854116821361102</td>\n", | |
" <td>Ricardo Hernandez</td>\n", | |
" <td>1052734731465949_1168143303220571</td>\n", | |
" <td>Pobres pendejos quieren seguir ordeñando la vaca.</td>\n", | |
" <td>[pobres, pendejos, quieren, seguir, ordeñando,...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>558</th>\n", | |
" <td>2016-04-28T21:43:10+0000</td>\n", | |
" <td>599039010260924</td>\n", | |
" <td>Samm Sourdon</td>\n", | |
" <td>1052734731465949_1012526615462395</td>\n", | |
" <td>a huevo no se imaginan estar en la cárcel y es...</td>\n", | |
" <td>[huevo, imaginan, estar, carcel, estar, comien...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>559</th>\n", | |
" <td>2016-04-28T22:18:51+0000</td>\n", | |
" <td>1056358417752313</td>\n", | |
" <td>Macario Lopez</td>\n", | |
" <td>1052734731465949_1168198759881692</td>\n", | |
" <td>Q gane el q el pueblo elija sin corrupción sin...</td>\n", | |
" <td>[gane, pueblo, elija, sin, corrupcion, sin, pl...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" <tr>\n", | |
" <th>560</th>\n", | |
" <td>2016-04-28T23:45:12+0000</td>\n", | |
" <td>207245306334552</td>\n", | |
" <td>Joel Quevedo</td>\n", | |
" <td>1052734731465949_1012575425457514</td>\n", | |
" <td>ay se esta tragando nuetros ipuestos concomida...</td>\n", | |
" <td>[esta, tragando, nuetros, ipuestos, concomidas...</td>\n", | |
" <td>none</td>\n", | |
" </tr>\n", | |
" </tbody>\n", | |
"</table>\n", | |
"<p>547 rows × 7 columns</p>\n", | |
"</div>" | |
], | |
"text/plain": [ | |
" created_time from_id \\\n", | |
"0 2016-04-19T22:10:23+0000 1129125517119186 \n", | |
"1 2016-04-19T22:20:31+0000 563927170436016 \n", | |
"2 2016-04-19T22:27:06+0000 716106398532421 \n", | |
"4 2016-04-19T22:32:14+0000 232046980484475 \n", | |
"5 2016-04-19T22:38:29+0000 1005519999541281 \n", | |
"6 2016-04-19T22:39:48+0000 1161542603879742 \n", | |
"7 2016-04-19T22:51:22+0000 1008574712554591 \n", | |
"8 2016-04-19T22:51:40+0000 10209072954923008 \n", | |
"9 2016-04-19T22:53:56+0000 640669849416464 \n", | |
"10 2016-04-19T22:56:29+0000 1051815134886799 \n", | |
"11 2016-04-19T23:03:16+0000 10206410155160328 \n", | |
"12 2016-04-19T23:04:13+0000 1150097811688100 \n", | |
"13 2016-04-19T23:04:26+0000 1020323774729225 \n", | |
"14 2016-04-19T23:06:58+0000 1710921779175951 \n", | |
"15 2016-04-19T23:08:22+0000 1619483091707011 \n", | |
"16 2016-04-19T23:10:19+0000 10206247953030159 \n", | |
"17 2016-04-19T23:10:23+0000 10206247953030159 \n", | |
"18 2016-04-19T23:10:35+0000 10209410945889904 \n", | |
"19 2016-04-19T23:12:39+0000 1059514784122092 \n", | |
"20 2016-04-19T23:14:48+0000 224509774594310 \n", | |
"21 2016-04-19T23:20:18+0000 214934918887206 \n", | |
"22 2016-04-19T23:21:21+0000 214934918887206 \n", | |
"23 2016-04-19T23:22:52+0000 1171739079525238 \n", | |
"24 2016-04-19T23:24:27+0000 1551872245115511 \n", | |
"25 2016-04-19T23:28:01+0000 1792764180944470 \n", | |
"26 2016-04-19T23:30:16+0000 1029174180509737 \n", | |
"27 2016-04-19T23:30:42+0000 1754337714825307 \n", | |
"28 2016-04-19T23:34:52+0000 10208954940047997 \n", | |
"29 2016-04-19T23:37:40+0000 224744787882164 \n", | |
"30 2016-04-19T23:38:42+0000 1717243161856281 \n", | |
".. ... ... \n", | |
"531 2016-04-27T00:10:38+0000 967327370055232 \n", | |
"532 2016-04-27T00:27:49+0000 233495237006715 \n", | |
"533 2016-04-27T00:29:47+0000 232703960433073 \n", | |
"534 2016-04-27T00:59:52+0000 1706548062935044 \n", | |
"535 2016-04-27T01:35:16+0000 1750965218482905 \n", | |
"536 2016-04-27T01:45:42+0000 586079581556228 \n", | |
"537 2016-04-27T01:48:31+0000 641439986021125 \n", | |
"538 2016-04-27T01:56:53+0000 1585790621733381 \n", | |
"539 2016-04-27T02:07:33+0000 804647173001125 \n", | |
"540 2016-04-27T02:10:56+0000 1682535325342955 \n", | |
"541 2016-04-27T02:24:09+0000 1300648329949876 \n", | |
"542 2016-04-27T04:10:03+0000 1331456030202694 \n", | |
"543 2016-04-27T04:47:12+0000 525312784322250 \n", | |
"544 2016-04-27T08:21:44+0000 994158437337758 \n", | |
"545 2016-04-27T22:07:11+0000 1792976970923203 \n", | |
"546 2016-04-27T23:54:24+0000 241101932917101 \n", | |
"547 2016-04-27T23:55:22+0000 241101932917101 \n", | |
"548 2016-04-28T00:05:19+0000 272612976407755 \n", | |
"549 2016-04-28T01:58:18+0000 240210256369371 \n", | |
"550 2016-04-28T02:29:23+0000 1760048690881980 \n", | |
"551 2016-04-28T03:27:53+0000 1619054318419436 \n", | |
"552 2016-04-28T03:58:19+0000 1604808463179358 \n", | |
"553 2016-04-28T03:59:18+0000 1117966451575523 \n", | |
"554 2016-04-28T13:21:45+0000 251456561874663 \n", | |
"555 2016-04-28T17:40:11+0000 572881672892104 \n", | |
"556 2016-04-28T19:07:07+0000 1674866359441422 \n", | |
"557 2016-04-28T20:11:55+0000 854116821361102 \n", | |
"558 2016-04-28T21:43:10+0000 599039010260924 \n", | |
"559 2016-04-28T22:18:51+0000 1056358417752313 \n", | |
"560 2016-04-28T23:45:12+0000 207245306334552 \n", | |
"\n", | |
" from_name id \\\n", | |
"0 Javier Lecter 1052734731465949_1052775478128541 \n", | |
"1 Ivan Jist 1052734731465949_1052779208128168 \n", | |
"2 Pequeño Corazonsito Cruz 1052734731465949_1052781654794590 \n", | |
"4 David Camacho 1052734731465949_1052783438127745 \n", | |
"5 Raymundo Gomez 1052734731465949_1052785638127525 \n", | |
"6 Carlos Lopez 1052734731465949_1052785974794158 \n", | |
"7 Basi Poet Hernandez 1052734731465949_1052790111460411 \n", | |
"8 Trigos Estrellix 1052734731465949_1052790221460400 \n", | |
"9 Eduardo Alfonso Ruiz 1052734731465949_1052790738127015 \n", | |
"10 Jose Luis Martinez Lara 1052734731465949_1052791428126946 \n", | |
"11 Rikrdo Lopz 1052734731465949_1052793558126733 \n", | |
"12 Angel Vasquez Vera 1052734731465949_1052793991460023 \n", | |
"13 Carmen Salazar Mora 1052734731465949_1052794061460016 \n", | |
"14 Liliana Del Carmen García Zárate 1052734731465949_1052794981459924 \n", | |
"15 Noe Juarez 1052734731465949_1052795288126560 \n", | |
"16 Elsi Hernandez Lopez 1052734731465949_1052796388126450 \n", | |
"17 Elsi Hernandez Lopez 1052734731465949_1052796404793115 \n", | |
"18 Gray Fox Die 1052734731465949_1052796481459774 \n", | |
"19 Peter Infante Cruz 1052734731465949_1052797171459705 \n", | |
"20 Erik Cruz 1052734731465949_1052797721459650 \n", | |
"21 Axel Gabino San Juan Bautizta 1052734731465949_1052799821459440 \n", | |
"22 Axel Gabino San Juan Bautizta 1052734731465949_1052800151459407 \n", | |
"23 Omar Suriano Calles 1052734731465949_1052800621459360 \n", | |
"24 Concepcion Zamora 1052734731465949_1052800978125991 \n", | |
"25 Jose Luis Serrano Lagunes 1052734731465949_1052802578125831 \n", | |
"26 Gonzalo Kaphwan 1052734731465949_1052803254792430 \n", | |
"27 Roger Rivas 1052734731465949_1052803408125748 \n", | |
"28 Marck Anthony 1052734731465949_1052804934792262 \n", | |
"29 Alfredo Alvarado 1052734731465949_1052805834792172 \n", | |
"30 Valentina Posadas 1052734731465949_1052806238125465 \n", | |
".. ... ... \n", | |
"531 Leonardo Rojas H 1052734731465949_1167015786666656 \n", | |
"532 Israel Bautista 1052734731465949_1011402615574795 \n", | |
"533 Lupi Rubio 1052734731465949_1011403168908073 \n", | |
"534 Margarito Ramirez Mendoza 1052734731465949_1011412155573841 \n", | |
"535 Manuel Martinez Garcia 1052734731465949_1011422658906124 \n", | |
"536 Fork Bautista 1052734731465949_1167052893329612 \n", | |
"537 Irene Hernandez 1052734731465949_1167053903329511 \n", | |
"538 Raul Malaga Cruz 1052734731465949_1011429478905442 \n", | |
"539 Amelia Cuellar 1052734731465949_1011434012238322 \n", | |
"540 Hilda Rojas 1052734731465949_1167062729995295 \n", | |
"541 Javier Alva Rex 1052734731465949_1011439922237731 \n", | |
"542 Elisa Rosendo Castillo 1052734731465949_1167105313324370 \n", | |
"543 Hortencia Galindo 1052734731465949_1167120353322866 \n", | |
"544 Alfred Garcia 1052734731465949_1011583748890015 \n", | |
"545 Ana Gabriela Estrada 1052734731465949_1011956045519452 \n", | |
"546 Ale Zamudio Cruz 1052734731465949_1167634389938129 \n", | |
"547 Ale Zamudio Cruz 1052734731465949_1167634623271439 \n", | |
"548 Mario Moreno 1052734731465949_1167637853271116 \n", | |
"549 Arturo Estudillo 1052734731465949_1167695349932033 \n", | |
"550 Rafael Aguilar García 1052734731465949_1167706059930962 \n", | |
"551 Hernandez Vallejo 1052734731465949_1167730699928498 \n", | |
"552 Carlos Daniel Espinoza 1052734731465949_1012102398838150 \n", | |
"553 Landy Castillo Sierra 1052734731465949_1167743733260528 \n", | |
"554 Joseph Tauroasesino 1052734731465949_1167964776571757 \n", | |
"555 Ceci Sanchez 1052734731465949_1168072516560983 \n", | |
"556 Isabel Alfaro 1052734731465949_1012459905469066 \n", | |
"557 Ricardo Hernandez 1052734731465949_1168143303220571 \n", | |
"558 Samm Sourdon 1052734731465949_1012526615462395 \n", | |
"559 Macario Lopez 1052734731465949_1168198759881692 \n", | |
"560 Joel Quevedo 1052734731465949_1012575425457514 \n", | |
"\n", | |
" message \\\n", | |
"0 igual que en Tamaulipas ya van para afuera por... \n", | |
"1 Y el pri por robar todo el dinero a la Uv y ci... \n", | |
"2 Yo \n", | |
"4 El pri está dando patadas de hogado, ya no pue... \n", | |
"5 No pasa nada eso dice nuestro gobernador puñal... \n", | |
"6 Ya vio que la gente de estado está hasta la ma... \n", | |
"7 NI UN VOTO PARA EL PRI. RATASSSSSSSS \n", | |
"8 PAN* \n", | |
"9 POR HABER GOLPEADO A LOS VIEJOS PENSIONADOS\\nP... \n", | |
"10 Fuera!!! \n", | |
"11 El pri no debería ni siquiera estar en las enc... \n", | |
"12 Eso, ya se esperaba de la maquinaria roja. Per... \n", | |
"13 Quien este durmiendo y que por una despensa qu... \n", | |
"14 \n", | |
"15 Todos son coructos y el pri ocupa el primer lu... \n", | |
"16 \n", | |
"17 \n", | |
"18 Sigan votando por el pri que les da miserias a... \n", | |
"19 Yo creo que el sr Miguel ángel va con todo y m... \n", | |
"20 Siempre es lo mismo con el pri carvallo donde ... \n", | |
"21 Q nos engañen otra ves una monos y hagamos la ... \n", | |
"22 \n", | |
"23 Es increíble k el pri este en segundo lugar en... \n", | |
"24 Ni un voto a el priiu \n", | |
"25 A chingar asu madre el pri del estado no mas pri \n", | |
"26 Jacobo Ceron , \n", | |
"27 FUERA FUERA EL PRI..JAJAJAJAJAJJAJA \n", | |
"28 Y 34% se me hace demasiado Jajajajjaja al Pri ... \n", | |
"29 Hay que darle el voto a yunes Linares,para sac... \n", | |
"30 \n", | |
".. ... \n", | |
"531 Chismosos!! Como inventan!!. \n", | |
"532 Arriba el peje entre ellos se tiran flores par... \n", | |
"533 Saludes. Disfruten paseo las s. Quiero \n", | |
"534 No se dejen engañar son patadas de ahogado que... \n", | |
"535 C corruptohico niñote \n", | |
"536 son puras mamadas la polita ya k le toke al pa... \n", | |
"537 sinvergüenzas no k moy limpios. Sus mapaches. ... \n", | |
"538 El pri no gana almenos qué juege sucio como ya... \n", | |
"539 Gobierno corrupto junto con todos los que se a... \n", | |
"540 Ni a cual ir todos lis partidos por política s... \n", | |
"541 Yunes Linares ganará aún con la lluvia de lodo. \n", | |
"542 #están desesperados y somos 7millones de votos... \n", | |
"543 Y la marrana sigue comiendo !!!!! \n", | |
"544 eso ya no es novedad \n", | |
"545 Todos los del pri son una bola de rrateros es ... \n", | |
"546 y pinche rata del Duarte muy tranquilo contod... \n", | |
"547 con su risa burlona para que vea \n", | |
"548 Ahora es cuando hay que darle con todo al PRI ... \n", | |
"549 Es una madriguera de ratas andan diario aca en... \n", | |
"550 Ya se lo cargo el payaso. Gracias a Fidel y La... \n", | |
"551 Solo dios puede ayudarnos \n", | |
"552 Por esos hijos de sptm este estado esta asi ya... \n", | |
"553 LLa desesperada guerra sucia del PRI contra e... \n", | |
"554 Ese puto del gobernador que pague lo que debe ... \n", | |
"555 Traga pinche gordo..mientras al estado lo unde... \n", | |
"556 Muy cierto \n", | |
"557 Pobres pendejos quieren seguir ordeñando la vaca. \n", | |
"558 a huevo no se imaginan estar en la cárcel y es... \n", | |
"559 Q gane el q el pueblo elija sin corrupción sin... \n", | |
"560 ay se esta tragando nuetros ipuestos concomida... \n", | |
"\n", | |
" message_clean categoria \n", | |
"0 [igual, que, tamaulipas, van, para, afuera, po... none \n", | |
"1 [pri, por, robar, todo, dinero, cierto, robo, ... none \n", | |
"2 [] none \n", | |
"4 [pri, esta, dando, patadas, hogado, puede, man... none \n", | |
"5 [pasa, nada, eso, dice, nuestro, gobernador, p... none \n", | |
"6 [vio, que, gente, estado, esta, hasta, madre, ... none \n", | |
"7 [voto, para, pri, ratassssssss] none \n", | |
"8 [pan] none \n", | |
"9 [por, haber, golpeado, los, viejos, pensionado... none \n", | |
"10 [fuera] none \n", | |
"11 [pri, deberia, siquiera, estar, las, encuestas... none \n", | |
"12 [eso, esperaba, maquinaria, roja, pero, aun, c... none \n", | |
"13 [quien, este, durmiendo, que, por, una, despen... none \n", | |
"14 [] none \n", | |
"15 [todos, son, coructos, pri, ocupa, primer, lug... none \n", | |
"16 [] none \n", | |
"17 [] none \n", | |
"18 [sigan, votando, por, pri, que, les, miserias,... none \n", | |
"19 [creo, que, miguel, angel, con, todo, conformo... none \n", | |
"20 [siempre, mismo, con, pri, carvallo, donde, an... none \n", | |
"21 [nos, engañen, otra, ves, una, monos, hagamos,... none \n", | |
"22 [] none \n", | |
"23 [increible, pri, este, segundo, lugar, encuesta] none \n", | |
"24 [voto, priiu] none \n", | |
"25 [chingar, asu, madre, pri, del, estado, mas, pri] none \n", | |
"26 [jacobo, ceron] none \n", | |
"27 [fuera, fuera, pri, jajajajajajjaja] none \n", | |
"28 [34%, hace, demasiado, jajajajjaja, pri, hay, ... none \n", | |
"29 [hay, que, darle, voto, yunes, linares, para, ... none \n", | |
"30 [] none \n", | |
".. ... ... \n", | |
"531 [chismosos, como, inventan] none \n", | |
"532 [arriba, peje, entre, ellos, tiran, flores, pa... none \n", | |
"533 [saludes, disfruten, paseo, las, quiero] none \n", | |
"534 [dejen, engañar, son, patadas, ahogado, que, e... none \n", | |
"535 [corruptohico, niñote] none \n", | |
"536 [son, puras, mamadas, polita, toke, pan, tambi... none \n", | |
"537 [sinvergüenzas, moy, limpios, sus, mapaches, l... none \n", | |
"538 [pri, gana, almenos, que, juege, sucio, como, ... none \n", | |
"539 [gobierno, corrupto, junto, con, todos, los, q... none \n", | |
"540 [cual, todos, lis, partidos, por, politica, so... none \n", | |
"541 [yunes, linares, ganara, aun, con, lluvia, lodo] none \n", | |
"542 [estan, desesperados, somos, 7millones, votos,... none \n", | |
"543 [marrana, sigue, comiendo] none \n", | |
"544 [eso, novedad] none \n", | |
"545 [todos, los, del, pri, son, una, bola, rratero... none \n", | |
"546 [pinche, rata, del, duarte, muy, tranquilo, co... none \n", | |
"547 [con, risa, burlona, para, que, vea] none \n", | |
"548 [ahora, cuando, hay, que, darle, con, todo, pr... none \n", | |
"549 [una, madriguera, ratas, andan, diario, aca, f... none \n", | |
"550 [cargo, payaso, gracias, fidel, gorda, duarte] none \n", | |
"551 [solo, dios, puede, ayudarnos] none \n", | |
"552 [por, esos, hijos, sptm, este, estado, esta, a... none \n", | |
"553 [lla, desesperada, guerra, sucia, del, pri, co... none \n", | |
"554 [ese, puto, del, gobernador, que, pague, que, ... none \n", | |
"555 [traga, pinche, gordo, mientras, estado, undes... none \n", | |
"556 [muy, cierto] none \n", | |
"557 [pobres, pendejos, quieren, seguir, ordeñando,... none \n", | |
"558 [huevo, imaginan, estar, carcel, estar, comien... none \n", | |
"559 [gane, pueblo, elija, sin, corrupcion, sin, pl... none \n", | |
"560 [esta, tragando, nuetros, ipuestos, concomidas... none \n", | |
"\n", | |
"[547 rows x 7 columns]" | |
] | |
}, | |
"execution_count": 531, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_df_categorización[comments_df_categorización[\"categoria\"] == \"none\"]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 543, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"'Todos los del pri son una bola de rrateros es momento de un cambio'" | |
] | |
}, | |
"execution_count": 543, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"comments_df_categorización.iloc[545][\"message\"]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 546, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"texto_post_11 =comments_df_categorización.iloc[545][\"message\"]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 547, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"([1.3020162605081804e-10, 4.838474579901545e-10],\n", | |
" {'anti-morena': 1.3020162605081804e-10, 'anti-pri': 4.838474579901545e-10})" | |
] | |
}, | |
"execution_count": 547, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"classify_message(texto_post_11)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Probemos clasificandose a si mismo" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 548, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"morena_post= comments_df_categorización.iloc[232][\"message\"]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 549, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"([8.776258782644729e-37, 1.709041247826042e-43],\n", | |
" {'anti-morena': 8.776258782644729e-37, 'anti-pri': 1.709041247826042e-43})" | |
] | |
}, | |
"execution_count": 549, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"classify_message(morena_post)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 550, | |
"metadata": { | |
"collapsed": false, | |
"scrolled": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"342\n" | |
] | |
} | |
], | |
"source": [ | |
"i = 0\n", | |
"for text in comments_df_categorización[\"message\"]:\n", | |
" output_lista, output_dict = classify_message(text)\n", | |
" if output_dict[\"anti-pri\"]>output_dict[\"anti-morena\"]:\n", | |
" i +=1\n", | |
"print(i)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 551, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"190\n" | |
] | |
} | |
], | |
"source": [ | |
"i = 0\n", | |
"for text in comments_df_categorización[\"message\"]:\n", | |
" output_lista, output_dict = classify_message(text)\n", | |
" if output_dict[\"anti-morena\"]>output_dict[\"anti-pri\"]:\n", | |
" i +=1\n", | |
"print(i)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": true | |
}, | |
"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": "3.4.1" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment