{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Data Science Academy - Python Fundamentos - Capítulo 6\n", "\n", "## Download: http://github.com/dsacademybr" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Stream de Dados do Twitter com MongoDB, Pandas e Scikit Learn" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Preparando a Conexão com o Twitter" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Instala o pacote tweepy\n", "!pip install tweepy" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Importando os módulos Tweepy, Datetime e Json\n", "from tweepy.streaming import StreamListener\n", "from tweepy import OAuthHandler\n", "from tweepy import Stream\n", "from datetime import datetime\n", "import json" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Veja no manual em pdf como criar sua API no Twitter e configure as suas chaves abaixo." ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Adicione aqui sua Consumer Key\n", "consumer_key = \"xxxxxxxxx\"" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Adicione aqui sua Consumer Secret \n", "consumer_secret = \"xxxxxxxxx\"" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Adicione aqui seu Access Token\n", "access_token = \"xxxxxxxxx\"" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Adicione aqui seu Access Token Secret\n", "access_token_secret = \"xxxxxxxxx\"" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Criando as chaves de autenticação\n", "auth = OAuthHandler(consumer_key, consumer_secret)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": true }, "outputs": [], "source": [ "auth.set_access_token(access_token, access_token_secret)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Criando uma classe para capturar os stream de dados do Twitter e \n", "# armazenar no MongoDB\n", "class MyListener(StreamListener):\n", " def on_data(self, dados):\n", " tweet = json.loads(dados)\n", " created_at = tweet[\"created_at\"]\n", " id_str = tweet[\"id_str\"]\n", " text = tweet[\"text\"]\n", " obj = {\"created_at\":created_at,\"id_str\":id_str,\"text\":text,}\n", " tweetind = col.insert_one(obj).inserted_id\n", " print (obj)\n", " return True" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Criando o objeto mylistener\n", "mylistener = MyListener()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Criando o objeto mystream\n", "mystream = Stream(auth, listener = mylistener)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Preparando a Conexão com o MongoDB" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Importando do PyMongo o módulo MongoClient\n", "from pymongo import MongoClient " ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Criando a conexão ao MongoDB\n", "client = MongoClient('localhost', 27017)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Criando o banco de dados twitterdb\n", "db = client.twitterdb" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Criando a collection \"col\"\n", "col = db.tweets " ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Criando uma lista de palavras chave para buscar nos Tweets\n", "keywords = ['Big Data', 'Python', 'Data Mining', 'Data Science']" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Coletando os Tweets" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "scrolled": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "{'created_at': 'Thu Apr 19 23:27:20 +0000 2018', 'id_str': '987110427745173504', 'text': '【必要な経験】\\n以下のコンピュータ関連の経験\\n・PC操作（Office等の一般的なアプリケーションの利用経験）\\n・Unix （Linux, MacOS等）上でのプログラミング経験（シェルスクリプト, C, Pythonなど）\\n・画… https://t.co/c3mkI6wAuE', '_id': ObjectId('5ad925d8b093151a487bc040')}\n", "{'created_at': 'Thu Apr 19 23:27:21 +0000 2018', 'id_str': '987110432581308417', 'text': 'RT @treventos: #Python, É hora de Aprender!\\n\\nhttps://t.co/VTx87nzEzx https://t.co/zIXwI3ch2E', '_id': ObjectId('5ad925d9b093151a487bc041')}\n", "{'created_at': 'Thu Apr 19 23:27:21 +0000 2018', 'id_str': '987110433109635072', 'text': 'RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初めて起動したらあいつ『ようこそ』とか言い出すんだよ。なーにがようこそだよ！人様の家に来てるんだから『お邪魔します』とか『よろしくお願いします』だろうが！」って言い出して爆笑した', '_id': ObjectId('5ad925d9b093151a487bc042')}\n", "{'created_at': 'Thu Apr 19 23:27:22 +0000 2018', 'id_str': '987110438721740800', 'text': 'Why airlines are finally poised to unlock Big Data to enhance the passenger experience https://t.co/4V8DJuPP4S #SPShotels #HotelProfs', '_id': ObjectId('5ad925dbb093151a487bc043')}\n", "{'created_at': 'Thu Apr 19 23:27:33 +0000 2018', 'id_str': '987110482635997185', 'text': \"RT @JonTrevithick: The first Python to utter, 'And now for something completely different' was actually Eric Idle, in the 2nd episode. http…\", '_id': ObjectId('5ad925e5b093151a487bc044')}\n", "{'created_at': 'Thu Apr 19 23:27:35 +0000 2018', 'id_str': '987110493641830400', 'text': '@LazyBeeScripts I plan to use my profits at serial spamming to help fund a Broadway production of Monty Python and… https://t.co/jaI1G8cdKr', '_id': ObjectId('5ad925e8b093151a487bc045')}\n", "{'created_at': 'Thu Apr 19 23:27:37 +0000 2018', 'id_str': '987110501439094785', 'text': 'RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部のAIセミナー行ってくるやでー」\\nぼく「おっいってらっしゃいませ」\\n\\n～今～\\n上司さんメール\\n「件名：助けて」\\n\\nぼく「一体何が」\\n\\n上司さんメール\\n「ずっとpython？とかいうプログラム…', '_id': ObjectId('5ad925eab093151a487bc046')}\n", "{'created_at': 'Thu Apr 19 23:27:38 +0000 2018', 'id_str': '987110504450555904', 'text': 'Importance of “Big Data” สำคัญสำหรับธุรกิจยุค 4.0 อย่างไร - https://t.co/UrnnyqaqkW #BigData #Business', '_id': ObjectId('5ad925eab093151a487bc047')}\n", "{'created_at': 'Thu Apr 19 23:27:38 +0000 2018', 'id_str': '987110504689627136', 'text': 'RT @DozenDolls: @yontengoP @Xatz よくある数式をあえて書かず、\\nNNライブラリもあえて使わず、\\npythonのnumpy行列計算のコードを積み重ねて\\n手書き文字認識が出来るとこまで解説する\\n「ゼロからはじめるディープラーニング」\\nというオライリー…', '_id': ObjectId('5ad925eab093151a487bc048')}\n", "{'created_at': 'Thu Apr 19 23:27:39 +0000 2018', 'id_str': '987110507545968640', 'text': 'RT @Akira_Kido_N: C# の Linq が python の２倍遅い、は嘘 on @Qiita https://t.co/vYr394r7ca', '_id': ObjectId('5ad925ebb093151a487bc049')}\n", "{'created_at': 'Thu Apr 19 23:27:41 +0000 2018', 'id_str': '987110514982404096', 'text': \"@redrock_bball Traded for a four'n'twenty and a killer python.\", '_id': ObjectId('5ad925edb093151a487bc04a')}\n", "{'created_at': 'Thu Apr 19 23:27:41 +0000 2018', 'id_str': '987110517318668288', 'text': 'RT @DozenDolls: @yontengoP @Xatz やべ、タイトル間違えてた\\n\\nhttps://t.co/FFIK8FEAYL\\n\\nこれね\\n原理的なところを独学独習したい人にはおすすめです\\n\\npython知らない人が読むと\\n件の上司の方のように\\npythonの説明ば…', '_id': ObjectId('5ad925edb093151a487bc04b')}\n", "{'created_at': 'Thu Apr 19 23:27:42 +0000 2018', 'id_str': '987110519269019649', 'text': 'RT @DozenDolls: @yontengoP @Xatz やべ、タイトル間違えてた\\n\\nhttps://t.co/FFIK8FEAYL\\n\\nこれね\\n原理的なところを独学独習したい人にはおすすめです\\n\\npython知らない人が読むと\\n件の上司の方のように\\npythonの説明ば…', '_id': ObjectId('5ad925eeb093151a487bc04c')}\n", "{'created_at': 'Thu Apr 19 23:27:45 +0000 2018', 'id_str': '987110532229582848', 'text': \"RT @carolecadwalla: Wow. This is BIG. @Arron_banks, are you listening to Brittany Kaiser give evidence? She's talking about transferring da…\", '_id': ObjectId('5ad925f1b093151a487bc04d')}\n", "{'created_at': 'Thu Apr 19 23:27:45 +0000 2018', 'id_str': '987110532732731392', 'text': 'tinterのラベルフレーム生成をクラスにまとめる時、フレームサイズを指示しないと表示されないのなんでだろ。packのオプションなしにすると表示されないけど、適当にサイズ指定すると表示される。\\n#python #tkinter #プログラミング初心者', '_id': ObjectId('5ad925f1b093151a487bc04e')}\n", "{'created_at': 'Thu Apr 19 23:27:45 +0000 2018', 'id_str': '987110534318145536', 'text': 'RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部のAIセミナー行ってくるやでー」\\nぼく「おっいってらっしゃいませ」\\n\\n～今～\\n上司さんメール\\n「件名：助けて」\\n\\nぼく「一体何が」\\n\\n上司さんメール\\n「ずっとpython？とかいうプログラム…', '_id': ObjectId('5ad925f2b093151a487bc04f')}\n", "{'created_at': 'Thu Apr 19 23:27:46 +0000 2018', 'id_str': '987110536230948864', 'text': '@leyasupls @HanAlolaSH si tu as un compte netflix, ya les monty python (très cool) et one punch man, pour rigoler un peu', '_id': ObjectId('5ad925f2b093151a487bc050')}\n", "{'created_at': 'Thu Apr 19 23:27:47 +0000 2018', 'id_str': '987110540714631169', 'text': 'have and climb python milkman No to with #diorsauvage', '_id': ObjectId('5ad925f3b093151a487bc051')}\n", "{'created_at': 'Thu Apr 19 23:27:49 +0000 2018', 'id_str': '987110550290087937', 'text': 'Fun consequence of functions as first class values, if you mindlessly call print(print) instead of what you were tr… https://t.co/ye96i1GxFM', '_id': ObjectId('5ad925f5b093151a487bc052')}\n", "{'created_at': 'Thu Apr 19 23:27:52 +0000 2018', 'id_str': '987110564559138816', 'text': 'RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなりアグレッシブで\\n「じゃあその場で講師がpythonをライブコーディングして書いて、観客からは適宜、歓声や罵声、指摘や質問が飛ぶ」\\nという尖りまくった内容らしい。\\n\\nなお上司さんはプログラ…', '_id': ObjectId('5ad925f9b093151a487bc053')}\n", "{'created_at': 'Thu Apr 19 23:27:58 +0000 2018', 'id_str': '987110586910556160', 'text': 'RT @Avery1776: @BenKTallmadge @JohnBrennan A FEW MORE MENTIONS\\nUnderwear Bomber\\nDrone Wars\\nSpying on Congress\\nHacking the State Dept\\n\"Moder…', '_id': ObjectId('5ad925feb093151a487bc054')}\n", "{'created_at': 'Thu Apr 19 23:27:59 +0000 2018', 'id_str': '987110593390759936', 'text': 'RT @DozenDolls: @yontengoP @Xatz よくある数式をあえて書かず、\\nNNライブラリもあえて使わず、\\npythonのnumpy行列計算のコードを積み重ねて\\n手書き文字認識が出来るとこまで解説する\\n「ゼロからはじめるディープラーニング」\\nというオライリー…', '_id': ObjectId('5ad925ffb093151a487bc055')}\n", "{'created_at': 'Thu Apr 19 23:28:00 +0000 2018', 'id_str': '987110598352629762', 'text': '@AlexCatto_ i could go a killer python right about now', '_id': ObjectId('5ad92601b093151a487bc056')}\n", "{'created_at': 'Thu Apr 19 23:28:03 +0000 2018', 'id_str': '987110608855281665', 'text': 'RT @drbiomass: Why are data science leaders running for the exit? https://t.co/RJBTLqg7hA #AI #MachineLearning #BigData #DataScience #FinTe…', '_id': ObjectId('5ad92603b093151a487bc057')}\n", "{'created_at': 'Thu Apr 19 23:28:06 +0000 2018', 'id_str': '987110623367413760', 'text': 'RT @BigDataBlogs: Data Science: Top 100 Influencers, Brands and Publications » https://t.co/bYkM2gyAFf #DataScientist #BigData', '_id': ObjectId('5ad92607b093151a487bc058')}\n", "{'created_at': 'Thu Apr 19 23:28:08 +0000 2018', 'id_str': '987110629071728640', 'text': 'My day-old, new pc’s OS install malfunctioned due to a known bug in the latest update, and needed to be clean insta… https://t.co/wn3FDDjDwd', '_id': ObjectId('5ad92608b093151a487bc059')}\n", "{'created_at': 'Thu Apr 19 23:28:15 +0000 2018', 'id_str': '987110657626587137', 'text': 'RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部のAIセミナー行ってくるやでー」\\nぼく「おっいってらっしゃいませ」\\n\\n～今～\\n上司さんメール\\n「件名：助けて」\\n\\nぼく「一体何が」\\n\\n上司さんメール\\n「ずっとpython？とかいうプログラム…', '_id': ObjectId('5ad9260fb093151a487bc05a')}\n", "{'created_at': 'Thu Apr 19 23:28:16 +0000 2018', 'id_str': '987110665251831813', 'text': \"RT @kevinarnovitz: Snakes in a backpack. How Robert Covington's python, TJ McConnell's coffee addiction, JJ Redick's fascination with Simul…\", '_id': ObjectId('5ad92611b093151a487bc05b')}\n", "{'created_at': 'Thu Apr 19 23:28:17 +0000 2018', 'id_str': '987110668313640960', 'text': 'RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなりアグレッシブで\\n「じゃあその場で講師がpythonをライブコーディングして書いて、観客からは適宜、歓声や罵声、指摘や質問が飛ぶ」\\nという尖りまくった内容らしい。\\n\\nなお上司さんはプログラ…', '_id': ObjectId('5ad92611b093151a487bc05c')}\n", "{'created_at': 'Thu Apr 19 23:28:18 +0000 2018', 'id_str': '987110672776552448', 'text': \"RT @onyematomorrow4: Retweeted Mary Mkemdi (@NkemdiMary):\\n\\nI hope the python Governor don't send his dancing pythons to attack the striking…\", '_id': ObjectId('5ad92613b093151a487bc05d')}\n", "{'created_at': 'Thu Apr 19 23:28:27 +0000 2018', 'id_str': '987110708167913472', 'text': '@Chet_Cannon @ChiefFabulous https://t.co/MhOIjDuZVl', '_id': ObjectId('5ad9261bb093151a487bc05e')}\n", "{'created_at': 'Thu Apr 19 23:28:28 +0000 2018', 'id_str': '987110714996211712', 'text': 'オラクル、JavaやJavaScript、Ruby、Pythonなど多言語対応を単一ランタイムで実現する「GraalVM」をオープンソースで公開。Twitterが本番環境で採用 － Publickey https://t.co/sAFBRKz2hb', '_id': ObjectId('5ad9261db093151a487bc05f')}\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'created_at': 'Thu Apr 19 23:28:29 +0000 2018', 'id_str': '987110717999407104', 'text': 'RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初めて起動したらあいつ『ようこそ』とか言い出すんだよ。なーにがようこそだよ！人様の家に来てるんだから『お邪魔します』とか『よろしくお願いします』だろうが！」って言い出して爆笑した', '_id': ObjectId('5ad9261db093151a487bc060')}\n", "{'created_at': 'Thu Apr 19 23:28:30 +0000 2018', 'id_str': '987110720683753472', 'text': 'RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初めて起動したらあいつ『ようこそ』とか言い出すんだよ。なーにがようこそだよ！人様の家に来てるんだから『お邪魔します』とか『よろしくお願いします』だろうが！」って言い出して爆笑した', '_id': ObjectId('5ad9261eb093151a487bc061')}\n", "{'created_at': 'Thu Apr 19 23:28:34 +0000 2018', 'id_str': '987110738677284864', 'text': \"@toygrind Transformers '86\\nHot Fuzz\\nMonty Python and the Holy Grail\\nThe Big Lebowski\", '_id': ObjectId('5ad92622b093151a487bc062')}\n", "{'created_at': 'Thu Apr 19 23:28:38 +0000 2018', 'id_str': '987110756935139328', 'text': 'Really excited for what @wesmckinn is planning https://t.co/O2iuz4fsvY', '_id': ObjectId('5ad92627b093151a487bc063')}\n", "{'created_at': 'Thu Apr 19 23:28:39 +0000 2018', 'id_str': '987110758826827777', 'text': 'Python Developer, #Cambridge, Cambridgeshire, £40,000 - £55,000/annum\\xa0 #python https://t.co/ap3pyKS6cx', '_id': ObjectId('5ad92627b093151a487bc064')}\n", "{'created_at': 'Thu Apr 19 23:28:40 +0000 2018', 'id_str': '987110765852110848', 'text': '@MoeAkikaede 错了，给我一个前端我用不来，只能用基于这个前端的wp主题…并且HTML和PHP也才学起走…\\nc语言和Python对我来说太遥远🌚', '_id': ObjectId('5ad92629b093151a487bc065')}\n", "{'created_at': 'Thu Apr 19 23:28:43 +0000 2018', 'id_str': '987110776262492160', 'text': 'RT @IainLJBrown: Calgary sports fans are having more fun because of big data\\n\\nRead more here: https://t.co/gl3ciyEtZY\\n\\n#BigData #DataScienc…', '_id': ObjectId('5ad9262bb093151a487bc066')}\n", "{'created_at': 'Thu Apr 19 23:28:45 +0000 2018', 'id_str': '987110783657168896', 'text': \"RT @DrDenaGrayson: 🔥PALANTIR🔥\\n\\nIt's far past time for #Palantir founder/#Facebook board member Peter THIEL's turn in the barrel‼️\\n\\nPalantir…\", '_id': ObjectId('5ad9262db093151a487bc067')}\n", "{'created_at': 'Thu Apr 19 23:28:46 +0000 2018', 'id_str': '987110789285797889', 'text': 'RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初めて起動したらあいつ『ようこそ』とか言い出すんだよ。なーにがようこそだよ！人様の家に来てるんだから『お邪魔します』とか『よろしくお願いします』だろうが！」って言い出して爆笑した', '_id': ObjectId('5ad9262eb093151a487bc068')}\n", "{'created_at': 'Thu Apr 19 23:28:47 +0000 2018', 'id_str': '987110793417129984', 'text': 'RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部のAIセミナー行ってくるやでー」\\nぼく「おっいってらっしゃいませ」\\n\\n～今～\\n上司さんメール\\n「件名：助けて」\\n\\nぼく「一体何が」\\n\\n上司さんメール\\n「ずっとpython？とかいうプログラム…', '_id': ObjectId('5ad9262fb093151a487bc069')}\n", "{'created_at': 'Thu Apr 19 23:28:50 +0000 2018', 'id_str': '987110807577096192', 'text': 'RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなりアグレッシブで\\n「じゃあその場で講師がpythonをライブコーディングして書いて、観客からは適宜、歓声や罵声、指摘や質問が飛ぶ」\\nという尖りまくった内容らしい。\\n\\nなお上司さんはプログラ…', '_id': ObjectId('5ad92633b093151a487bc06a')}\n", "{'created_at': 'Thu Apr 19 23:28:52 +0000 2018', 'id_str': '987110816427139074', 'text': 'RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部のAIセミナー行ってくるやでー」\\nぼく「おっいってらっしゃいませ」\\n\\n～今～\\n上司さんメール\\n「件名：助けて」\\n\\nぼく「一体何が」\\n\\n上司さんメール\\n「ずっとpython？とかいうプログラム…', '_id': ObjectId('5ad92635b093151a487bc06b')}\n", "{'created_at': 'Thu Apr 19 23:28:57 +0000 2018', 'id_str': '987110836907855872', 'text': '#OMX #ProjectShivom #Blockchain #healthcare #genomics #cryptocurrency https://t.co/sP0H2w4WYv', '_id': ObjectId('5ad9263ab093151a487bc06c')}\n", "{'created_at': 'Thu Apr 19 23:28:59 +0000 2018', 'id_str': '987110845514575872', 'text': 'RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなりアグレッシブで\\n「じゃあその場で講師がpythonをライブコーディングして書いて、観客からは適宜、歓声や罵声、指摘や質問が飛ぶ」\\nという尖りまくった内容らしい。\\n\\nなお上司さんはプログラ…', '_id': ObjectId('5ad9263cb093151a487bc06d')}\n", "{'created_at': 'Thu Apr 19 23:29:01 +0000 2018', 'id_str': '987110852116574208', 'text': 'また発音悩む系\\nhttps://t.co/P0acOjBTCQ\\nオラクル、JavaやJavaScript、Ruby、Pythonなど多言語対応を単一ランタイムで実現する「GraalVM」をオープンソースで公開。Twitterが本番環境で採用', '_id': ObjectId('5ad9263eb093151a487bc06e')}\n", "{'created_at': 'Thu Apr 19 23:29:03 +0000 2018', 'id_str': '987110859980681216', 'text': 'RT @tictoc: Palantir is using War on Terror tools to track American citizens. The scary thing? The data-mining company is desperate for new…', '_id': ObjectId('5ad9263fb093151a487bc06f')}\n" ] }, { "ename": "KeyboardInterrupt", "evalue": "", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mWantReadError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/urllib3/contrib/pyopenssl.py\u001b[0m in \u001b[0;36mrecv_into\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 279\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 280\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconnection\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 281\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mOpenSSL\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSSL\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSysCallError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/OpenSSL/SSL.py\u001b[0m in \u001b[0;36mrecv_into\u001b[0;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[1;32m 1624\u001b[0m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_lib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSSL_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_ssl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbuf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnbytes\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1625\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_raise_ssl_error\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_ssl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1626\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/OpenSSL/SSL.py\u001b[0m in \u001b[0;36m_raise_ssl_error\u001b[0;34m(self, ssl, result)\u001b[0m\n\u001b[1;32m 1430\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0merror\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0m_lib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSSL_ERROR_WANT_READ\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1431\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mWantReadError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1432\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0merror\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0m_lib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSSL_ERROR_WANT_WRITE\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;31mWantReadError\u001b[0m: ", "\nDuring handling of the above exception, another exception occurred:\n", "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Iniciando o filtro e gravando os tweets no MongoDB\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mmystream\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfilter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrack\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mkeywords\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/tweepy/streaming.py\u001b[0m in \u001b[0;36mfilter\u001b[0;34m(self, follow, track, async, locations, stall_warnings, languages, encoding, filter_level)\u001b[0m\n\u001b[1;32m 448\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msession\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparams\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m'delimited'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'length'\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 449\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhost\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'stream.twitter.com'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 450\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_start\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0masync\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 451\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 452\u001b[0m def sitestream(self, follow, stall_warnings=False,\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/tweepy/streaming.py\u001b[0m in \u001b[0;36m_start\u001b[0;34m(self, async)\u001b[0m\n\u001b[1;32m 362\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_thread\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstart\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 363\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 364\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_run\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 365\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 366\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mon_closed\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mresp\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/tweepy/streaming.py\u001b[0m in \u001b[0;36m_run\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 264\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msnooze_time\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msnooze_time_step\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 265\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlistener\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_connect\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 266\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_read_loop\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresp\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 267\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mTimeout\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mssl\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSSLError\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 268\u001b[0m \u001b[0;31m# This is still necessary, as a SSLError can actually be\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/tweepy/streaming.py\u001b[0m in \u001b[0;36m_read_loop\u001b[0;34m(self, resp)\u001b[0m\n\u001b[1;32m 314\u001b[0m \u001b[0mlength\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 315\u001b[0m \u001b[0;32mwhile\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mresp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mraw\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclosed\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 316\u001b[0;31m \u001b[0mline\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbuf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_line\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstrip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 317\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mline\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 318\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlistener\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeep_alive\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# keep-alive new lines are expected\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/tweepy/streaming.py\u001b[0m in \u001b[0;36mread_line\u001b[0;34m(self, sep)\u001b[0m\n\u001b[1;32m 179\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 180\u001b[0m \u001b[0mstart\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_buffer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 181\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_buffer\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stream\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_chunk_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 182\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0msix\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mb\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m''\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 183\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/urllib3/response.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, amt, decode_content, cache_content)\u001b[0m\n\u001b[1;32m 382\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 383\u001b[0m \u001b[0mcache_content\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 384\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_fp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mamt\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 385\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mamt\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0;36m0\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# Platform-specific: Buggy versions of Python.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 386\u001b[0m \u001b[0;31m# Close the connection when no data is returned\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/http/client.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, amt)\u001b[0m\n\u001b[1;32m 447\u001b[0m \u001b[0;31m# Amount is given, implement using readinto\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 448\u001b[0m \u001b[0mb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbytearray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mamt\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 449\u001b[0;31m \u001b[0mn\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreadinto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 450\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mmemoryview\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mn\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtobytes\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 451\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/http/client.py\u001b[0m in \u001b[0;36mreadinto\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m 481\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 482\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mchunked\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 483\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_readinto_chunked\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 484\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 485\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlength\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/http/client.py\u001b[0m in \u001b[0;36m_readinto_chunked\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m 576\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 577\u001b[0m \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 578\u001b[0;31m \u001b[0mchunk_left\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_chunk_left\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 579\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mchunk_left\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 580\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mtotal_bytes\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/http/client.py\u001b[0m in \u001b[0;36m_get_chunk_left\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 544\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_safe_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# toss the CRLF at the end of the chunk\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 545\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 546\u001b[0;31m \u001b[0mchunk_left\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_read_next_chunk_size\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 547\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 548\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mIncompleteRead\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mb''\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/http/client.py\u001b[0m in \u001b[0;36m_read_next_chunk_size\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 504\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_read_next_chunk_size\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 505\u001b[0m \u001b[0;31m# Read the next chunk size from the file\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 506\u001b[0;31m \u001b[0mline\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreadline\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_MAXLINE\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 507\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mline\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0m_MAXLINE\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 508\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mLineTooLong\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"chunk size\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/socket.py\u001b[0m in \u001b[0;36mreadinto\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m 584\u001b[0m \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 585\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 586\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sock\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 587\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 588\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_timeout_occurred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/urllib3/contrib/pyopenssl.py\u001b[0m in \u001b[0;36mrecv_into\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 290\u001b[0m \u001b[0;32mraise\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 291\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mOpenSSL\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSSL\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mWantReadError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 292\u001b[0;31m \u001b[0mrd\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mutil\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait_for_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msocket\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msocket\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgettimeout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 293\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mrd\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 294\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'The read operation timed out'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/urllib3/util/wait.py\u001b[0m in \u001b[0;36mwait_for_read\u001b[0;34m(socks, timeout)\u001b[0m\n\u001b[1;32m 31\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0moptionally\u001b[0m \u001b[0ma\u001b[0m \u001b[0msingle\u001b[0m \u001b[0msocket\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mpassed\u001b[0m \u001b[0;32min\u001b[0m\u001b[0;34m.\u001b[0m \u001b[0mReturns\u001b[0m \u001b[0ma\u001b[0m \u001b[0mlist\u001b[0m \u001b[0mof\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 32\u001b[0m sockets that can be read from immediately. \"\"\"\n\u001b[0;32m---> 33\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0m_wait_for_io_events\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msocks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mEVENT_READ\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 34\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 35\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/urllib3/util/wait.py\u001b[0m in \u001b[0;36m_wait_for_io_events\u001b[0;34m(socks, events, timeout)\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[0mselector\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mregister\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msock\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mevents\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 25\u001b[0m return [key[0].fileobj for key in\n\u001b[0;32m---> 26\u001b[0;31m selector.select(timeout) if key[1] & events]\n\u001b[0m\u001b[1;32m 27\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 28\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/urllib3/util/selectors.py\u001b[0m in \u001b[0;36mselect\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m 511\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 512\u001b[0m kevent_list = _syscall_wrapper(self._kqueue.control, True,\n\u001b[0;32m--> 513\u001b[0;31m None, max_events, timeout)\n\u001b[0m\u001b[1;32m 514\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 515\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mkevent\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mkevent_list\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/urllib3/util/selectors.py\u001b[0m in \u001b[0;36m_syscall_wrapper\u001b[0;34m(func, _, *args, **kwargs)\u001b[0m\n\u001b[1;32m 62\u001b[0m and recalculate their timeouts. \"\"\"\n\u001b[1;32m 63\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 64\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 65\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mOSError\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mIOError\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mselect\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merror\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 66\u001b[0m \u001b[0merrcode\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;31mKeyboardInterrupt\u001b[0m: " ] } ], "source": [ "# Iniciando o filtro e gravando os tweets no MongoDB\n", "mystream.filter(track=keywords)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## --> Pressione o botão Stop na barra de ferramentas para encerrar a captura dos Tweets" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Consultando os Dados no MongoDB" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "collapsed": true }, "outputs": [], "source": [ "mystream.disconnect()" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'_id': ObjectId('5ad925d8b093151a487bc040'),\n", " 'created_at': 'Thu Apr 19 23:27:20 +0000 2018',\n", " 'id_str': '987110427745173504',\n", " 'text': '【必要な経験】\\n以下のコンピュータ関連の経験\\n・PC操作（Office等の一般的なアプリケーションの利用経験）\\n・Unix （Linux, MacOS等）上でのプログラミング経験（シェルスクリプト, C, Pythonなど）\\n・画… https://t.co/c3mkI6wAuE'}" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Verificando um documento no collection\n", "col.find_one()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Análise de Dados com Pandas e Scikit-Learn" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# criando um dataset com dados retornados do MongoDB\n", "dataset = [{\"created_at\": item[\"created_at\"], \"text\": item[\"text\"],} for item in col.find()]" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Importando o módulo Pandas para trabalhar com datasets em Python\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Criando um dataframe a partir do dataset \n", "df = pd.DataFrame(dataset)" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
created_attext
0Thu Apr 19 23:27:20 +0000 2018【必要な経験】\\n以下のコンピュータ関連の経験\\n・PC操作（Office等の一般的なアプリ...
1Thu Apr 19 23:27:21 +0000 2018RT @treventos: #Python, É hora de Aprender!\\n\\...
2Thu Apr 19 23:27:21 +0000 2018RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初め...
3Thu Apr 19 23:27:22 +0000 2018Why airlines are finally poised to unlock Big ...
4Thu Apr 19 23:27:33 +0000 2018RT @JonTrevithick: The first Python to utter, ...
5Thu Apr 19 23:27:35 +0000 2018@LazyBeeScripts I plan to use my profits at se...
6Thu Apr 19 23:27:37 +0000 2018RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部の...
7Thu Apr 19 23:27:38 +0000 2018Importance of “Big Data” สำคัญสำหรับธุรกิจยุค ...
8Thu Apr 19 23:27:38 +0000 2018RT @DozenDolls: @yontengoP @Xatz よくある数式をあえて書かず...
9Thu Apr 19 23:27:39 +0000 2018RT @Akira_Kido_N: C# の Linq が python の２倍遅い、は嘘 ...
10Thu Apr 19 23:27:41 +0000 2018@redrock_bball Traded for a four'n'twenty and ...
11Thu Apr 19 23:27:41 +0000 2018RT @DozenDolls: @yontengoP @Xatz やべ、タイトル間違えてた\\...
12Thu Apr 19 23:27:42 +0000 2018RT @DozenDolls: @yontengoP @Xatz やべ、タイトル間違えてた\\...
13Thu Apr 19 23:27:45 +0000 2018RT @carolecadwalla: Wow. This is BIG. @Arron_b...
14Thu Apr 19 23:27:45 +0000 2018tinterのラベルフレーム生成をクラスにまとめる時、フレームサイズを指示しないと表示されな...
15Thu Apr 19 23:27:45 +0000 2018RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部の...
16Thu Apr 19 23:27:46 +0000 2018@leyasupls @HanAlolaSH si tu as un compte netf...
17Thu Apr 19 23:27:47 +0000 2018have and climb python milkman No to with #dior...
18Thu Apr 19 23:27:49 +0000 2018Fun consequence of functions as first class va...
19Thu Apr 19 23:27:52 +0000 2018RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなり...
20Thu Apr 19 23:27:58 +0000 2018RT @Avery1776: @BenKTallmadge @JohnBrennan A F...
21Thu Apr 19 23:27:59 +0000 2018RT @DozenDolls: @yontengoP @Xatz よくある数式をあえて書かず...
22Thu Apr 19 23:28:00 +0000 2018@AlexCatto_ i could go a killer python right a...
23Thu Apr 19 23:28:03 +0000 2018RT @drbiomass: Why are data science leaders ru...
24Thu Apr 19 23:28:06 +0000 2018RT @BigDataBlogs: Data Science: Top 100 Influe...
25Thu Apr 19 23:28:08 +0000 2018My day-old, new pc’s OS install malfunctioned ...
26Thu Apr 19 23:28:15 +0000 2018RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部の...
27Thu Apr 19 23:28:16 +0000 2018RT @kevinarnovitz: Snakes in a backpack. How R...
28Thu Apr 19 23:28:17 +0000 2018RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなり...
29Thu Apr 19 23:28:18 +0000 2018RT @onyematomorrow4: Retweeted Mary Mkemdi (@N...
30Thu Apr 19 23:28:27 +0000 2018@Chet_Cannon @ChiefFabulous https://t.co/MhOIj...
31Thu Apr 19 23:28:28 +0000 2018オラクル、JavaやJavaScript、Ruby、Pythonなど多言語対応を単一ランタイ...
32Thu Apr 19 23:28:29 +0000 2018RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初め...
33Thu Apr 19 23:28:30 +0000 2018RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初め...
34Thu Apr 19 23:28:34 +0000 2018@toygrind Transformers '86\\nHot Fuzz\\nMonty Py...
35Thu Apr 19 23:28:38 +0000 2018Really excited for what @wesmckinn is planning...
36Thu Apr 19 23:28:39 +0000 2018Python Developer, #Cambridge, Cambridgeshire, ...
37Thu Apr 19 23:28:40 +0000 2018@MoeAkikaede 错了，给我一个前端我用不来，只能用基于这个前端的wp主题…并且HT...
38Thu Apr 19 23:28:43 +0000 2018RT @IainLJBrown: Calgary sports fans are havin...
39Thu Apr 19 23:28:45 +0000 2018RT @DrDenaGrayson: 🔥PALANTIR🔥\\n\\nIt's far past...
40Thu Apr 19 23:28:46 +0000 2018RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初め...
41Thu Apr 19 23:28:47 +0000 2018RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部の...
42Thu Apr 19 23:28:50 +0000 2018RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなり...
43Thu Apr 19 23:28:52 +0000 2018RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部の...
44Thu Apr 19 23:28:57 +0000 2018#OMX #ProjectShivom #Blockchain #healthcare #g...
45Thu Apr 19 23:28:59 +0000 2018RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなり...
46Thu Apr 19 23:29:01 +0000 2018また発音悩む系\\nhttps://t.co/P0acOjBTCQ\\nオラクル、JavaやJa...
47Thu Apr 19 23:29:03 +0000 2018RT @tictoc: Palantir is using War on Terror to...
\n", "
" ], "text/plain": [ " created_at \\\n", "0 Thu Apr 19 23:27:20 +0000 2018 \n", "1 Thu Apr 19 23:27:21 +0000 2018 \n", "2 Thu Apr 19 23:27:21 +0000 2018 \n", "3 Thu Apr 19 23:27:22 +0000 2018 \n", "4 Thu Apr 19 23:27:33 +0000 2018 \n", "5 Thu Apr 19 23:27:35 +0000 2018 \n", "6 Thu Apr 19 23:27:37 +0000 2018 \n", "7 Thu Apr 19 23:27:38 +0000 2018 \n", "8 Thu Apr 19 23:27:38 +0000 2018 \n", "9 Thu Apr 19 23:27:39 +0000 2018 \n", "10 Thu Apr 19 23:27:41 +0000 2018 \n", "11 Thu Apr 19 23:27:41 +0000 2018 \n", "12 Thu Apr 19 23:27:42 +0000 2018 \n", "13 Thu Apr 19 23:27:45 +0000 2018 \n", "14 Thu Apr 19 23:27:45 +0000 2018 \n", "15 Thu Apr 19 23:27:45 +0000 2018 \n", "16 Thu Apr 19 23:27:46 +0000 2018 \n", "17 Thu Apr 19 23:27:47 +0000 2018 \n", "18 Thu Apr 19 23:27:49 +0000 2018 \n", "19 Thu Apr 19 23:27:52 +0000 2018 \n", "20 Thu Apr 19 23:27:58 +0000 2018 \n", "21 Thu Apr 19 23:27:59 +0000 2018 \n", "22 Thu Apr 19 23:28:00 +0000 2018 \n", "23 Thu Apr 19 23:28:03 +0000 2018 \n", "24 Thu Apr 19 23:28:06 +0000 2018 \n", "25 Thu Apr 19 23:28:08 +0000 2018 \n", "26 Thu Apr 19 23:28:15 +0000 2018 \n", "27 Thu Apr 19 23:28:16 +0000 2018 \n", "28 Thu Apr 19 23:28:17 +0000 2018 \n", "29 Thu Apr 19 23:28:18 +0000 2018 \n", "30 Thu Apr 19 23:28:27 +0000 2018 \n", "31 Thu Apr 19 23:28:28 +0000 2018 \n", "32 Thu Apr 19 23:28:29 +0000 2018 \n", "33 Thu Apr 19 23:28:30 +0000 2018 \n", "34 Thu Apr 19 23:28:34 +0000 2018 \n", "35 Thu Apr 19 23:28:38 +0000 2018 \n", "36 Thu Apr 19 23:28:39 +0000 2018 \n", "37 Thu Apr 19 23:28:40 +0000 2018 \n", "38 Thu Apr 19 23:28:43 +0000 2018 \n", "39 Thu Apr 19 23:28:45 +0000 2018 \n", "40 Thu Apr 19 23:28:46 +0000 2018 \n", "41 Thu Apr 19 23:28:47 +0000 2018 \n", "42 Thu Apr 19 23:28:50 +0000 2018 \n", "43 Thu Apr 19 23:28:52 +0000 2018 \n", "44 Thu Apr 19 23:28:57 +0000 2018 \n", "45 Thu Apr 19 23:28:59 +0000 2018 \n", "46 Thu Apr 19 23:29:01 +0000 2018 \n", "47 Thu Apr 19 23:29:03 +0000 2018 \n", "\n", " text \n", "0 【必要な経験】\\n以下のコンピュータ関連の経験\\n・PC操作（Office等の一般的なアプリ... \n", "1 RT @treventos: #Python, É hora de Aprender!\\n\\... \n", "2 RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初め... \n", "3 Why airlines are finally poised to unlock Big ... \n", "4 RT @JonTrevithick: The first Python to utter, ... \n", "5 @LazyBeeScripts I plan to use my profits at se... \n", "6 RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部の... \n", "7 Importance of “Big Data” สำคัญสำหรับธุรกิจยุค ... \n", "8 RT @DozenDolls: @yontengoP @Xatz よくある数式をあえて書かず... \n", "9 RT @Akira_Kido_N: C# の Linq が python の２倍遅い、は嘘 ... \n", "10 @redrock_bball Traded for a four'n'twenty and ... \n", "11 RT @DozenDolls: @yontengoP @Xatz やべ、タイトル間違えてた\\... \n", "12 RT @DozenDolls: @yontengoP @Xatz やべ、タイトル間違えてた\\... \n", "13 RT @carolecadwalla: Wow. This is BIG. @Arron_b... \n", "14 tinterのラベルフレーム生成をクラスにまとめる時、フレームサイズを指示しないと表示されな... \n", "15 RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部の... \n", "16 @leyasupls @HanAlolaSH si tu as un compte netf... \n", "17 have and climb python milkman No to with #dior... \n", "18 Fun consequence of functions as first class va... \n", "19 RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなり... \n", "20 RT @Avery1776: @BenKTallmadge @JohnBrennan A F... \n", "21 RT @DozenDolls: @yontengoP @Xatz よくある数式をあえて書かず... \n", "22 @AlexCatto_ i could go a killer python right a... \n", "23 RT @drbiomass: Why are data science leaders ru... \n", "24 RT @BigDataBlogs: Data Science: Top 100 Influe... \n", "25 My day-old, new pc’s OS install malfunctioned ... \n", "26 RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部の... \n", "27 RT @kevinarnovitz: Snakes in a backpack. How R... \n", "28 RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなり... \n", "29 RT @onyematomorrow4: Retweeted Mary Mkemdi (@N... \n", "30 @Chet_Cannon @ChiefFabulous https://t.co/MhOIj... \n", "31 オラクル、JavaやJavaScript、Ruby、Pythonなど多言語対応を単一ランタイ... \n", "32 RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初め... \n", "33 RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初め... \n", "34 @toygrind Transformers '86\\nHot Fuzz\\nMonty Py... \n", "35 Really excited for what @wesmckinn is planning... \n", "36 Python Developer, #Cambridge, Cambridgeshire, ... \n", "37 @MoeAkikaede 错了，给我一个前端我用不来，只能用基于这个前端的wp主题…并且HT... \n", "38 RT @IainLJBrown: Calgary sports fans are havin... \n", "39 RT @DrDenaGrayson: 🔥PALANTIR🔥\\n\\nIt's far past... \n", "40 RT @_nametaketakewo: Pythonの授業の教員が「Mac買った時さ、初め... \n", "41 RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部の... \n", "42 RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなり... \n", "43 RT @yontengoP: ～午前中～\\n上司さん「俺もAIとか勉強するために今日は外部の... \n", "44 #OMX #ProjectShivom #Blockchain #healthcare #g... \n", "45 RT @yontengoP: 休憩中に電話で聞いたところでは、IT寄りセミナーの中でもかなり... \n", "46 また発音悩む系\\nhttps://t.co/P0acOjBTCQ\\nオラクル、JavaやJa... \n", "47 RT @tictoc: Palantir is using War on Terror to... " ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Imprimindo o dataframe\n", "df" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Importando o módulo Scikit Learn\n", "from sklearn.feature_extraction.text import CountVectorizer" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Usando o método CountVectorizer para criar uma matriz de documentos\n", "cv = CountVectorizer()\n", "count_matrix = cv.fit_transform(df.text)" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
wordcount
0rt29
1co20
2https20
3python14
4the13
5yontengop13
6to11
7ぼく10
8上司さんメール10
9and7
10for6
11data6
12ずっとpython5
13とかいうプログラム5
14件名5
15一体何が5
16上司さん5
17big5
18おっいってらっしゃいませ5
19俺もaiとか勉強するために今日は外部のaiセミナー行ってくるやでー5
20of5
21助けて5
22午前中5
23休憩中に電話で聞いたところでは4
24in4
25ようこそ4
26だろうが4
27it寄りセミナーの中でもかなりアグレッシブで4
28_nametaketakewo4
29is4
30なお上司さんはプログラ4
31なーにがようこそだよ4
32よろしくお願いします4
33とか言い出すんだよ4
34指摘や質問が飛ぶ4
35とか4
36という尖りまくった内容らしい4
37歓声や罵声4
38are4
39観客からは適宜4
40xatz4
41じゃあその場で講師がpythonをライブコーディングして書いて4
42mac買った時さ4
43palantir4
44bigdata4
45dozendolls4
46pythonの授業の教員が4
47人様の家に来てるんだから4
48お邪魔します4
49初めて起動したらあいつ4
\n", "
" ], "text/plain": [ " word count\n", "0 rt 29\n", "1 co 20\n", "2 https 20\n", "3 python 14\n", "4 the 13\n", "5 yontengop 13\n", "6 to 11\n", "7 ぼく 10\n", "8 上司さんメール 10\n", "9 and 7\n", "10 for 6\n", "11 data 6\n", "12 ずっとpython 5\n", "13 とかいうプログラム 5\n", "14 件名 5\n", "15 一体何が 5\n", "16 上司さん 5\n", "17 big 5\n", "18 おっいってらっしゃいませ 5\n", "19 俺もaiとか勉強するために今日は外部のaiセミナー行ってくるやでー 5\n", "20 of 5\n", "21 助けて 5\n", "22 午前中 5\n", "23 休憩中に電話で聞いたところでは 4\n", "24 in 4\n", "25 ようこそ 4\n", "26 だろうが 4\n", "27 it寄りセミナーの中でもかなりアグレッシブで 4\n", "28 _nametaketakewo 4\n", "29 is 4\n", "30 なお上司さんはプログラ 4\n", "31 なーにがようこそだよ 4\n", "32 よろしくお願いします 4\n", "33 とか言い出すんだよ 4\n", "34 指摘や質問が飛ぶ 4\n", "35 とか 4\n", "36 という尖りまくった内容らしい 4\n", "37 歓声や罵声 4\n", "38 are 4\n", "39 観客からは適宜 4\n", "40 xatz 4\n", "41 じゃあその場で講師がpythonをライブコーディングして書いて 4\n", "42 mac買った時さ 4\n", "43 palantir 4\n", "44 bigdata 4\n", "45 dozendolls 4\n", "46 pythonの授業の教員が 4\n", "47 人様の家に来てるんだから 4\n", "48 お邪魔します 4\n", "49 初めて起動したらあいつ 4" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Contando o número de ocorrências das principais palavras em nosso dataset\n", "word_count = pd.DataFrame(cv.get_feature_names(), columns=[\"word\"])\n", "word_count[\"count\"] = count_matrix.sum(axis=0).tolist()[0]\n", "word_count = word_count.sort_values(\"count\", ascending=False).reset_index(drop=True)\n", "word_count[:50]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Fim" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Obrigado - Data Science Academy - facebook.com/dsacademybr" ] } ], "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": "3.6.5" } }, "nbformat": 4, "nbformat_minor": 1 }