diff --git a/your-code/challenge-1.ipynb b/your-code/challenge-1.ipynb index 0808166..5749699 100644 --- a/your-code/challenge-1.ipynb +++ b/your-code/challenge-1.ipynb @@ -66,9 +66,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "'ironhack s q website is'" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "def clean_up(s):\n", " \"\"\"\n", @@ -79,7 +90,19 @@ "\n", " Returns:\n", " A string that has been cleaned up.\n", - " \"\"\"" + " \"\"\"\n", + " import re\n", + " \n", + " # remove URLs\n", + " s = re.sub(r'http.+', '', s)\n", + " \n", + " # remove special characters\n", + " s = re.sub(r'[^a-zA-Z\\s]+', ' ', s)\n", + " \n", + " return \" \".join([word for word in s.lower().split()])\n", + " \n", + "\n", + "clean_up(\"@Ironhack's-#Q website 776-is http://ironhack.com [(2018)]\\\")\")" ] }, { @@ -101,10 +124,35 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[nltk_data] Downloading package punkt to\n", + "[nltk_data] /Users/rickardramhoj/nltk_data...\n", + "[nltk_data] Package punkt is already up-to-date!\n" + ] + }, + { + "data": { + "text/plain": [ + "['ironhack', 's', 'q', 'website', 'is']" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ + "# import nltk and tokenizer\n", + "import nltk\n", + "from nltk.tokenize import word_tokenize\n", + "nltk.download(\"punkt\")\n", + "\n", "def tokenize(s):\n", " \"\"\"\n", " Tokenize a string.\n", @@ -114,7 +162,12 @@ "\n", " Returns:\n", " A list of words as the result of tokenization.\n", - " \"\"\"" + " \"\"\"\n", + " \n", + " return [word.lower() for word in word_tokenize(s) if word.isalpha()]\n", + "\n", + "# test it\n", + "tokenize(\"ironhack s q website is\")" ] }, { @@ -145,9 +198,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[nltk_data] Downloading package wordnet to\n", + "[nltk_data] /Users/rickardramhoj/nltk_data...\n", + "[nltk_data] Package wordnet is already up-to-date!\n" + ] + }, + { + "data": { + "text/plain": [ + "['ironhack', 's', 'q', 'websit', 'is']" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "def stem_and_lemmatize(l):\n", " \"\"\"\n", @@ -158,7 +231,33 @@ "\n", " Returns:\n", " A list of strings after being stemmed and lemmatized.\n", - " \"\"\"" + " \"\"\"\n", + " \n", + " # import libraries\n", + " from nltk.stem import PorterStemmer\n", + " nltk.download(\"wordnet\")\n", + " from nltk.stem import WordNetLemmatizer\n", + " \n", + " #initiate stemmer \n", + " stemmer = PorterStemmer()\n", + " \n", + " # initiate lemmatizer\n", + " lemmatizer = WordNetLemmatizer()\n", + " \n", + " # define list\n", + " new_list = []\n", + " \n", + " # loop words and append lemmatized and stemmed\n", + " for word in l:\n", + " lemmatized = lemmatizer.lemmatize(word)\n", + " new_list.append(stemmer.stem(lemmatized))\n", + " #new_list.append({\"stemmed\": stemmer.stem(word), \"lemmatized\": lemmatizer.lemmatize(word)})\n", + " \n", + " return new_list\n", + " \n", + "# test it\n", + "stem_and_lemmatize(['ironhack', 's', 'q', 'website', 'is'])\n", + " " ] }, { @@ -176,9 +275,29 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 12, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[nltk_data] Downloading package stopwords to\n", + "[nltk_data] /Users/rickardramhoj/nltk_data...\n", + "[nltk_data] Package stopwords is already up-to-date!\n" + ] + }, + { + "data": { + "text/plain": [ + "['ironhack', 'q', 'websit']" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "def remove_stopwords(l):\n", " \"\"\"\n", @@ -189,7 +308,18 @@ "\n", " Returns:\n", " A list of strings after stop words are removed.\n", - " \"\"\"" + " \"\"\"\n", + " \n", + " # import stopwords\n", + " nltk.download(\"stopwords\")\n", + " from nltk.corpus import stopwords\n", + " \n", + " return [word for word in l if word not in stopwords.words()]\n", + "\n", + "# test it\n", + "remove_stopwords(['ironhack', 's', 'q', 'websit', 'is'])\n", + " \n", + " " ] }, { @@ -204,7 +334,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -218,7 +348,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.7.6" } }, "nbformat": 4, diff --git a/your-code/challenge-2.ipynb b/your-code/challenge-2.ipynb index 6b0e116..b3f6d9d 100644 --- a/your-code/challenge-2.ipynb +++ b/your-code/challenge-2.ipynb @@ -46,11 +46,120 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, - "outputs": [], + "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", + "
targetiddateflagusertext
51429302190584004Tue Jun 16 03:08:48 PDT 2009NO_QUERYVicki_Geei miss nikki nu nu already shes always there ...
14228201881451988Fri May 22 04:42:15 PDT 2009NO_QUERYPatCashinSo I had a dream last night. I remember a sig...
40372702058252964Sat Jun 06 14:34:17 PDT 2009NO_QUERYdeelectable@girlyghost ohh poor sickly you (((hugs)) ho...
64950302237307600Fri Jun 19 05:34:22 PDT 2009NO_QUERYjustinekepait is raining again
61078902224301193Thu Jun 18 09:20:06 PDT 2009NO_QUERYcmatt007@MissKeriBaby wish I was in LA right now
\n", + "
" + ], + "text/plain": [ + " target id date flag \\\n", + "514293 0 2190584004 Tue Jun 16 03:08:48 PDT 2009 NO_QUERY \n", + "142282 0 1881451988 Fri May 22 04:42:15 PDT 2009 NO_QUERY \n", + "403727 0 2058252964 Sat Jun 06 14:34:17 PDT 2009 NO_QUERY \n", + "649503 0 2237307600 Fri Jun 19 05:34:22 PDT 2009 NO_QUERY \n", + "610789 0 2224301193 Thu Jun 18 09:20:06 PDT 2009 NO_QUERY \n", + "\n", + " user text \n", + "514293 Vicki_Gee i miss nikki nu nu already shes always there ... \n", + "142282 PatCashin So I had a dream last night. I remember a sig... \n", + "403727 deelectable @girlyghost ohh poor sickly you (((hugs)) ho... \n", + "649503 justinekepa it is raining again \n", + "610789 cmatt007 @MissKeriBaby wish I was in LA right now " + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "# import pandas\n", + "import pandas as pd\n", + "\n", + "# load data limited to 20000 rows\n", + "tweets = pd.read_csv(\"/Users/rickardramhoj/Downloads/training.1600000.processed.noemoticon.csv\", names=['target','id','date','flag','user','text'], encoding = 'latin-1').sample(n=20000, random_state=1)\n", + "\n", + "# look at data\n", + "tweets.head()" ] }, { @@ -76,11 +185,234 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 2, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[nltk_data] Downloading package punkt to\n", + "[nltk_data] /Users/rickardramhoj/nltk_data...\n", + "[nltk_data] Package punkt is already up-to-date!\n", + "[nltk_data] Downloading package wordnet to\n", + "[nltk_data] /Users/rickardramhoj/nltk_data...\n", + "[nltk_data] Package wordnet is already up-to-date!\n", + "[nltk_data] Downloading package stopwords to\n", + "[nltk_data] /Users/rickardramhoj/nltk_data...\n", + "[nltk_data] Package stopwords is already up-to-date!\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
targetiddateflagusertexttext_processed
51429302190584004Tue Jun 16 03:08:48 PDT 2009NO_QUERYVicki_Geei miss nikki nu nu already shes always there ...[miss, nikki, alreadi, alway, need, thank, xxx]
14228201881451988Fri May 22 04:42:15 PDT 2009NO_QUERYPatCashinSo I had a dream last night. I remember a sig...[dream, last, night, rememb, sign, clearli, to...
40372702058252964Sat Jun 06 14:34:17 PDT 2009NO_QUERYdeelectable@girlyghost ohh poor sickly you (((hugs)) ho...[girlyghost, ohh, poor, sickli, hug, hope, fee...
64950302237307600Fri Jun 19 05:34:22 PDT 2009NO_QUERYjustinekepait is raining again[rain]
61078902224301193Thu Jun 18 09:20:06 PDT 2009NO_QUERYcmatt007@MissKeriBaby wish I was in LA right now[misskeribabi, wish, wa, right]
\n", + "
" + ], + "text/plain": [ + " target id date flag \\\n", + "514293 0 2190584004 Tue Jun 16 03:08:48 PDT 2009 NO_QUERY \n", + "142282 0 1881451988 Fri May 22 04:42:15 PDT 2009 NO_QUERY \n", + "403727 0 2058252964 Sat Jun 06 14:34:17 PDT 2009 NO_QUERY \n", + "649503 0 2237307600 Fri Jun 19 05:34:22 PDT 2009 NO_QUERY \n", + "610789 0 2224301193 Thu Jun 18 09:20:06 PDT 2009 NO_QUERY \n", + "\n", + " user text \\\n", + "514293 Vicki_Gee i miss nikki nu nu already shes always there ... \n", + "142282 PatCashin So I had a dream last night. I remember a sig... \n", + "403727 deelectable @girlyghost ohh poor sickly you (((hugs)) ho... \n", + "649503 justinekepa it is raining again \n", + "610789 cmatt007 @MissKeriBaby wish I was in LA right now \n", + "\n", + " text_processed \n", + "514293 [miss, nikki, alreadi, alway, need, thank, xxx] \n", + "142282 [dream, last, night, rememb, sign, clearli, to... \n", + "403727 [girlyghost, ohh, poor, sickli, hug, hope, fee... \n", + "649503 [rain] \n", + "610789 [misskeribabi, wish, wa, right] " + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "# import nltk and tokenizer\n", + "import nltk\n", + "from nltk.tokenize import word_tokenize\n", + "nltk.download(\"punkt\")\n", + "from nltk.stem import PorterStemmer\n", + "nltk.download(\"wordnet\")\n", + "from nltk.stem import WordNetLemmatizer\n", + "nltk.download(\"stopwords\")\n", + "from nltk.corpus import stopwords\n", + "\n", + "# define functions\n", + "def clean_up(s):\n", + " \"\"\"\n", + " Cleans up numbers, URLs, and special characters from a string.\n", + "\n", + " Args:\n", + " s: The string to be cleaned up.\n", + "\n", + " Returns:\n", + " A string that has been cleaned up.\n", + " \"\"\"\n", + " import re\n", + " \n", + " # remove URLs\n", + " s = re.sub(r'http.+', '', s)\n", + " \n", + " # remove special characters\n", + " s = re.sub(r'[^a-zA-Z\\s]+', ' ', s)\n", + " \n", + " return \" \".join([word for word in s.lower().split()])\n", + "\n", + "def tokenize(s):\n", + " \"\"\"\n", + " Tokenize a string.\n", + "\n", + " Args:\n", + " s: String to be tokenized.\n", + "\n", + " Returns:\n", + " A list of words as the result of tokenization.\n", + " \"\"\"\n", + " \n", + " return [word.lower() for word in word_tokenize(s) if word.isalpha()]\n", + "\n", + "def stem_and_lemmatize(l):\n", + " \"\"\"\n", + " Perform stemming and lemmatization on a list of words.\n", + "\n", + " Args:\n", + " l: A list of strings.\n", + "\n", + " Returns:\n", + " A list of strings after being stemmed and lemmatized.\n", + " \"\"\"\n", + " \n", + " #initiate stemmer \n", + " stemmer = PorterStemmer()\n", + " \n", + " # initiate lemmatizer\n", + " lemmatizer = WordNetLemmatizer()\n", + " \n", + " # define list\n", + " new_list = []\n", + " \n", + " # loop words and append lemmatized and stemmed\n", + " for word in l:\n", + " lemmatized = lemmatizer.lemmatize(word)\n", + " new_list.append(stemmer.stem(lemmatized))\n", + " #new_list.append({\"stemmed\": stemmer.stem(word), \"lemmatized\": lemmatizer.lemmatize(word)})\n", + " \n", + " return new_list\n", + "\n", + "def remove_stopwords(l):\n", + " \"\"\"\n", + " Remove English stopwords from a list of strings.\n", + "\n", + " Args:\n", + " l: A list of strings.\n", + "\n", + " Returns:\n", + " A list of strings after stop words are removed.\n", + " \"\"\"\n", + " \n", + " return [word for word in l if word not in stopwords.words()]\n", + "\n", + "tweets[\"text_processed\"] = tweets[\"text\"].apply(clean_up)\n", + "tweets[\"text_processed\"] = tweets[\"text_processed\"].apply(tokenize)\n", + "tweets[\"text_processed\"] = tweets[\"text_processed\"].apply(stem_and_lemmatize)\n", + "tweets[\"text_processed\"] = tweets[\"text_processed\"].apply(remove_stopwords)\n", + "\n", + "# check dataframe\n", + "tweets.head()" ] }, { @@ -98,11 +430,1034 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "['go',\n", + " 'get',\n", + " 'wa',\n", + " 'day',\n", + " 'good',\n", + " 'like',\n", + " 'love',\n", + " 'work',\n", + " 'got',\n", + " 'quot',\n", + " 'time',\n", + " 'today',\n", + " 'miss',\n", + " 'lol',\n", + " 'thank',\n", + " 'back',\n", + " 'realli',\n", + " 'know',\n", + " 'think',\n", + " 'see',\n", + " 'feel',\n", + " 'amp',\n", + " 'watch',\n", + " 'need',\n", + " 'still',\n", + " 'night',\n", + " 'well',\n", + " 'make',\n", + " 'hope',\n", + " 'oh',\n", + " 'home',\n", + " 'new',\n", + " 'look',\n", + " 'twitter',\n", + " 'much',\n", + " 'last',\n", + " 'wish',\n", + " 'morn',\n", + " 'great',\n", + " 'wait',\n", + " 'sad',\n", + " 'tomorrow',\n", + " 'would',\n", + " 'sleep',\n", + " 'haha',\n", + " 'right',\n", + " 'whi',\n", + " 'follow',\n", + " 'thing',\n", + " 'fun',\n", + " 'tonight',\n", + " 'onli',\n", + " 'happi',\n", + " 'week',\n", + " 'friend',\n", + " 'bad',\n", + " 'nice',\n", + " 'veri',\n", + " 'sorri',\n", + " 'hi',\n", + " 'say',\n", + " 'way',\n", + " 'better',\n", + " 'school',\n", + " 'could',\n", + " 'hate',\n", + " 'yeah',\n", + " 'bed',\n", + " 'start',\n", + " 'tweet',\n", + " 'peopl',\n", + " 'gon',\n", + " 'though',\n", + " 'hour',\n", + " 'show',\n", + " 'even',\n", + " 'guy',\n", + " 'weekend',\n", + " 'ye',\n", + " 'life',\n", + " 'play',\n", + " 'everyon',\n", + " 'let',\n", + " 'final',\n", + " 'cant',\n", + " 'littl',\n", + " 'hey',\n", + " 'wan',\n", + " 'use',\n", + " 'movi',\n", + " 'lt',\n", + " 'rain',\n", + " 'sick',\n", + " 'year',\n", + " 'first',\n", + " 'ok',\n", + " 'tire',\n", + " 'find',\n", + " 'awesom',\n", + " 'x',\n", + " 'never',\n", + " 'next',\n", + " 'best',\n", + " 'soon',\n", + " 'ani',\n", + " 'talk',\n", + " 'call',\n", + " 'done',\n", + " 'head',\n", + " 'phone',\n", + " 'sure',\n", + " 'dont',\n", + " 'long',\n", + " 'alreadi',\n", + " 'help',\n", + " 'alway',\n", + " 'anoth',\n", + " 'hurt',\n", + " 'mayb',\n", + " 'keep',\n", + " 'pleas',\n", + " 'cool',\n", + " 'lot',\n", + " 'yay',\n", + " 'song',\n", + " 'someth',\n", + " 'girl',\n", + " 'eat',\n", + " 'made',\n", + " 'bore',\n", + " 'old',\n", + " 'enjoy',\n", + " 'suck',\n", + " 'leav',\n", + " 'yet',\n", + " 'ever',\n", + " 'read',\n", + " 'thought',\n", + " 'becaus',\n", + " 'lost',\n", + " 'ur',\n", + " 'readi',\n", + " 'away',\n", + " 'pretti',\n", + " 'actual',\n", + " 'finish',\n", + " 'live',\n", + " 'sound',\n", + " 'hous',\n", + " 'went',\n", + " 'excit',\n", + " 'listen',\n", + " 'hear',\n", + " 'game',\n", + " 'someon',\n", + " 'summer',\n", + " 'happen',\n", + " 'w',\n", + " 'left',\n", + " 'guess',\n", + " 'earli',\n", + " 'noth',\n", + " 'wonder',\n", + " 'befor',\n", + " 'b',\n", + " 'late',\n", + " 'babi',\n", + " 'job',\n", + " 'sinc',\n", + " 'doe',\n", + " 'tell',\n", + " 'omg',\n", + " 'glad',\n", + " 'ugh',\n", + " 'gone',\n", + " 'weather',\n", + " 'car',\n", + " 'mom',\n", + " 'kid',\n", + " 'p',\n", + " 'wow',\n", + " 'later',\n", + " 'saw',\n", + " 'beauti',\n", + " 'damn',\n", + " 'r',\n", + " 'amaz',\n", + " 'bit',\n", + " 'birthday',\n", + " 'stop',\n", + " 'mean',\n", + " 'big',\n", + " 'said',\n", + " 'check',\n", + " 'hot',\n", + " 'parti',\n", + " 'give',\n", + " 'sun',\n", + " 'god',\n", + " 'run',\n", + " 'may',\n", + " 'two',\n", + " 'updat',\n", + " 'shit',\n", + " 'must',\n", + " 'seem',\n", + " 'move',\n", + " 'world',\n", + " 'hard',\n", + " 'put',\n", + " 'iphon',\n", + " 'free',\n", + " 'cold',\n", + " 'luck',\n", + " 'yesterday',\n", + " 'th',\n", + " 'studi',\n", + " 'stay',\n", + " 'might',\n", + " 'meet',\n", + " 'month',\n", + " 'found',\n", + " 'book',\n", + " 'boy',\n", + " 'music',\n", + " 'friday',\n", + " 'lunch',\n", + " 'gt',\n", + " 'mani',\n", + " 'woke',\n", + " 'exam',\n", + " 'fuck',\n", + " 'aww',\n", + " 'buy',\n", + " 'shop',\n", + " 'tho',\n", + " 'around',\n", + " 'least',\n", + " 'monday',\n", + " 'post',\n", + " 'stuff',\n", + " 'clean',\n", + " 'cri',\n", + " 'famili',\n", + " 'okay',\n", + " 'anyth',\n", + " 'video',\n", + " 'xx',\n", + " 'forward',\n", + " 'drink',\n", + " 'welcom',\n", + " 'everyth',\n", + " 'sooo',\n", + " 'pictur',\n", + " 'busi',\n", + " 'believ',\n", + " 'hahaha',\n", + " 'drive',\n", + " 'food',\n", + " 'train',\n", + " 'stupid',\n", + " 'walk',\n", + " 'everi',\n", + " 'anyon',\n", + " 'sweet',\n", + " 'sunday',\n", + " 'probabl',\n", + " 'outsid',\n", + " 'win',\n", + " 'turn',\n", + " 'plan',\n", + " 'poor',\n", + " 'chang',\n", + " 'almost',\n", + " 'write',\n", + " 'hair',\n", + " 'far',\n", + " 'dad',\n", + " 'wrong',\n", + " 'dream',\n", + " 'place',\n", + " 'real',\n", + " 'cute',\n", + " 'kill',\n", + " 'ask',\n", + " 'rememb',\n", + " 'tv',\n", + " 'goodnight',\n", + " 'caus',\n", + " 'fan',\n", + " 'blog',\n", + " 'repli',\n", + " 'wake',\n", + " 'rest',\n", + " 'funni',\n", + " 'total',\n", + " 'quit',\n", + " 'eye',\n", + " 'worri',\n", + " 'anymor',\n", + " 'class',\n", + " 'room',\n", + " 'came',\n", + " 'hit',\n", + " 'dinner',\n", + " 'money',\n", + " 'true',\n", + " 'mother',\n", + " 'without',\n", + " 'sister',\n", + " 'els',\n", + " 'hang',\n", + " 'send',\n", + " 'offic',\n", + " 'news',\n", + " 'brother',\n", + " 'word',\n", + " 'seen',\n", + " 'whole',\n", + " 'danc',\n", + " 'aw',\n", + " 'onc',\n", + " 'open',\n", + " 'either',\n", + " 'vote',\n", + " 'took',\n", + " 'link',\n", + " 'pain',\n", + " 'break',\n", + " 'person',\n", + " 'headach',\n", + " 'coffe',\n", + " 'www',\n", + " 'half',\n", + " 'hehe',\n", + " 'saturday',\n", + " 'idea',\n", + " 'hug',\n", + " 'st',\n", + " 'bring',\n", + " 'hello',\n", + " 'anyway',\n", + " 'photo',\n", + " 'ah',\n", + " 'onlin',\n", + " 'text',\n", + " 'abl',\n", + " 'enough',\n", + " 'g',\n", + " 'set',\n", + " 'close',\n", + " 'full',\n", + " 'crap',\n", + " 'awww',\n", + " 'kinda',\n", + " 'jealou',\n", + " 'cours',\n", + " 'trip',\n", + " 'reason',\n", + " 'dude',\n", + " 'crazi',\n", + " 'fall',\n", + " 'comput',\n", + " 'fix',\n", + " 'season',\n", + " 'heard',\n", + " 'pm',\n", + " 'forgot',\n", + " 'didnt',\n", + " 'kind',\n", + " 'fine',\n", + " 'site',\n", + " 'heart',\n", + " 'wont',\n", + " 'interest',\n", + " 'bought',\n", + " 'high',\n", + " 'mr',\n", + " 'add',\n", + " 'visit',\n", + " 'rock',\n", + " 'pay',\n", + " 'awak',\n", + " 'favorit',\n", + " 'relax',\n", + " 'problem',\n", + " 'sunni',\n", + " 'super',\n", + " 'star',\n", + " 'red',\n", + " 'beach',\n", + " 'line',\n", + " 'learn',\n", + " 'ago',\n", + " 'soo',\n", + " 'cuz',\n", + " 'asleep',\n", + " 'dead',\n", + " 'smile',\n", + " 'mileycyru',\n", + " 'sign',\n", + " 'fail',\n", + " 'hell',\n", + " 'sore',\n", + " 'tommcfli',\n", + " 'ride',\n", + " 'math',\n", + " 'afternoon',\n", + " 'lose',\n", + " 'part',\n", + " 'serious',\n", + " 'mind',\n", + " 'lucki',\n", + " 'drop',\n", + " 'power',\n", + " 'congrat',\n", + " 'definit',\n", + " 'concert',\n", + " 'facebook',\n", + " 'ticket',\n", + " 'ladi',\n", + " 'instead',\n", + " 'email',\n", + " 'shower',\n", + " 'hand',\n", + " 'mad',\n", + " 'offici',\n", + " 'youtub',\n", + " 'breakfast',\n", + " 'short',\n", + " 'internet',\n", + " 'boo',\n", + " 'broke',\n", + " 'wear',\n", + " 'sometim',\n", + " 'order',\n", + " 'nd',\n", + " 'dear',\n", + " 'bet',\n", + " 'agre',\n", + " 'perfect',\n", + " 'btw',\n", + " 'park',\n", + " 'award',\n", + " 'gym',\n", + " 'catch',\n", + " 'togeth',\n", + " 'test',\n", + " 'team',\n", + " 'suppos',\n", + " 'figur',\n", + " 'sat',\n", + " 'homework',\n", + " 'mention',\n", + " 'june',\n", + " 'alon',\n", + " 'beat',\n", + " 'nap',\n", + " 'pack',\n", + " 'soooo',\n", + " 'pick',\n", + " 'yea',\n", + " 'sing',\n", + " 'lmao',\n", + " 'nite',\n", + " 'xxx',\n", + " 'second',\n", + " 'album',\n", + " 'stuck',\n", + " 'store',\n", + " 'wed',\n", + " 'sigh',\n", + " 'goin',\n", + " 'ice',\n", + " 'vacat',\n", + " 'air',\n", + " 'upload',\n", + " 'coupl',\n", + " 'water',\n", + " 'hungri',\n", + " 'cook',\n", + " 'cousin',\n", + " 'xd',\n", + " 'dress',\n", + " 'easi',\n", + " 'side',\n", + " 'laptop',\n", + " 'account',\n", + " 'holiday',\n", + " 'wors',\n", + " 'revis',\n", + " 'bless',\n", + " 'foot',\n", + " 'decid',\n", + " 'join',\n", + " 'mood',\n", + " 'spend',\n", + " 'point',\n", + " 'moment',\n", + " 'window',\n", + " 'stori',\n", + " 'save',\n", + " 'graduat',\n", + " 'past',\n", + " 'top',\n", + " 'sleepi',\n", + " 'ipod',\n", + " 'f',\n", + " 'current',\n", + " 'understand',\n", + " 'yep',\n", + " 'throat',\n", + " 'chanc',\n", + " 'town',\n", + " 'differ',\n", + " 'hmm',\n", + " 'told',\n", + " 'bout',\n", + " 'mtv',\n", + " 'cream',\n", + " 'annoy',\n", + " 'answer',\n", + " 'age',\n", + " 'mac',\n", + " 'forget',\n", + " 'road',\n", + " 'thursday',\n", + " 'tour',\n", + " 'fast',\n", + " 'load',\n", + " 'celebr',\n", + " 'realiz',\n", + " 'jonasbroth',\n", + " 'shoot',\n", + " 'camp',\n", + " 'scare',\n", + " 'cut',\n", + " 'co',\n", + " 'knew',\n", + " 'date',\n", + " 'ddlovato',\n", + " 'shirt',\n", + " 'episod',\n", + " 'fli',\n", + " 'chat',\n", + " 'ahhh',\n", + " 'complet',\n", + " 'kick',\n", + " 'fb',\n", + " 'lazi',\n", + " 'ive',\n", + " 'especi',\n", + " 'card',\n", + " 'ppl',\n", + " 'mum',\n", + " 'rather',\n", + " 'black',\n", + " 'download',\n", + " 'list',\n", + " 'tea',\n", + " 'chocol',\n", + " 'yr',\n", + " 'count',\n", + " 'expect',\n", + " 'cancel',\n", + " 'flight',\n", + " 'appl',\n", + " 'ate',\n", + " 'number',\n", + " 'film',\n", + " 'state',\n", + " 'bye',\n", + " 'pizza',\n", + " 'worst',\n", + " 'wtf',\n", + " 'wine',\n", + " 'juli',\n", + " 'present',\n", + " 'meant',\n", + " 'english',\n", + " 'manag',\n", + " 'share',\n", + " 'colleg',\n", + " 'sent',\n", + " 'servic',\n", + " 'ach',\n", + " 'question',\n", + " 'flu',\n", + " 'depress',\n", + " 'nope',\n", + " 'freak',\n", + " 'laugh',\n", + " 'smell',\n", + " 'unfortun',\n", + " 'due',\n", + " 'woman',\n", + " 'beer',\n", + " 'messag',\n", + " 'bitch',\n", + " 'worth',\n", + " 'search',\n", + " 'websit',\n", + " 'bike',\n", + " 'comment',\n", + " 'touch',\n", + " 'shoe',\n", + " 'parent',\n", + " 'church',\n", + " 'sunshin',\n", + " 'swim',\n", + " 'miley',\n", + " 'boyfriend',\n", + " 'pool',\n", + " 'stomach',\n", + " 'lil',\n", + " 'burn',\n", + " 'support',\n", + " 'followfriday',\n", + " 'mess',\n", + " 'lay',\n", + " 'weird',\n", + " 'leg',\n", + " 'bum',\n", + " 'appar',\n", + " 'becom',\n", + " 'father',\n", + " 'cake',\n", + " 'hill',\n", + " 'case',\n", + " 'airport',\n", + " 'event',\n", + " 'shame',\n", + " 'hr',\n", + " 'london',\n", + " 'surpris',\n", + " 'round',\n", + " 'tummi',\n", + " 'hmmm',\n", + " 'voic',\n", + " 'broken',\n", + " 'blue',\n", + " 'safe',\n", + " 'spent',\n", + " 'fell',\n", + " 'possibl',\n", + " 'practic',\n", + " 'type',\n", + " 'usual',\n", + " 'yummi',\n", + " 'insid',\n", + " 'stress',\n", + " 'warm',\n", + " 'absolut',\n", + " 'normal',\n", + " 'alright',\n", + " 'cheer',\n", + " 'moon',\n", + " 'idk',\n", + " 'hold',\n", + " 'horribl',\n", + " 'stand',\n", + " 'near',\n", + " 'page',\n", + " 'chill',\n", + " 'note',\n", + " 'shot',\n", + " 'doctor',\n", + " 'uk',\n", + " 'xoxo',\n", + " 'club',\n", + " 'fire',\n", + " 'pray',\n", + " 'huge',\n", + " 'taken',\n", + " 'ball',\n", + " 'cup',\n", + " 'slow',\n", + " 'shall',\n", + " 'cd',\n", + " 'scari',\n", + " 'deserv',\n", + " 'disappoint',\n", + " 'block',\n", + " 'box',\n", + " 'pass',\n", + " 'exactli',\n", + " 'green',\n", + " 'sooooo',\n", + " 'bro',\n", + " 'band',\n", + " 'paper',\n", + " 'confus',\n", + " 'terribl',\n", + " 'myspac',\n", + " 'ear',\n", + " 'tan',\n", + " 'notic',\n", + " 'except',\n", + " 'twitpic',\n", + " 'googl',\n", + " 'issu',\n", + " 'low',\n", + " 'doesnt',\n", + " 'lie',\n", + " 'fair',\n", + " 'sadli',\n", + " 'mile',\n", + " 'mate',\n", + " 'project',\n", + " 'app',\n", + " 'pop',\n", + " 'countri',\n", + " 'wit',\n", + " 'longer',\n", + " 'crash',\n", + " 'raini',\n", + " 'arm',\n", + " 'david',\n", + " 'cover',\n", + " 'sell',\n", + " 'wednesday',\n", + " 'sim',\n", + " 'shift',\n", + " 'finger',\n", + " 'woo',\n", + " 'hubbi',\n", + " 'fit',\n", + " 'gorgeou',\n", + " 'gosh',\n", + " 'ff',\n", + " 'hangov',\n", + " 'caught',\n", + " 'mail',\n", + " 'return',\n", + " 'luv',\n", + " 'fight',\n", + " 'earlier',\n", + " 'yup',\n", + " 'plu',\n", + " 'lame',\n", + " 'gave',\n", + " 'ahead',\n", + " 'invit',\n", + " 'connect',\n", + " 'act',\n", + " 'special',\n", + " 'nearli',\n", + " 'isnt',\n", + " 'prepar',\n", + " 'watchin',\n", + " 'via',\n", + " 'white',\n", + " 'taylor',\n", + " 'sort',\n", + " 'interview',\n", + " 'blackberri',\n", + " 'recommend',\n", + " 'tom',\n", + " 'argh',\n", + " 'guitar',\n", + " 'bill',\n", + " 'front',\n", + " 'offer',\n", + " 'fact',\n", + " 'piec',\n", + " 'upset',\n", + " 'joy',\n", + " 'glass',\n", + " 'radio',\n", + " 'tuesday',\n", + " 'xo',\n", + " 'matter',\n", + " 'fill',\n", + " 'inde',\n", + " 'exhaust',\n", + " 'self',\n", + " 'congratul',\n", + " 'avail',\n", + " 'deal',\n", + " 'lone',\n", + " 'chees',\n", + " 'version',\n", + " 'john',\n", + " 'breath',\n", + " 'proud',\n", + " 'product',\n", + " 'gig',\n", + " 'teeth',\n", + " 'blah',\n", + " 'quiet',\n", + " 'kiss',\n", + " 'view',\n", + " 'drunk',\n", + " 'fever',\n", + " 'singl',\n", + " 'forev',\n", + " 'folk',\n", + " 'gettin',\n", + " 'pink',\n", + " 'bird',\n", + " 'promis',\n", + " 'goodby',\n", + " 'everybodi',\n", + " 'experi',\n", + " 'quick',\n", + " 'import',\n", + " 'tune',\n", + " 'although',\n", + " 'daughter',\n", + " 'sexi',\n", + " 'sky',\n", + " 'aint',\n", + " 'grow',\n", + " 'small',\n", + " 'fantast',\n", + " 'bar',\n", + " 'three',\n", + " 'design',\n", + " 'nose',\n", + " 'huh',\n", + " 'thx',\n", + " 'lesson',\n", + " 'fish',\n", + " 'bday',\n", + " 'arriv',\n", + " 'storm',\n", + " 'mix',\n", + " 'seat',\n", + " 'lake',\n", + " 'daddi',\n", + " 'fav',\n", + " 'piss',\n", + " 'blood',\n", + " 'knee',\n", + " 'child',\n", + " 'havent',\n", + " 'middl',\n", + " 'memori',\n", + " 'bag',\n", + " 'group',\n", + " 'dvd',\n", + " 'dure',\n", + " 'art',\n", + " 'behind',\n", + " 'jack',\n", + " 'paint',\n", + " 'hospit',\n", + " 'swine',\n", + " 'futur',\n", + " 'perform',\n", + " 'magic',\n", + " 'cloth',\n", + " 'remind',\n", + " 'stick',\n", + " 'web',\n", + " 'australia',\n", + " 'releas',\n", + " 'dentist',\n", + " 'land',\n", + " 'appreci',\n", + " 'session',\n", + " 'ring',\n", + " 'bloodi',\n", + " 'track',\n", + " 'info',\n", + " 'peac',\n", + " 'ouch',\n", + " 'delet',\n", + " 'channel',\n", + " 'nail',\n", + " 'race',\n", + " 'addict',\n", + " 'ran',\n", + " 'ny',\n", + " 'bbq',\n", + " 'gut',\n", + " 'trend',\n", + " 'cooki',\n", + " 'tear',\n", + " 'camera',\n", + " 'joe',\n", + " 'french',\n", + " 'roll',\n", + " 'buddi',\n", + " 'system',\n", + " 'edit',\n", + " 'doubl',\n", + " 'twilight',\n", + " 'puppi',\n", + " 'tast',\n", + " 'ng',\n", + " 'nobodi',\n", + " 'histori',\n", + " 'jon',\n", + " 'chicken',\n", + " 'compani',\n", + " 'plz',\n", + " 'mommi',\n", + " 'feelin',\n", + " 'record',\n", + " 'light',\n", + " 'ohh',\n", + " 'dr',\n", + " 'young',\n", + " 'rule',\n", + " 'form',\n", + " 'garden',\n", + " 'neck',\n", + " 'felt',\n", + " 'badli',\n", + " 'dark',\n", + " 'street',\n", + " 'slept',\n", + " 'local',\n", + " 'continu',\n", + " 'adam',\n", + " 'yum',\n", + " 'shut',\n", + " 'ahh',\n", + " 'fri',\n", + " 'brain',\n", + " 'profil',\n", + " 'gay',\n", + " 'teacher',\n", + " 'davidarchi',\n", + " 'file',\n", + " 'jk',\n", + " 'travel',\n", + " 'nyc',\n", + " 'natur',\n", + " 'vip',\n", + " 'dunno',\n", + " 'suggest',\n", + " 'whatev',\n", + " 'dm',\n", + " 'allow',\n", + " 'trek',\n", + " 'inspir',\n", + " 'extra',\n", + " 'board',\n", + " 'four',\n", + " 'shoulder',\n", + " 'contact',\n", + " 'bowl',\n", + " 'space',\n", + " 'pl',\n", + " 'twit',\n", + " 'ooh',\n", + " 'entertain',\n", + " 'king',\n", + " 'babe',\n", + " 'rob',\n", + " 'laker',\n", + " 'tree',\n", + " 'festiv',\n", + " 'ruin',\n", + " 'random',\n", + " 'joke',\n", + " 'bear',\n", + " 'hahah',\n", + " 'gift',\n", + " 'trailer',\n", + " 'marri',\n", + " 'midnight',\n", + " 'bunch',\n", + " 'forc',\n", + " 'vega',\n", + " 'pc',\n", + " 'entir',\n", + " 'report',\n", + " 'essay',\n", + " 'shine',\n", + " 'plane',\n", + " 'apart',\n", + " 'fam',\n", + " 'alot',\n", + " 'kate',\n", + " 'wind',\n", + " 'inform',\n", + " 'paid',\n", + " 'hannah',\n", + " 'bright',\n", + " 'eh',\n", + " 'cloud',\n", + " 'along',\n", + " 'nick',\n", + " 'chines',\n", + " 'seriou',\n", + " 'mmm',\n", + " 'seri',\n", + " 'thru',\n", + " 'teach',\n", + " 'chillin',\n", + " 'bb',\n", + " 'key',\n", + " 'begin',\n", + " 'rip',\n", + " 'server',\n", + " 'mama',\n", + " 'sum',\n", + " ...]" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "# put together all words in a list\n", + "words = [item for sublist in tweets[\"text_processed\"] for item in sublist]\n", + "\n", + "# get frequency distribution\n", + "freqs = nltk.FreqDist(words)\n", + "\n", + "# select top 5000\n", + "top5000 = list(freqs)[:5000]\n", + "#top5000 = freqs.most_common(5000)\n", + "\n", + "top5000\n" ] }, { @@ -167,11 +1522,1050 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "({'go': False,\n", + " 'get': False,\n", + " 'wa': False,\n", + " 'day': False,\n", + " 'good': True,\n", + " 'like': False,\n", + " 'love': False,\n", + " 'work': False,\n", + " 'got': False,\n", + " 'quot': False,\n", + " 'time': False,\n", + " 'today': True,\n", + " 'miss': False,\n", + " 'lol': False,\n", + " 'thank': False,\n", + " 'back': False,\n", + " 'realli': False,\n", + " 'know': False,\n", + " 'think': False,\n", + " 'see': False,\n", + " 'feel': False,\n", + " 'amp': False,\n", + " 'watch': False,\n", + " 'need': True,\n", + " 'still': False,\n", + " 'night': False,\n", + " 'well': False,\n", + " 'make': False,\n", + " 'hope': False,\n", + " 'oh': False,\n", + " 'home': False,\n", + " 'new': False,\n", + " 'look': False,\n", + " 'twitter': False,\n", + " 'much': False,\n", + " 'last': False,\n", + " 'wish': False,\n", + " 'morn': False,\n", + " 'great': False,\n", + " 'wait': False,\n", + " 'sad': False,\n", + " 'tomorrow': False,\n", + " 'would': False,\n", + " 'sleep': False,\n", + " 'haha': False,\n", + " 'right': False,\n", + " 'whi': False,\n", + " 'follow': False,\n", + " 'thing': False,\n", + " 'fun': False,\n", + " 'tonight': False,\n", + " 'onli': False,\n", + " 'happi': True,\n", + " 'week': False,\n", + " 'friend': False,\n", + " 'bad': False,\n", + " 'nice': False,\n", + " 'veri': False,\n", + " 'sorri': False,\n", + " 'hi': False,\n", + " 'say': False,\n", + " 'way': False,\n", + " 'better': False,\n", + " 'school': False,\n", + " 'could': False,\n", + " 'hate': False,\n", + " 'yeah': False,\n", + " 'bed': False,\n", + " 'start': False,\n", + " 'tweet': False,\n", + " 'peopl': False,\n", + " 'gon': False,\n", + " 'though': False,\n", + " 'hour': False,\n", + " 'show': False,\n", + " 'even': False,\n", + " 'guy': False,\n", + " 'weekend': False,\n", + " 'ye': False,\n", + " 'life': False,\n", + " 'play': False,\n", + " 'everyon': False,\n", + " 'let': False,\n", + " 'final': False,\n", + " 'cant': False,\n", + " 'littl': False,\n", + " 'hey': False,\n", + " 'wan': False,\n", + " 'use': False,\n", + " 'movi': False,\n", + " 'lt': False,\n", + " 'rain': False,\n", + " 'sick': False,\n", + " 'year': False,\n", + " 'first': False,\n", + " 'ok': False,\n", + " 'tire': False,\n", + " 'find': True,\n", + " 'awesom': False,\n", + " 'x': False,\n", + " 'never': False,\n", + " 'next': False,\n", + " 'best': False,\n", + " 'soon': False,\n", + " 'ani': False,\n", + " 'talk': False,\n", + " 'call': False,\n", + " 'done': False,\n", + " 'head': False,\n", + " 'phone': False,\n", + " 'sure': False,\n", + " 'dont': False,\n", + " 'long': False,\n", + " 'alreadi': False,\n", + " 'help': False,\n", + " 'alway': False,\n", + " 'anoth': False,\n", + " 'hurt': False,\n", + " 'mayb': False,\n", + " 'keep': False,\n", + " 'pleas': False,\n", + " 'cool': False,\n", + " 'lot': False,\n", + " 'yay': False,\n", + " 'song': False,\n", + " 'someth': False,\n", + " 'girl': False,\n", + " 'eat': False,\n", + " 'made': False,\n", + " 'bore': False,\n", + " 'old': False,\n", + " 'enjoy': False,\n", + " 'suck': False,\n", + " 'leav': False,\n", + " 'yet': False,\n", + " 'ever': False,\n", + " 'read': False,\n", + " 'thought': False,\n", + " 'becaus': False,\n", + " 'lost': True,\n", + " 'ur': False,\n", + " 'readi': False,\n", + " 'away': False,\n", + " 'pretti': False,\n", + " 'actual': False,\n", + " 'finish': False,\n", + " 'live': False,\n", + " 'sound': False,\n", + " 'hous': False,\n", + " 'went': False,\n", + " 'excit': False,\n", + " 'listen': False,\n", + " 'hear': False,\n", + " 'game': False,\n", + " 'someon': False,\n", + " 'summer': False,\n", + " 'happen': False,\n", + " 'w': False,\n", + " 'left': False,\n", + " 'guess': False,\n", + " 'earli': False,\n", + " 'noth': False,\n", + " 'wonder': False,\n", + " 'befor': False,\n", + " 'b': False,\n", + " 'late': False,\n", + " 'babi': False,\n", + " 'job': False,\n", + " 'sinc': False,\n", + " 'doe': False,\n", + " 'tell': False,\n", + " 'omg': False,\n", + " 'glad': False,\n", + " 'ugh': False,\n", + " 'gone': False,\n", + " 'weather': False,\n", + " 'car': False,\n", + " 'mom': False,\n", + " 'kid': False,\n", + " 'p': False,\n", + " 'wow': False,\n", + " 'later': False,\n", + " 'saw': False,\n", + " 'beauti': False,\n", + " 'damn': False,\n", + " 'r': False,\n", + " 'amaz': False,\n", + " 'bit': False,\n", + " 'birthday': False,\n", + " 'stop': False,\n", + " 'mean': False,\n", + " 'big': False,\n", + " 'said': False,\n", + " 'check': False,\n", + " 'hot': False,\n", + " 'parti': True,\n", + " 'give': False,\n", + " 'sun': False,\n", + " 'god': False,\n", + " 'run': False,\n", + " 'may': False,\n", + " 'two': False,\n", + " 'updat': False,\n", + " 'shit': False,\n", + " 'must': False,\n", + " 'seem': False,\n", + " 'move': False,\n", + " 'world': False,\n", + " 'hard': False,\n", + " 'put': False,\n", + " 'iphon': False,\n", + " 'free': False,\n", + " 'cold': False,\n", + " 'luck': False,\n", + " 'yesterday': False,\n", + " 'th': False,\n", + " 'studi': False,\n", + " 'stay': False,\n", + " 'might': False,\n", + " 'meet': False,\n", + " 'month': False,\n", + " 'found': False,\n", + " 'book': False,\n", + " 'boy': False,\n", + " 'music': False,\n", + " 'friday': False,\n", + " 'lunch': False,\n", + " 'gt': False,\n", + " 'mani': False,\n", + " 'woke': False,\n", + " 'exam': False,\n", + " 'fuck': False,\n", + " 'aww': False,\n", + " 'buy': False,\n", + " 'shop': False,\n", + " 'tho': False,\n", + " 'around': False,\n", + " 'least': False,\n", + " 'monday': False,\n", + " 'post': False,\n", + " 'stuff': False,\n", + " 'clean': False,\n", + " 'cri': False,\n", + " 'famili': False,\n", + " 'okay': False,\n", + " 'anyth': False,\n", + " 'video': False,\n", + " 'xx': False,\n", + " 'forward': False,\n", + " 'drink': False,\n", + " 'welcom': False,\n", + " 'everyth': False,\n", + " 'sooo': False,\n", + " 'pictur': False,\n", + " 'busi': False,\n", + " 'believ': False,\n", + " 'hahaha': False,\n", + " 'drive': False,\n", + " 'food': False,\n", + " 'train': False,\n", + " 'stupid': False,\n", + " 'walk': False,\n", + " 'everi': False,\n", + " 'anyon': False,\n", + " 'sweet': False,\n", + " 'sunday': False,\n", + " 'probabl': False,\n", + " 'outsid': False,\n", + " 'win': False,\n", + " 'turn': False,\n", + " 'plan': False,\n", + " 'poor': False,\n", + " 'chang': False,\n", + " 'almost': False,\n", + " 'write': False,\n", + " 'hair': False,\n", + " 'far': False,\n", + " 'dad': False,\n", + " 'wrong': False,\n", + " 'dream': False,\n", + " 'place': False,\n", + " 'real': False,\n", + " 'cute': False,\n", + " 'kill': False,\n", + " 'ask': False,\n", + " 'rememb': False,\n", + " 'tv': False,\n", + " 'goodnight': False,\n", + " 'caus': False,\n", + " 'fan': False,\n", + " 'blog': False,\n", + " 'repli': False,\n", + " 'wake': False,\n", + " 'rest': False,\n", + " 'funni': False,\n", + " 'total': False,\n", + " 'quit': False,\n", + " 'eye': False,\n", + " 'worri': False,\n", + " 'anymor': False,\n", + " 'class': False,\n", + " 'room': False,\n", + " 'came': False,\n", + " 'hit': False,\n", + " 'dinner': False,\n", + " 'money': False,\n", + " 'true': False,\n", + " 'mother': False,\n", + " 'without': False,\n", + " 'sister': False,\n", + " 'els': False,\n", + " 'hang': False,\n", + " 'send': False,\n", + " 'offic': False,\n", + " 'news': False,\n", + " 'brother': False,\n", + " 'word': False,\n", + " 'seen': False,\n", + " 'whole': False,\n", + " 'danc': False,\n", + " 'aw': False,\n", + " 'onc': False,\n", + " 'open': False,\n", + " 'either': False,\n", + " 'vote': False,\n", + " 'took': True,\n", + " 'link': False,\n", + " 'pain': False,\n", + " 'break': False,\n", + " 'person': False,\n", + " 'headach': False,\n", + " 'coffe': False,\n", + " 'www': False,\n", + " 'half': False,\n", + " 'hehe': False,\n", + " 'saturday': False,\n", + " 'idea': False,\n", + " 'hug': False,\n", + " 'st': False,\n", + " 'bring': False,\n", + " 'hello': False,\n", + " 'anyway': False,\n", + " 'photo': False,\n", + " 'ah': False,\n", + " 'onlin': False,\n", + " 'text': False,\n", + " 'abl': False,\n", + " 'enough': False,\n", + " 'g': False,\n", + " 'set': False,\n", + " 'close': False,\n", + " 'full': False,\n", + " 'crap': False,\n", + " 'awww': False,\n", + " 'kinda': False,\n", + " 'jealou': False,\n", + " 'cours': False,\n", + " 'trip': False,\n", + " 'reason': False,\n", + " 'dude': False,\n", + " 'crazi': False,\n", + " 'fall': False,\n", + " 'comput': False,\n", + " 'fix': False,\n", + " 'season': False,\n", + " 'heard': False,\n", + " 'pm': False,\n", + " 'forgot': False,\n", + " 'didnt': False,\n", + " 'kind': False,\n", + " 'fine': False,\n", + " 'site': False,\n", + " 'heart': False,\n", + " 'wont': False,\n", + " 'interest': False,\n", + " 'bought': False,\n", + " 'high': False,\n", + " 'mr': False,\n", + " 'add': False,\n", + " 'visit': False,\n", + " 'rock': False,\n", + " 'pay': False,\n", + " 'awak': False,\n", + " 'favorit': False,\n", + " 'relax': False,\n", + " 'problem': False,\n", + " 'sunni': False,\n", + " 'super': False,\n", + " 'star': False,\n", + " 'red': False,\n", + " 'beach': False,\n", + " 'line': False,\n", + " 'learn': False,\n", + " 'ago': False,\n", + " 'soo': False,\n", + " 'cuz': False,\n", + " 'asleep': False,\n", + " 'dead': False,\n", + " 'smile': False,\n", + " 'mileycyru': False,\n", + " 'sign': False,\n", + " 'fail': False,\n", + " 'hell': False,\n", + " 'sore': False,\n", + " 'tommcfli': False,\n", + " 'ride': False,\n", + " 'math': False,\n", + " 'afternoon': False,\n", + " 'lose': False,\n", + " 'part': False,\n", + " 'serious': False,\n", + " 'mind': False,\n", + " 'lucki': False,\n", + " 'drop': False,\n", + " 'power': False,\n", + " 'congrat': False,\n", + " 'definit': False,\n", + " 'concert': False,\n", + " 'facebook': False,\n", + " 'ticket': False,\n", + " 'ladi': False,\n", + " 'instead': False,\n", + " 'email': False,\n", + " 'shower': False,\n", + " 'hand': False,\n", + " 'mad': False,\n", + " 'offici': False,\n", + " 'youtub': False,\n", + " 'breakfast': False,\n", + " 'short': False,\n", + " 'internet': False,\n", + " 'boo': False,\n", + " 'broke': False,\n", + " 'wear': False,\n", + " 'sometim': False,\n", + " 'order': False,\n", + " 'nd': False,\n", + " 'dear': False,\n", + " 'bet': False,\n", + " 'agre': False,\n", + " 'perfect': False,\n", + " 'btw': False,\n", + " 'park': False,\n", + " 'award': False,\n", + " 'gym': False,\n", + " 'catch': False,\n", + " 'togeth': False,\n", + " 'test': False,\n", + " 'team': False,\n", + " 'suppos': False,\n", + " 'figur': False,\n", + " 'sat': False,\n", + " 'homework': False,\n", + " 'mention': False,\n", + " 'june': False,\n", + " 'alon': False,\n", + " 'beat': False,\n", + " 'nap': False,\n", + " 'pack': False,\n", + " 'soooo': False,\n", + " 'pick': False,\n", + " 'yea': False,\n", + " 'sing': False,\n", + " 'lmao': False,\n", + " 'nite': False,\n", + " 'xxx': False,\n", + " 'second': False,\n", + " 'album': False,\n", + " 'stuck': False,\n", + " 'store': False,\n", + " 'wed': False,\n", + " 'sigh': False,\n", + " 'goin': False,\n", + " 'ice': False,\n", + " 'vacat': False,\n", + " 'air': False,\n", + " 'upload': False,\n", + " 'coupl': False,\n", + " 'water': False,\n", + " 'hungri': False,\n", + " 'cook': False,\n", + " 'cousin': False,\n", + " 'xd': False,\n", + " 'dress': False,\n", + " 'easi': False,\n", + " 'side': False,\n", + " 'laptop': False,\n", + " 'account': False,\n", + " 'holiday': False,\n", + " 'wors': False,\n", + " 'revis': False,\n", + " 'bless': False,\n", + " 'foot': False,\n", + " 'decid': False,\n", + " 'join': False,\n", + " 'mood': False,\n", + " 'spend': False,\n", + " 'point': False,\n", + " 'moment': False,\n", + " 'window': False,\n", + " 'stori': False,\n", + " 'save': False,\n", + " 'graduat': False,\n", + " 'past': False,\n", + " 'top': False,\n", + " 'sleepi': False,\n", + " 'ipod': False,\n", + " 'f': False,\n", + " 'current': False,\n", + " 'understand': False,\n", + " 'yep': False,\n", + " 'throat': False,\n", + " 'chanc': False,\n", + " 'town': False,\n", + " 'differ': False,\n", + " 'hmm': False,\n", + " 'told': False,\n", + " 'bout': False,\n", + " 'mtv': False,\n", + " 'cream': False,\n", + " 'annoy': False,\n", + " 'answer': False,\n", + " 'age': False,\n", + " 'mac': False,\n", + " 'forget': False,\n", + " 'road': False,\n", + " 'thursday': False,\n", + " 'tour': False,\n", + " 'fast': False,\n", + " 'load': False,\n", + " 'celebr': False,\n", + " 'realiz': False,\n", + " 'jonasbroth': False,\n", + " 'shoot': False,\n", + " 'camp': False,\n", + " 'scare': False,\n", + " 'cut': False,\n", + " 'co': False,\n", + " 'knew': False,\n", + " 'date': False,\n", + " 'ddlovato': False,\n", + " 'shirt': False,\n", + " 'episod': False,\n", + " 'fli': False,\n", + " 'chat': False,\n", + " 'ahhh': False,\n", + " 'complet': False,\n", + " 'kick': False,\n", + " 'fb': False,\n", + " 'lazi': False,\n", + " 'ive': False,\n", + " 'especi': False,\n", + " 'card': False,\n", + " 'ppl': False,\n", + " 'mum': False,\n", + " 'rather': False,\n", + " 'black': False,\n", + " 'download': False,\n", + " 'list': False,\n", + " 'tea': False,\n", + " 'chocol': False,\n", + " 'yr': False,\n", + " 'count': False,\n", + " 'expect': False,\n", + " 'cancel': False,\n", + " 'flight': False,\n", + " 'appl': False,\n", + " 'ate': False,\n", + " 'number': False,\n", + " 'film': False,\n", + " 'state': False,\n", + " 'bye': False,\n", + " 'pizza': False,\n", + " 'worst': False,\n", + " 'wtf': False,\n", + " 'wine': False,\n", + " 'juli': False,\n", + " 'present': False,\n", + " 'meant': False,\n", + " 'english': False,\n", + " 'manag': False,\n", + " 'share': False,\n", + " 'colleg': False,\n", + " 'sent': False,\n", + " 'servic': False,\n", + " 'ach': False,\n", + " 'question': False,\n", + " 'flu': False,\n", + " 'depress': False,\n", + " 'nope': False,\n", + " 'freak': False,\n", + " 'laugh': False,\n", + " 'smell': False,\n", + " 'unfortun': False,\n", + " 'due': False,\n", + " 'woman': False,\n", + " 'beer': False,\n", + " 'messag': False,\n", + " 'bitch': False,\n", + " 'worth': False,\n", + " 'search': False,\n", + " 'websit': False,\n", + " 'bike': False,\n", + " 'comment': False,\n", + " 'touch': False,\n", + " 'shoe': False,\n", + " 'parent': False,\n", + " 'church': False,\n", + " 'sunshin': False,\n", + " 'swim': False,\n", + " 'miley': False,\n", + " 'boyfriend': False,\n", + " 'pool': False,\n", + " 'stomach': False,\n", + " 'lil': False,\n", + " 'burn': False,\n", + " 'support': False,\n", + " 'followfriday': False,\n", + " 'mess': False,\n", + " 'lay': False,\n", + " 'weird': False,\n", + " 'leg': False,\n", + " 'bum': False,\n", + " 'appar': False,\n", + " 'becom': False,\n", + " 'father': False,\n", + " 'cake': False,\n", + " 'hill': False,\n", + " 'case': False,\n", + " 'airport': False,\n", + " 'event': False,\n", + " 'shame': False,\n", + " 'hr': False,\n", + " 'london': False,\n", + " 'surpris': False,\n", + " 'round': False,\n", + " 'tummi': False,\n", + " 'hmmm': False,\n", + " 'voic': False,\n", + " 'broken': False,\n", + " 'blue': False,\n", + " 'safe': False,\n", + " 'spent': False,\n", + " 'fell': False,\n", + " 'possibl': False,\n", + " 'practic': False,\n", + " 'type': False,\n", + " 'usual': False,\n", + " 'yummi': False,\n", + " 'insid': False,\n", + " 'stress': False,\n", + " 'warm': False,\n", + " 'absolut': False,\n", + " 'normal': False,\n", + " 'alright': False,\n", + " 'cheer': False,\n", + " 'moon': False,\n", + " 'idk': False,\n", + " 'hold': False,\n", + " 'horribl': False,\n", + " 'stand': False,\n", + " 'near': False,\n", + " 'page': False,\n", + " 'chill': False,\n", + " 'note': False,\n", + " 'shot': False,\n", + " 'doctor': False,\n", + " 'uk': False,\n", + " 'xoxo': False,\n", + " 'club': False,\n", + " 'fire': False,\n", + " 'pray': False,\n", + " 'huge': False,\n", + " 'taken': False,\n", + " 'ball': False,\n", + " 'cup': False,\n", + " 'slow': False,\n", + " 'shall': False,\n", + " 'cd': False,\n", + " 'scari': False,\n", + " 'deserv': False,\n", + " 'disappoint': False,\n", + " 'block': False,\n", + " 'box': False,\n", + " 'pass': False,\n", + " 'exactli': False,\n", + " 'green': False,\n", + " 'sooooo': False,\n", + " 'bro': False,\n", + " 'band': False,\n", + " 'paper': False,\n", + " 'confus': False,\n", + " 'terribl': False,\n", + " 'myspac': False,\n", + " 'ear': False,\n", + " 'tan': False,\n", + " 'notic': False,\n", + " 'except': False,\n", + " 'twitpic': False,\n", + " 'googl': False,\n", + " 'issu': False,\n", + " 'low': False,\n", + " 'doesnt': False,\n", + " 'lie': False,\n", + " 'fair': False,\n", + " 'sadli': False,\n", + " 'mile': False,\n", + " 'mate': False,\n", + " 'project': False,\n", + " 'app': False,\n", + " 'pop': False,\n", + " 'countri': False,\n", + " 'wit': False,\n", + " 'longer': False,\n", + " 'crash': False,\n", + " 'raini': False,\n", + " 'arm': False,\n", + " 'david': False,\n", + " 'cover': False,\n", + " 'sell': False,\n", + " 'wednesday': False,\n", + " 'sim': False,\n", + " 'shift': False,\n", + " 'finger': False,\n", + " 'woo': False,\n", + " 'hubbi': False,\n", + " 'fit': False,\n", + " 'gorgeou': False,\n", + " 'gosh': False,\n", + " 'ff': False,\n", + " 'hangov': False,\n", + " 'caught': False,\n", + " 'mail': False,\n", + " 'return': False,\n", + " 'luv': False,\n", + " 'fight': False,\n", + " 'earlier': False,\n", + " 'yup': False,\n", + " 'plu': False,\n", + " 'lame': False,\n", + " 'gave': False,\n", + " 'ahead': False,\n", + " 'invit': True,\n", + " 'connect': False,\n", + " 'act': False,\n", + " 'special': False,\n", + " 'nearli': False,\n", + " 'isnt': False,\n", + " 'prepar': False,\n", + " 'watchin': False,\n", + " 'via': False,\n", + " 'white': False,\n", + " 'taylor': False,\n", + " 'sort': False,\n", + " 'interview': False,\n", + " 'blackberri': False,\n", + " 'recommend': False,\n", + " 'tom': False,\n", + " 'argh': False,\n", + " 'guitar': False,\n", + " 'bill': False,\n", + " 'front': False,\n", + " 'offer': False,\n", + " 'fact': False,\n", + " 'piec': False,\n", + " 'upset': False,\n", + " 'joy': False,\n", + " 'glass': False,\n", + " 'radio': False,\n", + " 'tuesday': False,\n", + " 'xo': False,\n", + " 'matter': False,\n", + " 'fill': False,\n", + " 'inde': False,\n", + " 'exhaust': False,\n", + " 'self': False,\n", + " 'congratul': False,\n", + " 'avail': False,\n", + " 'deal': False,\n", + " 'lone': False,\n", + " 'chees': False,\n", + " 'version': False,\n", + " 'john': False,\n", + " 'breath': False,\n", + " 'proud': False,\n", + " 'product': False,\n", + " 'gig': False,\n", + " 'teeth': False,\n", + " 'blah': False,\n", + " 'quiet': False,\n", + " 'kiss': False,\n", + " 'view': False,\n", + " 'drunk': False,\n", + " 'fever': False,\n", + " 'singl': False,\n", + " 'forev': False,\n", + " 'folk': False,\n", + " 'gettin': False,\n", + " 'pink': False,\n", + " 'bird': False,\n", + " 'promis': False,\n", + " 'goodby': False,\n", + " 'everybodi': False,\n", + " 'experi': False,\n", + " 'quick': False,\n", + " 'import': False,\n", + " 'tune': False,\n", + " 'although': False,\n", + " 'daughter': False,\n", + " 'sexi': False,\n", + " 'sky': False,\n", + " 'aint': False,\n", + " 'grow': False,\n", + " 'small': False,\n", + " 'fantast': False,\n", + " 'bar': False,\n", + " 'three': False,\n", + " 'design': False,\n", + " 'nose': False,\n", + " 'huh': False,\n", + " 'thx': False,\n", + " 'lesson': False,\n", + " 'fish': False,\n", + " 'bday': False,\n", + " 'arriv': False,\n", + " 'storm': False,\n", + " 'mix': False,\n", + " 'seat': False,\n", + " 'lake': False,\n", + " 'daddi': False,\n", + " 'fav': False,\n", + " 'piss': False,\n", + " 'blood': False,\n", + " 'knee': False,\n", + " 'child': False,\n", + " 'havent': False,\n", + " 'middl': False,\n", + " 'memori': False,\n", + " 'bag': False,\n", + " 'group': False,\n", + " 'dvd': False,\n", + " 'dure': False,\n", + " 'art': False,\n", + " 'behind': False,\n", + " 'jack': False,\n", + " 'paint': False,\n", + " 'hospit': False,\n", + " 'swine': False,\n", + " 'futur': False,\n", + " 'perform': False,\n", + " 'magic': False,\n", + " 'cloth': False,\n", + " 'remind': False,\n", + " 'stick': False,\n", + " 'web': False,\n", + " 'australia': False,\n", + " 'releas': False,\n", + " 'dentist': False,\n", + " 'land': False,\n", + " 'appreci': False,\n", + " 'session': False,\n", + " 'ring': False,\n", + " 'bloodi': False,\n", + " 'track': False,\n", + " 'info': False,\n", + " 'peac': False,\n", + " 'ouch': False,\n", + " 'delet': False,\n", + " 'channel': False,\n", + " 'nail': False,\n", + " 'race': False,\n", + " 'addict': False,\n", + " 'ran': False,\n", + " 'ny': False,\n", + " 'bbq': False,\n", + " 'gut': False,\n", + " 'trend': False,\n", + " 'cooki': False,\n", + " 'tear': False,\n", + " 'camera': False,\n", + " 'joe': False,\n", + " 'french': False,\n", + " 'roll': False,\n", + " 'buddi': False,\n", + " 'system': False,\n", + " 'edit': False,\n", + " 'doubl': False,\n", + " 'twilight': False,\n", + " 'puppi': False,\n", + " 'tast': False,\n", + " 'ng': False,\n", + " 'nobodi': False,\n", + " 'histori': False,\n", + " 'jon': False,\n", + " 'chicken': False,\n", + " 'compani': False,\n", + " 'plz': False,\n", + " 'mommi': False,\n", + " 'feelin': False,\n", + " 'record': False,\n", + " 'light': False,\n", + " 'ohh': False,\n", + " 'dr': False,\n", + " 'young': False,\n", + " 'rule': False,\n", + " 'form': False,\n", + " 'garden': False,\n", + " 'neck': False,\n", + " 'felt': False,\n", + " 'badli': False,\n", + " 'dark': False,\n", + " 'street': False,\n", + " 'slept': False,\n", + " 'local': False,\n", + " 'continu': False,\n", + " 'adam': False,\n", + " 'yum': False,\n", + " 'shut': False,\n", + " 'ahh': False,\n", + " 'fri': False,\n", + " 'brain': False,\n", + " 'profil': False,\n", + " 'gay': False,\n", + " 'teacher': False,\n", + " 'davidarchi': False,\n", + " 'file': False,\n", + " 'jk': False,\n", + " 'travel': False,\n", + " 'nyc': False,\n", + " 'natur': False,\n", + " 'vip': False,\n", + " 'dunno': False,\n", + " 'suggest': False,\n", + " 'whatev': False,\n", + " 'dm': False,\n", + " 'allow': False,\n", + " 'trek': False,\n", + " 'inspir': False,\n", + " 'extra': False,\n", + " 'board': False,\n", + " 'four': False,\n", + " 'shoulder': False,\n", + " 'contact': False,\n", + " 'bowl': False,\n", + " 'space': False,\n", + " 'pl': False,\n", + " 'twit': False,\n", + " 'ooh': False,\n", + " 'entertain': False,\n", + " 'king': False,\n", + " 'babe': False,\n", + " 'rob': False,\n", + " 'laker': False,\n", + " 'tree': False,\n", + " 'festiv': False,\n", + " 'ruin': False,\n", + " 'random': False,\n", + " 'joke': False,\n", + " 'bear': False,\n", + " 'hahah': False,\n", + " 'gift': False,\n", + " 'trailer': False,\n", + " 'marri': False,\n", + " 'midnight': False,\n", + " 'bunch': False,\n", + " 'forc': False,\n", + " 'vega': False,\n", + " 'pc': False,\n", + " 'entir': False,\n", + " 'report': False,\n", + " 'essay': False,\n", + " 'shine': False,\n", + " 'plane': False,\n", + " 'apart': False,\n", + " 'fam': False,\n", + " 'alot': False,\n", + " 'kate': False,\n", + " 'wind': False,\n", + " 'inform': False,\n", + " 'paid': False,\n", + " 'hannah': False,\n", + " 'bright': False,\n", + " 'eh': False,\n", + " 'cloud': False,\n", + " 'along': False,\n", + " 'nick': False,\n", + " 'chines': False,\n", + " 'seriou': False,\n", + " 'mmm': False,\n", + " 'seri': False,\n", + " 'thru': False,\n", + " 'teach': False,\n", + " 'chillin': False,\n", + " 'bb': False,\n", + " 'key': False,\n", + " 'begin': False,\n", + " 'rip': False,\n", + " 'server': False,\n", + " 'mama': False,\n", + " 'sum': False,\n", + " ...},\n", + " True)" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "# your code here\n", + "import random\n", + "from nltk.corpus import movie_reviews\n", + "\n", + "# make target boolean\n", + "tweets[\"target\"] = tweets[\"target\"].astype('bool')\n", + "\n", + "# get list of words and category\n", + "documents = [(tweet[\"text_processed\"], tweet[\"target\"]) for index, tweet in tweets.iterrows()]\n", + " \n", + "random.shuffle(documents)\n", + "\n", + "# define function to find words from top5000\n", + "\n", + "def find_features(document):\n", + " words = set(document)\n", + " features = {}\n", + " for w in top5000:\n", + " features[w] = (w in words)\n", + "\n", + " return features\n", + "\n", + "# loop through texts and get boolean for whether the top5000 words are there\n", + "featuresets = [(find_features(rev), category) for (rev, category) in documents]\n", + "\n", + "# checking list\n", + "featuresets[0]\n", + "\n" ] }, { @@ -210,11 +2604,42 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 5, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Most Informative Features\n", + " sad = True False : True = 17.8 : 1.0\n", + " followfriday = True True : False = 17.1 : 1.0\n", + " congratul = True True : False = 15.1 : 1.0\n", + " welcom = True True : False = 12.3 : 1.0\n", + " kate = True False : True = 12.3 : 1.0\n", + " cancel = True False : True = 11.8 : 1.0\n", + " tune = True True : False = 11.7 : 1.0\n", + " dentist = True False : True = 11.6 : 1.0\n", + " knee = True False : True = 11.6 : 1.0\n", + " lone = True False : True = 11.6 : 1.0\n", + "None\n" + ] + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "# train set\n", + "training_set = featuresets[:16000]\n", + "\n", + "# test set\n", + "testing_set = featuresets[16000:]\n", + "\n", + "# train classifier\n", + "classifier = nltk.NaiveBayesClassifier.train(training_set)\n", + "\n", + "# print most informative features\n", + "print(classifier.show_most_informative_features())\n" ] }, { @@ -230,11 +2655,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Classifier accuracy percent: 0.7285\n" + ] + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "# accuracy score\n", + "print(\"Classifier accuracy percent:\",nltk.classify.accuracy(classifier, testing_set))" ] }, { @@ -252,7 +2688,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -270,7 +2706,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -288,7 +2724,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -298,7 +2734,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -312,7 +2748,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.7.6" } }, "nbformat": 4,