{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# HW4 PIPELINE + HW6 + HW7 + Final Project\n", "## Building off HW2 + HW3" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [], "source": [ "## =======================================================\n", "## IMPORTING\n", "## =======================================================\n", "import os\n", "def get_data_from_files(path):\n", " directory = os.listdir(path)\n", " results = []\n", " for file in directory:\n", " f=open(path+file)\n", " results.append(f.read())\n", " f.close()\n", " return results\n", "\n", "## =======================================================\n", "## TOKENIZING\n", "## =======================================================\n", "from nltk.tokenize import word_tokenize, sent_tokenize\n", "def get_tokens(sentence):\n", " tokens = word_tokenize(sentence)\n", " clean_tokens = [word.lower() for word in tokens if word.isalpha()]\n", " return clean_tokens\n", "\n", "def get_sentence_tokens(review):\n", " return sent_tokenize(review)\n", "\n", "## =======================================================\n", "## REMOVING STOPWORDS\n", "## =======================================================\n", "from nltk.corpus import stopwords\n", "stop_words = set(stopwords.words(\"english\"))\n", "def remove_stopwords(sentence):\n", " filtered_text = []\n", " for word in sentence:\n", " if word not in stop_words:\n", " filtered_text.append(word)\n", " return filtered_text\n", "\n", "## =======================================================\n", "## FREQUENCY DISTRIBUTIONS\n", "## =======================================================\n", "from nltk.probability import FreqDist\n", "def get_most_common(tokens):\n", " fdist = FreqDist(tokens)\n", " return fdist.most_common(12)\n", "\n", "def get_most_common(tokens):\n", " fdist = FreqDist(tokens)\n", " return fdist.most_common(12)\n", "\n", "def get_fdist(tokens):\n", " return (FreqDist(tokens))\n", "\n", "## =======================================================\n", "## SENTIMENT ANALYSIS\n", "## =======================================================\n", "from nltk.sentiment import SentimentAnalyzer\n", "from nltk.sentiment.util import *\n", "from nltk.sentiment.vader import SentimentIntensityAnalyzer\n", "sid = SentimentIntensityAnalyzer()\n", "\n", "def get_vader_score(review):\n", " return sid.polarity_scores(review)\n", "\n", "def separate_vader_score(vader_score, key):\n", " return vader_score[key]\n", "\n", "## =======================================================\n", "## SUMMARIZER\n", "## =======================================================\n", "def get_weighted_freq_dist(review, freq_dist):\n", " try:\n", " max_freq = max(freq_dist.values())\n", " for word in freq_dist.keys():\n", " freq_dist[word] = (freq_dist[word]/max_freq)\n", " return freq_dist\n", " except:\n", " for word in freq_dist.keys():\n", " freq_dist[word] = (freq_dist[word]/1)\n", " return freq_dist\n", " \n", "\n", "def get_sentence_score(review, freq_dist):\n", " sentence_scores = {}\n", " for sent in review:\n", " for word in nltk.word_tokenize(sent.lower()):\n", " if word in freq_dist.keys():\n", " if len(sent.split(' ')) < 30:\n", " if sent not in sentence_scores.keys():\n", " sentence_scores[sent] = freq_dist[word]\n", " else:\n", " sentence_scores[sent] += freq_dist[word]\n", " return sentence_scores\n", "\n", "def get_summary_sentences(sentence_scores):\n", " sorted_sentences = sorted(sentence_scores.items(), key=lambda kv: kv[1], reverse=True)\n", " return ''.join(sent[0] for sent in sorted_sentences[:5])\n", "\n", "def get_freq_words(freq_dist):\n", " sorted_words = sorted(freq_dist.items(), key=lambda kv: kv[1], reverse=True)\n", " return ' '.join(word[0] for word in sorted_words[:50])\n", "\n", "## =======================================================\n", "## MACHINE LEARNING -- NAIVE BAYES\n", "## =======================================================\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.naive_bayes import GaussianNB, MultinomialNB, BernoulliNB\n", "from sklearn import metrics\n", "from sklearn.metrics import confusion_matrix, classification_report\n", "\n", "# def get_NB(small_df, labels):\n", "# x_train, x_test, y_train, y_test = train_test_split(small_df.values, labels, test_size=0.3, random_state = 109)\n", "\n", "# gnb = GaussianNB()\n", "# gnb.fit(x_train, y_train)\n", "# y_pred = gnb.predict(x_test)\n", "# print(\"Accuracy:\", metrics.accuracy_score(y_test, y_pred))\n", " \n", " \n", "def get_NB(small_df, labels, classifier, title):\n", " seeds = [109, 210, 420, 19, 7]\n", " dfs = []\n", " overall = []\n", " print(title)\n", " for seed in seeds:\n", " x_train, x_test, y_train, y_test = train_test_split(small_df.values, \n", " labels, test_size=0.3, random_state = seed)\n", " gnb = classifier\n", " gnb.fit(x_train, y_train).score(x_train, y_train)\n", " y_pred = gnb.predict(x_test)\n", " accuracy = metrics.accuracy_score(y_test, y_pred)\n", " report = metrics.classification_report(y_test, y_pred)\n", " print(\"Accuracy:\", accuracy)\n", "# print(report)\n", " overall.append(accuracy)\n", " cm = confusion_matrix(y_test, y_pred)\n", " # confusion_matrix_graph(cm, accuracy, \"NB Multinomial Tokenized\")\n", "# tn, fp, fn, tp = cm.ravel()\n", " df = pd.DataFrame(cm.ravel())\n", " dfs.append(df)\n", " print('AVERAGE ACCURACY:', sum(overall)/len(overall))\n", " return dfs\n", "\n", "\n", "def display_NB_tables(dfs):\n", " for df in dfs:\n", " print(display(df))\n", " \n", "## =======================================================\n", "## PLOTS\n", "## ======================================================= \n", "import seaborn as sns\n", "import matplotlib.pyplot as plt \n", "def bar_plot(df, title): \n", " graph = sns.barplot(y = \"count\", x = \"word\", data = df, palette = \"husl\")\n", " plt.title(title)\n", " plt.xlabel(\"Word\")\n", " plt.ylabel(\"Count\")\n", " sns.set_context(\"talk\")\n", " plt.xticks(rotation = 90)\n", " return plt\n", "\n", "from nltk.tokenize import casual_tokenize\n", "from collections import Counter\n", "\n", "\n", "## =======================================================\n", "## CLEANERS\n", "## ======================================================= \n", "import re, string\n", "def diy_cleaner(review):\n", " try:\n", " both = review.split('\\n')\n", " title = both[0]\n", " review = both[1]\n", " review = review.replace(\"'\",\"\")\n", " except:\n", " review = review.replace(\"'\",\"\")\n", " pattern = re.compile('[\\W_]+')\n", " review = pattern.sub(' ', review)\n", " cleaned = title + ' ' + title + ' ' + review\n", " return cleaned.lower()\n", "\n", "def pruner(review):\n", " clean_review = ' '.join([word for word in review.split() if len(word) > 3])\n", " return clean_review\n", "\n", "sentim_analyzer = SentimentAnalyzer()\n", "def get_nltk_negs(tokens):\n", " all_words_neg = sentim_analyzer.all_words([mark_negation(tokens)])\n", " return all_words_neg\n", "\n", "def get_unigram_feats(neg_tokens):\n", " unigram_feats = sentim_analyzer.unigram_word_feats(neg_tokens)\n", " return unigram_feats\n", " \n", "def get_bigram_feats(tokens):\n", " ngrams = zip(*[tokens[i:] for i in range(2)])\n", " return [\"_\".join(ngram) for ngram in ngrams]\n", "\n", "## =======================================================\n", "## HELPERS\n", "## ======================================================= \n", "def get_bow_from_column(df, column):\n", " all_column_data = ' '.join(df[column].tolist())\n", " all_column_fd = Counter(all_column_data.split())\n", " return all_column_fd\n", "\n", "def get_common_words(num):\n", " most_common_neg = [word[0] for word in big_bow_n.most_common(num)]\n", " most_common_pos = [word[0] for word in big_bow_p.most_common(num)]\n", " in_both = np.intersect1d(most_common_neg, most_common_pos)\n", " neg_notpos = np.setdiff1d(most_common_neg, most_common_pos)\n", " pos_notneg = np.setdiff1d(most_common_pos, most_common_neg)\n", " return [len(in_both), len(neg_notpos), len(pos_notneg), len(in_both)/num, in_both, neg_notpos, pos_notneg]\n", "\n", "def get_only_polarized(tokens, common_words):\n", " return [token for token in tokens if token not in common_words[4]] # 70\n", "\n", "## =======================================================\n", "## VISUALS\n", "## ======================================================= \n", "import wordcloud\n", "from wordcloud import WordCloud, ImageColorGenerator\n", "from PIL import Image\n", "import seaborn as sns\n", "import matplotlib.pyplot as plt \n", "def create_word_cloud_with_mask(path_of_mask_image, dictionary, \n", " max_num_words, title):\n", " mask = np.array(Image.open(path_of_mask_image))\n", " word_cloud = WordCloud(background_color = \"white\", \n", " max_words = max_num_words, \n", " mask = mask, max_font_size = 125, \n", " random_state = 1006)\n", " word_cloud.generate_from_frequencies(dictionary)\n", " image_colors = ImageColorGenerator(mask)\n", " plt.figure(figsize = [8,8])\n", " plt.imshow(word_cloud.recolor(color_func = image_colors), interpolation = \"bilinear\")\n", " plt.title(title)\n", " sns.set_context(\"poster\")\n", " plt.axis(\"off\")\n", " return plt\n", " \n", "import seaborn as sns\n", "import matplotlib.pyplot as plt \n", "def bar_plot(df, title): \n", " graph = sns.barplot(y = \"count\", x = \"word\", data = df, palette = \"husl\")\n", " plt.title(title)\n", " plt.xlabel(\"Word\")\n", " plt.ylabel(\"Count\")\n", " sns.set_context(\"talk\")\n", " plt.xticks(rotation = 90)\n", " return plt" ] }, { "cell_type": "code", "execution_count": 29, "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", "
0labels
0yeah first_person_pronoun want to address the ...yes
1umm pamela can pronoun hear first_person_prono...yes
2its on september th kayla and david first_pers...yes
3hi ladies first_person_pronoun wanted to tell ...yes
4lord forgive pronoun pronoun dont know what pr...yes
.........
561i pray that first_person_pronoun family will r...unknown
562when asked if pronoun had a last statement pro...yes
563what is about to transpire in a few moments is...no
564noneyes
565statement to the media first_person_pronoun at...yes
\n", "

566 rows × 2 columns

\n", "
" ], "text/plain": [ " 0 labels\n", "0 yeah first_person_pronoun want to address the ... yes\n", "1 umm pamela can pronoun hear first_person_prono... yes\n", "2 its on september th kayla and david first_pers... yes\n", "3 hi ladies first_person_pronoun wanted to tell ... yes\n", "4 lord forgive pronoun pronoun dont know what pr... yes\n", ".. ... ...\n", "561 i pray that first_person_pronoun family will r... unknown\n", "562 when asked if pronoun had a last statement pro... yes\n", "563 what is about to transpire in a few moments is... no\n", "564 none yes\n", "565 statement to the media first_person_pronoun at... yes\n", "\n", "[566 rows x 2 columns]" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "\n", "\n", "\n", "# train=pd.read_csv(\"../WK7/kaggle-sentiment/train.tsv\", delimiter='\\t')\n", "# y=train['Sentiment'].values\n", "# X=train['Phrase'].values\n", "\n", "# all_df = pd.DataFrame(X)\n", "# all_df['labels'] = y\n", "# all_df\n", "\n", "df = pd.read_csv('../death_row_discritized.csv')\n", "\n", "def to_string(tokens):\n", " try:\n", " return \" \".join(eval(tokens))\n", " except:\n", " return \"error\"\n", " \n", "df['statement_string'] = df.apply(lambda x: to_string(x['last_statement']), axis=1)\n", "# y=df['vic_kid'].values\n", "y=df['prior_record'].values\n", "y_labels = list(set(y))\n", "X=df['statement_string'].values\n", "\n", "all_df = pd.DataFrame(X)\n", "all_df['labels'] = y\n", "all_df\n", "\n", "# neg_df = pd.DataFrame(neg)\n", "# pos_df = pd.DataFrame(pos)\n", "\n", "# pos_df['PoN'] = 'P'\n", "# neg_df['PoN'] = 'N'\n", "# all_df = neg_df.append(pos_df)" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [], "source": [ "# neg = get_data_from_files('../NEG_JK/')\n", "# pos = get_data_from_files('../POS_JK/')\n", "\n", "# neg = get_data_from_files('../neg_cornell/')\n", "# pos = get_data_from_files('../pos_cornell/')\n", "\n", "# neg = get_data_from_files('../neg_hw4/')\n", "# pos = get_data_from_files('../pos_hw4/')\n", "\n", "# neg = get_data_from_files('../hw4_lie_false/')\n", "# pos = get_data_from_files('../hw4_lie_true/')\n", "\n", "# pos = get_data_from_files('../hw4_lie_false/')\n", "# neg = get_data_from_files('../hw4_lie_true/')\n", "\n", "\n", "\n", "all_df['tokens'] = all_df.apply(lambda x: get_tokens(x[0]), axis=1)\n", "all_df['num_tokens'] = all_df.apply(lambda x: len(x['tokens']), axis=1)\n", "\n", "all_df = all_df.drop(all_df[all_df.num_tokens < 1].index)\n", "\n", "all_df['sentences'] = all_df.apply(lambda x: get_sentence_tokens(x[0]), axis=1)\n", "all_df['num_sentences'] = all_df.apply(lambda x: len(x['sentences']), axis=1)\n", "\n", "all_df['no_sw'] = all_df.apply(lambda x: remove_stopwords(x['tokens']),axis=1)\n", "all_df['num_no_sw'] = all_df.apply(lambda x: len(x['no_sw']),axis=1)\n", "\n", "all_df['topwords_unfil'] = all_df.apply(lambda x: get_most_common(x['tokens']),axis=1)\n", "all_df['topwords_fil'] = all_df.apply(lambda x: get_most_common(x['no_sw']),axis=1)\n", "\n", "all_df['freq_dist'] = all_df.apply(lambda x: get_fdist(x['no_sw']),axis=1)\n", "all_df['freq_dist_unfil'] = all_df.apply(lambda x: get_fdist(x['tokens']),axis=1)\n", "\n", "all_df['vader_all'] = all_df.apply(lambda x: get_vader_score(x[0]),axis=1)\n", "all_df['v_compound'] = all_df.apply(lambda x: separate_vader_score(x['vader_all'], 'compound'),axis=1)\n", "all_df['v_neg'] = all_df.apply(lambda x: separate_vader_score(x['vader_all'], 'neg'),axis=1)\n", "all_df['v_neu'] = all_df.apply(lambda x: separate_vader_score(x['vader_all'], 'neu'),axis=1)\n", "all_df['v_pos'] = all_df.apply(lambda x: separate_vader_score(x['vader_all'], 'pos'),axis=1)\n", "\n", "all_df['weighted_freq_dist'] = all_df.apply(lambda x: get_weighted_freq_dist(x['sentences'], x['freq_dist']),axis=1)\n", "all_df['sentence_scores'] = all_df.apply(lambda x: get_sentence_score(x['sentences'], x['freq_dist']),axis=1)\n", "all_df['summary_sentences'] = all_df.apply(lambda x: get_summary_sentences(x['sentence_scores']), axis=1)\n", "\n", "all_df['vader_sum_all'] = all_df.apply(lambda x: get_vader_score(x['summary_sentences']),axis=1)\n", "all_df['v_compound_sum'] = all_df.apply(lambda x: separate_vader_score(x['vader_sum_all'], 'compound'),axis=1)\n", "all_df['v_neg_sum'] = all_df.apply(lambda x: separate_vader_score(x['vader_sum_all'], 'neg'),axis=1)\n", "all_df['v_neu_sum'] = all_df.apply(lambda x: separate_vader_score(x['vader_sum_all'], 'neu'),axis=1)\n", "all_df['v_pos_sum'] = all_df.apply(lambda x: separate_vader_score(x['vader_sum_all'], 'pos'),axis=1)\n", "\n", "all_df['v_freq_words'] = all_df.apply(lambda x: get_freq_words(x['freq_dist']), axis=1)\n", "\n", "all_df['vader_fq_all'] = all_df.apply(lambda x: get_vader_score(x['v_freq_words']),axis=1)\n", "all_df['v_compound_fd'] = all_df.apply(lambda x: separate_vader_score(x['vader_fq_all'], 'compound'),axis=1)\n", "all_df['v_neg_fd'] = all_df.apply(lambda x: separate_vader_score(x['vader_fq_all'], 'neg'),axis=1)\n", "all_df['v_neu_fd'] = all_df.apply(lambda x: separate_vader_score(x['vader_fq_all'], 'neu'),axis=1)\n", "all_df['v_pos_fd'] = all_df.apply(lambda x: separate_vader_score(x['vader_fq_all'], 'pos'),axis=1)\n", "\n", "all_df['bow'] = all_df.apply(lambda x: Counter(x['tokens']), axis=1)\n", "all_df['bow_nosw'] = all_df.apply(lambda x: Counter(x['no_sw']), axis=1)\n", "\n", "all_df['diy_cleaner'] = all_df.apply(lambda x: diy_cleaner(x[0]), axis=1)\n", "all_df['pruned'] = all_df.apply(lambda x: pruner(x['diy_cleaner']), axis=1)\n", "\n", "all_df['nltk_negs'] = all_df.apply(lambda x: get_nltk_negs(x['tokens']), axis=1)\n", "all_df['unigram_feats'] = all_df.apply(lambda x: get_unigram_feats(x['nltk_negs']), axis=1)\n", "all_df['bigram_feats'] = all_df.apply(lambda x: get_bigram_feats(x['tokens']), axis=1)\n", "all_df['bigram_feats_neg'] = all_df.apply(lambda x: get_bigram_feats(x['nltk_negs']), axis=1)\n", "\n", "big_bow = get_bow_from_column(all_df, 'pruned')\n", "big_bow_1 = get_bow_from_column(all_df[all_df['labels'] == 'yes'], 'pruned')\n", "big_bow_2 = get_bow_from_column(all_df[all_df['labels'] == 'no'], 'pruned')\n", "big_bow_3 = get_bow_from_column(all_df[all_df['labels'] == 'unknown'], 'pruned')\n", "# big_bow_4 = get_bow_from_column(all_df[all_df['labels'] == 4], 'pruned')\n", "# big_bow_5 = get_bow_from_column(all_df[all_df['labels'] == 5], 'pruned')\n", "\n", "# most_common_1 = [word[0] for word in big_bow_n.most_common(100)]\n", "# most_common_2 = [word[0] for word in big_bow_p.most_common(100)]\n", "\n", "\n", "\n", "# all_df['no_shared_words'] = all_df.apply(lambda x: get_only_polarized(x['tokens'], get_common_words(500)), axis=1)\n", "\n" ] }, { "cell_type": "code", "execution_count": 31, "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", "
0labelstokensnum_tokenssentencesnum_sentencesno_swnum_no_swtopwords_unfiltopwords_fil...v_pos_fdbowbow_noswdiy_cleanerprunednltk_negsunigram_featsbigram_featsbigram_feats_negPoN
0yeah first_person_pronoun want to address the ...yes[yeah, want, to, address, the, roundtree, fami...48[yeah first_person_pronoun want to address the...1[yeah, want, address, roundtree, family, apolo...26[(and, 6), (to, 5), (pronoun, 4), (the, 3), (f...[(pronoun, 4), (family, 2), (im, 2), (yeah, 1)......0.356{'yeah': 1, 'want': 1, 'to': 5, 'address': 1, ...{'yeah': 1, 'want': 1, 'address': 1, 'roundtre...yeah first_person_pronoun want to address the ...yeah first_person_pronoun want address roundtr...[yeah, want, to, address, the, roundtree, fami...[to, the, and, and_NEG, family, pronoun, to_NE...[yeah_want, want_to, to_address, address_the, ...[yeah_want, want_to, to_address, address_the, ...yes
1umm pamela can pronoun hear first_person_prono...yes[umm, pamela, can, pronoun, hear, stephanie, h...52[umm pamela can pronoun hear first_person_pron...1[umm, pamela, pronoun, hear, stephanie, hardy,...34[(pronoun, 4), (and, 4), (yall, 4), (tell, 3),...[(pronoun, 4), (yall, 4), (tell, 3), (love, 2)......0.272{'umm': 1, 'pamela': 1, 'can': 1, 'pronoun': 4...{'umm': 1, 'pamela': 1, 'pronoun': 4, 'hear': ...umm pamela can pronoun hear first_person_prono...pamela pronoun hear first_person_pronoun steph...[umm, pamela, can, pronoun, hear, stephanie, h...[pronoun, and, yall, tell, the, love, am, for,...[umm_pamela, pamela_can, can_pronoun, pronoun_...[umm_pamela, pamela_can, can_pronoun, pronoun_...yes
2its on september th kayla and david first_pers...yes[its, on, september, th, kayla, and, david, wa...110[its on september th kayla and david first_per...1[september, th, kayla, david, wanted, apologiz...60[(to, 6), (the, 5), (yall, 5), (pain, 4), (cau...[(yall, 5), (pain, 4), (caused, 4), (apologize......0.199{'its': 1, 'on': 1, 'september': 1, 'th': 1, '...{'september': 1, 'th': 1, 'kayla': 1, 'david':...its on september th kayla and david first_pers...september kayla david first_person_pronoun wan...[its, on, september, th, kayla, and, david, wa...[yall_NEG, to, the_NEG, pain_NEG, caused_NEG, ...[its_on, on_september, september_th, th_kayla,...[its_on, on_september, september_th, th_kayla,...yes
\n", "

3 rows × 40 columns

\n", "
" ], "text/plain": [ " 0 labels \\\n", "0 yeah first_person_pronoun want to address the ... yes \n", "1 umm pamela can pronoun hear first_person_prono... yes \n", "2 its on september th kayla and david first_pers... yes \n", "\n", " tokens num_tokens \\\n", "0 [yeah, want, to, address, the, roundtree, fami... 48 \n", "1 [umm, pamela, can, pronoun, hear, stephanie, h... 52 \n", "2 [its, on, september, th, kayla, and, david, wa... 110 \n", "\n", " sentences num_sentences \\\n", "0 [yeah first_person_pronoun want to address the... 1 \n", "1 [umm pamela can pronoun hear first_person_pron... 1 \n", "2 [its on september th kayla and david first_per... 1 \n", "\n", " no_sw num_no_sw \\\n", "0 [yeah, want, address, roundtree, family, apolo... 26 \n", "1 [umm, pamela, pronoun, hear, stephanie, hardy,... 34 \n", "2 [september, th, kayla, david, wanted, apologiz... 60 \n", "\n", " topwords_unfil \\\n", "0 [(and, 6), (to, 5), (pronoun, 4), (the, 3), (f... \n", "1 [(pronoun, 4), (and, 4), (yall, 4), (tell, 3),... \n", "2 [(to, 6), (the, 5), (yall, 5), (pain, 4), (cau... \n", "\n", " topwords_fil ... v_pos_fd \\\n", "0 [(pronoun, 4), (family, 2), (im, 2), (yeah, 1)... ... 0.356 \n", "1 [(pronoun, 4), (yall, 4), (tell, 3), (love, 2)... ... 0.272 \n", "2 [(yall, 5), (pain, 4), (caused, 4), (apologize... ... 0.199 \n", "\n", " bow \\\n", "0 {'yeah': 1, 'want': 1, 'to': 5, 'address': 1, ... \n", "1 {'umm': 1, 'pamela': 1, 'can': 1, 'pronoun': 4... \n", "2 {'its': 1, 'on': 1, 'september': 1, 'th': 1, '... \n", "\n", " bow_nosw \\\n", "0 {'yeah': 1, 'want': 1, 'address': 1, 'roundtre... \n", "1 {'umm': 1, 'pamela': 1, 'pronoun': 4, 'hear': ... \n", "2 {'september': 1, 'th': 1, 'kayla': 1, 'david':... \n", "\n", " diy_cleaner \\\n", "0 yeah first_person_pronoun want to address the ... \n", "1 umm pamela can pronoun hear first_person_prono... \n", "2 its on september th kayla and david first_pers... \n", "\n", " pruned \\\n", "0 yeah first_person_pronoun want address roundtr... \n", "1 pamela pronoun hear first_person_pronoun steph... \n", "2 september kayla david first_person_pronoun wan... \n", "\n", " nltk_negs \\\n", "0 [yeah, want, to, address, the, roundtree, fami... \n", "1 [umm, pamela, can, pronoun, hear, stephanie, h... \n", "2 [its, on, september, th, kayla, and, david, wa... \n", "\n", " unigram_feats \\\n", "0 [to, the, and, and_NEG, family, pronoun, to_NE... \n", "1 [pronoun, and, yall, tell, the, love, am, for,... \n", "2 [yall_NEG, to, the_NEG, pain_NEG, caused_NEG, ... \n", "\n", " bigram_feats \\\n", "0 [yeah_want, want_to, to_address, address_the, ... \n", "1 [umm_pamela, pamela_can, can_pronoun, pronoun_... \n", "2 [its_on, on_september, september_th, th_kayla,... \n", "\n", " bigram_feats_neg PoN \n", "0 [yeah_want, want_to, to_address, address_the, ... yes \n", "1 [umm_pamela, pamela_can, can_pronoun, pronoun_... yes \n", "2 [its_on, on_september, september_th, th_kayla,... yes \n", "\n", "[3 rows x 40 columns]" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "all_df['PoN'] = all_df['labels']\n", "all_df[:3]\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## SAVE TO CSV!" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [], "source": [ "# all_df.to_csv('hw7_data_sentiment.csv',index=False)\n", "# all_df['PoN'] = all_df['labels']\n", "# all_df" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Vader Scores -- Gaussian\n", "Accuracy: 0.5058823529411764\n", "Accuracy: 0.5117647058823529\n", "Accuracy: 0.49411764705882355\n", "Accuracy: 0.5176470588235295\n", "Accuracy: 0.5176470588235295\n", "AVERAGE ACCURACY: 0.5094117647058823\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] } ], "source": [ "small_df = all_df.filter(['v_compound','v_pos', 'v_neg', 'v_neu'])\n", "tables = get_NB(small_df, all_df['PoN'], GaussianNB(), 'Vader Scores -- Gaussian')\n", "# display_NB_tables(tables)" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Positive Vader Scores -- Multinomial\n", "Accuracy: 0.5470588235294118\n", "Accuracy: 0.5764705882352941\n", "Accuracy: 0.5058823529411764\n", "Accuracy: 0.5176470588235295\n", "Accuracy: 0.5352941176470588\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "AVERAGE ACCURACY: 0.536470588235294\n" ] } ], "source": [ "small_df = all_df.filter(['v_pos','v_neu'])\n", "tables = get_NB(small_df, all_df['PoN'], MultinomialNB(), 'Positive Vader Scores -- Multinomial')" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Vader Scores from Summary -- Gaussian\n", "Accuracy: 0.06470588235294118\n", "Accuracy: 0.06470588235294118\n", "Accuracy: 0.10588235294117647\n", "Accuracy: 0.06470588235294118\n", "Accuracy: 0.08823529411764706\n", "AVERAGE ACCURACY: 0.07764705882352942\n" ] } ], "source": [ "small_df = all_df.filter(['v_compound_sum','v_pos_sum', 'v_neg_sum', 'v_neu_sum']) \n", "tables = get_NB(small_df, all_df['PoN'], GaussianNB(), 'Vader Scores from Summary -- Gaussian')" ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Vader Scores (original) and Vader Scores (summary) -- Gaussian\n", "Accuracy: 0.07058823529411765\n", "Accuracy: 0.07058823529411765\n", "Accuracy: 0.08823529411764706\n", "Accuracy: 0.10588235294117647\n", "Accuracy: 0.1\n", "AVERAGE ACCURACY: 0.08705882352941177\n" ] } ], "source": [ "small_df = all_df.filter(['v_compound_sum','v_pos_sum', 'v_neg_sum', 'v_neu_sum', \n", " 'v_compound','v_pos', 'v_neg', 'v_neu'])\n", "tables = get_NB(small_df, all_df['PoN'], GaussianNB(), 'Vader Scores (original) and Vader Scores (summary) -- Gaussian')" ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Vader Scores 50 most frequent filtered words -- Gaussian\n", "Accuracy: 0.47058823529411764\n", "Accuracy: 0.45294117647058824\n", "Accuracy: 0.4588235294117647\n", "Accuracy: 0.49411764705882355\n", "Accuracy: 0.5235294117647059\n", "AVERAGE ACCURACY: 0.48\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] } ], "source": [ "small_df = all_df.filter(['v_compound_fd','v_pos_fd', 'v_neu_fd', 'v_neg_fd'])\n", "tables = get_NB(small_df, all_df['PoN'], GaussianNB(), 'Vader Scores 50 most frequent filtered words -- Gaussian')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Bag of Words & Machine Learning " ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Starting point -- Gaussian\n", "Accuracy: 0.34705882352941175\n", "Accuracy: 0.34705882352941175\n", "Accuracy: 0.3588235294117647\n", "Accuracy: 0.4176470588235294\n", "Accuracy: 0.4294117647058823\n", "AVERAGE ACCURACY: 0.38\n" ] } ], "source": [ "all_df['bow_v1'] = all_df.apply(lambda x: Counter(x['tokens']), axis=1)\n", "all_df\n", "new_df = pd.DataFrame(all_df['bow_v1'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, GaussianNB(), 'Starting point -- Gaussian')" ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Starting point -- Gaussian\n", "Accuracy: 0.34705882352941175\n", "Accuracy: 0.34705882352941175\n", "Accuracy: 0.3588235294117647\n", "Accuracy: 0.4176470588235294\n", "Accuracy: 0.4294117647058823\n", "AVERAGE ACCURACY: 0.38\n" ] } ], "source": [ "tables = get_NB(new_df, new_df.index, GaussianNB(), 'Starting point -- Gaussian')" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Starting point -- Multinomial\n", "Accuracy: 0.4647058823529412\n", "Accuracy: 0.5\n", "Accuracy: 0.48823529411764705\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.5117647058823529\n", "Accuracy: 0.5058823529411764\n", "AVERAGE ACCURACY: 0.49411764705882355\n" ] } ], "source": [ "all_df['bow_v1'] = all_df.apply(lambda x: Counter(x['tokens']), axis=1)\n", "new_df = pd.DataFrame(all_df['bow_v1'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, MultinomialNB(), 'Starting point -- Multinomial')" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Starting point -- Bernoulli\n", "Accuracy: 0.48823529411764705\n", "Accuracy: 0.49411764705882355\n", "Accuracy: 0.5470588235294118\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.4588235294117647\n", "Accuracy: 0.5117647058823529\n", "AVERAGE ACCURACY: 0.5\n" ] } ], "source": [ "new_df = new_df.astype(bool).astype(int)\n", "tables = get_NB(new_df, new_df.index, BernoulliNB(), 'Starting point -- Bernoulli')" ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "DIY Cleaner -- Gaussian\n", "Accuracy: 0.34705882352941175\n", "Accuracy: 0.34705882352941175\n", "Accuracy: 0.3588235294117647\n", "Accuracy: 0.4176470588235294\n", "Accuracy: 0.4294117647058823\n", "AVERAGE ACCURACY: 0.38\n" ] } ], "source": [ "all_df['bow_v2'] = all_df.apply(lambda x: Counter(casual_tokenize(x['diy_cleaner'])), axis=1)\n", "new_df = pd.DataFrame(all_df['bow_v2'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, GaussianNB(), 'DIY Cleaner -- Gaussian')" ] }, { "cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "DIY Cleaner -- Multinomial\n", "Accuracy: 0.4647058823529412\n", "Accuracy: 0.4823529411764706\n", "Accuracy: 0.47058823529411764\n", "Accuracy: 0.48823529411764705\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.48823529411764705\n", "AVERAGE ACCURACY: 0.4788235294117647\n" ] } ], "source": [ "all_df['bow_v2'] = all_df.apply(lambda x: Counter(casual_tokenize(x['diy_cleaner'])), axis=1)\n", "new_df = pd.DataFrame(all_df['bow_v2'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, MultinomialNB(), 'DIY Cleaner -- Multinomial')" ] }, { "cell_type": "code", "execution_count": 44, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "DIY Cleaner -- Bernoulli\n", "Accuracy: 0.48823529411764705\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.5\n", "Accuracy: 0.5470588235294118\n", "Accuracy: 0.4588235294117647\n", "Accuracy: 0.5117647058823529\n", "AVERAGE ACCURACY: 0.5011764705882353\n" ] } ], "source": [ "new_df = new_df.astype(bool).astype(int)\n", "tables = get_NB(new_df, new_df.index, BernoulliNB(), 'DIY Cleaner -- Bernoulli')" ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Pruned Words -- Gaussian\n", "Accuracy: 0.37058823529411766\n", "Accuracy: 0.34705882352941175\n", "Accuracy: 0.36470588235294116\n", "Accuracy: 0.40588235294117647\n", "Accuracy: 0.43529411764705883\n", "AVERAGE ACCURACY: 0.3847058823529412\n" ] } ], "source": [ "all_df['bow_v3'] = all_df.apply(lambda x: Counter(casual_tokenize(x['pruned'])), axis=1)\n", "new_df = pd.DataFrame(all_df['bow_v3'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, GaussianNB(), 'Pruned Words -- Gaussian')" ] }, { "cell_type": "code", "execution_count": 46, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Pruned Words -- Multinomial\n", "Accuracy: 0.4823529411764706\n", "Accuracy: 0.49411764705882355\n", "Accuracy: 0.47058823529411764\n", "Accuracy: 0.5\n", "Accuracy: 0.4588235294117647\n", "AVERAGE ACCURACY: 0.48117647058823537\n" ] } ], "source": [ "all_df['bow_v3'] = all_df.apply(lambda x: Counter(casual_tokenize(x['pruned'])), axis=1)\n", "new_df = pd.DataFrame(all_df['bow_v3'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, MultinomialNB(), 'Pruned Words -- Multinomial')" ] }, { "cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Pruned Words -- Bernoulli\n", "Accuracy: 0.5\n", "Accuracy: 0.5117647058823529\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.5411764705882353\n", "Accuracy: 0.45294117647058824\n", "Accuracy: 0.5235294117647059\n", "AVERAGE ACCURACY: 0.5058823529411764\n" ] } ], "source": [ "new_df = new_df.astype(bool).astype(int)\n", "tables = get_NB(new_df, new_df.index, BernoulliNB(), 'Pruned Words -- Bernoulli')" ] }, { "cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "NLTK negs -- Gaussian\n", "Accuracy: 0.32941176470588235\n", "Accuracy: 0.36470588235294116\n", "Accuracy: 0.4\n", "Accuracy: 0.43529411764705883\n", "Accuracy: 0.4588235294117647\n", "AVERAGE ACCURACY: 0.3976470588235294\n" ] } ], "source": [ "all_df['bow_v4'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['nltk_negs']))), axis=1)\n", "new_df = pd.DataFrame(all_df['bow_v4'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, GaussianNB(), 'NLTK negs -- Gaussian')" ] }, { "cell_type": "code", "execution_count": 49, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "NLTK negs -- Multinomial\n", "Accuracy: 0.32941176470588235\n", "Accuracy: 0.36470588235294116\n", "Accuracy: 0.4\n", "Accuracy: 0.43529411764705883\n", "Accuracy: 0.4588235294117647\n", "AVERAGE ACCURACY: 0.3976470588235294\n" ] } ], "source": [ "all_df['bow_v4'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['nltk_negs']))), axis=1)\n", "new_df = pd.DataFrame(all_df['bow_v4'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, GaussianNB(), 'NLTK negs -- Multinomial')" ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "NLTK negs -- Bernoulli\n", "Accuracy: 0.5176470588235295\n", "Accuracy: 0.5235294117647059\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.5823529411764706\n", "Accuracy: 0.4647058823529412\n", "Accuracy: 0.5\n", "AVERAGE ACCURACY: 0.5176470588235295\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] } ], "source": [ "new_df = new_df.astype(bool).astype(int)\n", "tables = get_NB(new_df, new_df.index, BernoulliNB(), 'NLTK negs -- Bernoulli')" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Bigram Feats -- Gaussian\n", "Accuracy: 0.40588235294117647\n", "Accuracy: 0.4176470588235294\n", "Accuracy: 0.4117647058823529\n", "Accuracy: 0.40588235294117647\n", "Accuracy: 0.4647058823529412\n", "AVERAGE ACCURACY: 0.4211764705882353\n" ] } ], "source": [ "all_df['bow_v5'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['bigram_feats']))), axis=1)\n", "new_df = pd.DataFrame(all_df['bow_v5'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, GaussianNB(), 'Bigram Feats -- Gaussian')" ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Bigram Feats -- Multinomial\n", "Accuracy: 0.5117647058823529\n", "Accuracy: 0.5470588235294118\n", "Accuracy: 0.45294117647058824\n", "Accuracy: 0.5\n", "Accuracy: 0.4823529411764706\n", "AVERAGE ACCURACY: 0.4988235294117647\n" ] } ], "source": [ "all_df['bow_v5'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['bigram_feats']))), axis=1)\n", "new_df = pd.DataFrame(all_df['bow_v5'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, MultinomialNB(), 'Bigram Feats -- Multinomial')" ] }, { "cell_type": "code", "execution_count": 53, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Bigram Feats -- Bernoulli\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.5470588235294118\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.5588235294117647\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.5294117647058824\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.48823529411764705\n", "Accuracy: 0.5235294117647059\n", "AVERAGE ACCURACY: 0.5294117647058824\n" ] } ], "source": [ "new_df = new_df.astype(bool).astype(int)\n", "tables = get_NB(new_df, new_df.index, BernoulliNB(), 'Bigram Feats -- Bernoulli')" ] }, { "cell_type": "code", "execution_count": 55, "metadata": {}, "outputs": [], "source": [ "# all_df['bow_v6'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['no_shared_words']))), axis=1)\n", "# new_df = pd.DataFrame(all_df['bow_v6'].tolist(), all_df['PoN'])\n", "# new_df = new_df.fillna(0).astype(int)\n", "# new_df[:5]\n", "# tables = get_NB(new_df, new_df.index, GaussianNB(), 'No Shared Words -- Gaussian')" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "all_df['bow_v6'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['no_shared_words']))), axis=1)\n", "new_df = pd.DataFrame(all_df['bow_v6'].tolist(), all_df['PoN'])\n", "new_df = new_df.fillna(0).astype(int)\n", "new_df[:5]\n", "tables = get_NB(new_df, new_df.index, MultinomialNB(), 'No Shared Words -- Multinomial')" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "new_df = new_df.astype(bool).astype(int)\n", "tables = get_NB(new_df, new_df.index, BernoulliNB(), 'No Shared Words -- Bernoulli')" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "create_word_cloud_with_mask('yellow_square.png', big_bow, 750, \"Top Words\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "create_word_cloud_with_mask('red_square.png', big_bow_n, 750, \"Top Negative Words\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "create_word_cloud_with_mask('green_square.png', big_bow_p, 750, \"Top Positive Words\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from sklearn.pipeline import Pipeline\n", "from sklearn.feature_extraction.text import CountVectorizer\n", "from sklearn.model_selection import cross_val_score\n", "from sklearn.naive_bayes import BernoulliNB, MultinomialNB\n", "\n", "def runPipeline(classifier, boolean, cv, X, y):\n", " nb_clf_pipe = Pipeline([('vect', CountVectorizer(encoding='latin-1', binary=boolean)),('nb', classifier)])\n", " scores = cross_val_score(nb_clf_pipe, X, y, cv=cv)\n", " avg=sum(scores)/len(scores)\n", "# pretty_line = \"{} | Accuracy using {} -- and booleans? {}\"\n", " pretty_line = \"{} | B? {} | CV: {} | Classifier: {}\"\n", " print(pretty_line.format(avg, str(boolean)[0], cv, str(classifier).split('(')[0]))\n", "\n", "# X = array of data\n", "# y = array of labels\n", "\n", "hw6 = all_df[[0,'PoN']]\n", "X = hw6[0].tolist()\n", "y = hw6['PoN'].tolist()\n", "\n", "runPipeline(BernoulliNB(), False, 5, X=X, y=y)\n", "runPipeline(BernoulliNB(), False, 3, X=X, y=y)\n", "runPipeline(MultinomialNB(), False, 5, X=X, y=y)\n", "runPipeline(MultinomialNB(), False, 3, X=X, y=y)\n", "runPipeline(MultinomialNB(), True, 5, X=X, y=y)\n", "runPipeline(MultinomialNB(), True, 3, X=X, y=y)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from tabulate import tabulate\n", "\n", "df = hw6\n", "def shorten(long_string):\n", " return long_string[:1] if len(long_string) < 21 else long_string[:20]\n", "\n", "def df_for_tabulate(df, column):\n", " pretty_df = df.copy()\n", " pretty_df[column] = pretty_df.apply(lambda x: shorten(x[column]), axis = 1)\n", " return pretty_df\n", " \n", "tabulate_df = df_for_tabulate(df, 0)\n", "print(tabulate(tabulate_df[:10], tablefmt=\"simple\", headers=tabulate_df.columns))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.4" } }, "nbformat": 4, "nbformat_minor": 2 }