{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Sentiment Analysis\n", "## TextBlob + Vader + NLTK + Naive Bayes\n", "via [this tutorial](https://levelup.gitconnected.com/sentiment-analysis-using-machine-learning-python-9122e03f8f7b) |10-6-19" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "from textblob import TextBlob\n", "from IPython.display import display, HTML\n", "import os\n", "import pandas as pd\n", "import numpy as np\n", "from nltk.sentiment.vader import SentimentIntensityAnalyzer\n", "sid = SentimentIntensityAnalyzer()" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "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", "# HW 1\n", "neg_k = get_data_from_files('AI_NEG/')\n", "pos_k = get_data_from_files('AI_POS/')\n", "neg_a = get_data_from_files('NEG/')\n", "pos_a = get_data_from_files('POS/')\n", "\n", "# HW2\n", "neg_cornell = get_data_from_files('neg_cornell/')\n", "pos_cornell = get_data_from_files('pos_cornell/')\n", "\n", "# HW3\n", "neg_dirty = get_data_from_files('NEG_dirty/')\n", "pos_dirty = get_data_from_files('POS_dirty/')\n", "neg_joker = get_data_from_files('NEG_JK/')\n", "pos_joker = get_data_from_files('POS_JK/')\n", "\n", "# HW4\n", "neg_hw4 = get_data_from_files('neg_hw4/')\n", "pos_hw4 = get_data_from_files('pos_hw4/')\n", "\n", "# HW4\n", "false_lie_hw4 = get_data_from_files('hw4_lie_false/')\n", "true_lie_hw4 = get_data_from_files('hw4_lie_true/')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# TEXT BLOB" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "def get_pn(num):\n", " return 'neg' if num < 0 else 'pos'\n", "\n", "def get_sentiment(array, label):\n", " blobs = [[TextBlob(text), text] for text in array]\n", " return ([{'label': label,\n", " 'prediction': get_pn(obj.sentiment.polarity),\n", " 'sentiment': obj.sentiment.polarity,\n", " 'length': len(text), \n", " 'excerpt': text[:50]} for obj,text in blobs])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 1: Kendra's Data" ] }, { "cell_type": "code", "execution_count": 46, "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", "
labelpredictionsentimentlengthexcerptaccurate
0negneg-0.15714376WHERE ARE THE JOBS?! OH THAT'S RIGHT. ARTIFICI...yes
1negneg-0.75000096How can we trust Artificial Intelligence to dr...yes
2negneg-0.77500031I hate artificial intelligence!yes
3negneg-0.75000047My dog is terrified by artificial intelligence!yes
4negneg-0.75000068Artificial intelligence is going to melt the b...yes
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 neg neg -0.157143 76 \n", "1 neg neg -0.750000 96 \n", "2 neg neg -0.775000 31 \n", "3 neg neg -0.750000 47 \n", "4 neg neg -0.750000 68 \n", "\n", " excerpt accurate \n", "0 WHERE ARE THE JOBS?! OH THAT'S RIGHT. ARTIFICI... yes \n", "1 How can we trust Artificial Intelligence to dr... yes \n", "2 I hate artificial intelligence! yes \n", "3 My dog is terrified by artificial intelligence! yes \n", "4 Artificial intelligence is going to melt the b... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictionsentimentlengthexcerptaccurate
0posneg-0.11250065My dog is excited by the advancements in artif...no
1posneg-0.075000133I'm excited for my child to grow up and have t...no
2posneg-0.12500031I love artificial intelligence!no
3posneg-0.300000121Order my groceries, pay my taxes, take my kids...no
4posneg-0.133333116I'm grateful every day that my child will like...no
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 pos neg -0.112500 65 \n", "1 pos neg -0.075000 133 \n", "2 pos neg -0.125000 31 \n", "3 pos neg -0.300000 121 \n", "4 pos neg -0.133333 116 \n", "\n", " excerpt accurate \n", "0 My dog is excited by the advancements in artif... no \n", "1 I'm excited for my child to grow up and have t... no \n", "2 I love artificial intelligence! no \n", "3 Order my groceries, pay my taxes, take my kids... no \n", "4 I'm grateful every day that my child will like... no " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 5 out of 5 1.0\n", "CORRECT PREDICT TRUE: 0 out of 5 0.0\n" ] } ], "source": [ "df_n = pd.DataFrame(get_sentiment(neg_k, 'neg'))\n", "df_p = pd.DataFrame(get_sentiment(pos_k, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n)\n", "display(df_p)\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 2: Ami's Data" ] }, { "cell_type": "code", "execution_count": 45, "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", "
labelpredictionsentimentlengthexcerptaccurate
0negneg-0.0545773554that's exactly how long the movie felt to me ....yes
1negpos0.0254672929\" quest for camelot \" is warner bros . ' firs...no
2negpos0.0033343365so ask yourself what \" 8mm \" ( \" eight millime...no
3negpos0.0229254418synopsis : a mentally unstable man undergoing ...no
4negpos0.0432343911capsule : in 2176 on the planet mars police ta...no
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 neg neg -0.054577 3554 \n", "1 neg pos 0.025467 2929 \n", "2 neg pos 0.003334 3365 \n", "3 neg pos 0.022925 4418 \n", "4 neg pos 0.043234 3911 \n", "\n", " excerpt accurate \n", "0 that's exactly how long the movie felt to me .... yes \n", "1 \" quest for camelot \" is warner bros . ' firs... no \n", "2 so ask yourself what \" 8mm \" ( \" eight millime... no \n", "3 synopsis : a mentally unstable man undergoing ... no \n", "4 capsule : in 2176 on the planet mars police ta... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictionsentimentlengthexcerptaccurate
0pospos0.0236634227films adapted from comic books have had plenty...yes
1pospos0.1310922421you've got mail works alot better than it dese...yes
2pospos0.1106266092\" jaws \" is a rare film that grabs your atten...yes
3pospos0.1038474096every now and then a movie comes along from a ...yes
4posneg-0.0701513898moviemaking is a lot like being the general ma...no
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 pos pos 0.023663 4227 \n", "1 pos pos 0.131092 2421 \n", "2 pos pos 0.110626 6092 \n", "3 pos pos 0.103847 4096 \n", "4 pos neg -0.070151 3898 \n", "\n", " excerpt accurate \n", "0 films adapted from comic books have had plenty... yes \n", "1 you've got mail works alot better than it dese... yes \n", "2 \" jaws \" is a rare film that grabs your atten... yes \n", "3 every now and then a movie comes along from a ... yes \n", "4 moviemaking is a lot like being the general ma... no " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 1 out of 5 0.2\n", "CORRECT PREDICT TRUE: 4 out of 5 0.8\n" ] } ], "source": [ "df_n = pd.DataFrame(get_sentiment(neg_a, 'neg'))\n", "df_p = pd.DataFrame(get_sentiment(pos_a, 'pos'))\n", "\n", "import numpy as np\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n)\n", "display(df_p)\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 3: Cornell Data" ] }, { "cell_type": "code", "execution_count": 44, "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", "
labelpredictionsentimentlengthexcerptaccurate
0negpos0.0262405953bad . bad . \\nbad . \\nthat one word seems to p...no
1negpos0.0760403396isn't it the ultimate sign of a movie's cinema...no
2negneg-0.1287332762\" gordy \" is not a movie , it is a 90-minute-...yes
3negneg-0.0004853840disconnect the phone line . \\ndon't accept the...yes
4negpos0.1227702270when robert forster found himself famous again...no
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 neg pos 0.026240 5953 \n", "1 neg pos 0.076040 3396 \n", "2 neg neg -0.128733 2762 \n", "3 neg neg -0.000485 3840 \n", "4 neg pos 0.122770 2270 \n", "\n", " excerpt accurate \n", "0 bad . bad . \\nbad . \\nthat one word seems to p... no \n", "1 isn't it the ultimate sign of a movie's cinema... no \n", "2 \" gordy \" is not a movie , it is a 90-minute-... yes \n", "3 disconnect the phone line . \\ndon't accept the... yes \n", "4 when robert forster found himself famous again... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictionsentimentlengthexcerptaccurate
0pospos0.2211734662assume nothing . \\nthe phrase is perhaps one o...yes
1pospos0.0897363839plot : derek zoolander is a male model . \\nhe ...yes
2pospos0.2067439380i actually am a fan of the original 1961 or so...yes
3pospos0.1419052407a movie that's been as highly built up as the ...yes
4pospos0.1763321840\" good will hunting \" is two movies in one : ...yes
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 pos pos 0.221173 4662 \n", "1 pos pos 0.089736 3839 \n", "2 pos pos 0.206743 9380 \n", "3 pos pos 0.141905 2407 \n", "4 pos pos 0.176332 1840 \n", "\n", " excerpt accurate \n", "0 assume nothing . \\nthe phrase is perhaps one o... yes \n", "1 plot : derek zoolander is a male model . \\nhe ... yes \n", "2 i actually am a fan of the original 1961 or so... yes \n", "3 a movie that's been as highly built up as the ... yes \n", "4 \" good will hunting \" is two movies in one : ... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 229 out of 1000 0.229\n", "CORRECT PREDICT TRUE: 971 out of 1000 0.971\n" ] } ], "source": [ "df_n = pd.DataFrame(get_sentiment(neg_cornell, 'neg'))\n", "df_p = pd.DataFrame(get_sentiment(pos_cornell, 'pos'))\n", "\n", "import numpy as np\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n[:5])\n", "display(df_p[:5])\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 4: Dirty Data" ] }, { "cell_type": "code", "execution_count": 43, "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", "
labelpredictionsentimentlengthexcerptaccurate
0negneg-0.0046653777by starring in amy heckerlings clueless two ...yes
1negpos0.1191843639i have little against remakes and updates of o...no
2negpos0.1008864247i cant recall a previous film experience where...no
3negpos0.0975264308the tagline for this film is : some houses ar...no
4negpos0.0487455175warner brothers ; rated pg-13 ( mild violence ...no
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 neg neg -0.004665 3777 \n", "1 neg pos 0.119184 3639 \n", "2 neg pos 0.100886 4247 \n", "3 neg pos 0.097526 4308 \n", "4 neg pos 0.048745 5175 \n", "\n", " excerpt accurate \n", "0 by starring in amy heckerlings clueless two ... yes \n", "1 i have little against remakes and updates of o... no \n", "2 i cant recall a previous film experience where... no \n", "3 the tagline for this film is : some houses ar... no \n", "4 warner brothers ; rated pg-13 ( mild violence ... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictionsentimentlengthexcerptaccurate
0pospos0.1346414584for the first reel of girls town , you just ca...yes
1pospos0.1371343102field of dreams almost defies description . al...yes
2pospos0.1813553521meet joe black is your classic boy-meets-girl ...yes
3pospos0.1041012192an indian runner was more than a courier . he ...yes
4pospos0.2049674955every once in a while , when an exceptional fa...yes
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 pos pos 0.134641 4584 \n", "1 pos pos 0.137134 3102 \n", "2 pos pos 0.181355 3521 \n", "3 pos pos 0.104101 2192 \n", "4 pos pos 0.204967 4955 \n", "\n", " excerpt accurate \n", "0 for the first reel of girls town , you just ca... yes \n", "1 field of dreams almost defies description . al... yes \n", "2 meet joe black is your classic boy-meets-girl ... yes \n", "3 an indian runner was more than a courier . he ... yes \n", "4 every once in a while , when an exceptional fa... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 227 out of 1000 0.227\n", "CORRECT PREDICT TRUE: 972 out of 1000 0.972\n" ] } ], "source": [ "df_n = pd.DataFrame(get_sentiment(neg_dirty, 'neg'))\n", "df_p = pd.DataFrame(get_sentiment(pos_dirty, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n[:5])\n", "display(df_p[:5])\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 5: Joker Review Data" ] }, { "cell_type": "code", "execution_count": 42, "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", "
labelpredictionsentimentlengthexcerptaccurate
0negpos0.1520831734Missed Opportunity\\nI had been very excited t...no
1negneg-0.0018523285/5 for Phoenix's acting..\\nI don't think the...yes
2negpos0.200000145Everyone praised an overrated movie.\\nOverrat...no
3negneg-0.038095350What idiotic FIlm\\nI can say that Phoenix is ...yes
4negpos0.126398711Terrible\\nThe only thing good about this movi...no
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 neg pos 0.152083 1734 \n", "1 neg neg -0.001852 328 \n", "2 neg pos 0.200000 145 \n", "3 neg neg -0.038095 350 \n", "4 neg pos 0.126398 711 \n", "\n", " excerpt accurate \n", "0 Missed Opportunity\\nI had been very excited t... no \n", "1 5/5 for Phoenix's acting..\\nI don't think the... yes \n", "2 Everyone praised an overrated movie.\\nOverrat... no \n", "3 What idiotic FIlm\\nI can say that Phoenix is ... yes \n", "4 Terrible\\nThe only thing good about this movi... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictionsentimentlengthexcerptaccurate
0pospos0.1071625554funny like a clown\\nGreetings again from the ...yes
1pospos0.014881473Only certain people can relate\\nThis is a mov...yes
2pospos0.0082942509\"That's Life.\"\\nIn an era of cinema so satura...yes
3pospos0.0369394022Best DC movie since The Dark Knight Rises\\nDC...yes
4posneg-0.0171621430unbelievable, unrelatable, a bit boring to be...no
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 pos pos 0.107162 5554 \n", "1 pos pos 0.014881 473 \n", "2 pos pos 0.008294 2509 \n", "3 pos pos 0.036939 4022 \n", "4 pos neg -0.017162 1430 \n", "\n", " excerpt accurate \n", "0 funny like a clown\\nGreetings again from the ... yes \n", "1 Only certain people can relate\\nThis is a mov... yes \n", "2 \"That's Life.\"\\nIn an era of cinema so satura... yes \n", "3 Best DC movie since The Dark Knight Rises\\nDC... yes \n", "4 unbelievable, unrelatable, a bit boring to be... no " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 64 out of 123 0.5203252032520326\n", "CORRECT PREDICT TRUE: 114 out of 123 0.926829268292683\n" ] } ], "source": [ "df_n = pd.DataFrame(get_sentiment(neg_joker, 'neg'))\n", "df_p = pd.DataFrame(get_sentiment(pos_joker, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n[:5])\n", "display(df_p[:5])\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 6: HW4 [Sentiment]" ] }, { "cell_type": "code", "execution_count": 41, "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", "
labelpredictionsentimentlengthexcerptaccurate
0negneg-0.273958251I went to XYZ restaurant last week and I was v...yes
1negpos0.083333359In each of the diner dish there are at least o...no
2negneg-0.134722748This is the last place you would want to dine ...yes
3negneg-0.166667378I went to this restaurant where I had ordered ...yes
4negpos0.152455381I went there with two friends at 6pm. Long que...no
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 neg neg -0.273958 251 \n", "1 neg pos 0.083333 359 \n", "2 neg neg -0.134722 748 \n", "3 neg neg -0.166667 378 \n", "4 neg pos 0.152455 381 \n", "\n", " excerpt accurate \n", "0 I went to XYZ restaurant last week and I was v... yes \n", "1 In each of the diner dish there are at least o... no \n", "2 This is the last place you would want to dine ... yes \n", "3 I went to this restaurant where I had ordered ... yes \n", "4 I went there with two friends at 6pm. Long que... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictionsentimentlengthexcerptaccurate
0pospos0.626786132This restaurant ROCKS! I mean the food is grea...yes
1pospos0.500000441Stronghearts cafe is the BEST! The owners have...yes
2pospos0.480208485I went to cruise dinner in NYC with Spirit Cru...yes
3pospos0.240278404Halos is home. I have been here numerous times...yes
4pospos0.552083324The best restaurant I have ever been was a sma...yes
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 pos pos 0.626786 132 \n", "1 pos pos 0.500000 441 \n", "2 pos pos 0.480208 485 \n", "3 pos pos 0.240278 404 \n", "4 pos pos 0.552083 324 \n", "\n", " excerpt accurate \n", "0 This restaurant ROCKS! I mean the food is grea... yes \n", "1 Stronghearts cafe is the BEST! The owners have... yes \n", "2 I went to cruise dinner in NYC with Spirit Cru... yes \n", "3 Halos is home. I have been here numerous times... yes \n", "4 The best restaurant I have ever been was a sma... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 26 out of 46 0.5652173913043478\n", "CORRECT PREDICT TRUE: 46 out of 46 1.0\n" ] } ], "source": [ "df_n = pd.DataFrame(get_sentiment(neg_hw4, 'neg'))\n", "df_p = pd.DataFrame(get_sentiment(pos_hw4, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n[:5])\n", "display(df_p[:5])\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 7: HW4 [Deception]" ] }, { "cell_type": "code", "execution_count": 40, "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", "
labelpredictionsentimentlengthexcerptaccurate
0negpos0.442752386Gannon’s Isle Ice Cream served the best ice cr...no
1negpos0.197500340Hibachi the grill is one of my favorite restau...no
2negpos0.353912790RIM KAAP One of the best Thai restaurants in t...no
3negpos0.578788391It is a France restaurant which has Michelin t...no
4negpos0.331373710Its hard to pick a favorite dining experience ...no
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 neg pos 0.442752 386 \n", "1 neg pos 0.197500 340 \n", "2 neg pos 0.353912 790 \n", "3 neg pos 0.578788 391 \n", "4 neg pos 0.331373 710 \n", "\n", " excerpt accurate \n", "0 Gannon’s Isle Ice Cream served the best ice cr... no \n", "1 Hibachi the grill is one of my favorite restau... no \n", "2 RIM KAAP One of the best Thai restaurants in t... no \n", "3 It is a France restaurant which has Michelin t... no \n", "4 Its hard to pick a favorite dining experience ... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictionsentimentlengthexcerptaccurate
0pospos0.0000001?yes
1pospos0.236833289Twin Trees Cicero NY HUGE salad bar and high q...yes
2posneg-0.249762519The worst restaurant that I have ever eaten in...no
3pospos0.0000001?yes
4pospos0.019481234I have been to a Asian restaurant in New York ...yes
\n", "
" ], "text/plain": [ " label prediction sentiment length \\\n", "0 pos pos 0.000000 1 \n", "1 pos pos 0.236833 289 \n", "2 pos neg -0.249762 519 \n", "3 pos pos 0.000000 1 \n", "4 pos pos 0.019481 234 \n", "\n", " excerpt accurate \n", "0 ? yes \n", "1 Twin Trees Cicero NY HUGE salad bar and high q... yes \n", "2 The worst restaurant that I have ever eaten in... no \n", "3 ? yes \n", "4 I have been to a Asian restaurant in New York ... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 14 out of 46 0.30434782608695654\n", "CORRECT PREDICT TRUE: 34 out of 46 0.7391304347826086\n" ] } ], "source": [ "df_n = pd.DataFrame(get_sentiment(false_lie_hw4, 'neg'))\n", "df_p = pd.DataFrame(get_sentiment(true_lie_hw4, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n[:5])\n", "display(df_p[:5])\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# VADER" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "def get_pn(num):\n", " return 'neg' if num < 0 else 'pos'\n", "\n", "def get_vader_scores(array, label):\n", " vader_array = []\n", " for sentence in array:\n", " ss = sid.polarity_scores(sentence)\n", " vader_array.append({'label': label,\n", " 'prediction': get_pn(ss['compound']),\n", " 'compound': ss['compound'], \n", " 'excerpt': sentence[:50]})\n", " return vader_array" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[\"WHERE ARE THE JOBS?! OH THAT'S RIGHT. ARTIFICIAL INTELLIGENCE TOOK OUR JOBS.\",\n", " \"How can we trust Artificial Intelligence to drive our cars when they can't even hack a captcha?!\",\n", " 'I hate artificial intelligence!',\n", " 'My dog is terrified by artificial intelligence!',\n", " 'Artificial intelligence is going to melt the brains of our children!']" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "neg_k" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 1: Kendra's Data" ] }, { "cell_type": "code", "execution_count": 38, "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", "
labelpredictioncompoundexcerptaccurate
0negpos0.5255WHERE ARE THE JOBS?! OH THAT'S RIGHT. ARTIFICI...no
1negpos0.7712How can we trust Artificial Intelligence to dr...no
2negneg-0.2244I hate artificial intelligence!yes
3negneg-0.2942My dog is terrified by artificial intelligence!yes
4negpos0.5255Artificial intelligence is going to melt the b...no
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 neg pos 0.5255 \n", "1 neg pos 0.7712 \n", "2 neg neg -0.2244 \n", "3 neg neg -0.2942 \n", "4 neg pos 0.5255 \n", "\n", " excerpt accurate \n", "0 WHERE ARE THE JOBS?! OH THAT'S RIGHT. ARTIFICI... no \n", "1 How can we trust Artificial Intelligence to dr... no \n", "2 I hate artificial intelligence! yes \n", "3 My dog is terrified by artificial intelligence! yes \n", "4 Artificial intelligence is going to melt the b... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictioncompoundexcerptaccurate
0pospos0.6705My dog is excited by the advancements in artif...yes
1pospos0.8271I'm excited for my child to grow up and have t...yes
2pospos0.8221I love artificial intelligence!yes
3pospos0.8213Order my groceries, pay my taxes, take my kids...yes
4pospos0.8402I'm grateful every day that my child will like...yes
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 pos pos 0.6705 \n", "1 pos pos 0.8271 \n", "2 pos pos 0.8221 \n", "3 pos pos 0.8213 \n", "4 pos pos 0.8402 \n", "\n", " excerpt accurate \n", "0 My dog is excited by the advancements in artif... yes \n", "1 I'm excited for my child to grow up and have t... yes \n", "2 I love artificial intelligence! yes \n", "3 Order my groceries, pay my taxes, take my kids... yes \n", "4 I'm grateful every day that my child will like... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 2 out of 5 0.4\n", "CORRECT PREDICT TRUE: 5 out of 5 1.0\n" ] } ], "source": [ "df_n = pd.DataFrame(get_vader_scores(neg_k, 'neg'))\n", "df_p = pd.DataFrame(get_vader_scores(pos_k, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n)\n", "display(df_p)\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 2: Ami's Data" ] }, { "cell_type": "code", "execution_count": 37, "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", "
labelpredictioncompoundexcerptaccurate
0negpos0.7836that's exactly how long the movie felt to me ....no
1negneg-0.8481\" quest for camelot \" is warner bros . ' firs...yes
2negneg-0.9753so ask yourself what \" 8mm \" ( \" eight millime...yes
3negpos0.6824synopsis : a mentally unstable man undergoing ...no
4negneg-0.9879capsule : in 2176 on the planet mars police ta...yes
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 neg pos 0.7836 \n", "1 neg neg -0.8481 \n", "2 neg neg -0.9753 \n", "3 neg pos 0.6824 \n", "4 neg neg -0.9879 \n", "\n", " excerpt accurate \n", "0 that's exactly how long the movie felt to me .... no \n", "1 \" quest for camelot \" is warner bros . ' firs... yes \n", "2 so ask yourself what \" 8mm \" ( \" eight millime... yes \n", "3 synopsis : a mentally unstable man undergoing ... no \n", "4 capsule : in 2176 on the planet mars police ta... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictioncompoundexcerptaccurate
0posneg-0.5887films adapted from comic books have had plenty...no
1pospos0.9964you've got mail works alot better than it dese...yes
2pospos0.9868\" jaws \" is a rare film that grabs your atten...yes
3pospos0.8825every now and then a movie comes along from a ...yes
4posneg-0.3525moviemaking is a lot like being the general ma...no
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 pos neg -0.5887 \n", "1 pos pos 0.9964 \n", "2 pos pos 0.9868 \n", "3 pos pos 0.8825 \n", "4 pos neg -0.3525 \n", "\n", " excerpt accurate \n", "0 films adapted from comic books have had plenty... no \n", "1 you've got mail works alot better than it dese... yes \n", "2 \" jaws \" is a rare film that grabs your atten... yes \n", "3 every now and then a movie comes along from a ... yes \n", "4 moviemaking is a lot like being the general ma... no " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 3 out of 5 0.6\n", "CORRECT PREDICT TRUE: 3 out of 5 0.6\n" ] } ], "source": [ "df_n = pd.DataFrame(get_vader_scores(neg_a, 'neg'))\n", "df_p = pd.DataFrame(get_vader_scores(pos_a, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n)\n", "display(df_p)\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 3: Cornell Data" ] }, { "cell_type": "code", "execution_count": 47, "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", "
labelpredictioncompoundexcerptaccurate
0negpos0.9695bad . bad . \\nbad . \\nthat one word seems to p...no
1negpos0.1722isn't it the ultimate sign of a movie's cinema...no
2negneg-0.9970\" gordy \" is not a movie , it is a 90-minute-...yes
3negpos0.9861disconnect the phone line . \\ndon't accept the...no
4negpos0.7445when robert forster found himself famous again...no
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 neg pos 0.9695 \n", "1 neg pos 0.1722 \n", "2 neg neg -0.9970 \n", "3 neg pos 0.9861 \n", "4 neg pos 0.7445 \n", "\n", " excerpt accurate \n", "0 bad . bad . \\nbad . \\nthat one word seems to p... no \n", "1 isn't it the ultimate sign of a movie's cinema... no \n", "2 \" gordy \" is not a movie , it is a 90-minute-... yes \n", "3 disconnect the phone line . \\ndon't accept the... no \n", "4 when robert forster found himself famous again... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictioncompoundexcerptaccurate
0pospos0.9985assume nothing . \\nthe phrase is perhaps one o...yes
1pospos0.9853plot : derek zoolander is a male model . \\nhe ...yes
2pospos0.9998i actually am a fan of the original 1961 or so...yes
3pospos0.9671a movie that's been as highly built up as the ...yes
4pospos0.9300\" good will hunting \" is two movies in one : ...yes
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 pos pos 0.9985 \n", "1 pos pos 0.9853 \n", "2 pos pos 0.9998 \n", "3 pos pos 0.9671 \n", "4 pos pos 0.9300 \n", "\n", " excerpt accurate \n", "0 assume nothing . \\nthe phrase is perhaps one o... yes \n", "1 plot : derek zoolander is a male model . \\nhe ... yes \n", "2 i actually am a fan of the original 1961 or so... yes \n", "3 a movie that's been as highly built up as the ... yes \n", "4 \" good will hunting \" is two movies in one : ... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 445 out of 1000 0.445\n", "CORRECT PREDICT TRUE: 828 out of 1000 0.828\n" ] } ], "source": [ "df_n = pd.DataFrame(get_vader_scores(neg_cornell, 'neg'))\n", "df_p = pd.DataFrame(get_vader_scores(pos_cornell, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n[:5])\n", "display(df_p[:5])\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 4: Dirty Data" ] }, { "cell_type": "code", "execution_count": 48, "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", "
labelpredictioncompoundexcerptaccurate
0negneg-0.9326by starring in amy heckerlings clueless two ...yes
1negpos0.8326i have little against remakes and updates of o...no
2negpos0.9491i cant recall a previous film experience where...no
3negpos0.9854the tagline for this film is : some houses ar...no
4negneg-0.8077warner brothers ; rated pg-13 ( mild violence ...yes
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 neg neg -0.9326 \n", "1 neg pos 0.8326 \n", "2 neg pos 0.9491 \n", "3 neg pos 0.9854 \n", "4 neg neg -0.8077 \n", "\n", " excerpt accurate \n", "0 by starring in amy heckerlings clueless two ... yes \n", "1 i have little against remakes and updates of o... no \n", "2 i cant recall a previous film experience where... no \n", "3 the tagline for this film is : some houses ar... no \n", "4 warner brothers ; rated pg-13 ( mild violence ... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictioncompoundexcerptaccurate
0posneg-0.9888for the first reel of girls town , you just ca...no
1pospos0.9885field of dreams almost defies description . al...yes
2pospos0.9806meet joe black is your classic boy-meets-girl ...yes
3posneg-0.9614an indian runner was more than a courier . he ...no
4pospos0.9992every once in a while , when an exceptional fa...yes
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 pos neg -0.9888 \n", "1 pos pos 0.9885 \n", "2 pos pos 0.9806 \n", "3 pos neg -0.9614 \n", "4 pos pos 0.9992 \n", "\n", " excerpt accurate \n", "0 for the first reel of girls town , you just ca... no \n", "1 field of dreams almost defies description . al... yes \n", "2 meet joe black is your classic boy-meets-girl ... yes \n", "3 an indian runner was more than a courier . he ... no \n", "4 every once in a while , when an exceptional fa... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 454 out of 1000 0.454\n", "CORRECT PREDICT TRUE: 824 out of 1000 0.824\n" ] } ], "source": [ "df_n = pd.DataFrame(get_vader_scores(neg_dirty, 'neg'))\n", "df_p = pd.DataFrame(get_vader_scores(pos_dirty, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n[:5])\n", "display(df_p[:5])\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 5: Joker Review Data" ] }, { "cell_type": "code", "execution_count": 49, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
labelpredictioncompoundexcerptaccurate
0negpos0.7501Missed Opportunity\\nI had been very excited t...no
1negpos0.71845/5 for Phoenix's acting..\\nI don't think the...no
2negpos0.7269Everyone praised an overrated movie.\\nOverrat...no
3negneg-0.6698What idiotic FIlm\\nI can say that Phoenix is ...yes
4negpos0.7184Terrible\\nThe only thing good about this movi...no
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 neg pos 0.7501 \n", "1 neg pos 0.7184 \n", "2 neg pos 0.7269 \n", "3 neg neg -0.6698 \n", "4 neg pos 0.7184 \n", "\n", " excerpt accurate \n", "0 Missed Opportunity\\nI had been very excited t... no \n", "1 5/5 for Phoenix's acting..\\nI don't think the... no \n", "2 Everyone praised an overrated movie.\\nOverrat... no \n", "3 What idiotic FIlm\\nI can say that Phoenix is ... yes \n", "4 Terrible\\nThe only thing good about this movi... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictioncompoundexcerptaccurate
0pospos0.9976funny like a clown\\nGreetings again from the ...yes
1pospos0.9231Only certain people can relate\\nThis is a mov...yes
2pospos0.9796\"That's Life.\"\\nIn an era of cinema so satura...yes
3posneg-0.9586Best DC movie since The Dark Knight Rises\\nDC...no
4posneg-0.8813unbelievable, unrelatable, a bit boring to be...no
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 pos pos 0.9976 \n", "1 pos pos 0.9231 \n", "2 pos pos 0.9796 \n", "3 pos neg -0.9586 \n", "4 pos neg -0.8813 \n", "\n", " excerpt accurate \n", "0 funny like a clown\\nGreetings again from the ... yes \n", "1 Only certain people can relate\\nThis is a mov... yes \n", "2 \"That's Life.\"\\nIn an era of cinema so satura... yes \n", "3 Best DC movie since The Dark Knight Rises\\nDC... no \n", "4 unbelievable, unrelatable, a bit boring to be... no " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 68 out of 123 0.5528455284552846\n", "CORRECT PREDICT TRUE: 94 out of 123 0.7642276422764228\n" ] } ], "source": [ "df_n = pd.DataFrame(get_vader_scores(neg_joker, 'neg'))\n", "df_p = pd.DataFrame(get_vader_scores(pos_joker, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n[:5])\n", "display(df_p[:5])\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 6: HW4 [Sentiment]" ] }, { "cell_type": "code", "execution_count": 34, "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", "
labelpredictioncompoundexcerptaccurate
0negneg-0.6807I went to XYZ restaurant last week and I was v...yes
1negneg-0.6329In each of the diner dish there are at least o...yes
2negpos0.5161This is the last place you would want to dine ...no
3negneg-0.5423I went to this restaurant where I had ordered ...yes
4negpos0.8842I went there with two friends at 6pm. Long que...no
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 neg neg -0.6807 \n", "1 neg neg -0.6329 \n", "2 neg pos 0.5161 \n", "3 neg neg -0.5423 \n", "4 neg pos 0.8842 \n", "\n", " excerpt accurate \n", "0 I went to XYZ restaurant last week and I was v... yes \n", "1 In each of the diner dish there are at least o... yes \n", "2 This is the last place you would want to dine ... no \n", "3 I went to this restaurant where I had ordered ... yes \n", "4 I went there with two friends at 6pm. Long que... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictioncompoundexcerptaccurate
0pospos0.9840This restaurant ROCKS! I mean the food is grea...yes
1pospos0.9702Stronghearts cafe is the BEST! The owners have...yes
2pospos0.9106I went to cruise dinner in NYC with Spirit Cru...yes
3pospos0.9349Halos is home. I have been here numerous times...yes
4pospos0.9686The best restaurant I have ever been was a sma...yes
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 pos pos 0.9840 \n", "1 pos pos 0.9702 \n", "2 pos pos 0.9106 \n", "3 pos pos 0.9349 \n", "4 pos pos 0.9686 \n", "\n", " excerpt accurate \n", "0 This restaurant ROCKS! I mean the food is grea... yes \n", "1 Stronghearts cafe is the BEST! The owners have... yes \n", "2 I went to cruise dinner in NYC with Spirit Cru... yes \n", "3 Halos is home. I have been here numerous times... yes \n", "4 The best restaurant I have ever been was a sma... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 26 out of 46 0.5652173913043478\n", "CORRECT PREDICT TRUE: 45 out of 46 0.9782608695652174\n" ] } ], "source": [ "df_n = pd.DataFrame(get_vader_scores(neg_hw4, 'neg'))\n", "df_p = pd.DataFrame(get_vader_scores(pos_hw4, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n[:5])\n", "display(df_p[:5])\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 7: HW4 [Deception]" ] }, { "cell_type": "code", "execution_count": 33, "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", "
labelpredictioncompoundexcerptaccurate
0negpos0.9328Gannon’s Isle Ice Cream served the best ice cr...no
1negpos0.8885Hibachi the grill is one of my favorite restau...no
2negpos0.9915RIM KAAP One of the best Thai restaurants in t...no
3negpos0.8625It is a France restaurant which has Michelin t...no
4negpos0.9360Its hard to pick a favorite dining experience ...no
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 neg pos 0.9328 \n", "1 neg pos 0.8885 \n", "2 neg pos 0.9915 \n", "3 neg pos 0.8625 \n", "4 neg pos 0.9360 \n", "\n", " excerpt accurate \n", "0 Gannon’s Isle Ice Cream served the best ice cr... no \n", "1 Hibachi the grill is one of my favorite restau... no \n", "2 RIM KAAP One of the best Thai restaurants in t... no \n", "3 It is a France restaurant which has Michelin t... no \n", "4 Its hard to pick a favorite dining experience ... no " ] }, "metadata": {}, "output_type": "display_data" }, { "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", "
labelpredictioncompoundexcerptaccurate
0pospos0.0000?yes
1pospos0.8321Twin Trees Cicero NY HUGE salad bar and high q...yes
2posneg-0.8641The worst restaurant that I have ever eaten in...no
3pospos0.0000?yes
4pospos0.5267I have been to a Asian restaurant in New York ...yes
\n", "
" ], "text/plain": [ " label prediction compound \\\n", "0 pos pos 0.0000 \n", "1 pos pos 0.8321 \n", "2 pos neg -0.8641 \n", "3 pos pos 0.0000 \n", "4 pos pos 0.5267 \n", "\n", " excerpt accurate \n", "0 ? yes \n", "1 Twin Trees Cicero NY HUGE salad bar and high q... yes \n", "2 The worst restaurant that I have ever eaten in... no \n", "3 ? yes \n", "4 I have been to a Asian restaurant in New York ... yes " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "CORRECT PREDICT FALSE: 13 out of 46 0.2826086956521739\n", "CORRECT PREDICT TRUE: 32 out of 46 0.6956521739130435\n" ] } ], "source": [ "df_n = pd.DataFrame(get_vader_scores(false_lie_hw4, 'neg'))\n", "df_p = pd.DataFrame(get_vader_scores(true_lie_hw4, 'pos'))\n", "\n", "df_n['accurate'] = np.where(df_n['label'] == df_n['prediction'], 'yes', 'no')\n", "df_p['accurate'] = np.where(df_p['label'] == df_p['prediction'], 'yes', 'no')\n", "\n", "display(df_n[:5])\n", "display(df_p[:5])\n", "\n", "sum_correct_n = (df_n['accurate']=='yes').sum()\n", "sum_correct_p = (df_p['accurate']=='yes').sum()\n", "\n", "print('CORRECT PREDICT FALSE:', sum_correct_n, 'out of', len(df_n), sum_correct_n/len(df_n))\n", "print('CORRECT PREDICT TRUE:', sum_correct_p, 'out of', len(df_p), sum_correct_p/len(df_p))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# NLTK with NaiveBayes" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [], "source": [ "from nltk.classify import NaiveBayesClassifier\n", "from nltk.tokenize import word_tokenize\n", "from nltk.sentiment import SentimentAnalyzer\n", "from nltk.sentiment.util import *\n", "\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_nltk_train_test(array, label, num_train):\n", " tokens = [get_tokens(sentence) for sentence in array]\n", " docs = [(sent, label) for sent in tokens]\n", " train_docs = docs[:num_train]\n", " test_docs = docs[num_train:len(array)]\n", " return [train_docs, test_docs]\n", "\n", "\n", "def get_nltk_NB(NEG_DATA, POS_DATA, num_train):\n", " train_neg, test_neg = get_nltk_train_test(NEG_DATA, 'neg', num_train)\n", " train_pos, test_pos = get_nltk_train_test(POS_DATA, 'pos', num_train)\n", "\n", " training_docs = train_neg + train_pos\n", " testing_docs = test_neg + test_pos\n", "\n", " sentim_analyzer = SentimentAnalyzer()\n", " all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs])\n", " unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg)\n", " sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)\n", " training_set = sentim_analyzer.apply_features(training_docs)\n", " test_set = sentim_analyzer.apply_features(testing_docs)\n", "\n", " trainer = NaiveBayesClassifier.train\n", " classifier = sentim_analyzer.train(trainer, training_set)\n", " \n", " results = []\n", " for key,value in sorted(sentim_analyzer.evaluate(test_set).items()):\n", " print('{0}: {1}'.format(key,value))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 1: Kendra's Data" ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training classifier\n", "Evaluating NaiveBayesClassifier results...\n", "Accuracy: 1.0\n", "F-measure [neg]: 1.0\n", "F-measure [pos]: 1.0\n", "Precision [neg]: 1.0\n", "Precision [pos]: 1.0\n", "Recall [neg]: 1.0\n", "Recall [pos]: 1.0\n" ] } ], "source": [ "get_nltk_NB(neg_k, pos_k, 4)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 2: Ami's Data" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training classifier\n", "Evaluating NaiveBayesClassifier results...\n", "Accuracy: 0.5\n", "F-measure [neg]: 0.6666666666666666\n", "F-measure [pos]: None\n", "Precision [neg]: 0.5\n", "Precision [pos]: None\n", "Recall [neg]: 1.0\n", "Recall [pos]: 0.0\n" ] } ], "source": [ "get_nltk_NB(neg_a, pos_a, 4)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 3: Cornell's Data" ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training classifier\n", "Evaluating NaiveBayesClassifier results...\n", "Accuracy: 0.8125\n", "F-measure [neg]: 0.8259860788863109\n", "F-measure [pos]: 0.7967479674796748\n", "Precision [neg]: 0.7705627705627706\n", "Precision [pos]: 0.8698224852071006\n", "Recall [neg]: 0.89\n", "Recall [pos]: 0.735\n" ] } ], "source": [ "get_nltk_NB(neg_cornell, pos_cornell, 800)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 4: Dirty Data" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training classifier\n", "Evaluating NaiveBayesClassifier results...\n", "Accuracy: 0.7775\n", "F-measure [neg]: 0.7944572748267898\n", "F-measure [pos]: 0.757493188010899\n", "Precision [neg]: 0.7381974248927039\n", "Precision [pos]: 0.8323353293413174\n", "Recall [neg]: 0.86\n", "Recall [pos]: 0.695\n" ] } ], "source": [ "get_nltk_NB(neg_dirty, pos_dirty, 800)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 5: Joker Review Data" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training classifier\n", "Evaluating NaiveBayesClassifier results...\n", "Accuracy: 0.581081081081081\n", "F-measure [neg]: 0.6593406593406593\n", "F-measure [pos]: 0.456140350877193\n", "Precision [neg]: 0.5555555555555556\n", "Precision [pos]: 0.65\n", "Recall [neg]: 0.8108108108108109\n", "Recall [pos]: 0.35135135135135137\n" ] } ], "source": [ "get_nltk_NB(neg_joker, pos_joker, 86)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 6: HW4 [Sentiment]" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training classifier\n", "Evaluating NaiveBayesClassifier results...\n", "Accuracy: 0.75\n", "F-measure [neg]: 0.6956521739130435\n", "F-measure [pos]: 0.787878787878788\n", "Precision [neg]: 0.8888888888888888\n", "Precision [pos]: 0.6842105263157895\n", "Recall [neg]: 0.5714285714285714\n", "Recall [pos]: 0.9285714285714286\n" ] } ], "source": [ "get_nltk_NB(neg_hw4, pos_hw4, 32)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## CASE STUDY 7: HW4 [Deception]" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training classifier\n", "Evaluating NaiveBayesClassifier results...\n", "Accuracy: 0.5714285714285714\n", "F-measure [neg]: 0.5714285714285714\n", "F-measure [pos]: 0.5714285714285714\n", "Precision [neg]: 0.5714285714285714\n", "Precision [pos]: 0.5714285714285714\n", "Recall [neg]: 0.5714285714285714\n", "Recall [pos]: 0.5714285714285714\n" ] } ], "source": [ "get_nltk_NB(false_lie_hw4, true_lie_hw4, 32)" ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "list" ] }, "execution_count": 50, "metadata": {}, "output_type": "execute_result" } ], "source": [ "type(false_lie_hw4)" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Gannon’s Isle Ice Cream served the best ice cream and you better believe it! The place is ideally situated and it is easy to get too. The ice cream is delicious the best I had. There were so many varieties that I had trouble choosing it. I had the chocolate and raspberry. A weird combination but the smooth sweet chocolate combined with the sharp taste of raspberry was devine! Try it!'" ] }, "execution_count": 51, "metadata": {}, "output_type": "execute_result" } ], "source": [ "false_lie_hw4[0]" ] }, { "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 }