{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Sentiment Analysis: TextBlob + Vader \n",
    "via [this tutorial](https://levelup.gitconnected.com/sentiment-analysis-using-machine-learning-python-9122e03f8f7b) |10-6-19"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "from textblob import TextBlob\n",
    "from IPython.display import display, HTML\n",
    "import os\n",
    "import pandas as pd\n",
    "from nltk.sentiment.vader import SentimentIntensityAnalyzer\n",
    "sid = SentimentIntensityAnalyzer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "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",
    "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",
    "neg_cornell = get_data_from_files('neg_cornell/')\n",
    "pos_cornell = get_data_from_files('pos_cornell/')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# TEXT BLOB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "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": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>prediction</th>\n",
       "      <th>sentiment</th>\n",
       "      <th>length</th>\n",
       "      <th>excerpt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>neg</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.157143</td>\n",
       "      <td>76</td>\n",
       "      <td>WHERE ARE THE JOBS?! OH THAT'S RIGHT. ARTIFICI...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>neg</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.750000</td>\n",
       "      <td>96</td>\n",
       "      <td>How can we trust Artificial Intelligence to dr...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>neg</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.775000</td>\n",
       "      <td>31</td>\n",
       "      <td>I hate artificial intelligence!</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>neg</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.750000</td>\n",
       "      <td>47</td>\n",
       "      <td>My dog is terrified by artificial intelligence!</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>neg</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.750000</td>\n",
       "      <td>68</td>\n",
       "      <td>Artificial intelligence is going to melt the b...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "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  \n",
       "0  WHERE ARE THE JOBS?! OH THAT'S RIGHT. ARTIFICI...  \n",
       "1  How can we trust Artificial Intelligence to dr...  \n",
       "2                    I hate artificial intelligence!  \n",
       "3    My dog is terrified by artificial intelligence!  \n",
       "4  Artificial intelligence is going to melt the b...  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>prediction</th>\n",
       "      <th>sentiment</th>\n",
       "      <th>length</th>\n",
       "      <th>excerpt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>pos</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.112500</td>\n",
       "      <td>65</td>\n",
       "      <td>My dog is excited by the advancements in artif...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>pos</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.075000</td>\n",
       "      <td>133</td>\n",
       "      <td>I'm excited for my child to grow up and have t...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>pos</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.125000</td>\n",
       "      <td>31</td>\n",
       "      <td>I love artificial intelligence!</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>pos</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.300000</td>\n",
       "      <td>121</td>\n",
       "      <td>Order my groceries, pay my taxes, take my kids...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>pos</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.133333</td>\n",
       "      <td>116</td>\n",
       "      <td>I'm grateful every day that my child will like...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "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  \n",
       "0  My dog is excited by the advancements in artif...  \n",
       "1  I'm excited for my child to grow up and have t...  \n",
       "2                    I love artificial intelligence!  \n",
       "3  Order my groceries, pay my taxes, take my kids...  \n",
       "4  I'm grateful every day that my child will like...  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "display(pd.DataFrame(get_sentiment(neg_k, 'neg')))\n",
    "display(pd.DataFrame(get_sentiment(pos_k, 'pos')))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## CASE STUDY 2: Ami's Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>prediction</th>\n",
       "      <th>sentiment</th>\n",
       "      <th>length</th>\n",
       "      <th>excerpt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>neg</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.054577</td>\n",
       "      <td>3554</td>\n",
       "      <td>that's exactly how long the movie felt to me ....</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>neg</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.025467</td>\n",
       "      <td>2929</td>\n",
       "      <td>\" quest for camelot \" is warner bros . ' firs...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>neg</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.003334</td>\n",
       "      <td>3365</td>\n",
       "      <td>so ask yourself what \" 8mm \" ( \" eight millime...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>neg</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.022925</td>\n",
       "      <td>4418</td>\n",
       "      <td>synopsis : a mentally unstable man undergoing ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>neg</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.043234</td>\n",
       "      <td>3911</td>\n",
       "      <td>capsule : in 2176 on the planet mars police ta...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "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  \n",
       "0  that's exactly how long the movie felt to me ....  \n",
       "1   \" quest for camelot \" is warner bros . ' firs...  \n",
       "2  so ask yourself what \" 8mm \" ( \" eight millime...  \n",
       "3  synopsis : a mentally unstable man undergoing ...  \n",
       "4  capsule : in 2176 on the planet mars police ta...  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>prediction</th>\n",
       "      <th>sentiment</th>\n",
       "      <th>length</th>\n",
       "      <th>excerpt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.023663</td>\n",
       "      <td>4227</td>\n",
       "      <td>films adapted from comic books have had plenty...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.131092</td>\n",
       "      <td>2421</td>\n",
       "      <td>you've got mail works alot better than it dese...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.110626</td>\n",
       "      <td>6092</td>\n",
       "      <td>\" jaws \" is a rare film that grabs your atten...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.103847</td>\n",
       "      <td>4096</td>\n",
       "      <td>every now and then a movie comes along from a ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>pos</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.070151</td>\n",
       "      <td>3898</td>\n",
       "      <td>moviemaking is a lot like being the general ma...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "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  \n",
       "0  films adapted from comic books have had plenty...  \n",
       "1  you've got mail works alot better than it dese...  \n",
       "2   \" jaws \" is a rare film that grabs your atten...  \n",
       "3  every now and then a movie comes along from a ...  \n",
       "4  moviemaking is a lot like being the general ma...  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "display(pd.DataFrame(get_sentiment(neg_a, 'neg')))\n",
    "display(pd.DataFrame(get_sentiment(pos_a, 'pos')))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## CASE STUDY 3: Cornell Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "229\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>prediction</th>\n",
       "      <th>sentiment</th>\n",
       "      <th>length</th>\n",
       "      <th>excerpt</th>\n",
       "      <th>accurate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>neg</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.026240</td>\n",
       "      <td>5953</td>\n",
       "      <td>bad . bad . \\nbad . \\nthat one word seems to p...</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>neg</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.076040</td>\n",
       "      <td>3396</td>\n",
       "      <td>isn't it the ultimate sign of a movie's cinema...</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>neg</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.128733</td>\n",
       "      <td>2762</td>\n",
       "      <td>\" gordy \" is not a movie , it is a 90-minute-...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>neg</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.000485</td>\n",
       "      <td>3840</td>\n",
       "      <td>disconnect the phone line . \\ndon't accept the...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>neg</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.122770</td>\n",
       "      <td>2270</td>\n",
       "      <td>when robert forster found himself famous again...</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>995</td>\n",
       "      <td>neg</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.145489</td>\n",
       "      <td>1945</td>\n",
       "      <td>synopsis : when a meteorite crashlands in the ...</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>996</td>\n",
       "      <td>neg</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.102723</td>\n",
       "      <td>3116</td>\n",
       "      <td>it's now the anniversary of the slayings of ju...</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>997</td>\n",
       "      <td>neg</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.042473</td>\n",
       "      <td>1755</td>\n",
       "      <td>coinciding with the emerging popularity of mov...</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>998</td>\n",
       "      <td>neg</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.048656</td>\n",
       "      <td>2826</td>\n",
       "      <td>and now the high-flying hong kong style of fil...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>999</td>\n",
       "      <td>neg</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.090655</td>\n",
       "      <td>4165</td>\n",
       "      <td>battlefield long , boring and just plain stupi...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1000 rows × 6 columns</p>\n",
       "</div>"
      ],
      "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",
       "995   neg        pos   0.145489    1945   \n",
       "996   neg        pos   0.102723    3116   \n",
       "997   neg        pos   0.042473    1755   \n",
       "998   neg        neg  -0.048656    2826   \n",
       "999   neg        neg  -0.090655    4165   \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  \n",
       "..                                                 ...      ...  \n",
       "995  synopsis : when a meteorite crashlands in the ...       no  \n",
       "996  it's now the anniversary of the slayings of ju...       no  \n",
       "997  coinciding with the emerging popularity of mov...       no  \n",
       "998  and now the high-flying hong kong style of fil...      yes  \n",
       "999  battlefield long , boring and just plain stupi...      yes  \n",
       "\n",
       "[1000 rows x 6 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "971\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>prediction</th>\n",
       "      <th>sentiment</th>\n",
       "      <th>length</th>\n",
       "      <th>excerpt</th>\n",
       "      <th>accurate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.221173</td>\n",
       "      <td>4662</td>\n",
       "      <td>assume nothing . \\nthe phrase is perhaps one o...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.089736</td>\n",
       "      <td>3839</td>\n",
       "      <td>plot : derek zoolander is a male model . \\nhe ...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.206743</td>\n",
       "      <td>9380</td>\n",
       "      <td>i actually am a fan of the original 1961 or so...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.141905</td>\n",
       "      <td>2407</td>\n",
       "      <td>a movie that's been as highly built up as the ...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.176332</td>\n",
       "      <td>1840</td>\n",
       "      <td>\" good will hunting \" is two movies in one : ...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>995</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.072815</td>\n",
       "      <td>2658</td>\n",
       "      <td>one of the funniest carry on movies and the th...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>996</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.102879</td>\n",
       "      <td>4196</td>\n",
       "      <td>i remember making a pact , right after `patch ...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>997</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.195097</td>\n",
       "      <td>2094</td>\n",
       "      <td>barely scrapping by playing at a nyc piano bar...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>998</td>\n",
       "      <td>pos</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.117530</td>\n",
       "      <td>4575</td>\n",
       "      <td>if the current trends of hollywood filmmaking ...</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>999</td>\n",
       "      <td>pos</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.013569</td>\n",
       "      <td>3870</td>\n",
       "      <td>capsule : the director of cure brings a weird ...</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1000 rows × 6 columns</p>\n",
       "</div>"
      ],
      "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",
       "995   pos        pos   0.072815    2658   \n",
       "996   pos        pos   0.102879    4196   \n",
       "997   pos        pos   0.195097    2094   \n",
       "998   pos        pos   0.117530    4575   \n",
       "999   pos        neg  -0.013569    3870   \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  \n",
       "..                                                 ...      ...  \n",
       "995  one of the funniest carry on movies and the th...      yes  \n",
       "996  i remember making a pact , right after `patch ...      yes  \n",
       "997  barely scrapping by playing at a nyc piano bar...      yes  \n",
       "998  if the current trends of hollywood filmmaking ...      yes  \n",
       "999  capsule : the director of cure brings a weird ...       no  \n",
       "\n",
       "[1000 rows x 6 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "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",
    "print((df_n['accurate']=='yes').sum())\n",
    "display(df_n)\n",
    "\n",
    "print((df_p['accurate']=='yes').sum())\n",
    "display(df_p)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# VADER"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "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, 'compound': ss['compound'], 'excerpt': sentence[:50]})\n",
    "    return vader_array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "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": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "neg_k"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## CASE STUDY 1: Kendra's Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>compound</th>\n",
       "      <th>excerpt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>neg</td>\n",
       "      <td>0.5255</td>\n",
       "      <td>WHERE ARE THE JOBS?! OH THAT'S RIGHT. ARTIFICI...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>neg</td>\n",
       "      <td>0.7712</td>\n",
       "      <td>How can we trust Artificial Intelligence to dr...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.2244</td>\n",
       "      <td>I hate artificial intelligence!</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.2942</td>\n",
       "      <td>My dog is terrified by artificial intelligence!</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>neg</td>\n",
       "      <td>0.5255</td>\n",
       "      <td>Artificial intelligence is going to melt the b...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  label  compound                                            excerpt\n",
       "0   neg    0.5255  WHERE ARE THE JOBS?! OH THAT'S RIGHT. ARTIFICI...\n",
       "1   neg    0.7712  How can we trust Artificial Intelligence to dr...\n",
       "2   neg   -0.2244                    I hate artificial intelligence!\n",
       "3   neg   -0.2942    My dog is terrified by artificial intelligence!\n",
       "4   neg    0.5255  Artificial intelligence is going to melt the b..."
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>compound</th>\n",
       "      <th>excerpt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.6705</td>\n",
       "      <td>My dog is excited by the advancements in artif...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.8271</td>\n",
       "      <td>I'm excited for my child to grow up and have t...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.8221</td>\n",
       "      <td>I love artificial intelligence!</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.8213</td>\n",
       "      <td>Order my groceries, pay my taxes, take my kids...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.8402</td>\n",
       "      <td>I'm grateful every day that my child will like...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  label  compound                                            excerpt\n",
       "0   pos    0.6705  My dog is excited by the advancements in artif...\n",
       "1   pos    0.8271  I'm excited for my child to grow up and have t...\n",
       "2   pos    0.8221                    I love artificial intelligence!\n",
       "3   pos    0.8213  Order my groceries, pay my taxes, take my kids...\n",
       "4   pos    0.8402  I'm grateful every day that my child will like..."
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "display(pd.DataFrame(get_vader_scores(neg_k, 'neg')))\n",
    "display(pd.DataFrame(get_vader_scores(pos_k, 'pos')))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## CASE STUDY 2: Ami's Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>compound</th>\n",
       "      <th>excerpt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>neg</td>\n",
       "      <td>0.7836</td>\n",
       "      <td>that's exactly how long the movie felt to me ....</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.8481</td>\n",
       "      <td>\" quest for camelot \" is warner bros . ' firs...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.9753</td>\n",
       "      <td>so ask yourself what \" 8mm \" ( \" eight millime...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>neg</td>\n",
       "      <td>0.6824</td>\n",
       "      <td>synopsis : a mentally unstable man undergoing ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>neg</td>\n",
       "      <td>-0.9879</td>\n",
       "      <td>capsule : in 2176 on the planet mars police ta...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  label  compound                                            excerpt\n",
       "0   neg    0.7836  that's exactly how long the movie felt to me ....\n",
       "1   neg   -0.8481   \" quest for camelot \" is warner bros . ' firs...\n",
       "2   neg   -0.9753  so ask yourself what \" 8mm \" ( \" eight millime...\n",
       "3   neg    0.6824  synopsis : a mentally unstable man undergoing ...\n",
       "4   neg   -0.9879  capsule : in 2176 on the planet mars police ta..."
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>compound</th>\n",
       "      <th>excerpt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>pos</td>\n",
       "      <td>-0.5887</td>\n",
       "      <td>films adapted from comic books have had plenty...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.9964</td>\n",
       "      <td>you've got mail works alot better than it dese...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.9868</td>\n",
       "      <td>\" jaws \" is a rare film that grabs your atten...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>pos</td>\n",
       "      <td>0.8825</td>\n",
       "      <td>every now and then a movie comes along from a ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>pos</td>\n",
       "      <td>-0.3525</td>\n",
       "      <td>moviemaking is a lot like being the general ma...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  label  compound                                            excerpt\n",
       "0   pos   -0.5887  films adapted from comic books have had plenty...\n",
       "1   pos    0.9964  you've got mail works alot better than it dese...\n",
       "2   pos    0.9868   \" jaws \" is a rare film that grabs your atten...\n",
       "3   pos    0.8825  every now and then a movie comes along from a ...\n",
       "4   pos   -0.3525  moviemaking is a lot like being the general ma..."
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "display(pd.DataFrame(get_vader_scores(neg_a, 'neg')))\n",
    "display(pd.DataFrame(get_vader_scores(pos_a, 'pos')))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# NLTK with NaiveBayes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "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)"
   ]
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}