Youtube_Comments.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#EDA Packages\n",
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# ML Packages For Vectorization of Text For Feature Extraction\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Visualization Packages\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Dataset from https://archive.ics.uci.edu/ml/datasets/YouTube+Spam+Collection#\n",
    "df1 = pd.read_csv(\"Youtube01-Psy.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>COMMENT_ID</th>\n",
       "      <th>AUTHOR</th>\n",
       "      <th>DATE</th>\n",
       "      <th>CONTENT</th>\n",
       "      <th>CLASS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>LZQPQhLyRh80UYxNuaDWhIGQYNQ96IuCg-AYWqNPjpU</td>\n",
       "      <td>Julius NM</td>\n",
       "      <td>2013-11-07T06:20:48</td>\n",
       "      <td>Huh, anyway check out this you[tube] channel: ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>LZQPQhLyRh_C2cTtd9MvFRJedxydaVW-2sNg5Diuo4A</td>\n",
       "      <td>adam riyati</td>\n",
       "      <td>2013-11-07T12:37:15</td>\n",
       "      <td>Hey guys check out my new channel and our firs...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>LZQPQhLyRh9MSZYnf8djyk0gEF9BHDPYrrK-qCczIY8</td>\n",
       "      <td>Evgeny Murashkin</td>\n",
       "      <td>2013-11-08T17:34:21</td>\n",
       "      <td>just for test I have to say murdev.com</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>z13jhp0bxqncu512g22wvzkasxmvvzjaz04</td>\n",
       "      <td>ElNino Melendez</td>\n",
       "      <td>2013-11-09T08:28:43</td>\n",
       "      <td>me shaking my sexy ass on my channel enjoy ^_^ ﻿</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>z13fwbwp1oujthgqj04chlngpvzmtt3r3dw</td>\n",
       "      <td>GsMega</td>\n",
       "      <td>2013-11-10T16:05:38</td>\n",
       "      <td>watch?v=vtaRGgvGtWQ   Check this out .﻿</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                    COMMENT_ID            AUTHOR  \\\n",
       "0  LZQPQhLyRh80UYxNuaDWhIGQYNQ96IuCg-AYWqNPjpU         Julius NM   \n",
       "1  LZQPQhLyRh_C2cTtd9MvFRJedxydaVW-2sNg5Diuo4A       adam riyati   \n",
       "2  LZQPQhLyRh9MSZYnf8djyk0gEF9BHDPYrrK-qCczIY8  Evgeny Murashkin   \n",
       "3          z13jhp0bxqncu512g22wvzkasxmvvzjaz04   ElNino Melendez   \n",
       "4          z13fwbwp1oujthgqj04chlngpvzmtt3r3dw            GsMega   \n",
       "\n",
       "                  DATE                                            CONTENT  \\\n",
       "0  2013-11-07T06:20:48  Huh, anyway check out this you[tube] channel: ...   \n",
       "1  2013-11-07T12:37:15  Hey guys check out my new channel and our firs...   \n",
       "2  2013-11-08T17:34:21             just for test I have to say murdev.com   \n",
       "3  2013-11-09T08:28:43   me shaking my sexy ass on my channel enjoy ^_^ ﻿   \n",
       "4  2013-11-10T16:05:38            watch?v=vtaRGgvGtWQ   Check this out .﻿   \n",
       "\n",
       "   CLASS  \n",
       "0      1  \n",
       "1      1  \n",
       "2      1  \n",
       "3      1  \n",
       "4      1  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load all our dataset to merge them\n",
    "df2 = pd.read_csv(\"Youtube02-KatyPerry.csv\")\n",
    "df3 = pd.read_csv(\"Youtube03-LMFAO.csv\")\n",
    "df4 = pd.read_csv(\"Youtube04-Eminem.csv\")\n",
    "df5 = pd.read_csv(\"Youtube05-Shakira.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "frames = [df1,df2,df3,df4,df5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Merging or Concatenating our DF\n",
    "df_merged = pd.concat(frames)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1956, 5)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Total Size\n",
    "df_merged.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Merging with Keys\n",
    "keys = [\"Psy\",\"KatyPerry\",\"LMFAO\",\"Eminem\",\"Shakira\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_with_keys = pd.concat(frames,keys=keys)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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></th>\n",
       "      <th>COMMENT_ID</th>\n",
       "      <th>AUTHOR</th>\n",
       "      <th>DATE</th>\n",
       "      <th>CONTENT</th>\n",
       "      <th>CLASS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td rowspan=\"5\" valign=\"top\">Psy</td>\n",
       "      <td>0</td>\n",
       "      <td>LZQPQhLyRh80UYxNuaDWhIGQYNQ96IuCg-AYWqNPjpU</td>\n",
       "      <td>Julius NM</td>\n",
       "      <td>2013-11-07T06:20:48</td>\n",
       "      <td>Huh, anyway check out this you[tube] channel: ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>LZQPQhLyRh_C2cTtd9MvFRJedxydaVW-2sNg5Diuo4A</td>\n",
       "      <td>adam riyati</td>\n",
       "      <td>2013-11-07T12:37:15</td>\n",
       "      <td>Hey guys check out my new channel and our firs...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>LZQPQhLyRh9MSZYnf8djyk0gEF9BHDPYrrK-qCczIY8</td>\n",
       "      <td>Evgeny Murashkin</td>\n",
       "      <td>2013-11-08T17:34:21</td>\n",
       "      <td>just for test I have to say murdev.com</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>z13jhp0bxqncu512g22wvzkasxmvvzjaz04</td>\n",
       "      <td>ElNino Melendez</td>\n",
       "      <td>2013-11-09T08:28:43</td>\n",
       "      <td>me shaking my sexy ass on my channel enjoy ^_^ ﻿</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>z13fwbwp1oujthgqj04chlngpvzmtt3r3dw</td>\n",
       "      <td>GsMega</td>\n",
       "      <td>2013-11-10T16:05:38</td>\n",
       "      <td>watch?v=vtaRGgvGtWQ   Check this out .﻿</td>\n",
       "      <td>1</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 rowspan=\"5\" valign=\"top\">Shakira</td>\n",
       "      <td>365</td>\n",
       "      <td>_2viQ_Qnc6-bMSjqyL1NKj57ROicCSJV5SwTrw-RFFA</td>\n",
       "      <td>Katie Mettam</td>\n",
       "      <td>2013-07-13T13:27:39.441000</td>\n",
       "      <td>I love this song because we sing it at Camp al...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>366</td>\n",
       "      <td>_2viQ_Qnc6-pY-1yR6K2FhmC5i48-WuNx5CumlHLDAI</td>\n",
       "      <td>Sabina Pearson-Smith</td>\n",
       "      <td>2013-07-13T13:14:30.021000</td>\n",
       "      <td>I love this song for two reasons: 1.it is abou...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>367</td>\n",
       "      <td>_2viQ_Qnc6_k_n_Bse9zVhJP8tJReZpo8uM2uZfnzDs</td>\n",
       "      <td>jeffrey jules</td>\n",
       "      <td>2013-07-13T12:09:31.188000</td>\n",
       "      <td>wow</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>368</td>\n",
       "      <td>_2viQ_Qnc6_yBt8UGMWyg3vh0PulTqcqyQtdE7d4Fl0</td>\n",
       "      <td>Aishlin Maciel</td>\n",
       "      <td>2013-07-13T11:17:52.308000</td>\n",
       "      <td>Shakira u are so wiredo</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>369</td>\n",
       "      <td>_2viQ_Qnc685RPw1aSa1tfrIuHXRvAQ2rPT9R06KTqA</td>\n",
       "      <td>Latin Bosch</td>\n",
       "      <td>2013-07-12T22:33:27.916000</td>\n",
       "      <td>Shakira is the best dancer</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1956 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              COMMENT_ID  \\\n",
       "Psy     0    LZQPQhLyRh80UYxNuaDWhIGQYNQ96IuCg-AYWqNPjpU   \n",
       "        1    LZQPQhLyRh_C2cTtd9MvFRJedxydaVW-2sNg5Diuo4A   \n",
       "        2    LZQPQhLyRh9MSZYnf8djyk0gEF9BHDPYrrK-qCczIY8   \n",
       "        3            z13jhp0bxqncu512g22wvzkasxmvvzjaz04   \n",
       "        4            z13fwbwp1oujthgqj04chlngpvzmtt3r3dw   \n",
       "...                                                  ...   \n",
       "Shakira 365  _2viQ_Qnc6-bMSjqyL1NKj57ROicCSJV5SwTrw-RFFA   \n",
       "        366  _2viQ_Qnc6-pY-1yR6K2FhmC5i48-WuNx5CumlHLDAI   \n",
       "        367  _2viQ_Qnc6_k_n_Bse9zVhJP8tJReZpo8uM2uZfnzDs   \n",
       "        368  _2viQ_Qnc6_yBt8UGMWyg3vh0PulTqcqyQtdE7d4Fl0   \n",
       "        369  _2viQ_Qnc685RPw1aSa1tfrIuHXRvAQ2rPT9R06KTqA   \n",
       "\n",
       "                           AUTHOR                        DATE  \\\n",
       "Psy     0               Julius NM         2013-11-07T06:20:48   \n",
       "        1             adam riyati         2013-11-07T12:37:15   \n",
       "        2        Evgeny Murashkin         2013-11-08T17:34:21   \n",
       "        3         ElNino Melendez         2013-11-09T08:28:43   \n",
       "        4                  GsMega         2013-11-10T16:05:38   \n",
       "...                           ...                         ...   \n",
       "Shakira 365          Katie Mettam  2013-07-13T13:27:39.441000   \n",
       "        366  Sabina Pearson-Smith  2013-07-13T13:14:30.021000   \n",
       "        367         jeffrey jules  2013-07-13T12:09:31.188000   \n",
       "        368        Aishlin Maciel  2013-07-13T11:17:52.308000   \n",
       "        369           Latin Bosch  2013-07-12T22:33:27.916000   \n",
       "\n",
       "                                                       CONTENT  CLASS  \n",
       "Psy     0    Huh, anyway check out this you[tube] channel: ...      1  \n",
       "        1    Hey guys check out my new channel and our firs...      1  \n",
       "        2               just for test I have to say murdev.com      1  \n",
       "        3     me shaking my sexy ass on my channel enjoy ^_^ ﻿      1  \n",
       "        4              watch?v=vtaRGgvGtWQ   Check this out .﻿      1  \n",
       "...                                                        ...    ...  \n",
       "Shakira 365  I love this song because we sing it at Camp al...      0  \n",
       "        366  I love this song for two reasons: 1.it is abou...      0  \n",
       "        367                                                wow      0  \n",
       "        368                            Shakira u are so wiredo      0  \n",
       "        369                         Shakira is the best dancer      0  \n",
       "\n",
       "[1956 rows x 5 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_with_keys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>COMMENT_ID</th>\n",
       "      <th>AUTHOR</th>\n",
       "      <th>DATE</th>\n",
       "      <th>CONTENT</th>\n",
       "      <th>CLASS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>z13lgffb5w3ddx1ul22qy1wxspy5cpkz504</td>\n",
       "      <td>dharma pal</td>\n",
       "      <td>2015-05-29T02:30:18.971000</td>\n",
       "      <td>Nice song﻿</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>z123dbgb0mqjfxbtz22ucjc5jvzcv3ykj</td>\n",
       "      <td>Tiza Arellano</td>\n",
       "      <td>2015-05-29T00:14:48.748000</td>\n",
       "      <td>I love song ﻿</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>z12quxxp2vutflkxv04cihggzt2azl34pms0k</td>\n",
       "      <td>Prìñçeśś Âliś Łøvê Dømíñø Mâđiś™ ﻿</td>\n",
       "      <td>2015-05-28T21:00:08.607000</td>\n",
       "      <td>I love song ﻿</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>z12icv3ysqvlwth2c23eddlykyqut5z1h</td>\n",
       "      <td>Eric Gonzalez</td>\n",
       "      <td>2015-05-28T20:47:12.193000</td>\n",
       "      <td>860,000,000 lets make it first female to reach...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>z133stly3kete3tly22petvwdpmghrlli</td>\n",
       "      <td>Analena López</td>\n",
       "      <td>2015-05-28T17:08:29.827000</td>\n",
       "      <td>shakira is best for worldcup﻿</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>365</td>\n",
       "      <td>_2viQ_Qnc6-bMSjqyL1NKj57ROicCSJV5SwTrw-RFFA</td>\n",
       "      <td>Katie Mettam</td>\n",
       "      <td>2013-07-13T13:27:39.441000</td>\n",
       "      <td>I love this song because we sing it at Camp al...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>366</td>\n",
       "      <td>_2viQ_Qnc6-pY-1yR6K2FhmC5i48-WuNx5CumlHLDAI</td>\n",
       "      <td>Sabina Pearson-Smith</td>\n",
       "      <td>2013-07-13T13:14:30.021000</td>\n",
       "      <td>I love this song for two reasons: 1.it is abou...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>367</td>\n",
       "      <td>_2viQ_Qnc6_k_n_Bse9zVhJP8tJReZpo8uM2uZfnzDs</td>\n",
       "      <td>jeffrey jules</td>\n",
       "      <td>2013-07-13T12:09:31.188000</td>\n",
       "      <td>wow</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>368</td>\n",
       "      <td>_2viQ_Qnc6_yBt8UGMWyg3vh0PulTqcqyQtdE7d4Fl0</td>\n",
       "      <td>Aishlin Maciel</td>\n",
       "      <td>2013-07-13T11:17:52.308000</td>\n",
       "      <td>Shakira u are so wiredo</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>369</td>\n",
       "      <td>_2viQ_Qnc685RPw1aSa1tfrIuHXRvAQ2rPT9R06KTqA</td>\n",
       "      <td>Latin Bosch</td>\n",
       "      <td>2013-07-12T22:33:27.916000</td>\n",
       "      <td>Shakira is the best dancer</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>370 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                      COMMENT_ID  \\\n",
       "0            z13lgffb5w3ddx1ul22qy1wxspy5cpkz504   \n",
       "1              z123dbgb0mqjfxbtz22ucjc5jvzcv3ykj   \n",
       "2          z12quxxp2vutflkxv04cihggzt2azl34pms0k   \n",
       "3              z12icv3ysqvlwth2c23eddlykyqut5z1h   \n",
       "4              z133stly3kete3tly22petvwdpmghrlli   \n",
       "..                                           ...   \n",
       "365  _2viQ_Qnc6-bMSjqyL1NKj57ROicCSJV5SwTrw-RFFA   \n",
       "366  _2viQ_Qnc6-pY-1yR6K2FhmC5i48-WuNx5CumlHLDAI   \n",
       "367  _2viQ_Qnc6_k_n_Bse9zVhJP8tJReZpo8uM2uZfnzDs   \n",
       "368  _2viQ_Qnc6_yBt8UGMWyg3vh0PulTqcqyQtdE7d4Fl0   \n",
       "369  _2viQ_Qnc685RPw1aSa1tfrIuHXRvAQ2rPT9R06KTqA   \n",
       "\n",
       "                                 AUTHOR                        DATE  \\\n",
       "0                            dharma pal  2015-05-29T02:30:18.971000   \n",
       "1                         Tiza Arellano  2015-05-29T00:14:48.748000   \n",
       "2    Prìñçeśś Âliś Łøvê Dømíñø Mâđiś™ ﻿  2015-05-28T21:00:08.607000   \n",
       "3                         Eric Gonzalez  2015-05-28T20:47:12.193000   \n",
       "4                         Analena López  2015-05-28T17:08:29.827000   \n",
       "..                                  ...                         ...   \n",
       "365                        Katie Mettam  2013-07-13T13:27:39.441000   \n",
       "366                Sabina Pearson-Smith  2013-07-13T13:14:30.021000   \n",
       "367                       jeffrey jules  2013-07-13T12:09:31.188000   \n",
       "368                      Aishlin Maciel  2013-07-13T11:17:52.308000   \n",
       "369                         Latin Bosch  2013-07-12T22:33:27.916000   \n",
       "\n",
       "                                               CONTENT  CLASS  \n",
       "0                                           Nice song﻿      0  \n",
       "1                                        I love song ﻿      0  \n",
       "2                                        I love song ﻿      0  \n",
       "3    860,000,000 lets make it first female to reach...      0  \n",
       "4                        shakira is best for worldcup﻿      0  \n",
       "..                                                 ...    ...  \n",
       "365  I love this song because we sing it at Camp al...      0  \n",
       "366  I love this song for two reasons: 1.it is abou...      0  \n",
       "367                                                wow      0  \n",
       "368                            Shakira u are so wiredo      0  \n",
       "369                         Shakira is the best dancer      0  \n",
       "\n",
       "[370 rows x 5 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Checking for Only Comments on Shakira\n",
    "df_with_keys.loc['Shakira']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save and Write Merged Data to csv\n",
    "df_with_keys.to_csv(\"YoutubeSpamMergeddata.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df_with_keys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9780"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.size"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data Cleaning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['COMMENT_ID', 'AUTHOR', 'DATE', 'CONTENT', 'CLASS'], dtype='object')"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Checking for Consistent Column Name\n",
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "COMMENT_ID    object\n",
       "AUTHOR        object\n",
       "DATE          object\n",
       "CONTENT       object\n",
       "CLASS          int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Checking for Datatypes\n",
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "COMMENT_ID    0\n",
       "AUTHOR        0\n",
       "DATE          0\n",
       "CONTENT       0\n",
       "CLASS         0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check for missing nan\n",
    "df.isnull().isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Psy      0             2013-11-07T06:20:48\n",
       "         1             2013-11-07T12:37:15\n",
       "         2             2013-11-08T17:34:21\n",
       "         3             2013-11-09T08:28:43\n",
       "         4             2013-11-10T16:05:38\n",
       "                           ...            \n",
       "Shakira  365    2013-07-13T13:27:39.441000\n",
       "         366    2013-07-13T13:14:30.021000\n",
       "         367    2013-07-13T12:09:31.188000\n",
       "         368    2013-07-13T11:17:52.308000\n",
       "         369    2013-07-12T22:33:27.916000\n",
       "Name: DATE, Length: 1956, dtype: object"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Checking for Date\n",
    "df[\"DATE\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Psy      0                 Julius NM\n",
       "         1               adam riyati\n",
       "         2          Evgeny Murashkin\n",
       "         3           ElNino Melendez\n",
       "         4                    GsMega\n",
       "                        ...         \n",
       "Shakira  365            Katie Mettam\n",
       "         366    Sabina Pearson-Smith\n",
       "         367           jeffrey jules\n",
       "         368          Aishlin Maciel\n",
       "         369             Latin Bosch\n",
       "Name: AUTHOR, Length: 1956, dtype: object"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.AUTHOR\n",
    "# Convert the Author Name to First Name and Last Name\n",
    "#df[[\"FIRSTNAME\",\"LASTNAME\"]] = df['AUTHOR'].str.split(expand=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Working With Text Content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_data = df[[\"CONTENT\",\"CLASS\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['CONTENT', 'CLASS'], dtype='object')"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_data.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_x = df_data['CONTENT']\n",
    "df_y = df_data['CLASS']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Feature Extraction From Text\n",
    "## CountVectorizer\n",
    "## TfidfVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv = CountVectorizer()\n",
    "ex = cv.fit_transform([\"Great song but check this out\",\"What is this song?\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1, 1, 1, 0, 1, 1, 1, 0],\n",
       "       [0, 0, 0, 1, 0, 1, 1, 1]], dtype=int64)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ex.toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['but', 'check', 'great', 'is', 'out', 'song', 'this', 'what']"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv.get_feature_names()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Extract Feature With CountVectorizer\n",
    "corpus = df_x\n",
    "cv = CountVectorizer()\n",
    "X = cv.fit_transform(corpus) # Fit the Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       ...,\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0],\n",
       "       [0, 0, 0, ..., 0, 0, 0]], dtype=int64)"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['00',\n",
       " '000',\n",
       " '002',\n",
       " '018',\n",
       " '02',\n",
       " '034',\n",
       " '04',\n",
       " '047000',\n",
       " '05',\n",
       " '053012',\n",
       " '0687119038',\n",
       " '08',\n",
       " '09',\n",
       " '0cb8qfjaa',\n",
       " '0d878a889c',\n",
       " '0dbhjzdw0lbsjbi40gxm0d0p5krhv8xinqli53__wqbahs8zx4mjhw5vwrkpxfoeks',\n",
       " '0laviqu2b',\n",
       " '10',\n",
       " '100',\n",
       " '1000',\n",
       " '10000000',\n",
       " '1000000000',\n",
       " '100000415527985',\n",
       " '100005244783212',\n",
       " '100007085325116',\n",
       " '10001',\n",
       " '100877300245414',\n",
       " '101721377578919894134',\n",
       " '10200253113705769',\n",
       " '1030',\n",
       " '104999962146104962510',\n",
       " '10626048',\n",
       " '10626835',\n",
       " '106865403',\n",
       " '107297364',\n",
       " '1073741825',\n",
       " '1073741828',\n",
       " '1073741830',\n",
       " '1073741943',\n",
       " '108k',\n",
       " '109',\n",
       " '10b35481',\n",
       " '11',\n",
       " '1111',\n",
       " '1111111111111111111',\n",
       " '111719098841907',\n",
       " '111982027348137311818',\n",
       " '112720997191206369631',\n",
       " '11cpwb',\n",
       " '11th',\n",
       " '12',\n",
       " '123',\n",
       " '124',\n",
       " '124923004',\n",
       " '126',\n",
       " '127',\n",
       " '128gb',\n",
       " '12year',\n",
       " '13',\n",
       " '13017194',\n",
       " '131275322914',\n",
       " '131338190916',\n",
       " '1337',\n",
       " '1340488',\n",
       " '1340489',\n",
       " '1340490',\n",
       " '1340491',\n",
       " '1340492',\n",
       " '1340493',\n",
       " '1340494',\n",
       " '1340499',\n",
       " '1340500',\n",
       " '1340502',\n",
       " '1340503',\n",
       " '1340504',\n",
       " '1340517',\n",
       " '1340518',\n",
       " '1340519',\n",
       " '1340520',\n",
       " '1340521',\n",
       " '1340522',\n",
       " '1340523',\n",
       " '1340524',\n",
       " '134470083389909',\n",
       " '14',\n",
       " '1408122684',\n",
       " '1415297812',\n",
       " '1442646731',\n",
       " '1446084',\n",
       " '1461302180794905',\n",
       " '1495323920744243',\n",
       " '1496241863981208',\n",
       " '1496273723978022',\n",
       " '1498561870415874',\n",
       " '14gkvdo',\n",
       " '15',\n",
       " '16',\n",
       " '161620527267482',\n",
       " '16gb',\n",
       " '17',\n",
       " '171183229277',\n",
       " '1727483389',\n",
       " '17yr',\n",
       " '18',\n",
       " '19',\n",
       " '19255',\n",
       " '1990',\n",
       " '19924',\n",
       " '1b',\n",
       " '1bi',\n",
       " '1billiom',\n",
       " '1billion',\n",
       " '1bsefqe',\n",
       " '1fhenqx1twqm153v2ptayiejnealahzvem',\n",
       " '1firo',\n",
       " '1hmvtx',\n",
       " '1k',\n",
       " '1m',\n",
       " '1m00s',\n",
       " '1min',\n",
       " '20',\n",
       " '200',\n",
       " '2004',\n",
       " '2005',\n",
       " '2008',\n",
       " '2009',\n",
       " '200k',\n",
       " '200mm',\n",
       " '2010',\n",
       " '2011',\n",
       " '2012',\n",
       " '2012430',\n",
       " '2012bitches',\n",
       " '2013',\n",
       " '2014',\n",
       " '201470069872822',\n",
       " '2015',\n",
       " '2016',\n",
       " '2017',\n",
       " '207230212795137',\n",
       " '21',\n",
       " '210',\n",
       " '2177367',\n",
       " '229508',\n",
       " '23',\n",
       " '23active',\n",
       " '23awesome',\n",
       " '23eminem',\n",
       " '23everydayimvaping',\n",
       " '23giraffebruuh',\n",
       " '23king',\n",
       " '23kinglothedancer',\n",
       " '23lmfao',\n",
       " '23lovethewayyoulie',\n",
       " '23rapgod',\n",
       " '23rt',\n",
       " '23share',\n",
       " '24',\n",
       " '24398',\n",
       " '243a',\n",
       " '247',\n",
       " '25',\n",
       " '250',\n",
       " '25000',\n",
       " '251638183951',\n",
       " '25874',\n",
       " '25th',\n",
       " '26',\n",
       " '26032883',\n",
       " '26t22',\n",
       " '27',\n",
       " '279',\n",
       " '28',\n",
       " '29',\n",
       " '2asfn9shghk',\n",
       " '2b',\n",
       " '2b4wywphi8c',\n",
       " '2billion',\n",
       " '2f',\n",
       " '2fen',\n",
       " '2flist_of_most_viewed_youtube_videos',\n",
       " '2fwiki',\n",
       " '2m19s',\n",
       " '2nd',\n",
       " '2parale',\n",
       " '2tggp3pv6l',\n",
       " '2x10',\n",
       " '2zme8f',\n",
       " '30',\n",
       " '300',\n",
       " '3000',\n",
       " '301',\n",
       " '302703146601369',\n",
       " '30th',\n",
       " '313327',\n",
       " '313454548839369',\n",
       " '315',\n",
       " '31st',\n",
       " '320',\n",
       " '322',\n",
       " '327568907427561',\n",
       " '32gb',\n",
       " '33',\n",
       " '333',\n",
       " '333607726823679',\n",
       " '333608120156973',\n",
       " '33gxrf',\n",
       " '342',\n",
       " '35',\n",
       " '360',\n",
       " '365',\n",
       " '36loseweight',\n",
       " '385',\n",
       " '387',\n",
       " '3873',\n",
       " '389088',\n",
       " '39',\n",
       " '390',\n",
       " '390875584405933',\n",
       " '391725794320912',\n",
       " '3a',\n",
       " '3bie',\n",
       " '3bkeywords',\n",
       " '3bqid',\n",
       " '3bsr',\n",
       " '3d',\n",
       " '3m',\n",
       " '3m40s',\n",
       " '3m57s',\n",
       " '3rd',\n",
       " '40',\n",
       " '4000',\n",
       " '4000dollars',\n",
       " '40beuutvu2zkxk4utgpz8k',\n",
       " '41',\n",
       " '421',\n",
       " '43',\n",
       " '433',\n",
       " '4344749',\n",
       " '4436607',\n",
       " '4477063',\n",
       " '447935454150',\n",
       " '4483179854075',\n",
       " '448800865296855',\n",
       " '45',\n",
       " '4500',\n",
       " '46',\n",
       " '4604617',\n",
       " '476000',\n",
       " '48051',\n",
       " '482',\n",
       " '484',\n",
       " '490',\n",
       " '492',\n",
       " '4e',\n",
       " '4g',\n",
       " '4gb',\n",
       " '4m11s',\n",
       " '4netjobs',\n",
       " '4s',\n",
       " '4shared',\n",
       " '4snjqp',\n",
       " '4th',\n",
       " '50',\n",
       " '500',\n",
       " '5000',\n",
       " '500k',\n",
       " '500m',\n",
       " '505b0232',\n",
       " '5094',\n",
       " '50k',\n",
       " '510',\n",
       " '515',\n",
       " '521',\n",
       " '5242575',\n",
       " '5277478',\n",
       " '5287',\n",
       " '53331',\n",
       " '5337555197',\n",
       " '53481',\n",
       " '543627485763966',\n",
       " '55',\n",
       " '550',\n",
       " '5575096797',\n",
       " '55mm',\n",
       " '566',\n",
       " '57',\n",
       " '58',\n",
       " '5800',\n",
       " '5af506e1',\n",
       " '5bgkg2iwphzohwaeuesrwnegqg_labco7rw9wfx8hao',\n",
       " '5c',\n",
       " '5c2f',\n",
       " '5ggs_m_9ma3ti40fs6mvpics',\n",
       " '5million',\n",
       " '5s',\n",
       " '5th',\n",
       " '5tu9gn1l310',\n",
       " '60',\n",
       " '600',\n",
       " '600m',\n",
       " '613000',\n",
       " '616375350',\n",
       " '6174122',\n",
       " '629',\n",
       " '629410220489046',\n",
       " '633807',\n",
       " '636',\n",
       " '6381501',\n",
       " '6401116',\n",
       " '661',\n",
       " '666',\n",
       " '674732645945877',\n",
       " '682',\n",
       " '694',\n",
       " '6_h0m5sayho',\n",
       " '6th',\n",
       " '700',\n",
       " '704682339621282',\n",
       " '710',\n",
       " '710000',\n",
       " '73231344',\n",
       " '733634264',\n",
       " '733949243353321',\n",
       " '734237113324534',\n",
       " '74',\n",
       " '750',\n",
       " '753',\n",
       " '754989901225153',\n",
       " '764484966942313',\n",
       " '775510675841486',\n",
       " '783',\n",
       " '79',\n",
       " '7in',\n",
       " '7k',\n",
       " '800',\n",
       " '82',\n",
       " '821',\n",
       " '824',\n",
       " '8252267209931889',\n",
       " '832000',\n",
       " '84',\n",
       " '85',\n",
       " '851',\n",
       " '857',\n",
       " '860',\n",
       " '868',\n",
       " '8692160',\n",
       " '87',\n",
       " '870',\n",
       " '88',\n",
       " '884',\n",
       " '8851222',\n",
       " '898',\n",
       " '89___',\n",
       " '89c',\n",
       " '89iyec7nrwp5nytno5u7amhvmflutggl',\n",
       " '8a',\n",
       " '8bit',\n",
       " '90',\n",
       " '90000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000',\n",
       " '902099',\n",
       " '9082175',\n",
       " '9107',\n",
       " '911',\n",
       " '920',\n",
       " '9277547',\n",
       " '936868579660284',\n",
       " '937732262907249',\n",
       " '940',\n",
       " '950',\n",
       " '969',\n",
       " '999999999',\n",
       " '9bzkp7q19f0',\n",
       " '9gag',\n",
       " '9nl',\n",
       " '_0f9fa8aa',\n",
       " '__',\n",
       " '______________________',\n",
       " '______________________________',\n",
       " '__killuminati94',\n",
       " '_bzszz',\n",
       " '_chris_cz',\n",
       " '_fphgk5zllsvdqv0zuf0mb',\n",
       " '_gibu',\n",
       " '_o3h',\n",
       " '_ry6f57sprnd2xv',\n",
       " '_self',\n",
       " '_thqbeum69aqup1ih',\n",
       " '_trksid',\n",
       " '_vlczzrg8vgctlpsd9ongewhj8',\n",
       " 'a0qouc7q48v3_qiaaabpugaaacsqar0_vgoqwqxjmpuyvkosf3k',\n",
       " 'a7',\n",
       " 'aa',\n",
       " 'aaaaaaa',\n",
       " 'aaas',\n",
       " 'aavpwj9',\n",
       " 'abbas',\n",
       " 'ablaze',\n",
       " 'able',\n",
       " 'abominable',\n",
       " 'abomination',\n",
       " 'abonner',\n",
       " 'about',\n",
       " 'above',\n",
       " 'absolute',\n",
       " 'absolutely',\n",
       " 'absorbing',\n",
       " 'abuse',\n",
       " 'abused',\n",
       " 'abuses',\n",
       " 'abusive',\n",
       " 'abusue',\n",
       " 'ac',\n",
       " 'acaer',\n",
       " 'acceptance',\n",
       " 'access',\n",
       " 'accessories',\n",
       " 'accidental',\n",
       " 'accomplished',\n",
       " 'account',\n",
       " 'accounts',\n",
       " 'achieve',\n",
       " 'achieved',\n",
       " 'acidic',\n",
       " 'aclk',\n",
       " 'acn2g',\n",
       " 'acoustic',\n",
       " 'acquire',\n",
       " 'acquiring',\n",
       " 'across',\n",
       " 'act',\n",
       " 'acting',\n",
       " 'activates',\n",
       " 'active',\n",
       " 'actor',\n",
       " 'actorid',\n",
       " 'actors',\n",
       " 'actresses',\n",
       " 'actual',\n",
       " 'actually',\n",
       " 'ad',\n",
       " 'adam',\n",
       " 'adapt',\n",
       " 'add',\n",
       " 'addicting',\n",
       " 'adding',\n",
       " 'addition',\n",
       " 'adele',\n",
       " 'adf',\n",
       " 'adhoc',\n",
       " 'admirable',\n",
       " 'admire',\n",
       " 'admit',\n",
       " 'admitting',\n",
       " 'adore',\n",
       " 'adoult',\n",
       " 'adroid',\n",
       " 'adsense',\n",
       " 'adult',\n",
       " 'adurl',\n",
       " 'advance',\n",
       " 'advertise',\n",
       " 'advertisements',\n",
       " 'advertisiments',\n",
       " 'advertising',\n",
       " 'advice',\n",
       " 'affiliated',\n",
       " 'affiliateid',\n",
       " 'afflicted',\n",
       " 'afford',\n",
       " 'afiliati',\n",
       " 'afiliere',\n",
       " 'afqjcngkm',\n",
       " 'afraid',\n",
       " 'africa',\n",
       " 'african',\n",
       " 'africans',\n",
       " 'after',\n",
       " 'aftermath',\n",
       " 'again',\n",
       " 'against',\n",
       " 'age',\n",
       " 'ago',\n",
       " 'agree',\n",
       " 'agreeable',\n",
       " 'ah',\n",
       " 'ahead',\n",
       " 'ahhh',\n",
       " 'ai',\n",
       " 'aid',\n",
       " 'aiiima',\n",
       " 'aimbwbfqbzg',\n",
       " 'ain',\n",
       " 'air',\n",
       " 'airlines',\n",
       " 'airplane',\n",
       " 'aka',\n",
       " 'al',\n",
       " 'album',\n",
       " 'alcoholic',\n",
       " 'alert',\n",
       " 'alex',\n",
       " 'alfred',\n",
       " 'ali',\n",
       " 'alive',\n",
       " 'all',\n",
       " 'allot',\n",
       " 'allow',\n",
       " 'allows',\n",
       " 'allways',\n",
       " 'almond',\n",
       " 'almost',\n",
       " 'alo',\n",
       " 'aloidia',\n",
       " 'alone',\n",
       " 'alot',\n",
       " 'already',\n",
       " 'alright',\n",
       " 'also',\n",
       " 'alternate',\n",
       " 'alvar',\n",
       " 'always',\n",
       " 'am',\n",
       " 'amazed',\n",
       " 'amazement',\n",
       " 'amazing',\n",
       " 'amazon',\n",
       " 'ambition',\n",
       " 'ambitious',\n",
       " 'amendment',\n",
       " 'america',\n",
       " 'american',\n",
       " 'americans',\n",
       " 'amiable',\n",
       " 'amount',\n",
       " 'amp',\n",
       " 'amy',\n",
       " 'an',\n",
       " 'ana',\n",
       " 'anaconda',\n",
       " 'analyst',\n",
       " 'anand',\n",
       " 'ancestors',\n",
       " 'and',\n",
       " 'anderson',\n",
       " 'andrew',\n",
       " 'andrijamatf',\n",
       " 'android',\n",
       " 'angel',\n",
       " 'angels',\n",
       " 'angry',\n",
       " 'animal',\n",
       " 'animals',\n",
       " 'animation',\n",
       " 'animations',\n",
       " 'animator',\n",
       " 'anime',\n",
       " 'animes',\n",
       " 'annoyed',\n",
       " 'annoying',\n",
       " 'annoys',\n",
       " 'another',\n",
       " 'ans',\n",
       " 'answer',\n",
       " 'anthem',\n",
       " 'antrobofficial',\n",
       " 'anxious',\n",
       " 'any',\n",
       " 'anybody',\n",
       " 'anymore',\n",
       " 'anyone',\n",
       " 'anything',\n",
       " 'anyway',\n",
       " 'anywhere',\n",
       " 'anywon',\n",
       " 'aod64_1ofc7seh_1pop',\n",
       " 'aplica',\n",
       " 'apocalypse',\n",
       " 'apologies',\n",
       " 'apostles',\n",
       " 'app',\n",
       " 'apparel',\n",
       " 'apparently',\n",
       " 'applause',\n",
       " 'apple',\n",
       " 'applied',\n",
       " 'applocker',\n",
       " 'appoints',\n",
       " 'appreciate',\n",
       " 'appreciated',\n",
       " 'apprecitate',\n",
       " 'approve',\n",
       " 'apps',\n",
       " 'arbitrate',\n",
       " 'are',\n",
       " 'aren',\n",
       " 'arguements',\n",
       " 'arive',\n",
       " 'arkglzjqup0',\n",
       " 'arm',\n",
       " 'army',\n",
       " 'around',\n",
       " 'arrogant',\n",
       " 'arrowgance',\n",
       " 'art',\n",
       " 'artady',\n",
       " 'articles',\n",
       " 'artist',\n",
       " 'artists',\n",
       " 'as',\n",
       " 'aseris',\n",
       " 'asia',\n",
       " 'asian',\n",
       " 'asinine',\n",
       " 'ask',\n",
       " 'asked',\n",
       " 'asking',\n",
       " 'aslamu',\n",
       " 'aspiring',\n",
       " 'aspx',\n",
       " 'ass',\n",
       " 'assume',\n",
       " 'astauand',\n",
       " 'aswell',\n",
       " 'at',\n",
       " 'atlastatlas',\n",
       " 'attacks',\n",
       " 'attention',\n",
       " 'auburn',\n",
       " 'audio',\n",
       " 'audiojungle',\n",
       " 'audit',\n",
       " 'audition',\n",
       " 'auditiondetail_',\n",
       " 'auditioning',\n",
       " 'auditions',\n",
       " 'aunt',\n",
       " 'austin',\n",
       " 'australia',\n",
       " 'authenticviews',\n",
       " 'authority',\n",
       " 'auto',\n",
       " 'autotune',\n",
       " 'autotuned',\n",
       " 'avaaz',\n",
       " 'available',\n",
       " 'avicii',\n",
       " 'avoid',\n",
       " 'aw',\n",
       " 'awards',\n",
       " 'aware',\n",
       " 'away',\n",
       " 'aways',\n",
       " 'awesom',\n",
       " 'awesome',\n",
       " 'awesomeness',\n",
       " 'awesoooome',\n",
       " 'awesum',\n",
       " 'awful',\n",
       " 'awsome',\n",
       " 'axeljonssons',\n",
       " 'axiomatic',\n",
       " 'axy665',\n",
       " 'aye',\n",
       " 'ayyy',\n",
       " 'azerbaijan',\n",
       " 'b00ecvf93g',\n",
       " 'b00mppqhri',\n",
       " 'b3',\n",
       " 'b5',\n",
       " 'b5t',\n",
       " 'b7b',\n",
       " 'b8l',\n",
       " 'ba',\n",
       " 'baba',\n",
       " 'babe',\n",
       " 'baby',\n",
       " 'back',\n",
       " 'bad',\n",
       " 'bady',\n",
       " 'ball',\n",
       " 'ballad',\n",
       " 'balls',\n",
       " 'band',\n",
       " 'bands',\n",
       " 'bang',\n",
       " 'bangers',\n",
       " 'banging',\n",
       " 'bangladesh',\n",
       " 'barnesandnoble',\n",
       " 'bars',\n",
       " 'base',\n",
       " 'based',\n",
       " 'basically',\n",
       " 'basketball',\n",
       " 'bass',\n",
       " 'bastard',\n",
       " 'bd3721315',\n",
       " 'bdp',\n",
       " 'be',\n",
       " 'beast',\n",
       " 'beat',\n",
       " 'beatboxing',\n",
       " 'beaties',\n",
       " 'beating',\n",
       " 'beats',\n",
       " 'beautiful',\n",
       " 'beauty',\n",
       " 'because',\n",
       " 'become',\n",
       " 'becomes',\n",
       " 'been',\n",
       " 'before',\n",
       " 'begin',\n",
       " 'beginning',\n",
       " 'behavior',\n",
       " 'behind',\n",
       " 'behold',\n",
       " 'beibs',\n",
       " 'being',\n",
       " 'belarus',\n",
       " 'belgique',\n",
       " 'belgium',\n",
       " 'believe',\n",
       " 'believemefilm',\n",
       " 'believer',\n",
       " 'believing',\n",
       " 'bella',\n",
       " 'belle',\n",
       " 'belly',\n",
       " 'below',\n",
       " 'belrus',\n",
       " 'beneath',\n",
       " 'bengal',\n",
       " 'bennett',\n",
       " 'berzerk',\n",
       " 'besloor',\n",
       " 'best',\n",
       " 'bet',\n",
       " 'beta',\n",
       " 'betfair',\n",
       " 'better',\n",
       " 'between',\n",
       " 'beutiful',\n",
       " 'beware',\n",
       " 'bf4',\n",
       " 'bg',\n",
       " 'bgq',\n",
       " 'bieber',\n",
       " 'big',\n",
       " 'bigboss286',\n",
       " 'bigelow',\n",
       " 'bigger',\n",
       " 'bighit',\n",
       " 'bikini',\n",
       " 'bil',\n",
       " 'bilion',\n",
       " 'billboard',\n",
       " 'billie',\n",
       " 'billion',\n",
       " 'billions',\n",
       " 'billon',\n",
       " 'bills',\n",
       " 'binbox',\n",
       " 'bing',\n",
       " 'birtgday',\n",
       " 'birthday',\n",
       " 'bisexual',\n",
       " 'bishopsgravemarker',\n",
       " 'bit',\n",
       " 'bitch',\n",
       " 'bitcoins',\n",
       " 'bite',\n",
       " 'black',\n",
       " 'blanc',\n",
       " 'blank',\n",
       " 'blast',\n",
       " 'bleach',\n",
       " 'bless',\n",
       " 'blessing',\n",
       " 'block',\n",
       " 'blog',\n",
       " 'blogfa',\n",
       " 'blogspot',\n",
       " 'blond',\n",
       " 'blonde',\n",
       " 'blow',\n",
       " 'blows',\n",
       " 'blue',\n",
       " 'blushing',\n",
       " 'boa',\n",
       " 'boaconic',\n",
       " 'bocilile',\n",
       " 'body',\n",
       " 'bogdan',\n",
       " 'bomb',\n",
       " 'bones',\n",
       " 'bonus',\n",
       " 'boobs',\n",
       " 'book',\n",
       " 'bookies',\n",
       " 'bookmakers',\n",
       " 'boomerul',\n",
       " 'boooobs',\n",
       " 'boost',\n",
       " 'border',\n",
       " 'borderlands',\n",
       " 'bored',\n",
       " 'boring',\n",
       " 'born',\n",
       " 'bother',\n",
       " 'bots',\n",
       " 'bottom',\n",
       " 'bout',\n",
       " 'bowl',\n",
       " 'box',\n",
       " 'boxium',\n",
       " 'boy',\n",
       " 'boyfriend',\n",
       " 'boys',\n",
       " 'bps',\n",
       " 'br',\n",
       " 'brah',\n",
       " 'brain',\n",
       " 'brake',\n",
       " 'brand',\n",
       " 'brave',\n",
       " 'brazil',\n",
       " 'brazilian',\n",
       " 'break',\n",
       " 'breaken',\n",
       " 'breaks',\n",
       " 'breath',\n",
       " 'brew',\n",
       " 'briefs',\n",
       " 'bring',\n",
       " 'bringing',\n",
       " 'brings',\n",
       " 'brinkman',\n",
       " 'british',\n",
       " 'britishs',\n",
       " 'broken',\n",
       " 'brooooo',\n",
       " 'brother',\n",
       " 'brotherhood',\n",
       " 'brothers',\n",
       " 'brought',\n",
       " 'browser',\n",
       " 'brt0u5',\n",
       " 'brutally',\n",
       " 'bs',\n",
       " 'btw',\n",
       " 'bubblews',\n",
       " 'buchmair',\n",
       " 'bucket',\n",
       " 'bucks',\n",
       " 'buggti',\n",
       " 'build',\n",
       " 'bulgaria',\n",
       " 'bumps',\n",
       " 'bunch',\n",
       " 'burda',\n",
       " 'burder',\n",
       " 'burned',\n",
       " 'burst',\n",
       " 'bus',\n",
       " 'business',\n",
       " 'busyglide',\n",
       " 'but',\n",
       " 'butalabs',\n",
       " 'butt',\n",
       " 'button',\n",
       " 'butts',\n",
       " 'buy',\n",
       " 'buys',\n",
       " 'buzz',\n",
       " 'bv',\n",
       " 'bvm',\n",
       " 'bxrosr',\n",
       " 'by',\n",
       " 'c3',\n",
       " 'c349',\n",
       " 'ca',\n",
       " 'cabelo',\n",
       " 'cachebuster',\n",
       " 'cad',\n",
       " 'call',\n",
       " 'called',\n",
       " 'calls',\n",
       " 'came',\n",
       " 'camera',\n",
       " 'cameraman',\n",
       " 'camp',\n",
       " 'campid',\n",
       " 'can',\n",
       " 'canal',\n",
       " 'cancer',\n",
       " 'canibus',\n",
       " 'cant',\n",
       " 'canvas',\n",
       " 'cap',\n",
       " 'capitalized',\n",
       " 'car',\n",
       " 'card',\n",
       " 'cards',\n",
       " 'care',\n",
       " 'career',\n",
       " 'cares',\n",
       " 'caroline',\n",
       " 'case',\n",
       " 'cash',\n",
       " 'catch',\n",
       " 'catchy',\n",
       " 'categories',\n",
       " 'cats',\n",
       " 'cause',\n",
       " 'caution',\n",
       " 'cazzy',\n",
       " 'cd',\n",
       " 'cd92db3f4',\n",
       " 'ce',\n",
       " 'cease',\n",
       " 'cece',\n",
       " 'celeb',\n",
       " 'celebrate',\n",
       " 'celebrated',\n",
       " 'celebration',\n",
       " 'celebrity',\n",
       " 'censor',\n",
       " 'cent',\n",
       " 'central',\n",
       " 'cents',\n",
       " 'cereal',\n",
       " 'certain',\n",
       " 'certification',\n",
       " 'cevxzvsjlk8',\n",
       " 'cge',\n",
       " 'chacking',\n",
       " 'chainise',\n",
       " 'challenge',\n",
       " 'challenges',\n",
       " 'champion',\n",
       " 'chance',\n",
       " 'chanel',\n",
       " 'chanell',\n",
       " 'change',\n",
       " 'changeable',\n",
       " 'chanicka',\n",
       " 'channel',\n",
       " 'channels',\n",
       " 'channnnnnelll',\n",
       " 'chanson',\n",
       " 'chap',\n",
       " 'characterized',\n",
       " 'charity',\n",
       " 'charley',\n",
       " 'charlie',\n",
       " 'charlieee',\n",
       " 'chaste',\n",
       " 'chaîne',\n",
       " 'chcfcvzfzfbvzdr',\n",
       " 'cheat',\n",
       " 'cheating',\n",
       " 'cheats',\n",
       " 'check',\n",
       " 'checked',\n",
       " 'checking',\n",
       " 'cheer',\n",
       " 'cheers',\n",
       " 'cheetos',\n",
       " 'cheilith',\n",
       " 'chesture',\n",
       " 'chhanel',\n",
       " 'chick',\n",
       " 'child',\n",
       " 'children',\n",
       " 'chillpal',\n",
       " 'chills',\n",
       " 'chillstep',\n",
       " 'china',\n",
       " 'chinese',\n",
       " 'ching',\n",
       " 'chiptunes',\n",
       " 'choice',\n",
       " 'chooses',\n",
       " 'chorenn',\n",
       " 'chorus',\n",
       " 'chose',\n",
       " 'chrck',\n",
       " 'christ',\n",
       " 'christianity',\n",
       " 'christians',\n",
       " 'christmas',\n",
       " 'chubby',\n",
       " 'chubbz',\n",
       " 'chuck',\n",
       " 'cid',\n",
       " 'cirus',\n",
       " 'citizen',\n",
       " ...]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# get the feature names\n",
    "cv.get_feature_names()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model Building"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, df_y, test_size=0.33, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<1310x4454 sparse matrix of type '<class 'numpy.int64'>'\n",
       "\twith 17525 stored elements in Compressed Sparse Row format>"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9195046439628483"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Naive Bayes Classifier\n",
    "from sklearn.naive_bayes import MultinomialNB\n",
    "clf = MultinomialNB()\n",
    "clf.fit(X_train,y_train)\n",
    "clf.score(X_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Model 91.95046439628483 %\n"
     ]
    }
   ],
   "source": [
    "# Accuracy of our Model\n",
    "print(\"Accuracy of Model\",clf.score(X_test,y_test)*100,\"%\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 0, 1, 0,\n",
       "       1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1,\n",
       "       1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0,\n",
       "       0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1, 1,\n",
       "       1, 1, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1,\n",
       "       0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1,\n",
       "       1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 1,\n",
       "       1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1,\n",
       "       0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0,\n",
       "       1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0,\n",
       "       1, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1,\n",
       "       1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0,\n",
       "       1, 0, 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1,\n",
       "       0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1,\n",
       "       1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0,\n",
       "       1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1,\n",
       "       1, 0, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1,\n",
       "       0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0,\n",
       "       0, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1,\n",
       "       1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 0, 1, 1, 1,\n",
       "       1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0,\n",
       "       0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0,\n",
       "       0, 0, 1, 0, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 1,\n",
       "       0, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 0,\n",
       "       1, 0, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 1,\n",
       "       1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 0, 0,\n",
       "       0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0,\n",
       "       1, 1, 1, 0, 1, 0, 0, 0], dtype=int64)"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Predicting with our model\n",
    "clf.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Sample Prediciton\n",
    "comment = [\"Check this out\"]\n",
    "vect = cv.transform(comment).toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1], dtype=int64)"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.predict(vect)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "class_dict = {'ham':0,'spam':1}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_values([0, 1])"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "class_dict.values()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Spam\n"
     ]
    }
   ],
   "source": [
    "if clf.predict(vect) == 1:\n",
    "    print(\"Spam\")\n",
    "else:\n",
    "    print(\"Ham\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0], dtype=int64)"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Sample Prediciton 2\n",
    "comment1 = [\"Great song Friend\"]\n",
    "vect = cv.transform(comment1).toarray()\n",
    "clf.predict(vect)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Save The Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "naivebayesML = open(\"YtbSpam_model.pkl\",\"wb\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "pickle.dump(clf,naivebayesML)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "naivebayesML.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "ytb_model = open(\"YtbSpam_model.pkl\",\"rb\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_model = pickle.load(ytb_model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MultinomialNB(alpha=1.0, class_prior=None, fit_prior=True)"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1], dtype=int64)"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Sample Prediciton 3\n",
    "comment2 = [\"Hey Music Fans I really appreciate all of you,but see this song too\"]\n",
    "vect = cv.transform(comment2).toarray()\n",
    "new_model.predict(vect)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Spam\n"
     ]
    }
   ],
   "source": [
    "if new_model.predict(vect) == 1:\n",
    "    print(\"Spam\")\n",
    "else:\n",
    "    print(\"Ham\")"
   ]
  },
  {
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}