{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Using [this](https://www.youtube.com/watch?v=RZYjsw6P4nI) youtube tutorial"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1. Import data\n",
    "2. Change label columns to 1 and 0\n",
    "3. Split the columns\n",
    "4. Split into test and train\n",
    "5. TURN ALL DATA TO NUMBERS! Convert words/text data into numbers without losing much of the information\n",
    "\n",
    "    a. Bag of Words is one way (gives number to each word -- inefficient)\n",
    "    \n",
    "    b. CountVectorizer is better!\n",
    "        i. Counts number of words in document \n",
    "        ii. Number of features is the total number of (unique) words in corpus"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "# from sklearn.cross_validation import train_test_split\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.naive_bayes import MultinomialNB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.read_csv('spamham', sep='\\t', names=['Status', 'Message'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "====  ========  ====================\n",
      "  ..  Status    Message\n",
      "====  ========  ====================\n",
      "   0  ham       Go until jurong poin\n",
      "   1  ham       Ok lar... Joking wif\n",
      "   2  spam      Free entry in 2 a wk\n",
      "   3  ham       U dun say so early h\n",
      "   4  ham       Nah I don't think he\n",
      "====  ========  ====================\n"
     ]
    }
   ],
   "source": [
    "from tabulate import tabulate\n",
    "\n",
    "def shorten(long_string):\n",
    "    return long_string[:1] if len(long_string) < 21 else long_string[:20]\n",
    "\n",
    "def df_for_tabulate(df, column):\n",
    "    pretty_df = df.copy()\n",
    "    pretty_df[column] = pretty_df.apply(lambda x: shorten(x[column]), axis = 1)\n",
    "    return pretty_df\n",
    "    \n",
    "tabulate_df = df_for_tabulate(df, 'Message')\n",
    "print(tabulate(tabulate_df[:5], tablefmt=\"rst\", headers=tabulate_df.columns))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5572"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "# w.female[w.female == 'female'] = 1 \n",
    "# w.female[w.female == 'male']   = 0\n",
    "\n",
    "df['Status'][df['Status'] == 'ham'] = 1\n",
    "df['Status'][df['Status'] == 'spam'] = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "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>Status</th>\n",
       "      <th>Message</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Ok lar... Joking wif u oni...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>U dun say so early hor... U c already then say...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Nah I don't think he goes to usf, he lives aro...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Status                                            Message\n",
       "0      1  Go until jurong point, crazy.. Available only ...\n",
       "1      1                      Ok lar... Joking wif u oni...\n",
       "2      0  Free entry in 2 a wkly comp to win FA Cup fina...\n",
       "3      1  U dun say so early hor... U c already then say...\n",
       "4      1  Nah I don't think he goes to usf, he lives aro..."
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "# inverse_transform\n",
    "# fit_transform\n",
    "\n",
    "cv = CountVectorizer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "cv1 = cv.fit_transform(df['Message'])\n",
    "cv1b = cv.inverse_transform(df['Message'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "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]])"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv1.toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[array(['00', '000', '000pes', ..., 'online', 'onluy', 'only'],\n",
       "       dtype='<U34')]"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv1b"
   ]
  },
  {
   "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": 2
}