{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "i0wiJTpOoGOG"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import warnings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "id": "cTI8Z8tWrgHS"
   },
   "outputs": [],
   "source": [
    "warnings.filterwarnings(\"ignore\", category=FutureWarning, module=\"seaborn._oldcore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "id": "ADcHCCKHrgHT"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: chardet in c:\\users\\kiran\\anaconda3\\lib\\site-packages (4.0.0)\n"
     ]
    }
   ],
   "source": [
    "!pip install chardet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "id": "smO9dWKeDuJX"
   },
   "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>v1</th>\n",
       "      <th>v2</th>\n",
       "      <th>Unnamed: 2</th>\n",
       "      <th>Unnamed: 3</th>\n",
       "      <th>Unnamed: 4</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ham</td>\n",
       "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ham</td>\n",
       "      <td>Ok lar... Joking wif u oni...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>spam</td>\n",
       "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ham</td>\n",
       "      <td>U dun say so early hor... U c already then say...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ham</td>\n",
       "      <td>Nah I don't think he goes to usf, he lives aro...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     v1                                                 v2 Unnamed: 2  \\\n",
       "0   ham  Go until jurong point, crazy.. Available only ...        NaN   \n",
       "1   ham                      Ok lar... Joking wif u oni...        NaN   \n",
       "2  spam  Free entry in 2 a wkly comp to win FA Cup fina...        NaN   \n",
       "3   ham  U dun say so early hor... U c already then say...        NaN   \n",
       "4   ham  Nah I don't think he goes to usf, he lives aro...        NaN   \n",
       "\n",
       "  Unnamed: 3 Unnamed: 4  \n",
       "0        NaN        NaN  \n",
       "1        NaN        NaN  \n",
       "2        NaN        NaN  \n",
       "3        NaN        NaN  \n",
       "4        NaN        NaN  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import chardet\n",
    "\n",
    "with open('spam.csv', 'rb') as f:\n",
    "    result = chardet.detect(f.read())\n",
    "    encoding = result['encoding']\n",
    "\n",
    "df = pd.read_csv(\"spam.csv\", encoding=encoding)\n",
    "df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "id": "4x6SuNReszDt"
   },
   "outputs": [],
   "source": [
    "df=df.iloc[:,[0,1]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "id": "Y7958JSgs47x"
   },
   "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>v1</th>\n",
       "      <th>v2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ham</td>\n",
       "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ham</td>\n",
       "      <td>Ok lar... Joking wif u oni...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>spam</td>\n",
       "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ham</td>\n",
       "      <td>U dun say so early hor... U c already then say...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ham</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": [
       "     v1                                                 v2\n",
       "0   ham  Go until jurong point, crazy.. Available only ...\n",
       "1   ham                      Ok lar... Joking wif u oni...\n",
       "2  spam  Free entry in 2 a wkly comp to win FA Cup fina...\n",
       "3   ham  U dun say so early hor... U c already then say...\n",
       "4   ham  Nah I don't think he goes to usf, he lives aro..."
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "id": "h2IpwMKxs_Em"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5572, 2)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "id": "betBt_AMurFF"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5572 entries, 0 to 5571\n",
      "Data columns (total 2 columns):\n",
      " #   Column  Non-Null Count  Dtype \n",
      "---  ------  --------------  ----- \n",
      " 0   v1      5572 non-null   object\n",
      " 1   v2      5572 non-null   object\n",
      "dtypes: object(2)\n",
      "memory usage: 87.2+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "id": "goBz3TF9utsk"
   },
   "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>v1</th>\n",
       "      <th>v2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5572</td>\n",
       "      <td>5572</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>unique</th>\n",
       "      <td>2</td>\n",
       "      <td>5169</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>top</th>\n",
       "      <td>ham</td>\n",
       "      <td>Sorry, I'll call later</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>freq</th>\n",
       "      <td>4825</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          v1                      v2\n",
       "count   5572                    5572\n",
       "unique     2                    5169\n",
       "top      ham  Sorry, I'll call later\n",
       "freq    4825                      30"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "id": "lStRSnHLu7fr"
   },
   "outputs": [],
   "source": [
    "df.rename(columns ={\"v1\":\"output\",\"v2\":\"sms\"},inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "id": "QvZjCe2ZvaXE"
   },
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import LabelEncoder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "id": "ZJMWnDcJj7P2"
   },
   "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>output</th>\n",
       "      <th>sms</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>Ok lar... Joking wif u oni...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   output                                                sms\n",
       "0       0  Go until jurong point, crazy.. Available only ...\n",
       "1       0                      Ok lar... Joking wif u oni...\n",
       "2       1  Free entry in 2 a wkly comp to win FA Cup fina..."
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lb=LabelEncoder()\n",
    "df[\"output\"]=lb.fit_transform(df['output'])\n",
    "df.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "id": "-Oc9IXNrlS7F"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['ham', 'spam'], dtype=object)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lb.classes_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "id": "C2Rs6oeV0Jo6"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "403"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "id": "5UcdMhFh0Uu-"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5169, 2)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.drop_duplicates(keep=\"first\",inplace=True)\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "id": "vFd9jXvn05_0"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "output\n",
       "0    4516\n",
       "1     653\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['output'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "id": "G17Dv6oF_NrI"
   },
   "outputs": [],
   "source": [
    "import regex"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "id": "iMgHOpcLEXtS"
   },
   "outputs": [],
   "source": [
    "df['num_characters']=df['sms'].apply(len)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "id": "Sn300j9uElSq"
   },
   "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>output</th>\n",
       "      <th>sms</th>\n",
       "      <th>num_characters</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
       "      <td>111</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>Ok lar... Joking wif u oni...</td>\n",
       "      <td>29</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   output                                                sms  num_characters\n",
       "0       0  Go until jurong point, crazy.. Available only ...             111\n",
       "1       0                      Ok lar... Joking wif u oni...              29"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "id": "7MXt_gUeEo1k"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package punkt to\n",
      "[nltk_data]     C:\\Users\\kiran\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package punkt is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import nltk\n",
    "nltk.download('punkt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "id": "7tQN_YxAFFBI"
   },
   "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>output</th>\n",
       "      <th>sms</th>\n",
       "      <th>num_characters</th>\n",
       "      <th>num_of_words</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
       "      <td>111</td>\n",
       "      <td>24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>Ok lar... Joking wif u oni...</td>\n",
       "      <td>29</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   output                                                sms  num_characters  \\\n",
       "0       0  Go until jurong point, crazy.. Available only ...             111   \n",
       "1       0                      Ok lar... Joking wif u oni...              29   \n",
       "\n",
       "   num_of_words  \n",
       "0            24  \n",
       "1             8  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['num_of_words']=df.apply(lambda row: len(nltk.word_tokenize(row['sms'])), axis=1)\n",
    "df.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "id": "epdDZJ77F9Nr"
   },
   "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>output</th>\n",
       "      <th>sms</th>\n",
       "      <th>num_characters</th>\n",
       "      <th>num_of_words</th>\n",
       "      <th>num_of_sentences</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>Go until jurong point, crazy.. Available only ...</td>\n",
       "      <td>111</td>\n",
       "      <td>24</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>Ok lar... Joking wif u oni...</td>\n",
       "      <td>29</td>\n",
       "      <td>8</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   output                                                sms  num_characters  \\\n",
       "0       0  Go until jurong point, crazy.. Available only ...             111   \n",
       "1       0                      Ok lar... Joking wif u oni...              29   \n",
       "\n",
       "   num_of_words  num_of_sentences  \n",
       "0            24                 2  \n",
       "1             8                 2  "
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['num_of_sentences']=df.apply(lambda row: len(nltk.sent_tokenize(row['sms'])), axis=1)\n",
    "df.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "id": "0rHiDai5G3fg"
   },
   "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>num_characters</th>\n",
       "      <th>num_of_words</th>\n",
       "      <th>num_of_sentences</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5169.000000</td>\n",
       "      <td>5169.000000</td>\n",
       "      <td>5169.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>78.977945</td>\n",
       "      <td>18.455794</td>\n",
       "      <td>1.965564</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>58.236293</td>\n",
       "      <td>13.324758</td>\n",
       "      <td>1.448541</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>36.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>60.000000</td>\n",
       "      <td>15.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>117.000000</td>\n",
       "      <td>26.000000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>910.000000</td>\n",
       "      <td>220.000000</td>\n",
       "      <td>38.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       num_characters  num_of_words  num_of_sentences\n",
       "count     5169.000000   5169.000000       5169.000000\n",
       "mean        78.977945     18.455794          1.965564\n",
       "std         58.236293     13.324758          1.448541\n",
       "min          2.000000      1.000000          1.000000\n",
       "25%         36.000000      9.000000          1.000000\n",
       "50%         60.000000     15.000000          1.000000\n",
       "75%        117.000000     26.000000          2.000000\n",
       "max        910.000000    220.000000         38.000000"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[['num_characters','num_of_words','num_of_sentences']].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "id": "KyYNz3tDoshI"
   },
   "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>num_characters</th>\n",
       "      <th>num_of_words</th>\n",
       "      <th>num_of_sentences</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>4516.000000</td>\n",
       "      <td>4516.000000</td>\n",
       "      <td>4516.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>70.459256</td>\n",
       "      <td>17.123782</td>\n",
       "      <td>1.820195</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>56.358207</td>\n",
       "      <td>13.493970</td>\n",
       "      <td>1.383657</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>34.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>52.000000</td>\n",
       "      <td>13.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>90.000000</td>\n",
       "      <td>22.000000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>910.000000</td>\n",
       "      <td>220.000000</td>\n",
       "      <td>38.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       num_characters  num_of_words  num_of_sentences\n",
       "count     4516.000000   4516.000000       4516.000000\n",
       "mean        70.459256     17.123782          1.820195\n",
       "std         56.358207     13.493970          1.383657\n",
       "min          2.000000      1.000000          1.000000\n",
       "25%         34.000000      8.000000          1.000000\n",
       "50%         52.000000     13.000000          1.000000\n",
       "75%         90.000000     22.000000          2.000000\n",
       "max        910.000000    220.000000         38.000000"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(df[df['output']==0][['num_characters','num_of_words','num_of_sentences']]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "id": "68Fd7dPxpxMV"
   },
   "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>num_characters</th>\n",
       "      <th>num_of_words</th>\n",
       "      <th>num_of_sentences</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>653.000000</td>\n",
       "      <td>653.000000</td>\n",
       "      <td>653.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>137.891271</td>\n",
       "      <td>27.667688</td>\n",
       "      <td>2.970904</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>30.137753</td>\n",
       "      <td>7.008418</td>\n",
       "      <td>1.488425</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>13.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>132.000000</td>\n",
       "      <td>25.000000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>149.000000</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>157.000000</td>\n",
       "      <td>32.000000</td>\n",
       "      <td>4.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>224.000000</td>\n",
       "      <td>46.000000</td>\n",
       "      <td>9.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       num_characters  num_of_words  num_of_sentences\n",
       "count      653.000000    653.000000        653.000000\n",
       "mean       137.891271     27.667688          2.970904\n",
       "std         30.137753      7.008418          1.488425\n",
       "min         13.000000      2.000000          1.000000\n",
       "25%        132.000000     25.000000          2.000000\n",
       "50%        149.000000     29.000000          3.000000\n",
       "75%        157.000000     32.000000          4.000000\n",
       "max        224.000000     46.000000          9.000000"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(df[df['output']==1][['num_characters','num_of_words','num_of_sentences']]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "id": "9WxGssH4p3rT"
   },
   "outputs": [],
   "source": [
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "id": "1ep7GkdVp7OK"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,6))\n",
    "sns.histplot(data=df,x='num_characters',hue='output')\n",
    "plt.plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "id": "YV7QJLXCrCkL"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.PairGrid at 0x1ba9f75a790>"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 808.875x750 with 12 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.pairplot(df,hue=\"output\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "id": "ikN3mLNIr7Lo"
   },
   "outputs": [],
   "source": [
    "def lower_text(x):\n",
    "  return x.lower()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "id": "YAairKz8sA5O"
   },
   "outputs": [],
   "source": [
    "df['sms']=df['sms'].apply(lower_text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "id": "PFQSgJ5nsmTt"
   },
   "outputs": [],
   "source": [
    "pattern = r'[^a-zA-Z0-9\\s]'\n",
    "df['sms'] = df['sms'].str.replace(pattern, '', regex=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "id": "QwdGg964sxDp"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     C:\\Users\\kiran\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from nltk.corpus import stopwords\n",
    "nltk.download('stopwords')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "id": "V9ewnL6mtBYe"
   },
   "outputs": [],
   "source": [
    "def remove_stopwords(x):\n",
    "  tex=[]\n",
    "  for i in x.split(' '):\n",
    "      if(i not in stopwords.words('english')):\n",
    "        tex.append(i)\n",
    "  return tex"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "id": "nN2cRsTjasAh"
   },
   "outputs": [],
   "source": [
    "df['transformed_txt']=df['sms'].apply(remove_stopwords)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "id": "Wmwh2Z_Xg-ri"
   },
   "outputs": [],
   "source": [
    "from nltk.stem.porter import PorterStemmer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "id": "WNbiS38YhOuc"
   },
   "outputs": [],
   "source": [
    "ps=PorterStemmer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "id": "xJbymlROhXeh"
   },
   "outputs": [],
   "source": [
    "def stemming(x):\n",
    "  tex=[]\n",
    "  for i in x:\n",
    "      tex.append(ps.stem(i))\n",
    "  return \" \".join(tex)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "id": "5goUrPFOhnzc"
   },
   "outputs": [],
   "source": [
    "df['transformed_txt']=df['transformed_txt'].apply(stemming)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "id": "QvMkzP2uoPwI"
   },
   "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>output</th>\n",
       "      <th>sms</th>\n",
       "      <th>num_characters</th>\n",
       "      <th>num_of_words</th>\n",
       "      <th>num_of_sentences</th>\n",
       "      <th>transformed_txt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>go until jurong point crazy available only in ...</td>\n",
       "      <td>111</td>\n",
       "      <td>24</td>\n",
       "      <td>2</td>\n",
       "      <td>go jurong point crazi avail bugi n great world...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>ok lar joking wif u oni</td>\n",
       "      <td>29</td>\n",
       "      <td>8</td>\n",
       "      <td>2</td>\n",
       "      <td>ok lar joke wif u oni</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>free entry in 2 a wkly comp to win fa cup fina...</td>\n",
       "      <td>155</td>\n",
       "      <td>37</td>\n",
       "      <td>2</td>\n",
       "      <td>free entri 2 wkli comp win fa cup final tkt 21...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>u dun say so early hor u c already then say</td>\n",
       "      <td>49</td>\n",
       "      <td>13</td>\n",
       "      <td>1</td>\n",
       "      <td>u dun say earli hor u c alreadi say</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>nah i dont think he goes to usf he lives aroun...</td>\n",
       "      <td>61</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "      <td>nah dont think goe usf live around though</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   output                                                sms  num_characters  \\\n",
       "0       0  go until jurong point crazy available only in ...             111   \n",
       "1       0                            ok lar joking wif u oni              29   \n",
       "2       1  free entry in 2 a wkly comp to win fa cup fina...             155   \n",
       "3       0        u dun say so early hor u c already then say              49   \n",
       "4       0  nah i dont think he goes to usf he lives aroun...              61   \n",
       "\n",
       "   num_of_words  num_of_sentences  \\\n",
       "0            24                 2   \n",
       "1             8                 2   \n",
       "2            37                 2   \n",
       "3            13                 1   \n",
       "4            15                 1   \n",
       "\n",
       "                                     transformed_txt  \n",
       "0  go jurong point crazi avail bugi n great world...  \n",
       "1                              ok lar joke wif u oni  \n",
       "2  free entri 2 wkli comp win fa cup final tkt 21...  \n",
       "3                u dun say earli hor u c alreadi say  \n",
       "4          nah dont think goe usf live around though  "
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "id": "jwdSG90Qogx2"
   },
   "outputs": [],
   "source": [
    "from sklearn.feature_extraction.text import CountVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "id": "Sgi8FK1hebJW"
   },
   "outputs": [],
   "source": [
    "cv=CountVectorizer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "id": "viG6AZ7teecr"
   },
   "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": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x=cv.fit_transform(df['transformed_txt']).toarray()\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "id": "kG2jwwHEesVa"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0       0\n",
       "1       0\n",
       "2       1\n",
       "3       0\n",
       "4       0\n",
       "       ..\n",
       "5567    1\n",
       "5568    0\n",
       "5569    0\n",
       "5570    0\n",
       "5571    0\n",
       "Name: output, Length: 5169, dtype: int32"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y=df['output']\n",
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "id": "86GBPs5Yhami"
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "id": "b8seR8XKhSvy"
   },
   "outputs": [],
   "source": [
    "X_train,X_test,Y_train,Y_test=train_test_split(x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "id": "_ETMwxqUh1nN"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3876, 7983)"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "id": "NnWEN7Xrh9iW"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3876,)"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "id": "xOlv_js_iE2b"
   },
   "outputs": [],
   "source": [
    "from sklearn.naive_bayes import GaussianNB, BernoulliNB\n",
    "from sklearn.svm import SVC"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "id": "onhg0yc1jHMX"
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import accuracy_score, precision_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "id": "dpgBZr0zifCJ"
   },
   "outputs": [],
   "source": [
    "gnb=GaussianNB()\n",
    "bnb=BernoulliNB()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "id": "nYrK4D4oiw5R"
   },
   "outputs": [],
   "source": [
    "gnb.fit(X_train,Y_train)\n",
    "gnb_pred=gnb.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "id": "og8G2EpAjS-Y"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train Score:  0.9396284829721362\n",
      "Test Score:  0.8692962103634957\n"
     ]
    }
   ],
   "source": [
    "print(\"Train Score: \",gnb.score(X_train,Y_train))\n",
    "print(\"Test Score: \",accuracy_score(Y_test, gnb_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "id": "zaB0GG2rlKxz"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train Score:  0.9806501547987616\n",
      "Test Score:  0.9667440061871616\n"
     ]
    }
   ],
   "source": [
    "bnb.fit(X_train,Y_train)\n",
    "bnb_pred=bnb.predict(X_test)\n",
    "\n",
    "print(\"Train Score: \",bnb.score(X_train,Y_train))\n",
    "print(\"Test Score: \",accuracy_score(Y_test, bnb_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Spam msg Classifier (Binnary Classification)",
   "provenance": []
  },
  "kaggle": {
   "accelerator": "none",
   "dataSources": [
    {
     "datasetId": 483,
     "sourceId": 982,
     "sourceType": "datasetVersion"
    }
   ],
   "dockerImageVersionId": 30732,
   "isGpuEnabled": false,
   "isInternetEnabled": false,
   "language": "python",
   "sourceType": "notebook"
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}