pandas_profiling.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "75541a50",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from pandas_profiling import ProfileReport"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ddee1eb6",
   "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>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>bmi</th>\n",
       "      <th>children</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19</td>\n",
       "      <td>female</td>\n",
       "      <td>27.900</td>\n",
       "      <td>0</td>\n",
       "      <td>yes</td>\n",
       "      <td>southwest</td>\n",
       "      <td>16884.92400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18</td>\n",
       "      <td>male</td>\n",
       "      <td>33.770</td>\n",
       "      <td>1</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>1725.55230</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>male</td>\n",
       "      <td>33.000</td>\n",
       "      <td>3</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>4449.46200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33</td>\n",
       "      <td>male</td>\n",
       "      <td>22.705</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "      <td>northwest</td>\n",
       "      <td>21984.47061</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32</td>\n",
       "      <td>male</td>\n",
       "      <td>28.880</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "      <td>northwest</td>\n",
       "      <td>3866.85520</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age     sex     bmi  children smoker     region      charges\n",
       "0   19  female  27.900         0    yes  southwest  16884.92400\n",
       "1   18    male  33.770         1     no  southeast   1725.55230\n",
       "2   28    male  33.000         3     no  southeast   4449.46200\n",
       "3   33    male  22.705         0     no  northwest  21984.47061\n",
       "4   32    male  28.880         0     no  northwest   3866.85520"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"Data/insurance.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "53ba4955",
   "metadata": {},
   "source": [
    "# Creating a simple report quickly using Pandas Profiling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "49afbef9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Creating an instance of Profile_Report\n",
    "profile = ProfileReport(df, title=\"Pandas Profiling Report\", explorative=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "5dbdb52e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# profile"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d5e16639",
   "metadata": {},
   "outputs": [],
   "source": [
    "# profile.to_widgets()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "a00e6e79",
   "metadata": {},
   "outputs": [],
   "source": [
    "# profile.to_notebook_iframe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5a4380bd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "0bc8f680c5dd4b44a5fd915b4b4c7c0e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "83bca2de64ff4ea5a4c3c303dceebf58",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3b52a78be75c42f6aec86a41c6480ff5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Render HTML:   0%|          | 0/1 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "193dc434c1e44c339bed806dd2da3b3f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Export report to file:   0%|          | 0/1 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "profile.to_file(\"pandas_profiling.html\")"
   ]
  }
 ],
 "metadata": {
  "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}