{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "12dba44a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "1d480e94",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "zsh:1: command not found: kaggle\r\n"
     ]
    }
   ],
   "source": [
    "!kaggle datasets download -d gender_classification_v7.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "13a40d88",
   "metadata": {
    "scrolled": true
   },
   "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>long_hair</th>\n",
       "      <th>forehead_width_cm</th>\n",
       "      <th>forehead_height_cm</th>\n",
       "      <th>nose_wide</th>\n",
       "      <th>nose_long</th>\n",
       "      <th>lips_thin</th>\n",
       "      <th>distance_nose_to_lip_long</th>\n",
       "      <th>gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>11.8</td>\n",
       "      <td>6.1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>5.4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>11.8</td>\n",
       "      <td>6.3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>14.4</td>\n",
       "      <td>6.1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>13.5</td>\n",
       "      <td>5.9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\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",
       "      <th>4996</th>\n",
       "      <td>1</td>\n",
       "      <td>13.6</td>\n",
       "      <td>5.1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4997</th>\n",
       "      <td>1</td>\n",
       "      <td>11.9</td>\n",
       "      <td>5.4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4998</th>\n",
       "      <td>1</td>\n",
       "      <td>12.9</td>\n",
       "      <td>5.7</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4999</th>\n",
       "      <td>1</td>\n",
       "      <td>13.2</td>\n",
       "      <td>6.2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5000</th>\n",
       "      <td>1</td>\n",
       "      <td>15.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5001 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      long_hair  forehead_width_cm  forehead_height_cm  nose_wide  nose_long  \\\n",
       "0             1               11.8                 6.1          1          0   \n",
       "1             0               14.0                 5.4          0          0   \n",
       "2             0               11.8                 6.3          1          1   \n",
       "3             0               14.4                 6.1          0          1   \n",
       "4             1               13.5                 5.9          0          0   \n",
       "...         ...                ...                 ...        ...        ...   \n",
       "4996          1               13.6                 5.1          0          0   \n",
       "4997          1               11.9                 5.4          0          0   \n",
       "4998          1               12.9                 5.7          0          0   \n",
       "4999          1               13.2                 6.2          0          0   \n",
       "5000          1               15.4                 5.4          1          1   \n",
       "\n",
       "      lips_thin  distance_nose_to_lip_long  gender  \n",
       "0             1                          1    Male  \n",
       "1             1                          0  Female  \n",
       "2             1                          1    Male  \n",
       "3             1                          1    Male  \n",
       "4             0                          0  Female  \n",
       "...         ...                        ...     ...  \n",
       "4996          0                          0  Female  \n",
       "4997          0                          0  Female  \n",
       "4998          0                          0  Female  \n",
       "4999          0                          0  Female  \n",
       "5000          1                          1    Male  \n",
       "\n",
       "[5001 rows x 8 columns]"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "raw_data = pd.read_csv(\"gender_class.csv\")\n",
    "raw_data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "51c05e9a",
   "metadata": {},
   "source": [
    "Wyczyści zbiór z artefaktów (np. puste linie, przykłady z niepoprawnymi wartościami)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "c70571df",
   "metadata": {},
   "outputs": [],
   "source": [
    "def clean_data(data):\n",
    "    data.dropna(inplace=True)\n",
    "    return data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "0481b0dd",
   "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>long_hair</th>\n",
       "      <th>forehead_width_cm</th>\n",
       "      <th>forehead_height_cm</th>\n",
       "      <th>nose_wide</th>\n",
       "      <th>nose_long</th>\n",
       "      <th>lips_thin</th>\n",
       "      <th>distance_nose_to_lip_long</th>\n",
       "      <th>gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>11.8</td>\n",
       "      <td>6.1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>5.4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>11.8</td>\n",
       "      <td>6.3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>14.4</td>\n",
       "      <td>6.1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>13.5</td>\n",
       "      <td>5.9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\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",
       "      <th>4996</th>\n",
       "      <td>1</td>\n",
       "      <td>13.6</td>\n",
       "      <td>5.1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4997</th>\n",
       "      <td>1</td>\n",
       "      <td>11.9</td>\n",
       "      <td>5.4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4998</th>\n",
       "      <td>1</td>\n",
       "      <td>12.9</td>\n",
       "      <td>5.7</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4999</th>\n",
       "      <td>1</td>\n",
       "      <td>13.2</td>\n",
       "      <td>6.2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5000</th>\n",
       "      <td>1</td>\n",
       "      <td>15.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5001 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      long_hair  forehead_width_cm  forehead_height_cm  nose_wide  nose_long  \\\n",
       "0             1               11.8                 6.1          1          0   \n",
       "1             0               14.0                 5.4          0          0   \n",
       "2             0               11.8                 6.3          1          1   \n",
       "3             0               14.4                 6.1          0          1   \n",
       "4             1               13.5                 5.9          0          0   \n",
       "...         ...                ...                 ...        ...        ...   \n",
       "4996          1               13.6                 5.1          0          0   \n",
       "4997          1               11.9                 5.4          0          0   \n",
       "4998          1               12.9                 5.7          0          0   \n",
       "4999          1               13.2                 6.2          0          0   \n",
       "5000          1               15.4                 5.4          1          1   \n",
       "\n",
       "      lips_thin  distance_nose_to_lip_long  gender  \n",
       "0             1                          1    Male  \n",
       "1             1                          0  Female  \n",
       "2             1                          1    Male  \n",
       "3             1                          1    Male  \n",
       "4             0                          0  Female  \n",
       "...         ...                        ...     ...  \n",
       "4996          0                          0  Female  \n",
       "4997          0                          0  Female  \n",
       "4998          0                          0  Female  \n",
       "4999          0                          0  Female  \n",
       "5000          1                          1    Male  \n",
       "\n",
       "[5001 rows x 8 columns]"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "raw_data = clean_data(raw_data)\n",
    "raw_data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "717fab23",
   "metadata": {},
   "source": [
    "Dokona normalizacji danych w zbiorze (np. normalizacja wartości float do zakresu 0.0 - 1.0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "7fcacf03",
   "metadata": {},
   "outputs": [],
   "source": [
    "def normalize_data(data):\n",
    "    # znormalizuj wartości float do zakresu 0.0 - 1.0\n",
    "    for col in data.columns:\n",
    "        if data[col].dtype == float:\n",
    "            data[col] = (data[col] - data[col].min()) / (data[col].max() - data[col].min())\n",
    "\n",
    "    return data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "bfd844ad",
   "metadata": {},
   "outputs": [],
   "source": [
    "normalized_data = normalize_data(raw_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "2d0b8499",
   "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>long_hair</th>\n",
       "      <th>forehead_width_cm</th>\n",
       "      <th>forehead_height_cm</th>\n",
       "      <th>nose_wide</th>\n",
       "      <th>nose_long</th>\n",
       "      <th>lips_thin</th>\n",
       "      <th>distance_nose_to_lip_long</th>\n",
       "      <th>gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0.097561</td>\n",
       "      <td>0.50</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0.634146</td>\n",
       "      <td>0.15</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0.097561</td>\n",
       "      <td>0.60</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0.731707</td>\n",
       "      <td>0.50</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0.512195</td>\n",
       "      <td>0.40</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\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",
       "      <th>4996</th>\n",
       "      <td>1</td>\n",
       "      <td>0.536585</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4997</th>\n",
       "      <td>1</td>\n",
       "      <td>0.121951</td>\n",
       "      <td>0.15</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4998</th>\n",
       "      <td>1</td>\n",
       "      <td>0.365854</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4999</th>\n",
       "      <td>1</td>\n",
       "      <td>0.439024</td>\n",
       "      <td>0.55</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5000</th>\n",
       "      <td>1</td>\n",
       "      <td>0.975610</td>\n",
       "      <td>0.15</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5001 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      long_hair  forehead_width_cm  forehead_height_cm  nose_wide  nose_long  \\\n",
       "0             1           0.097561                0.50          1          0   \n",
       "1             0           0.634146                0.15          0          0   \n",
       "2             0           0.097561                0.60          1          1   \n",
       "3             0           0.731707                0.50          0          1   \n",
       "4             1           0.512195                0.40          0          0   \n",
       "...         ...                ...                 ...        ...        ...   \n",
       "4996          1           0.536585                0.00          0          0   \n",
       "4997          1           0.121951                0.15          0          0   \n",
       "4998          1           0.365854                0.30          0          0   \n",
       "4999          1           0.439024                0.55          0          0   \n",
       "5000          1           0.975610                0.15          1          1   \n",
       "\n",
       "      lips_thin  distance_nose_to_lip_long  gender  \n",
       "0             1                          1    Male  \n",
       "1             1                          0  Female  \n",
       "2             1                          1    Male  \n",
       "3             1                          1    Male  \n",
       "4             0                          0  Female  \n",
       "...         ...                        ...     ...  \n",
       "4996          0                          0  Female  \n",
       "4997          0                          0  Female  \n",
       "4998          0                          0  Female  \n",
       "4999          0                          0  Female  \n",
       "5000          1                          1    Male  \n",
       "\n",
       "[5001 rows x 8 columns]"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "normalized_data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "61fbcddc",
   "metadata": {},
   "source": [
    "2. Jeśli brak w zbiorze gotowego podziału na podzbiory train/dev/test, to dokona takiego podziału"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "dc386189",
   "metadata": {},
   "outputs": [],
   "source": [
    "train, dev, test = np.split(normalized_data.sample(frac=1, random_state=42), [int(.7*len(normalized_data)), int(.85*len(normalized_data))])\n",
    "\n",
    "# zapisz dane w osobnych plikach csv\n",
    "train.to_csv('train.csv', index=False)\n",
    "dev.to_csv('dev.csv', index=False)\n",
    "test.to_csv('test.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "9f888962",
   "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>long_hair</th>\n",
       "      <th>forehead_width_cm</th>\n",
       "      <th>forehead_height_cm</th>\n",
       "      <th>nose_wide</th>\n",
       "      <th>nose_long</th>\n",
       "      <th>lips_thin</th>\n",
       "      <th>distance_nose_to_lip_long</th>\n",
       "      <th>gender</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4432</th>\n",
       "      <td>1</td>\n",
       "      <td>0.512195</td>\n",
       "      <td>0.10</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2162</th>\n",
       "      <td>1</td>\n",
       "      <td>0.243902</td>\n",
       "      <td>0.70</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2396</th>\n",
       "      <td>1</td>\n",
       "      <td>0.512195</td>\n",
       "      <td>0.15</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4769</th>\n",
       "      <td>1</td>\n",
       "      <td>0.853659</td>\n",
       "      <td>0.10</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2271</th>\n",
       "      <td>1</td>\n",
       "      <td>0.292683</td>\n",
       "      <td>0.70</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\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",
       "      <th>846</th>\n",
       "      <td>1</td>\n",
       "      <td>0.097561</td>\n",
       "      <td>0.45</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2551</th>\n",
       "      <td>0</td>\n",
       "      <td>0.243902</td>\n",
       "      <td>0.35</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2928</th>\n",
       "      <td>1</td>\n",
       "      <td>0.634146</td>\n",
       "      <td>0.20</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>117</th>\n",
       "      <td>1</td>\n",
       "      <td>0.707317</td>\n",
       "      <td>0.50</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>645</th>\n",
       "      <td>1</td>\n",
       "      <td>0.195122</td>\n",
       "      <td>0.05</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Female</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>750 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      long_hair  forehead_width_cm  forehead_height_cm  nose_wide  nose_long  \\\n",
       "4432          1           0.512195                0.10          1          1   \n",
       "2162          1           0.243902                0.70          1          1   \n",
       "2396          1           0.512195                0.15          1          0   \n",
       "4769          1           0.853659                0.10          1          1   \n",
       "2271          1           0.292683                0.70          0          1   \n",
       "...         ...                ...                 ...        ...        ...   \n",
       "846           1           0.097561                0.45          1          1   \n",
       "2551          0           0.243902                0.35          1          1   \n",
       "2928          1           0.634146                0.20          0          0   \n",
       "117           1           0.707317                0.50          0          0   \n",
       "645           1           0.195122                0.05          1          0   \n",
       "\n",
       "      lips_thin  distance_nose_to_lip_long  gender  \n",
       "4432          1                          1    Male  \n",
       "2162          1                          1    Male  \n",
       "2396          0                          0  Female  \n",
       "4769          0                          1    Male  \n",
       "2271          0                          0  Female  \n",
       "...         ...                        ...     ...  \n",
       "846           1                          1    Male  \n",
       "2551          1                          1    Male  \n",
       "2928          0                          0  Female  \n",
       "117           0                          0  Female  \n",
       "645           0                          0  Female  \n",
       "\n",
       "[750 rows x 8 columns]"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dev"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "4598cea1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "         long_hair  forehead_width_cm  forehead_height_cm    nose_wide  \\\n",
      "count  5001.000000        5001.000000         5001.000000  5001.000000   \n",
      "mean      0.869626           0.434508            0.423155     0.493901   \n",
      "std       0.336748           0.270031            0.270634     0.500013   \n",
      "min       0.000000           0.000000            0.000000     0.000000   \n",
      "25%       1.000000           0.195122            0.200000     0.000000   \n",
      "50%       1.000000           0.414634            0.400000     0.000000   \n",
      "75%       1.000000           0.634146            0.650000     1.000000   \n",
      "max       1.000000           1.000000            1.000000     1.000000   \n",
      "\n",
      "         nose_long    lips_thin  distance_nose_to_lip_long  \n",
      "count  5001.000000  5001.000000                5001.000000  \n",
      "mean      0.507898     0.493101                   0.498900  \n",
      "std       0.499988     0.500002                   0.500049  \n",
      "min       0.000000     0.000000                   0.000000  \n",
      "25%       0.000000     0.000000                   0.000000  \n",
      "50%       1.000000     0.000000                   0.000000  \n",
      "75%       1.000000     1.000000                   1.000000  \n",
      "max       1.000000     1.000000                   1.000000  \n",
      "         long_hair  forehead_width_cm  forehead_height_cm    nose_wide  \\\n",
      "count  3500.000000        3500.000000         3500.000000  3500.000000   \n",
      "mean      0.870000           0.436021            0.425900     0.505714   \n",
      "std       0.336351           0.270492            0.271348     0.500039   \n",
      "min       0.000000           0.000000            0.000000     0.000000   \n",
      "25%       1.000000           0.195122            0.200000     0.000000   \n",
      "50%       1.000000           0.414634            0.400000     1.000000   \n",
      "75%       1.000000           0.634146            0.650000     1.000000   \n",
      "max       1.000000           1.000000            1.000000     1.000000   \n",
      "\n",
      "         nose_long    lips_thin  distance_nose_to_lip_long  \n",
      "count  3500.000000  3500.000000                3500.000000  \n",
      "mean      0.522000     0.499429                   0.507714  \n",
      "std       0.499587     0.500071                   0.500012  \n",
      "min       0.000000     0.000000                   0.000000  \n",
      "25%       0.000000     0.000000                   0.000000  \n",
      "50%       1.000000     0.000000                   1.000000  \n",
      "75%       1.000000     1.000000                   1.000000  \n",
      "max       1.000000     1.000000                   1.000000  \n",
      "        long_hair  forehead_width_cm  forehead_height_cm   nose_wide  \\\n",
      "count  750.000000         750.000000          750.000000  750.000000   \n",
      "mean     0.870667           0.419285            0.416933    0.472000   \n",
      "std      0.335792           0.264474            0.269500    0.499549   \n",
      "min      0.000000           0.000000            0.000000    0.000000   \n",
      "25%      1.000000           0.195122            0.200000    0.000000   \n",
      "50%      1.000000           0.414634            0.400000    0.000000   \n",
      "75%      1.000000           0.634146            0.637500    1.000000   \n",
      "max      1.000000           1.000000            1.000000    1.000000   \n",
      "\n",
      "        nose_long   lips_thin  distance_nose_to_lip_long  \n",
      "count  750.000000  750.000000                 750.000000  \n",
      "mean     0.466667    0.481333                   0.465333  \n",
      "std      0.499221    0.499985                   0.499130  \n",
      "min      0.000000    0.000000                   0.000000  \n",
      "25%      0.000000    0.000000                   0.000000  \n",
      "50%      0.000000    0.000000                   0.000000  \n",
      "75%      1.000000    1.000000                   1.000000  \n",
      "max      1.000000    1.000000                   1.000000  \n",
      "        long_hair  forehead_width_cm  forehead_height_cm   nose_wide  \\\n",
      "count  751.000000         751.000000          751.000000  751.000000   \n",
      "mean     0.866844           0.442662            0.416578    0.460719   \n",
      "std      0.339969           0.273141            0.268567    0.498787   \n",
      "min      0.000000           0.000000            0.000000    0.000000   \n",
      "25%      1.000000           0.195122            0.200000    0.000000   \n",
      "50%      1.000000           0.439024            0.400000    0.000000   \n",
      "75%      1.000000           0.658537            0.600000    1.000000   \n",
      "max      1.000000           1.000000            1.000000    1.000000   \n",
      "\n",
      "        nose_long   lips_thin  distance_nose_to_lip_long  \n",
      "count  751.000000  751.000000                 751.000000  \n",
      "mean     0.483356    0.475366                   0.491345  \n",
      "std      0.500056    0.499726                   0.500258  \n",
      "min      0.000000    0.000000                   0.000000  \n",
      "25%      0.000000    0.000000                   0.000000  \n",
      "50%      0.000000    0.000000                   0.000000  \n",
      "75%      1.000000    1.000000                   1.000000  \n",
      "max      1.000000    1.000000                   1.000000  \n"
     ]
    }
   ],
   "source": [
    "for d in [raw_data,train, dev, test]:\n",
    "    print( d.describe())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8fa84a56",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}