{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Chapter 7 - Feature Scaling"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 7.2. Standardisation "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "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>fare</th>\n",
       "      <th>pclass</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>22.0</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>38.0</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>26.0</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>35.0</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>35.0</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    age     fare  pclass\n",
       "0  22.0   7.2500       3\n",
       "1  38.0  71.2833       1\n",
       "2  26.0   7.9250       3\n",
       "3  35.0  53.1000       1\n",
       "4  35.0   8.0500       3"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "\n",
    "\n",
    "plt.rcParams[\"figure.figsize\"] = [8,6]\n",
    "sns.set_style(\"darkgrid\")\n",
    "\n",
    "titanic_data = sns.load_dataset('titanic')\n",
    "\n",
    "titanic_data  = titanic_data[[\"age\",\"fare\",\"pclass\"]]\n",
    "titanic_data.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "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>fare</th>\n",
       "      <th>pclass</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>714.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>29.699118</td>\n",
       "      <td>32.204208</td>\n",
       "      <td>2.308642</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>14.526497</td>\n",
       "      <td>49.693429</td>\n",
       "      <td>0.836071</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.420000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>20.125000</td>\n",
       "      <td>7.910400</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>28.000000</td>\n",
       "      <td>14.454200</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>38.000000</td>\n",
       "      <td>31.000000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>80.000000</td>\n",
       "      <td>512.329200</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              age        fare      pclass\n",
       "count  714.000000  891.000000  891.000000\n",
       "mean    29.699118   32.204208    2.308642\n",
       "std     14.526497   49.693429    0.836071\n",
       "min      0.420000    0.000000    1.000000\n",
       "25%     20.125000    7.910400    2.000000\n",
       "50%     28.000000   14.454200    3.000000\n",
       "75%     38.000000   31.000000    3.000000\n",
       "max     80.000000  512.329200    3.000000"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "scaler = StandardScaler()\n",
    "scaler.fit(titanic_data)\n",
    "\n",
    "titanic_data_scaled = scaler.transform(titanic_data)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>fare</th>\n",
       "      <th>pclass</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.530377</td>\n",
       "      <td>-0.502445</td>\n",
       "      <td>0.827377</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.571831</td>\n",
       "      <td>0.786845</td>\n",
       "      <td>-1.566107</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.254825</td>\n",
       "      <td>-0.488854</td>\n",
       "      <td>0.827377</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.365167</td>\n",
       "      <td>0.420730</td>\n",
       "      <td>-1.566107</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.365167</td>\n",
       "      <td>-0.486337</td>\n",
       "      <td>0.827377</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        age      fare    pclass\n",
       "0 -0.530377 -0.502445  0.827377\n",
       "1  0.571831  0.786845 -1.566107\n",
       "2 -0.254825 -0.488854  0.827377\n",
       "3  0.365167  0.420730 -1.566107\n",
       "4  0.365167 -0.486337  0.827377"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data_scaled = pd.DataFrame(titanic_data_scaled, columns = titanic_data.columns)\n",
    "titanic_data_scaled.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='age', ylabel='Density'>"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.kdeplot(titanic_data['age'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='age', ylabel='Density'>"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.kdeplot(titanic_data_scaled['age'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 7.3. Min/Max Scaling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "scaler = MinMaxScaler()\n",
    "scaler.fit(titanic_data)\n",
    "\n",
    "titanic_data_scaled = scaler.transform(titanic_data)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "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>fare</th>\n",
       "      <th>pclass</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.271174</td>\n",
       "      <td>0.014151</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.472229</td>\n",
       "      <td>0.139136</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.321438</td>\n",
       "      <td>0.015469</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.434531</td>\n",
       "      <td>0.103644</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.434531</td>\n",
       "      <td>0.015713</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        age      fare  pclass\n",
       "0  0.271174  0.014151     1.0\n",
       "1  0.472229  0.139136     0.0\n",
       "2  0.321438  0.015469     1.0\n",
       "3  0.434531  0.103644     0.0\n",
       "4  0.434531  0.015713     1.0"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data_scaled = pd.DataFrame(titanic_data_scaled, columns = titanic_data.columns)\n",
    "titanic_data_scaled.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='age', ylabel='Density'>"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.kdeplot(titanic_data_scaled['age'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 7.4. Mean Normalization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age       29.699118\n",
       "fare      32.204208\n",
       "pclass     2.308642\n",
       "dtype: float64"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_vals = titanic_data.mean(axis=0)\n",
    "mean_vals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age        79.5800\n",
       "fare      512.3292\n",
       "pclass      2.0000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "range_vals = titanic_data.max(axis=0) - titanic_data.min(axis=0)\n",
    "range_vals\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "titanic_data_scaled = (titanic_data - mean_vals) / range_vals\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='age', ylabel='Density'>"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.kdeplot(titanic_data_scaled['age'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 7.5. Maximum Absolute Scaling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import MaxAbsScaler\n",
    "scaler = MaxAbsScaler()\n",
    "scaler.fit(titanic_data)\n",
    "\n",
    "titanic_data_scaled = scaler.transform(titanic_data)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "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>fare</th>\n",
       "      <th>pclass</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.2750</td>\n",
       "      <td>0.014151</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.4750</td>\n",
       "      <td>0.139136</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.3250</td>\n",
       "      <td>0.015469</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.4375</td>\n",
       "      <td>0.103644</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.4375</td>\n",
       "      <td>0.015713</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      age      fare    pclass\n",
       "0  0.2750  0.014151  1.000000\n",
       "1  0.4750  0.139136  0.333333\n",
       "2  0.3250  0.015469  1.000000\n",
       "3  0.4375  0.103644  0.333333\n",
       "4  0.4375  0.015713  1.000000"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data_scaled = pd.DataFrame(titanic_data_scaled, columns = titanic_data.columns)\n",
    "titanic_data_scaled.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='age', ylabel='Density'>"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.kdeplot(titanic_data_scaled['age'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 7.6. Median and Quantile Scaling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import RobustScaler\n",
    "\n",
    "scaler = RobustScaler()\n",
    "scaler.fit(titanic_data)\n",
    "\n",
    "titanic_data_scaled = scaler.transform(titanic_data)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "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>fare</th>\n",
       "      <th>pclass</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.335664</td>\n",
       "      <td>-0.312011</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.559441</td>\n",
       "      <td>2.461242</td>\n",
       "      <td>-2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.111888</td>\n",
       "      <td>-0.282777</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.391608</td>\n",
       "      <td>1.673732</td>\n",
       "      <td>-2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.391608</td>\n",
       "      <td>-0.277363</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        age      fare  pclass\n",
       "0 -0.335664 -0.312011     0.0\n",
       "1  0.559441  2.461242    -2.0\n",
       "2 -0.111888 -0.282777     0.0\n",
       "3  0.391608  1.673732    -2.0\n",
       "4  0.391608 -0.277363     0.0"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data_scaled = pd.DataFrame(titanic_data_scaled, columns = titanic_data.columns)\n",
    "titanic_data_scaled.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='age', ylabel='Density'>"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.kdeplot(titanic_data_scaled['age'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 7.7. Vector Unit Length Scaling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import Normalizer\n",
    "titanic_data.dropna(inplace =True)\n",
    "scaler = Normalizer(norm='l1')\n",
    "scaler.fit(titanic_data)\n",
    "\n",
    "titanic_data_scaled = scaler.transform(titanic_data)\n",
    "\n"
   ]
  },
  {
   "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>age</th>\n",
       "      <th>fare</th>\n",
       "      <th>pclass</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.682171</td>\n",
       "      <td>0.224806</td>\n",
       "      <td>0.093023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.344567</td>\n",
       "      <td>0.646365</td>\n",
       "      <td>0.009068</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.704130</td>\n",
       "      <td>0.214624</td>\n",
       "      <td>0.081246</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.392817</td>\n",
       "      <td>0.595960</td>\n",
       "      <td>0.011223</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.760043</td>\n",
       "      <td>0.174810</td>\n",
       "      <td>0.065147</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        age      fare    pclass\n",
       "0  0.682171  0.224806  0.093023\n",
       "1  0.344567  0.646365  0.009068\n",
       "2  0.704130  0.214624  0.081246\n",
       "3  0.392817  0.595960  0.011223\n",
       "4  0.760043  0.174810  0.065147"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "titanic_data_scaled = pd.DataFrame(titanic_data_scaled, columns = titanic_data.columns)\n",
    "titanic_data_scaled.head()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='age', ylabel='Density'>"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.kdeplot(titanic_data_scaled['age'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 7.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Question 1\n",
    "\n",
    "After standardisation the mean value of the dataset becomes:\n",
    "\n",
    "A. 1 \\\n",
    "B. 0 \\\n",
    "C. -1 \\\n",
    "D. None of the above\n",
    "\n",
    "Answer: B"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Question 2\n",
    "\n",
    "What is the formula to apply mean normalization on the dataset?:\n",
    " \n",
    "A. (values - mean) / (max - min) \\\n",
    "B.  (value) / (max - min)  \\\n",
    "C.  (value) / (max)  \\\n",
    "D. None of the above\n",
    "\n",
    "Answer: A"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Question 3\n",
    "\n",
    "The formula `value/max(values)` is used to implement\n",
    " \n",
    "A. Min/Max Scaling \\\n",
    "B. Maximum Absolute Scaling  \\\n",
    "C. Standardisation \\\n",
    "D. Mean Normalization\n",
    "\n",
    "Answer: B"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 7.2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "On the `price` column of the following `diamonds`dataset, apply `min/max` scaling. \n",
    "Display kerneal density plot for the `price` column after scaling."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "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>price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>334</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>335</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   price\n",
       "0    326\n",
       "1    326\n",
       "2    327\n",
       "3    334\n",
       "4    335"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "plt.rcParams[\"figure.figsize\"] = [8,6]\n",
    "sns.set_style(\"darkgrid\")\n",
    "\n",
    "diamond_data = sns.load_dataset('diamonds')\n",
    "diamond_data = diamond_data[['price']]\n",
    "diamond_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='price', ylabel='Density'>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "scaler = MinMaxScaler()\n",
    "scaler.fit(diamond_data)\n",
    "\n",
    "diamond_data_scaled = scaler.transform(diamond_data)\n",
    "\n",
    "diamond_data_scaled = pd.DataFrame(diamond_data_scaled, columns = diamond_data.columns)\n",
    "diamond_data_scaled.head()\n",
    "\n",
    "sns.kdeplot(diamond_data_scaled['price'])"
   ]
  },
  {
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}