Customer Segmentation.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Loading Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "sns.set()\n",
    "sns.set_theme(style=\"whitegrid\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>CustomerID</th>\n",
       "      <th>Genre</th>\n",
       "      <th>Age</th>\n",
       "      <th>Annual Income (k$)</th>\n",
       "      <th>Spending Score (1-100)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Male</td>\n",
       "      <td>19</td>\n",
       "      <td>15</td>\n",
       "      <td>39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Male</td>\n",
       "      <td>21</td>\n",
       "      <td>15</td>\n",
       "      <td>81</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Female</td>\n",
       "      <td>20</td>\n",
       "      <td>16</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Female</td>\n",
       "      <td>23</td>\n",
       "      <td>16</td>\n",
       "      <td>77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Female</td>\n",
       "      <td>31</td>\n",
       "      <td>17</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   CustomerID   Genre  Age  Annual Income (k$)  Spending Score (1-100)\n",
       "0           1    Male   19                  15                      39\n",
       "1           2    Male   21                  15                      81\n",
       "2           3  Female   20                  16                       6\n",
       "3           4  Female   23                  16                      77\n",
       "4           5  Female   31                  17                      40"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.read_csv('Mall_Customers.csv')\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 200 entries, 0 to 199\n",
      "Data columns (total 5 columns):\n",
      " #   Column                  Non-Null Count  Dtype \n",
      "---  ------                  --------------  ----- \n",
      " 0   CustomerID              200 non-null    int64 \n",
      " 1   Genre                   200 non-null    object\n",
      " 2   Age                     200 non-null    int64 \n",
      " 3   Annual Income (k$)      200 non-null    int64 \n",
      " 4   Spending Score (1-100)  200 non-null    int64 \n",
      "dtypes: int64(4), object(1)\n",
      "memory usage: 7.9+ KB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>CustomerID</th>\n",
       "      <th>Age</th>\n",
       "      <th>Annual Income (k$)</th>\n",
       "      <th>Spending Score (1-100)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>200.000000</td>\n",
       "      <td>200.000000</td>\n",
       "      <td>200.000000</td>\n",
       "      <td>200.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>100.500000</td>\n",
       "      <td>38.850000</td>\n",
       "      <td>60.560000</td>\n",
       "      <td>50.200000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>57.879185</td>\n",
       "      <td>13.969007</td>\n",
       "      <td>26.264721</td>\n",
       "      <td>25.823522</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>15.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>50.750000</td>\n",
       "      <td>28.750000</td>\n",
       "      <td>41.500000</td>\n",
       "      <td>34.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>100.500000</td>\n",
       "      <td>36.000000</td>\n",
       "      <td>61.500000</td>\n",
       "      <td>50.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>150.250000</td>\n",
       "      <td>49.000000</td>\n",
       "      <td>78.000000</td>\n",
       "      <td>73.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>200.000000</td>\n",
       "      <td>70.000000</td>\n",
       "      <td>137.000000</td>\n",
       "      <td>99.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       CustomerID         Age  Annual Income (k$)  Spending Score (1-100)\n",
       "count  200.000000  200.000000          200.000000              200.000000\n",
       "mean   100.500000   38.850000           60.560000               50.200000\n",
       "std     57.879185   13.969007           26.264721               25.823522\n",
       "min      1.000000   18.000000           15.000000                1.000000\n",
       "25%     50.750000   28.750000           41.500000               34.750000\n",
       "50%    100.500000   36.000000           61.500000               50.000000\n",
       "75%    150.250000   49.000000           78.000000               73.000000\n",
       "max    200.000000   70.000000          137.000000               99.000000"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Checking outliers with boxplot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:ylabel='Annual Income (k$)'>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(y = \"Annual Income (k$)\", data = data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "Q1 = data['Annual Income (k$)'].quantile(0.25)\n",
    "Q3 = data['Annual Income (k$)'].quantile(0.75)\n",
    "IQR = Q3 - Q1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "low_limit: -13.25\n",
      "up_limit: 132.75\n"
     ]
    }
   ],
   "source": [
    "low_lim = Q1 - 1.5 * IQR\n",
    "up_lim = Q3 + 1.5 * IQR\n",
    "print('low_limit:', low_lim)\n",
    "print('up_limit:', up_lim)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "outlier: [137, 137]\n"
     ]
    }
   ],
   "source": [
    "outlier = []\n",
    "for x in data['Annual Income (k$)']:\n",
    "    if ((x > up_lim) or (x < low_lim)):\n",
    "         outlier.append(x)\n",
    "print('outlier:', outlier)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "61.5"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['Annual Income (k$)'].median()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "#replace outliers with median\n",
    "data.loc[data['Annual Income (k$)'] >= 137, 'Annual Income (k$)'] = 61.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:ylabel='Annual Income (k$)'>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(y = \"Annual Income (k$)\", data = data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# outliers is removed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:ylabel='Spending Score (1-100)'>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.boxplot(y = \"Spending Score (1-100)\", data = data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# there is no outliers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = data.iloc[:, -2:].values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using the Elbow Method to find the optimal numbers of cluster"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.cluster import KMeans\n",
    "wcss = []\n",
    "\n",
    "for i in range(1,11):\n",
    "    kmeans = KMeans(n_clusters = i, init = 'k-means++', random_state = 42)\n",
    "    kmeans.fit(x)\n",
    "    wcss.append(kmeans.inertia_)\n",
    "    \n",
    "plt.plot(range(1,11), wcss)\n",
    "plt.title('The Elbow Method')\n",
    "plt.xlabel('Number of Clusters')\n",
    "plt.ylabel('WCSS')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# optimum number of clusters is 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0,\n",
       "       3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 0, 3, 1,\n",
       "       3, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 4, 2, 1, 2, 4, 2, 4, 2,\n",
       "       4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 1, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2,\n",
       "       4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2,\n",
       "       4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2,\n",
       "       4, 2], dtype=int32)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kmeans = KMeans(n_clusters=5, init='k-means++', random_state=42)\n",
    "y_kmeans = kmeans.fit_predict(x)\n",
    "y_kmeans"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visualising Cluster"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(x[y_kmeans==0,0],x[y_kmeans==0,1], label='Cluster 1')\n",
    "plt.scatter(x[y_kmeans==1,0],x[y_kmeans==1,1], label='Cluster 2')\n",
    "plt.scatter(x[y_kmeans==2,0],x[y_kmeans==2,1], label='Cluster 3')\n",
    "plt.scatter(x[y_kmeans==3,0],x[y_kmeans==3,1], label='Cluster 4')\n",
    "plt.scatter(x[y_kmeans==4,0],x[y_kmeans==4,1], label='Cluster 5')\n",
    "plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s = 150, c = 'linen', label = 'Centroids')\n",
    "plt.title('Cluster of Customers')\n",
    "plt.xlabel('Annual Income (k$)')\n",
    "plt.ylabel('Spending Score (1-100)')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  }
 ],
 "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": 4
}