{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "zEQuq8LJA3tn"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.cluster import KMeans\n",
    "import altair as alt "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "ZgMleSBTtEO6"
   },
   "outputs": [],
   "source": [
    "file_url = '../DataSet/taxstats2015.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "OyDwHaKiCDYQ"
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(file_url, usecols=['Postcode', 'Average total business income', 'Average total business expenses'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "vnxGsM2kCGUp"
   },
   "outputs": [],
   "source": [
    "X = df[['Average total business income', 'Average total business expenses']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "ih5PpKnICH_7"
   },
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.preprocessing import StandardScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "WywT72WzCJUk",
    "outputId": "2245ba90-b235-4061-f348-bb111e48c3e7"
   },
   "outputs": [],
   "source": [
    "min_max_scaler = MinMaxScaler()\n",
    "min_max_scaler.fit(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 136
    },
    "colab_type": "code",
    "id": "LFbkKgsxCKq7",
    "outputId": "ac247615-4f3d-4756-fe18-805c02dd558c"
   },
   "outputs": [],
   "source": [
    "X_min_max = min_max_scaler.transform(X)\n",
    "X_min_max"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "colab_type": "code",
    "id": "5OehxZ5BCgG9",
    "outputId": "ca35030a-786b-449c-947f-473c40758fb8"
   },
   "outputs": [],
   "source": [
    "kmeans = KMeans(random_state=1, n_clusters=4, init='k-means++', n_init=5)\n",
    "kmeans.fit(X_min_max)   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "HF_9Aw8OC-5u"
   },
   "outputs": [],
   "source": [
    "df['cluster8'] = kmeans.predict(X_min_max)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 368
    },
    "colab_type": "code",
    "id": "D2-atFYFDIae",
    "outputId": "9e24a0cc-1918-433a-cae5-5c2f5480d8a8"
   },
   "outputs": [],
   "source": [
    "scatter_plot = alt.Chart(df).mark_circle()\n",
    "scatter_plot.encode(x='Average total business income', y='Average total business expenses',color='cluster8:N',\n",
    "    tooltip=['Postcode', 'cluster8', 'Average total business income', 'Average total business expenses']\n",
    ").interactive()   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "colab_type": "code",
    "id": "kvzQBGgvDVPO",
    "outputId": "329e0b77-e79e-45ea-dba6-89154eb8aa29"
   },
   "outputs": [],
   "source": [
    "standard_scaler = StandardScaler()\n",
    "X_scaled = standard_scaler.fit_transform(X)\n",
    "kmeans = KMeans(random_state=1, n_clusters=4, init='k-means++', n_init=5)\n",
    "kmeans.fit(X_scaled)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "X44fDpkqEPdY"
   },
   "outputs": [],
   "source": [
    "df['cluster9'] = kmeans.predict(X_scaled)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 368
    },
    "colab_type": "code",
    "id": "SiKXkI3bEj34",
    "outputId": "e8fb6558-9ea0-442c-9461-e1f83f5a887d"
   },
   "outputs": [],
   "source": [
    "scatter_plot = alt.Chart(df).mark_circle()\n",
    "scatter_plot.encode(x='Average total business income', y='Average total business expenses',color='cluster9:N',\n",
    "    tooltip=['Postcode', 'cluster9', 'Average total business income', 'Average total business expenses']\n",
    ").interactive()   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "eyoC0HiXElOC"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise5_5.ipynb",
   "provenance": []
  },
  "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": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}