{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "JBMdxhsVohF2"
   },
   "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": "iSwgbS3CooqD"
   },
   "outputs": [],
   "source": [
    "file_url = '../DataSet/taxstats2015.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "91P_EE8NpNHg"
   },
   "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": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "id": "YTXNZwfYpQkg",
    "outputId": "6b1ab7f7-cc4c-434e-c482-db4063c6d68d"
   },
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "86yRMdUtpgnI"
   },
   "outputs": [],
   "source": [
    "X = df[['Average total business income', 'Average total business expenses']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "tU9JPKJJpzBg"
   },
   "outputs": [],
   "source": [
    "clusters = pd.DataFrame()\n",
    "inertia = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Hu0Dv2tzqEB0"
   },
   "outputs": [],
   "source": [
    "clusters['cluster_range'] = range(1, 15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "RlEkLMUkqsbq"
   },
   "outputs": [],
   "source": [
    "for k in clusters['cluster_range']:\n",
    "    kmeans = KMeans(n_clusters=k).fit(X)\n",
    "    inertia.append(kmeans.inertia_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 483
    },
    "colab_type": "code",
    "id": "slnfmG3Mqtyy",
    "outputId": "7ea3a4ec-e566-44d7-d48a-d2602d33feb9"
   },
   "outputs": [],
   "source": [
    "clusters['inertia'] = inertia\n",
    "clusters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 368
    },
    "colab_type": "code",
    "id": "WHUQBZ8uqvly",
    "outputId": "195438e3-b79a-41f8-afd5-e2430070aed9"
   },
   "outputs": [],
   "source": [
    "alt.Chart(clusters).mark_line().encode(alt.X('cluster_range'), alt.Y('inertia'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "CUMT2XeIrIpf"
   },
   "outputs": [],
   "source": [
    "optim_cluster = 4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "colab_type": "code",
    "id": "UTb91dx0rsqD",
    "outputId": "f84bdf2a-e092-46ff-cc4e-baddebcc2ccb"
   },
   "outputs": [],
   "source": [
    "kmeans = KMeans(random_state=42, n_clusters=optim_cluster)\n",
    "kmeans.fit(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "4Zf9IGEsruV8"
   },
   "outputs": [],
   "source": [
    "df['cluster2'] = kmeans.predict(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "id": "LfxHSNcUrzA0",
    "outputId": "c220d3eb-6145-4bcf-b53e-e4e0b35c7b11"
   },
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 368
    },
    "colab_type": "code",
    "id": "JM-UjFvyr73R",
    "outputId": "c05e1733-37ea-4174-b279-ea028639d185"
   },
   "outputs": [],
   "source": [
    "alt.Chart(df).mark_circle().encode(x='Average total business income', y='Average total business expenses',color='cluster2:N', tooltip=['Postcode', 'cluster2', 'Average total business income', 'Average total business expenses']).interactive()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "aGMIPBYOscBQ"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise5_3.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
}