{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "zVIPgXoWlEXC"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.cluster import KMeans\n",
    "import altair as alt\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "EhSFCirNlG5J"
   },
   "outputs": [],
   "source": [
    "file_url = '../DataSet/taxstats2015.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "T9mNYH_WlLIG"
   },
   "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": 359
    },
    "colab_type": "code",
    "id": "yLUsDBmRlMot",
    "outputId": "f1c45d02-9230-4a93-d165-56a7f4f43424"
   },
   "outputs": [],
   "source": [
    "df.tail(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "n_Sfij90lOVg"
   },
   "outputs": [],
   "source": [
    "X = df[['Average total business income', 'Average total business expenses']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "colab_type": "code",
    "id": "w6ZLzCgGlbsG",
    "outputId": "ee95a798-8acf-4cd8-c44e-ec4576123b8d"
   },
   "outputs": [],
   "source": [
    "kmeans = KMeans(random_state=8)\n",
    "kmeans.fit(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "VX56G-A0ldDY",
    "outputId": "222b701c-4d67-4c78-dede-c160dc426171"
   },
   "outputs": [],
   "source": [
    "y_preds = kmeans.predict(X)\n",
    "y_preds[-10:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 359
    },
    "colab_type": "code",
    "id": "aPL8x8zalpvO",
    "outputId": "4708c18a-4619-4c2d-d13f-35857847408f"
   },
   "outputs": [],
   "source": [
    "df['cluster'] = y_preds\n",
    "df.tail(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 328
    },
    "colab_type": "code",
    "id": "GrYs7MjIl1Iu",
    "outputId": "6ef6192e-74d5-46b9-9abb-87a788a6ad01"
   },
   "outputs": [],
   "source": [
    "df.pivot_table(values=['Average total business income', 'Average total business expenses'], index='cluster', aggfunc=np.mean)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "TnY8IrMlmBWE"
   },
   "outputs": [],
   "source": [
    "scatter_plot = alt.Chart(df).mark_circle()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 368
    },
    "colab_type": "code",
    "id": "hp4SnbDAmMvE",
    "outputId": "07dfcef2-dd0b-468c-ca6c-1c0302ff9f14"
   },
   "outputs": [],
   "source": [
    "scatter_plot.encode(x='Average total business income', y='Average total business expenses', color='cluster:N', tooltip=['Postcode', 'cluster', 'Average total business income', 'Average total business expenses']).interactive()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "uhcS5AmkmQ10"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise5_2.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
}