{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "teVYTWp62NMf"
   },
   "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": "b_w9MPzrszPF"
   },
   "outputs": [],
   "source": [
    "file_url = '../DataSet/taxstats2015.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "9dP6E2ye3Jia"
   },
   "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": "6sx1xL3h4Ffz"
   },
   "outputs": [],
   "source": [
    "X = df[['Average total business income', 'Average total business expenses']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "k5zU1YmA4W-T"
   },
   "outputs": [],
   "source": [
    "business_income_min = df['Average total business income'].min()\n",
    "business_income_max = df['Average total business income'].max()\n",
    "\n",
    "business_expenses_min = df['Average total business expenses'].min()\n",
    "business_expenses_max = df['Average total business expenses'].max()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 85
    },
    "colab_type": "code",
    "id": "2IQm7qpU4p_S",
    "outputId": "7dc1ba5c-8b46-4fde-b910-fac098ab6c8a"
   },
   "outputs": [],
   "source": [
    "print(business_income_min)\n",
    "print(business_income_max)\n",
    "print(business_expenses_min)\n",
    "print(business_expenses_max)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "UlHRqugF4unX"
   },
   "outputs": [],
   "source": [
    "import random\n",
    "random.seed(42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "eqGlqkPi5Uo2"
   },
   "outputs": [],
   "source": [
    "centroids = pd.DataFrame()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "dMCfxYzA5Vv8"
   },
   "outputs": [],
   "source": [
    "centroids['Average total business income'] = random.sample(range(business_income_min, business_income_max), 4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "CE7GGrvv5wBm"
   },
   "outputs": [],
   "source": [
    "centroids['Average total business expenses'] = random.sample(range(business_expenses_min, business_expenses_max), 4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 173
    },
    "colab_type": "code",
    "id": "zBW4apPX5xb2",
    "outputId": "f6a9fec5-9075-489d-dd48-df3974f28eb9"
   },
   "outputs": [],
   "source": [
    "centroids['cluster'] = centroids.index\n",
    "centroids"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "eIA0hzt16xx7"
   },
   "outputs": [],
   "source": [
    "chart1 = alt.Chart(df.head()).mark_circle().encode(x='Average total business income', y='Average total business expenses', \n",
    "    color=alt.value('orange'),\n",
    "    tooltip=['Postcode', 'Average total business income', 'Average total business expenses']\n",
    ").interactive()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "7PGvAyEL63_R"
   },
   "outputs": [],
   "source": [
    "chart2 = alt.Chart(centroids).mark_circle(size=100).encode(x='Average total business income', y='Average total business expenses', \n",
    "    color=alt.value('black'),\n",
    "    tooltip=['cluster', 'Average total business income', 'Average total business expenses']\n",
    ").interactive()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 363
    },
    "colab_type": "code",
    "id": "Xm4FTXtp65ZB",
    "outputId": "b824d0a2-1440-42a4-bd21-4d12f9b1454d"
   },
   "outputs": [],
   "source": [
    "chart1 + chart2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "eQKhecFQ66sa"
   },
   "outputs": [],
   "source": [
    "def squared_euclidean(data_x, data_y, centroid_x, centroid_y, ):\n",
    "  return (data_x - centroid_x)**2 + (data_y - centroid_y)**2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "ORuNfqEy7zB5"
   },
   "outputs": [],
   "source": [
    "data_x = df.at[0, 'Average total business income']\n",
    "data_y = df.at[0, 'Average total business expenses']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "yakWRQoN70iU",
    "outputId": "abf5ef31-afc7-4eee-9b68-051a883212f6"
   },
   "outputs": [],
   "source": [
    "distances = [squared_euclidean(data_x, data_y, centroids.at[i, 'Average total business income'], centroids.at[i, 'Average total business expenses']) for i in range(4)]\n",
    "distances"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "azLmJ_FB7189"
   },
   "outputs": [],
   "source": [
    "cluster_index = distances.index(min(distances))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "wA2OZBYb9NoJ"
   },
   "outputs": [],
   "source": [
    "df.at[0, 'cluster'] = cluster_index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "id": "1kSpYhB89PBf",
    "outputId": "0905b440-75c5-42b8-ef3b-aa277673e9cd"
   },
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "id": "yj34XK-N9QKH",
    "outputId": "6b360e91-2cea-4f4d-af87-7d0e8f58f80e"
   },
   "outputs": [],
   "source": [
    "distances = [squared_euclidean(df.at[1, 'Average total business income'], df.at[1, 'Average total business expenses'], centroids.at[i, 'Average total business income'], centroids.at[i, 'Average total business expenses']) for i in range(4)]\n",
    "df.at[1, 'cluster'] = distances.index(min(distances))\n",
    "\n",
    "distances = [squared_euclidean(df.at[2, 'Average total business income'], df.at[2, 'Average total business expenses'], centroids.at[i, 'Average total business income'], centroids.at[i, 'Average total business expenses']) for i in range(4)]\n",
    "df.at[2, 'cluster'] = distances.index(min(distances))\n",
    "\n",
    "distances = [squared_euclidean(df.at[3, 'Average total business income'], df.at[3, 'Average total business expenses'], centroids.at[i, 'Average total business income'], centroids.at[i, 'Average total business expenses']) for i in range(4)]\n",
    "df.at[3, 'cluster'] = distances.index(min(distances))\n",
    "\n",
    "distances = [squared_euclidean(df.at[4, 'Average total business income'], df.at[4, 'Average total business expenses'], centroids.at[i, 'Average total business income'], centroids.at[i, 'Average total business expenses']) for i in range(4)]\n",
    "df.at[4, 'cluster'] = distances.index(min(distances))\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 363
    },
    "colab_type": "code",
    "id": "Gbodvbg190ee",
    "outputId": "879b69ec-52e1-473f-e9a0-9fcfe7e348d5"
   },
   "outputs": [],
   "source": [
    "chart1 = alt.Chart(df.head()).mark_circle().encode(x='Average total business income', y='Average total business expenses', \n",
    "    color='cluster:N',\n",
    "    tooltip=['Postcode', 'cluster', 'Average total business income', 'Average total business expenses']\n",
    ").interactive()\n",
    "\n",
    "chart2 = alt.Chart(centroids).mark_circle(size=100).encode(x='Average total business income', y='Average total business expenses', \n",
    "    color=alt.value('black'),\n",
    "    tooltip=['cluster', 'Average total business income', 'Average total business expenses']\n",
    ").interactive()\n",
    "chart1 + chart2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "waR0wfwn-OjS"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise5_4.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
}