mlessentials/Lab05/Exercise5.04/Exercise5_04.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "OpvvISIrbLkH"
   },
   "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": "arwd2VGxbQw_"
   },
   "outputs": [],
   "source": [
    "file_url = '../DataSet/taxstats2015.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "yTrw_H8CbYc5"
   },
   "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": "Ch3Uw25bbbfs"
   },
   "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": "wcrvaHY6bdsX",
    "outputId": "d0d8fc95-1826-4529-9cf6-b60274ba2c82"
   },
   "outputs": [],
   "source": [
    "kmeans = KMeans(random_state=1, n_clusters=4, init='random', n_init=1)\n",
    "kmeans.fit(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "STeQ3-U6bgXr"
   },
   "outputs": [],
   "source": [
    "df['cluster3'] = kmeans.predict(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "vmmjs2-Abgb0"
   },
   "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": "7RGhQXCpbklC",
    "outputId": "84a545ec-d4c9-42b2-f202-024bac3bcf0a"
   },
   "outputs": [],
   "source": [
    "scatter_plot.encode(x='Average total business income', y='Average total business expenses',color='cluster3:N',\n",
    "tooltip=['Postcode', 'cluster3', 'Average total business income', 'Average total business expenses']\n",
    ").interactive()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 368
    },
    "colab_type": "code",
    "id": "CDqsVn5lbknb",
    "outputId": "cdc68274-c524-45e0-f787-e81ab1483b03"
   },
   "outputs": [],
   "source": [
    "kmeans = KMeans(random_state=1, n_clusters=4, init='random', n_init=10)\n",
    "kmeans.fit(X)\n",
    "df['cluster4'] = kmeans.predict(X)\n",
    "scatter_plot = alt.Chart(df).mark_circle()\n",
    "\n",
    "scatter_plot.encode(x='Average total business income', y='Average total business expenses',color='cluster4:N',\n",
    "tooltip=['Postcode', 'cluster4', 'Average total business income', 'Average total business expenses']\n",
    ").interactive()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 368
    },
    "colab_type": "code",
    "id": "GpLqIG4hbkpv",
    "outputId": "d945fa30-667c-47e7-8f10-81f105d6a7af"
   },
   "outputs": [],
   "source": [
    "kmeans = KMeans(random_state=1, n_clusters=4, init='random', n_init=100)\n",
    "kmeans.fit(X)\n",
    "df['cluster5'] = kmeans.predict(X)\n",
    "scatter_plot = alt.Chart(df).mark_circle()\n",
    "scatter_plot.encode(x='Average total business income', y='Average total business expenses',color='cluster5:N',\n",
    "tooltip=['Postcode', 'cluster5', 'Average total business income', 'Average total business expenses']\n",
    ").interactive()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "dhTRyHeMbkrz"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise5_04.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
}