{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "# Lab 10\n", "\n", "Suppose you have a list of positions of possible clients of Uber in Lisbon (Passageiros.csv). How many cars could you use and where they could be positioned in order to reduce time? Use a cluster analysis appraoch to support the solution of this problem.\n", "\n", "* import the libraries needed\n", "* import dataset from Passageiros.csv file\n", "* Verify imported data\n", "* verify data types and convert into numeric if needed. Use for example, df['x']=pd.to_numeric(df['x'], errors='coerce')\n", "* plot a scatter chart\n", "* create a X dataframe including only numeric columns\n", "* calculete WCSS using X dataframe:\n", "\n", " wcss = []\n", "\n", " for i in range(1, 11):\n", "\n", " kmeans = KMeans(n_clusters=i, init='k-means++', max_iter=300, n_init=10, random_state=0)\n", "\n", " kmeans.fit(df)\n", "\n", " wcss.append(kmeans.inertia_)\n", "\n", " plt.plot(range(1, 11), wcss)\n", "\n", " plt.title('Elbow Method')\n", "\n", " plt.xlabel('Number of clusters')\n", "\n", " plt.ylabel('WCSS')\n", "\n", " plt.show()\n", "\n", " plot a scatter chart showing centroids of the clusters estimated\n", "\n" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "from sklearn.cluster import KMeans\n", "\n", "df = pd.read_csv(\"Passageiros.csv\")\n", "\n", "df.head(5)\n", "\n", "df[\"X\"]=pd.to_numeric(df[\"X\"], errors=\"coerce\")\n", "df[\"Y\"]=pd.to_numeric(df[\"Y\"], errors=\"coerce\")\n", "\n", "plt.scatter(df[\"X\"], df[\"Y\"])\n", "plt.title(\"Scatter plot\")\n", "plt.show()\n", "\n", "\n", "numerics = [\"float\", \"int\"]\n", "X = df.select_dtypes(include=numerics)\n", "\n", "wcss = []\n", "\n", "for i in range (1,11):\n", " kmeans = KMeans(n_clusters=i, init='k-means++', max_iter=300, n_init=10, random_state=0)\n", " kmeans.fit(X)\n", " wcss.append(kmeans.inertia_)\n", " \n", "plt.plot(range(1,11), wcss)\n", "plt.title(\"Elbow Method\")\n", "plt.xlabel(\"Number of Clusters\")\n", "plt.ylabel(\"WCSS\")\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "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": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }