{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Agrupamento Hierárquico\n", "#### Aplicando o algoritmo de agrupamento hierárquico em uma base de dados de salário por idade." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "# importando a biblioteca matplotlib do python\n", "import matplotlib.pyplot as plt\n", "%matplotlib inline\n", "\n", "# importando a biblioteca scipy do python\n", "from scipy.cluster.hierarchy import dendrogram, linkage\n", "\n", "# importando a biblioteca sklearn do python\n", "from sklearn.cluster import AgglomerativeClustering\n", "from sklearn.preprocessing import StandardScaler\n", "\n", "# importando a biblioteca numpy do python\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "# criando os dados para a variável x\n", "x = [20, 27, 21, 37, 46, 53, 55, 47, 52, 32, 39, 41, 39, 48, 48]\n", "# criando os dados para a variável y\n", "y = [1000, 1200, 2900, 1850, 900, 950, 2000, 2100, 3000, 5900, 4100, 5100, 7000, 5000, 6500]\n", "\n", "# criando uma lista vazia 'dataframe'\n", "dataframe = []\n", "\n", "# iterando os dados x e y em 'dataframe'\n", "for i in range (0, 15):\n", " dataframe.append((x[i], y[i]))\n", " \n", "# transformando a lista em um array numpy\n", "dataframe = np.asarray(dataframe)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "# criando o objeto 'scaler'\n", "scaler = StandardScaler()" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "# realizando o escalonamento de atributos em 'dataframe'\n", "dataframe = scaler.fit_transform(dataframe)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# configurando alguns detalhes do gráfico\n", "plt.figure(figsize = (20, 10))\n", "plt.title('Dendrograma')\n", "plt.xlabel('Pessoas')\n", "plt.ylabel('Distâncias Euclidianas')\n", "\n", "#configurando o objeto 'dendrograma' para gerar o gráfico \n", "dendrograma = dendrogram(linkage(dataframe, method = 'ward'))\n", "# 'linkage' responsável por unir os dados\n", "# 'method' é a escolha do tipo de função para cálculo das distâncias, 'ward' é a que possui melhores \n", "# resultados" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "# criando o objeto clusterizador 'hc'\n", "hc = AgglomerativeClustering(n_clusters = 3, affinity = 'euclidean', linkage = 'ward')" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "# treinando e realizando a clusterização com os dados do dataframe\n", "previsoes = hc.fit_predict(dataframe)" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# configurando o gráfico\n", "plt.figure(figsize = (10,5))\n", "plt.title('Dados Clusterizados')\n", "plt.scatter(dataframe[previsoes == 0, 0], dataframe[previsoes == 0, 1], s = 100, marker = 'x', c = 'red', \n", " label = 'Cluster 1')\n", "plt.scatter(dataframe[previsoes == 1, 0], dataframe[previsoes == 1, 1], s = 100, marker = 'x', c = 'blue', \n", " label = 'Cluster 2')\n", "plt.scatter(dataframe[previsoes == 2, 0], dataframe[previsoes == 2, 1], s = 100, marker = 'x', c = 'green', \n", " label = 'Cluster 3')\n", "plt.xlabel('Idade')\n", "plt.ylabel('Salário')\n", "plt.grid(True)\n", "plt.box(False)\n", "plt.legend()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Alguma Dúvida? Entre em Contato Comigo:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "- [Me envie um e-mail](mailto:alysson.barbosa@ee.ufcg.edu.br);" ] } ], "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": "3.7.4" } }, "nbformat": 4, "nbformat_minor": 4 }