In [6]:
from google.colab import drive
import os
drive.mount('/content/gdrive')
# Establecer ruta de acceso en dr
import os
print(os.getcwd())
os.chdir("/content/gdrive/My Drive")
Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount("/content/gdrive", force_remount=True).
/content/gdrive/My Drive
In [7]:
# K-Means Clustering
# Importacion de librerias
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Carga del conjunto de datos
dataset = pd.read_csv("Mall_Customers.csv", sep = ",")
dataset.head()
Out[7]:
| CustomerID | Genre | Age | Annual Income (k$) | Spending Score (1-100) | |
|---|---|---|---|---|---|
| 0 | 1 | Male | 19 | 15 | 39 |
| 1 | 2 | Male | 21 | 15 | 81 |
| 2 | 3 | Female | 20 | 16 | 6 |
| 3 | 4 | Female | 23 | 16 | 77 |
| 4 | 5 | Female | 31 | 17 | 40 |
In [8]:
#Generamos nuestra x
X = dataset.iloc[:, [3, 4]].values
In [9]:
X
Out[9]:
array([[ 15, 39],
[ 15, 81],
[ 16, 6],
[ 16, 77],
[ 17, 40],
[ 17, 76],
[ 18, 6],
[ 18, 94],
[ 19, 3],
[ 19, 72],
[ 19, 14],
[ 19, 99],
[ 20, 15],
[ 20, 77],
[ 20, 13],
[ 20, 79],
[ 21, 35],
[ 21, 66],
[ 23, 29],
[ 23, 98],
[ 24, 35],
[ 24, 73],
[ 25, 5],
[ 25, 73],
[ 28, 14],
[ 28, 82],
[ 28, 32],
[ 28, 61],
[ 29, 31],
[ 29, 87],
[ 30, 4],
[ 30, 73],
[ 33, 4],
[ 33, 92],
[ 33, 14],
[ 33, 81],
[ 34, 17],
[ 34, 73],
[ 37, 26],
[ 37, 75],
[ 38, 35],
[ 38, 92],
[ 39, 36],
[ 39, 61],
[ 39, 28],
[ 39, 65],
[ 40, 55],
[ 40, 47],
[ 40, 42],
[ 40, 42],
[ 42, 52],
[ 42, 60],
[ 43, 54],
[ 43, 60],
[ 43, 45],
[ 43, 41],
[ 44, 50],
[ 44, 46],
[ 46, 51],
[ 46, 46],
[ 46, 56],
[ 46, 55],
[ 47, 52],
[ 47, 59],
[ 48, 51],
[ 48, 59],
[ 48, 50],
[ 48, 48],
[ 48, 59],
[ 48, 47],
[ 49, 55],
[ 49, 42],
[ 50, 49],
[ 50, 56],
[ 54, 47],
[ 54, 54],
[ 54, 53],
[ 54, 48],
[ 54, 52],
[ 54, 42],
[ 54, 51],
[ 54, 55],
[ 54, 41],
[ 54, 44],
[ 54, 57],
[ 54, 46],
[ 57, 58],
[ 57, 55],
[ 58, 60],
[ 58, 46],
[ 59, 55],
[ 59, 41],
[ 60, 49],
[ 60, 40],
[ 60, 42],
[ 60, 52],
[ 60, 47],
[ 60, 50],
[ 61, 42],
[ 61, 49],
[ 62, 41],
[ 62, 48],
[ 62, 59],
[ 62, 55],
[ 62, 56],
[ 62, 42],
[ 63, 50],
[ 63, 46],
[ 63, 43],
[ 63, 48],
[ 63, 52],
[ 63, 54],
[ 64, 42],
[ 64, 46],
[ 65, 48],
[ 65, 50],
[ 65, 43],
[ 65, 59],
[ 67, 43],
[ 67, 57],
[ 67, 56],
[ 67, 40],
[ 69, 58],
[ 69, 91],
[ 70, 29],
[ 70, 77],
[ 71, 35],
[ 71, 95],
[ 71, 11],
[ 71, 75],
[ 71, 9],
[ 71, 75],
[ 72, 34],
[ 72, 71],
[ 73, 5],
[ 73, 88],
[ 73, 7],
[ 73, 73],
[ 74, 10],
[ 74, 72],
[ 75, 5],
[ 75, 93],
[ 76, 40],
[ 76, 87],
[ 77, 12],
[ 77, 97],
[ 77, 36],
[ 77, 74],
[ 78, 22],
[ 78, 90],
[ 78, 17],
[ 78, 88],
[ 78, 20],
[ 78, 76],
[ 78, 16],
[ 78, 89],
[ 78, 1],
[ 78, 78],
[ 78, 1],
[ 78, 73],
[ 79, 35],
[ 79, 83],
[ 81, 5],
[ 81, 93],
[ 85, 26],
[ 85, 75],
[ 86, 20],
[ 86, 95],
[ 87, 27],
[ 87, 63],
[ 87, 13],
[ 87, 75],
[ 87, 10],
[ 87, 92],
[ 88, 13],
[ 88, 86],
[ 88, 15],
[ 88, 69],
[ 93, 14],
[ 93, 90],
[ 97, 32],
[ 97, 86],
[ 98, 15],
[ 98, 88],
[ 99, 39],
[ 99, 97],
[101, 24],
[101, 68],
[103, 17],
[103, 85],
[103, 23],
[103, 69],
[113, 8],
[113, 91],
[120, 16],
[120, 79],
[126, 28],
[126, 74],
[137, 18],
[137, 83]])
Nos quedamos con las variables 3 y 4 de conjunto de datos, las cuales corresponden al ingreso anual en miles y la puntuación del cliente.
In [10]:
# Metodo del Codo para encontrar el numero optimo de clusters
from sklearn.cluster import KMeans
wcss = []
for i in range(1, 11):
kmeans = KMeans(n_clusters = i, init = 'k-means++', random_state = 42)
kmeans.fit(X)
wcss.append(kmeans.inertia_)
# Grafica de la suma de las distancias
plt.plot(range(1, 11), wcss)
plt.title('The Elbow Method')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()
En el bloque anterior, generamos los clusters para valores de 1 a 10 (en el rango de 1 a 11) y obtenemos para cada uno de ellos, la suma de las distancias con el tributo inertia_ del objeto kmeans. En la gráfica observamos que la disminución en la suma de las distancias se atenúa cuando el número de clusters es igual a 5, por lo que, para este caso práctico, el número óptimo de clusters será de 5.
In [11]:
# Creando el k-Means para los 5 grupos encontrados
kmeans = KMeans(n_clusters = 5, init = 'k-means++', random_state = 42) #k-means++ acelera la convergencia, respecto de random
y_kmeans = kmeans.fit_predict(X)
In [12]:
y_kmeans
Out[12]:
array([2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3,
2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 0,
2, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 4, 1, 4, 0, 4, 1, 4, 1, 4,
0, 4, 1, 4, 1, 4, 1, 4, 1, 4, 0, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4,
1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4,
1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4, 1, 4,
1, 4], dtype=int32)
In [13]:
dataset['pred']=y_kmeans
dataset
Out[13]:
| CustomerID | Genre | Age | Annual Income (k$) | Spending Score (1-100) | pred | |
|---|---|---|---|---|---|---|
| 0 | 1 | Male | 19 | 15 | 39 | 2 |
| 1 | 2 | Male | 21 | 15 | 81 | 3 |
| 2 | 3 | Female | 20 | 16 | 6 | 2 |
| 3 | 4 | Female | 23 | 16 | 77 | 3 |
| 4 | 5 | Female | 31 | 17 | 40 | 2 |
| ... | ... | ... | ... | ... | ... | ... |
| 195 | 196 | Female | 35 | 120 | 79 | 4 |
| 196 | 197 | Female | 45 | 126 | 28 | 1 |
| 197 | 198 | Male | 32 | 126 | 74 | 4 |
| 198 | 199 | Male | 32 | 137 | 18 | 1 |
| 199 | 200 | Male | 30 | 137 | 83 | 4 |
200 rows × 6 columns
In [14]:
dataset.groupby(['pred']).mean()
Out[14]:
| CustomerID | Age | Annual Income (k$) | Spending Score (1-100) | |
|---|---|---|---|---|
| pred | ||||
| 0 | 86.320988 | 42.716049 | 55.296296 | 49.518519 |
| 1 | 164.371429 | 41.114286 | 88.200000 | 17.114286 |
| 2 | 23.000000 | 45.217391 | 26.304348 | 20.913043 |
| 3 | 23.090909 | 25.272727 | 25.727273 | 79.363636 |
| 4 | 162.000000 | 32.692308 | 86.538462 | 82.128205 |
Para poder observar gráficamente la asignación de los 200 clientes a 5 grupos o clusters realizamos lo siguiente, le asignamos un color a cada grupo y marcamos los centroides en amarillo:
In [15]:
# Visualizacion grafica de los clusters
plt.scatter(X[y_kmeans == 0, 0], X[y_kmeans == 0, 1], s = 100, c = 'red', label = 'Cluster 1')
plt.scatter(X[y_kmeans == 1, 0], X[y_kmeans == 1, 1], s = 100, c = 'blue', label = 'Cluster 2')
plt.scatter(X[y_kmeans == 2, 0], X[y_kmeans == 2, 1], s = 100, c = 'green', label = 'Cluster 3')
plt.scatter(X[y_kmeans == 3, 0], X[y_kmeans == 3, 1], s = 100, c = 'cyan', label = 'Cluster 4')
plt.scatter(X[y_kmeans == 4, 0], X[y_kmeans == 4, 1], s = 100, c = 'magenta', label = 'Cluster 5')
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s = 300, c = 'yellow', label = 'Centroids')
plt.title('Clusters of customers')
plt.xlabel('Annual Income (k$)')
plt.ylabel('Spending Score (1-100)')
plt.legend()
plt.show()
Created in