0

我不知道我的代码哪里出错了我没有在我的情节中显示所有 4 个集群。有任何想法吗？

    kmeans = KMeans(n_clusters=4)
    kmeans.fit(x)
    y_kmeans = kmeans.fit_predict(x)
    print(kmeans.cluster_centers_)
    print(kmeans.labels_)

    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='magenta', label ='Cluster 4')

    plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=200, c='yellow', label = 
    'Centroids')
    plt.title('Clusters of Customers')
    plt.xlabel('Scores')
    plt.ylabel('')
    plt.show()

聚类

4

1 回答 1

1

您的数据是连续的还是分类的？它似乎是分类的。计算二进制变量之间的距离没有多大意义。并非所有数据都适合聚类。

我没有您的实际数据，但我将向您展示如何使用规范的 MTCars 样本数据正确和错误地进行聚类。

# import mtcars data from web, and do some clustering on the data set


import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.cluster import MiniBatchKMeans 


# Import CSV mtcars
data = pd.read_csv('https://gist.githubusercontent.com/ZeccaLehn/4e06d2575eb9589dbe8c365d61cb056c/raw/64f1660f38ef523b2a1a13be77b002b98665cdfe/mtcars.csv')
# Edit element of column header
data.rename(columns={'Unnamed: 0':'brand'}, inplace=True)


X1= data.iloc[:,1:12]
Y1= data.iloc[:,-1]

#lets try to plot Decision tree to find the feature importance
from sklearn.tree import DecisionTreeClassifier
tree= DecisionTreeClassifier(criterion='entropy', random_state=1)
tree.fit(X1, Y1)



imp= pd.DataFrame(index=X1.columns, data=tree.feature_importances_, columns=['Imp'] )
imp.sort_values(by='Imp', ascending=False)

sns.barplot(x=imp.index.tolist(), y=imp.values.ravel(), palette='coolwarm')

X=data[['cyl','drat']]
Y=data['carb']

#lets try to create segments using K means clustering
from sklearn.cluster import KMeans
#using elbow method to find no of clusters
wcss=[]
for i in range(1,7):
    kmeans= KMeans(n_clusters=i, init='k-means++', random_state=1)
    kmeans.fit(X)
    wcss.append(kmeans.inertia_)


plt.plot(range(1,7), wcss, linestyle='--', marker='o', label='WCSS value')
plt.title('WCSS value- Elbow method')
plt.xlabel('no of clusters- K value')
plt.ylabel('Wcss value')
plt.legend()
plt.show()

kmeans.predict(X)


#Cluster Center
kmeans = MiniBatchKMeans(n_clusters = 5)
kmeans.fit(X)

centroids = kmeans.cluster_centers_
labels = kmeans.labels_

print(centroids)
print(labels)


colors = ["green", "red", "blue", "yellow", "orange"]
plt.scatter(X.iloc[:,0], X.iloc[:,1], c=np.array(colors)[labels], s = 10, alpha=.1)
plt.scatter(centroids[:, 0], centroids[:, 1], marker = "x", s=150, linewidths = 5, zorder = 10, c=colors)
plt.show()

在此处输入图像描述

...now, I am just changing two features (two independent variables)...and re-running the same experiment...

X=data[['wt','qsec']]
Y=data['carb']

#lets try to create segments using K means clustering
from sklearn.cluster import KMeans
#using elbow method to find no of clusters
wcss=[]
for i in range(1,7):
    kmeans= KMeans(n_clusters=i, init='k-means++', random_state=1)
    kmeans.fit(X)
    wcss.append(kmeans.inertia_)


plt.plot(range(1,7), wcss, linestyle='--', marker='o', label='WCSS value')
plt.title('WCSS value- Elbow method')
plt.xlabel('no of clusters- K value')
plt.ylabel('Wcss value')
plt.legend()
plt.show()

kmeans.predict(X)


#Cluster Center
kmeans = MiniBatchKMeans(n_clusters = 5)
kmeans.fit(X)

centroids = kmeans.cluster_centers_
labels = kmeans.labels_

print(centroids)
print(labels)


colors = ["green", "red", "blue", "yellow", "orange"]
plt.scatter(X.iloc[:,0], X.iloc[:,1], c=np.array(colors)[labels], s = 10, alpha=.1)
plt.scatter(centroids[:, 0], centroids[:, 1], marker = "x", s=150, linewidths = 5, zorder = 10, c=colors)
plt.show()

在此处输入图像描述

如您所见，用于聚类的特征的选择会对结果产生巨大的影响（显然）。第一个例子看起来有点像你的结果，第二个例子看起来像一个更有用/有趣的聚类实验。

于 2021-03-12T03:41:37.690 回答