import pandas as pd from sklearn.manifold import TSNE import matplotlib.pyplot as plt # 读取数据集 customer = pd.read_csv('customer.csv',encoding='gbk') customer_data = customer.iloc[:,:-1] customer_target = customer.iloc[:,-1] # K-Means类聚 from sklearn.cluster import KMeans kmeans = KMeans(n_clusters=4,random_state=6).fit((customer_data)) # 使用TSNE进行数据降维，降成2维 tsne = TSNE(n_components=2,init='random', random_state=2).fit(customer_data) df = pd.DataFrame(tsne.embedding_) # 提取不同标签的数据 df1 = df[df['labels'] == 0] df2 = df[df['labels'] == 1] df3 = df[df['labels'] == 2] df4 = df[df['labels'] == 3] # 绘制图像 fig = plt.figure(figsize=(9,6)) # 用不同颜色表示不同数据 plt.plot(df1[0],df1[1],'bo',df2[0],df2[1],'r*', df3[0],df1[1],'gD',df4[0],df4[1],'kD') plt.show()这段代码有什么问题

这段代码有两个问题：

1. 在使用KMeans进行聚类时，没有将聚类的标签赋值给数据集，导致后续无法根据标签提取不同标签的数据。

2. 在绘制图像时，df3的y轴坐标应该是df3[1]而不是df1[1]。

以下是修改后的代码：

import pandas as pd 
from sklearn.manifold import TSNE 
import matplotlib.pyplot as plt 

# 读取数据集 
customer = pd.read_csv('customer.csv', encoding='gbk') 
customer_data = customer.iloc[:,:-1] 
customer_target = customer.iloc[:,-1] 

# K-Means类聚 
from sklearn.cluster import KMeans 
kmeans = KMeans(n_clusters=4, random_state=6).fit(customer_data) 
labels = kmeans.labels_

# 使用TSNE进行数据降维，降成2维 
tsne = TSNE(n_components=2, init='random', random_state=2).fit(customer_data) 
df = pd.DataFrame(tsne.embedding_) 
df['labels'] = labels

# 提取不同标签的数据 
df1 = df[df['labels'] == 0] 
df2 = df[df['labels'] == 1] 
df3 = df[df['labels'] == 2] 
df4 = df[df['labels'] == 3] 

# 绘制图像 
fig = plt.figure(figsize=(9,6)) 
plt.plot(df1[0], df1[1], 'bo', df2[0], df2[1], 'r*', df3[0], df3[1], 'gD', df4[0], df4[1], 'kD') 
plt.show()