问每个K均值聚类中的数据数量是多少

EN

import pandas as pd
import matplotlib.pyplot as plt
import re 
from sklearn.preprocessing import scale

from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer, TfidfTransformer
from sklearn.cluster import KMeans, MiniBatchKMeans, AffinityPropagation

from sklearn.metrics import silhouette_samples, silhouette_score
from sklearn.metrics.cluster import adjusted_mutual_info_score

from sklearn.decomposition import PCA

df = pd.read_csv('CNN Comments.csv')
df = df.head(8000)
#print(df)
x = df['Text Data']

cv = TfidfVectorizer(analyzer = 'word',max_features = 10000, preprocessor=None, lowercase=True, tokenizer=None, stop_words = 'english')
#cv = CountVectorizer(analyzer = 'word', max_features = 8000, preprocessor=None, lowercase=True, tokenizer=None, stop_words = 'english')  

x = cv.fit_transform(x)

my_list = []
list_of_clusters = []
for i in range(2,5):

    kmeans = KMeans(n_clusters = i, init = 'k-means++', random_state = 42)
    kmeans.fit(x)
    my_list.append(kmeans.inertia_)

    cluster_labels = kmeans.fit_predict(x)

    silhouette_avg = silhouette_score(x, cluster_labels) * 100
    print(round(silhouette_avg,2))
    list_of_clusters.append(round(silhouette_avg, 1))


plt.plot(range(2,5),my_list)
plt.show()


number_of_clusters = max(list_of_clusters)
number_of_clusters = list_of_clusters.index(number_of_clusters)+2

print('Number of clusters: ', number_of_clusters)