python文本聚类分析_python机器学习kmeans算法——对文本进行聚类分析

#!/usr/bin/env python#-*- coding: utf-8 -*-#@File : kmeans.py#@Author: 田智凯#@Date : 2020/3/19#@Desc :机器学习kmeans算法，对科技成果项目进行聚类分析

from __future__ importprint_functionimporttimefrom sklearn.feature_extraction.text importTfidfVectorizerimportmatplotlib.pyplot as pltfrom sklearn.cluster importKMeans, MiniBatchKMeansimportpymssql#读取sqlserver数据库

defget_dbdata():

conn_read= pymssql.connect("127.0.0.1", "sa", "###", "test", charset="GBK")

dataset=[]

sql= "select guanjianci from julei_test"cursor=conn_read.cursor()

cursor.execute(sql)

data_count=0for line incursor:

data_count+=1dataset.append(line[0])

cursor.close()

conn_read.close()print(dataset)returndatasetdef transform(dataset, n_features=1000):

vectorizer= TfidfVectorizer(max_df=0.5, max_features=n_features, min_df=2, use_idf=True)

X=vectorizer.fit_transform(dataset)returnX, vectorizerdef train(X, vectorizer, true_k=10, minibatch=False, showLable=False):#使用采样数据还是原始数据训练k-means，

ifminibatch:

km= MiniBatchKMeans(n_clusters=true_k, init='k-means++', n_init=1,

init_size=1000, batch_size=1000, verbose=False)else:

km= KMeans(n_clusters=true_k, init='k-means++', max_iter=300, n_init=1,

verbose=False)

km.fit(X)ifshowLable:print("Top terms per cluster:")

order_centroids= km.cluster_centers_.argsort()[:, ::-1]

terms=vectorizer.get_feature_names()print(vectorizer.get_stop_words())for i inrange(true_k):print("Cluster %d:" % i, end='')for ind in order_centroids[i, :10]:print('%s' % terms[ind], end='')print()

result=list(km.predict(X))print('Cluster distribution:')print(dict([(i, result.count(i)) for i inresult]))return -km.score(X)#指定簇的个数k

defk_determin():'''测试选择最优参数'''dataset=get_dbdata()print("%d documents" %len(dataset))

X, vectorizer= transform(dataset, n_features=500)

true_ks=[]

scores=[]#中心点的个数从3到200(根据自己的数据量改写)

for i in range(3, 200, 1):

score= train(X, vectorizer, true_k=i) /len(dataset)print(i, score)

true_ks.append(i)

scores.append(score)

plt.figure(figsize=(8, 4))

plt.plot(true_ks, scores, label="error", color="red", linewidth=1)

plt.xlabel("n_features")

plt.ylabel("error")

plt.legend()

plt.show()defmain():'''在最优参数下输出聚类结果'''dataset=get_dbdata()

X, vectorizer= transform(dataset, n_features=500)

score= train(X, vectorizer, true_k=25, showLable=True) /len(dataset)print(score)if __name__ == '__main__':

start=time.time()#k_determin()#先确定k值

main()

end=time.time()print('程序运行时间',end-start)