首先感謝Eastmount寫的內容http://blog.csdn.net/Eastmount/article/details/50545937。點選開啟連結

在此基礎上，主要實現以下改進及結果

1.替換使用sklearn.feature_extraction.text.TfidfVectorizer,將corpus文字轉換為tfidf值的svm向量。

2.通過PCA降維和Matplotlib顯示聚類3d三維影象，更容易區分各類。

3.jieba提取30個關鍵詞，作為特徵值，而非全文件內容，進行SVM。

目前剛到找工作中，希望大家看到後，能夠給些建議到[email protected]，感謝！

具體程式碼如下：

#  coding:utf-8
"""
Created on 2016-05-03 @author:[email protected]
"""
import re
import codecs
import jieba.analyse
import matplotlib.pyplot as plt
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from mpl_toolkits.mplot3d import 
 
Axes3D

if __name__ == "__main__":

    corpus = []
    for line in open('01_All_BHSpider_Content_Result.txt','r').readlines():  # 讀取1000行字串的txt文字
line = line.strip()
        # 運用正則表示式,過濾英文及標點符號,中文標點符號
line = line.decode("utf8")
        line = re.sub("[\s+\.\!\/_,$%^*(+\"\']+|[+——！，。？、[email protected]
 
#￥%……&*（）]+|[a-zA-Z]+".decode("utf8"),"/".decode("utf8"),line)
        # 用jieba的textrank演算法,每行字串提取30個特徵詞
line_feature = jieba.analyse.textrank(line , topK=30)
        line = "/".join(line_feature)
        corpus.append(line)

    # 參考官方文件運用sklearn.feature_extraction.text.TfidfVectorizer,將corpus文字轉換為tfidf值的svm向量
tfidfvec = TfidfVectorizer()
    cop_tfidf = tfidfvec.fit_transform(corpus)
    weight = cop_tfidf.toarray()

    # KMeans聚類,確定為4類
clf = KMeans(n_clusters=4)  #景區 動物 人物 國家
s = clf.fit(weight)
    # 輸出lable文件
result = codecs.open("lable.txt",'w','utf-8')
    i=1
while i<=len(clf.labels_):
        result.write(str(i)+','+str(clf.labels_[i-1])+'\r\n')
        i=i+1
result.close()

    # PCA降維,繪製三維圖
pca = PCA(n_components=3)
    newData = pca.fit_transform(weight)

    x1 =[]
    y1 =[]
    z1 =[]
    i=0
while i<400:
        x1.append(newData[i][0])
        y1.append(newData[i][1])
        z1.append(newData[i][2])
        i +=1
x2 =[]
    y2 =[]
    z2=[]
    i=400
while i<600:
        x2.append(newData[i][0])
        y2.append(newData[i][1])
        z2.append(newData[i][2])
        i +=1
x3 =[]
    y3 =[]
    z3=[]
    i=600
while i<800:
        x3.append(newData[i][0])
        y3.append(newData[i][1])
        z3.append(newData[i][2])
        i +=1
x4 =[]
    y4 =[]
    z4=[]
    i=800
while i<1000:
        x4.append(newData[i][0])
        y4.append(newData[i][1])
        z4.append(newData[i][2])
        i +=1
fig=plt.figure()
    ax=fig.add_subplot(111,projection='3d')
    ax.scatter(x1,y1,z1,c='b')
    ax.scatter(x2,y2,z2,c='r')
    ax.scatter(x3,y3,z3,c='k')
    ax.scatter(x4,y4,z4,c='g')
    plt.show()