对文本kmeans聚类，TF-IDF词频统计，TSNE降维数画散点图显示聚类结果

# coding: utf-8
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.cluster import KMeans
#聚类数据准备，字符串矩阵
corpus=[]
titles=[]
with open(r"D:\Neo4j\know——get\pyltp_jufafenxi\quchogfu.txt",encoding="utf-8") as fr:
   for lin in fr:
       if "SOL" not in lin and "O O" not in lin and "I-SOL" not in lin:
           lin=lin.replace("{","")
           lin = lin.replace("'SOL'", "")
           lin = lin.replace(":"