wyj95anan的博客

from textblob import TextBlobimport pandas as pd#报错Resource averaged_perceptron_tagger not found. Please use the NLTK Downloade的解决方法import nltknltk.download('averaged_perceptron_tagger')#读入数据Idea=pd.read_csv(r"E:\1.csv",encoding="utf-8")i=len(Ide.

本文使用python的gensim通过tf-idf计算文本相似性。相似度计算部分参考：https://www.jianshu.com/p/edf666d3995f1）导入相关包import jieba.posseg as psegimport codecsfrom gensim import corpora, models, similaritiesimport pandas as pdimport reimport stringfrom nltk.corpus import stopwo

可读性计算方法参考：https://python.ctolib.com/cdimascio-py-readability-metrics.html可读性计算方法有The Flesch Reading Ease formulaFlesch-Kincaid Grade LevelThe Fog Scale (Gunning FOG Formula)The SMOG IndexAutomated Readability IndexThe Coleman-Liau IndexLinsear Wri

信息熵：信息熵越大，信息越多，与以前的消息相比，措辞越独特，信息熵越高参考：信息熵求解部分：https://www.jianshu.com/p/468e2af86d59导入包import numpy as npimport pandas as pdimport nltkimport reimport stringfrom nltk.corpus import stopwordsfrom nltk.tokenize import word_tokenizefrom nltk.stem.p