大蟒蛇python教程共享python中文分词+词频统计的实现步骤

import jieba  from jieba.analyse import extract_tags  from sklearn.feature_extraction.text import tfidfvectorizer

jieba.load_userdict('extradict.txt')  # 导入自己建立词典

def stopwordlist():      stopwords = [line.strip() for line in open('chinesestopwords.txt', encoding='utf-8').readlines()]      # ---停用词补充,视具体情况而定---      i = 0      for i in range(19):          stopwords.append(str(10 + i))      # ----------------------         return stopwords

def seg_word(line):      # seg=jieba.cut_for_search(line.strip())      seg = jieba.cut(line.strip())      temp = ""      counts = {}      wordstop = stopwordlist()      for word in seg:          if word not in wordstop:              if word != ' ':                  temp += word                  temp += 'n'                  counts[word] = counts.get(word, 0) + 1#统计每个词出现的次数      return  temp #显示分词结果      #return str(sorted(counts.items(), key=lambda x: x[1], reverse=true)[:20])  # 统计出现前二十最多的词及次数

def output(inputfilename, outputfilename):      inputfile = open(inputfilename, encoding='utf-8', mode='r')      outputfile = open(outputfilename, encoding='utf-8', mode='w')      for line in inputfile.readlines():          line_seg = seg_word(line)          outputfile.write(line_seg)      inputfile.close()      outputfile.close()      return outputfile

if __name__ == '__main__':      print("__name__", __name__)      inputfilename = 'abstract.txt'      outputfilename = 'a1.txt'      output(inputfilename, outputfilename)

#定义字符串  sentences = """           # 字符串很长时用三个引号  love is more than a word  it says so much.  when i see these four letters,  i almost feel your touch.  this is only happened since  i fell in love with you.  why this word does this,  i haven't got a clue.  """  #具体实现  #  将句子里面的逗号去掉,去掉多种符号时请用循环，这里我就这样吧  sentences=sentences.replace(',','')     sentences=sentences.replace('.','')   #  将句子里面的.去掉  sentences = sentences.split()         # 将句子分开为单个的单词，分开后产生的是一个列表sentences  # print(sentences)  count_dict = {}  for sentence in sentences:      if sentence not in count_dict:    # 判断是否不在统计的字典中          count_dict[sentence] = 1      else:                              # 判断是否不在统计的字典中          count_dict[sentence] += 1  for key,value in count_dict.items():      print(f"{key}出现了{value}次")