csv分词记录

import csv
import nltk
from nltk.stem import PorterStemmer
from nltk.stem import WordNetLemmatizer
import pandas as pd
from pandas import read_csv
import numpy as np

#分词
def stopwordslist():
    stopwords = [line.strip() for line in open('stopwords_en.txt',encoding='UTF-8').readlines()]
    return stopwords
#停用词   
def seg_depart(sentence):
    cutwords1 = nltk.word_tokenize(sentence.strip())
    stopwords = stopwordslist()
    outstr = ''
    interpunctuations = [',', '.', ':', ';', '?', '(', ')', '[', ']', '&', '!', '*', '@', '#', '$', '%']    
    cutwords2 = [word for word in cutwords1 if (word not in interpunctuations)]
    for word in cutwords2:
         if word not in stopwords:
             if word != '\t':
                 outstr += word
                 outstr += " "
    return outstr 
    
with open('E:\\实验\\data\\test2.csv','r') as data:
#data= pd.read_csv('E:\\实验\\data\\test2.csv',engine='python') 
  reader = csv.DictReader(data)
  rows = [row['Abstract'] for row in reader]
  print (rows)   

  Rs2=[] #建立存储分词的列表
  for line in rows:
    result=[]
    line_seg = seg_depart(line)
    #for w in line_seg :#读取每一行分词
       #result.append(w)
    Rs2.append(line_seg)#将该行分词写入列表形式的总分词列表
  print (Rs2) 
#dataframe = pd.DataFrame({'a_name':a,'b_name':b})

#追加回原csv
dataframe= pd.read_csv("E:\\实验\\data\\test2.csv")
#labels = list(df.columns.values)
#data2 = np.array(df.loc[:,:])
#print(labels)  
dataframe['words']= Rs2
dataframe.to_csv("test2.csv",index=False)

df参考：

https://blog.csdn.net/zx1245773445/article/details/99445332?utm_medium=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromBaidu-1.control&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromBaidu-1.control

https://blog.csdn.net/xufankang/article/details/83688379?ops_request_misc=%25257B%252522request%25255Fid%252522%25253A%252522160853959816780302955206%252522%25252C%252522scm%252522%25253A%25252220140713.130102334..%252522%25257D&request_id=160853959816780302955206&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~all~sobaiduend~default-3-83688379.nonecase&utm_term=pandas%E7%AC%AC%E4%B8%80%E8%A1%8C