Question

我有5个不同的文本文件，1500.txt，1600.txt，1700.txt，1800.txt和1900.txt。我从1800.txt中选择最常用的单词，并将其与其他文本文件进行比较，以确定这些单词在其他文本文件中的使用时间。我的问题是我可以打印结果，但我想在csv文件上写结果。我的代码如下： -

import sys, string 
import codecs 
import re
from collections import Counter
import collections
import itertools
import csv
import re
import unicodedata

common_words_1800 = Counter()

with open('E:\\Book\\1800.txt', "r", encoding='ISO-8859-1') as File_1800:
    for line in File_1800:
        for match in re.finditer(r'\w+', line.lower()):
            word = match.group()
            if len(word) > 3:
                common_words_1800[word] += 1

common_words_1900 = Counter()

with open('E:\\Book\\1900.txt', "r", encoding='ISO-8859-1') as File_1900:
    for line in File_1900:
        for match in re.finditer(r'\w+', line.lower()):
            word = match.group()
            if len(word) > 3:
                common_words_1900[word] += 1

common_words_1700 = Counter()

with open('E:\\Book\\1700.txt', "r", encoding='ISO-8859-1') as File_1700:
    for line in File_1700:
        for match in re.finditer(r'\w+', line.lower()):
            word = match.group()
            if len(word) > 3:
                common_words_1700[word] += 1

common_words_1600 = Counter()

with open('E:\\Book\\1600.txt', "r", encoding='ISO-8859-1') as File_1600:
    for line in File_1600:
        for match in re.finditer(r'\w+', line.lower()):
            word = match.group()
            if len(word) > 3:
                common_words_1600[word] += 1

common_words_1500 = Counter()

with open('E:\\Book\\1500.txt', "r", encoding='ISO-8859-1') as File_1500:
    for line in File_1500:
        for match in re.finditer(r'\w+', line.lower()):
            word = match.group()
            if len(word) > 3:
                common_words_1500[word] += 1

for (word, count) in common_words_1800.most_common(50):
    try: 
        count_in_file2 = common_words_1900[word]
        count_in_file3 = common_words_1700[word]
        count_in_file4 = common_words_1600[word]
        count_in_file5 = common_words_1500[word]
    except KeyError:    
        count_in_file2 = 0 
        print("{0}\t{1}\t{2}\t{3}\t{4}\t{5}".format(word, count, count_in_file2, count_in_file3, count_in_file4, count_in_file5))

如何在Python中将数据写入csv文件

0 个答案: