python每日一练

前言

人生苦短，我用python【2018.6.3】

要求

统计文本文件中单词的个数

代码

# -*- coding:utf-8 -*-
import re


def main():
    fp = open("word.txt", "r")
    dictResult = {}
    for line in fp.readlines():
        li = re.findall(r"[\w-]+", line.lower(), re.I)
        for letter in li:
            dictResult[letter] = 1 + dictResult.get(letter, 0)
        # word_list = reduce(lambda x, y: x + y, li) #将多维列表 转化为一维列表
    # count total word
    print len(dictResult)
    # sort the key
    print sorted(dictResult.keys())
    # sort the value
    result = sorted(dictResult.items(), key=lambda item: item[1])  # dictResult.items()创建了可迭代的对象
    print result
    print dictResult


if __name__ == "__main__":
    main()

返回结果：

['allow', 'and', 'as', 'assets', 'bank', 'banks', 'beijing', 'by', 'central', 'china', 'chongqing', 'credit', 'economy', 'first', 'guangdong', 'high-quality', 'in', 'introduced', 'last', 'latest', 'move', 'municipalities', 'of', 'other', 'people', 'program', 'provinces', 'rated', 'refinance', 's', 'said', 'shandong', 'shanghai', 'six', 'support', 'the', 'to', 'was', 'will', 'year']
[('beijing', 1), ('shandong', 1), ('six', 1), ('people', 1), ('move', 1), ('year', 1), ('as', 1), ('program', 1), ('guangdong', 1), ('rated', 1), ('support', 1), ('shanghai', 1), ('other', 1), ('was', 1), ('economy', 1), ('municipalities', 1), ('last', 1), ('refinance', 1), ('said', 1), ('china', 1), ('central', 1), ('by', 1), ('chongqing', 1), ('introduced', 1), ('high-quality', 1), ('assets', 1), ('of', 1), ('will', 1), ('credit', 1), ('s', 1), ('allow', 1), ('banks', 1), ('first', 1), ('latest', 1), ('in', 2), ('provinces', 2), ('to', 2), ('bank', 2), ('and', 3), ('the', 5)]
{'and': 3, 'beijing': 1, 'shandong': 1, 'six': 1, 'people': 1, 'move': 1, 'year': 1, 'as': 1, 'program': 1, 'in': 2, 'guangdong': 1, 'provinces': 2, 'rated': 1, 'support': 1, 'shanghai': 1, 'to': 2, 'other': 1, 'was': 1, 'economy': 1, 'municipalities': 1, 'last': 1, 'refinance': 1, 'said': 1, 'china': 1, 'central': 1, 'by': 1, 'bank': 2, 'chongqing': 1, 'introduced': 1, 'high-quality': 1, 'assets': 1, 'of': 1, 'will': 1, 'credit': 1, 's': 1, 'allow': 1, 'banks': 1, 'the': 5, 'first': 1, 'latest': 1}

总结

学习了正则表达式的匹配和字典的用法，按key排序和按value排序，也浅尝了lambda表达式。