python - 如何获得python中字符串出现的次数？

Question

我创建了函数来检测我指定的单词并显示它在哪一行，但是，我还想知道这些特定单词在数据中重复了多少次或它们的计数

def search_multiple_strings_in_file(file_name, list_of_strings):
    """Get line from the file along with line numbers, which contains any string from the list"""
    line_number = 0
    list_of_results = []
    # Open the file in read only mode
    with open("Hello.csv", 'r') as read_obj:
        # Read all lines in the file one by one
        for line in read_obj:
            line_number += 1
            # For each line, check if line contains any string from the list of strings
            for string_to_search in list_of_strings:
                if string_to_search in line:
                    # If any string is found in line, then append that line along with line number in list
                    list_of_results.append((string_to_search, line_number, line.rstrip()))
 
    # Return list of tuples containing matched string, line numbers and lines where string is found
    return list_of_results

# search for given strings in the file 'sample.txt'

matched_lines = search_multiple_strings_in_file('hello.csv', ['pre existing ', 'exclusions','limitations','fourteen','authorize','frequency','automatic','renewal','provision','annual limit','fraud notice'])
 
print('Total Matched lines : ', len(matched_lines))
for elem in matched_lines:
    print('Word = ', elem[0], ' :: Line Number = ', elem[1], ' :: Line = ', elem[2])
  

有没有办法可以在 SO 上上传示例 csv？我是新来的，不确定我是否看过如何添加附件。但是这个应用程序可以与任何虚拟 csv 一起使用。
我只希望我的最终输出也显示单词及其计数，例如-

Words       Count
exclusions  10
renewal     22

Answer 1

在当前代码中包含计数的一种简单方法是使用 collections.defaultdict() 和 simple += 每个匹配字符串的计数。
然后我们可以将 dict 传递给 Dataframe.from_dict() 以生成我们的输出 df 。

import pandas as pd
from collections import defaultdict

def search_multiple_strings_in_file(file_name, list_of_strings):
    """Get line from the file along with line numbers, which contains any string from the list"""
    line_number = 0
    list_of_results = []
    count = defaultdict(lambda: 0)
    # Open the file in read only mode
    with open("Hello.csv", 'r') as read_obj:
        # Read all lines in the file one by one
        for line in read_obj:
            line_number += 1
            # For each line, check if line contains any string from the list of strings
            for string_to_search in list_of_strings:
                if string_to_search in line:
                    count[string_to_search] += line.count(string_to_search)
                    # If any string is found in line, then append that line along with line number in list
                    list_of_results.append((string_to_search, line_number, line.rstrip()))
 
    # Return list of tuples containing matched string, line numbers and lines where string is found
    return list_of_results, dict(count)


matched_lines, count = search_multiple_strings_in_file('hello.csv', ['pre existing ', 'exclusions','limitations','fourteen','authorize','frequency','automatic','renewal','provision','annual limit','fraud notice'])


df = pd.DataFrame.from_dict(count, orient='index').reset_index()
df.columns = ['Word', 'Count']

print(df)

输出

             Word  Count
0   pre existing       6
1        fourteen      5
2       authorize      5
3       frequency      5
4       automatic      5
5         renewal      5
6       provision      5
7    annual limit      6
8    fraud notice      6
9      exclusions      5
10    limitations      4