python - 模糊比较两列

Question

我有一个包含搜索词(数字和文本)的 CSV 文件，我想将其与其他词(数字和文本)列表进行比较，以确定是否存在任何匹配项或潜在匹配项。然后我希望将所有结果写入新的 CSV 中以供手动审核。我正在使用 fuzzywuzzy 插件创建一个“分数”来确定术语之间的匹配程度。理想情况下，我能够过滤比率。

我当前的代码将文件行一对一比较，而不是第一个文件中的一行与第二个文件中的所有行进行比较；这就是我需要的。

如何针对 file2 中的所有行对 file1 中的每一行执行模糊查找？

from fuzzywuzzy import fuzz
import csv
from itertools import zip_longest

f = open('FuzzyMatch2.csv', 'wt')
writer = csv.writer(f, lineterminator = '\n')


file1_loc = 'LookUp.csv'
file2_loc = 'Prod.csv'

file1 = csv.DictReader(open(file1_loc, 'r'), delimiter=',', quotechar='"')
file2 = csv.DictReader(open(file2_loc, 'r'), delimiter=',', quotechar='"')

for row in file1:
    for l1, l2 in zip_longest(file1, file2):
        if all((l1, l2)):
            partial_ratio = fuzz.token_sort_ratio(str(l1['SearchTerm']), str(l2['Description']))       

        a = [l1,l2,partial_ratio]
        writer.writerow(a)

f.close()

下面是上述代码的更简洁的版本，但仍然存在问题。代码报错

IndexError: list index out of range

知道如何使列表处于范围内并使代码正常工作吗？

from fuzzywuzzy import process
import csv

save_file = open('FuzzyResults.csv', 'wt')
writer = csv.writer(save_file, lineterminator = '\n')

def parse_csv(path):
    with open(path,'r') as f:
        for row in f:
            row = row.split()
            yield row


if __name__ == "__main__":
    ## Create lookup dictionary by parsing the products csv
    data = {}
    for row in parse_csv('Prod.csv'):
        data[row[0]] = row[1]

    ## For each row in the lookup compute the partial ratio
    for row in parse_csv("LookUp.csv"):

        for found, score in process.extract(row, data, limit=100):
            if score >= 10:
                print('%d%% partial match: "%s" with "%s" ' % (score, row, found))
                Digi_Results = [score, row, found]
                writer.writerow(Digi_Results)


save_file.close()

Answer 1

下面的代码可以工作。确保安装了最新的 FuzzyWuzzy - 最后更新日期为 2015 年 4 月 28 日。否则您将收到“unicode”错误。希望这有帮助!

from fuzzywuzzy import process
import csv

save_file = open('FuzzyResults3.csv', 'w')
writer = csv.writer(save_file, lineterminator = '\n')

def parse_csv(path):

    with open(path,'r') as f:
        reader = csv.reader(f, delimiter=',')
        for row in reader:
            yield row


if __name__ == "__main__":
    ## Create lookup dictionary by parsing the products csv
    data = {}
    for row in parse_csv('File1.csv'):
        data[row[0]] = row[1]

    ## For each row in the lookup compute the partial ratio
    for row in parse_csv("File2.csv"):
        #print(process.extract(row,data, limit = 100))
        for found, score, matchrow in process.extract(row, data, limit=100):
            if score >= 60:
                print('%d%% partial match: "%s" with "%s" ' % (score, row, found))
                Digi_Results = [score, row, found]
                writer.writerow(Digi_Results)


save_file.close()