0

我有很长的推文列表存储在 python 列表中(超过 50k)。我正处于比较每个项目与其他项目的阶段,以通过使用 difflib 找到推文之间的相似性(删除那些相似的 755 条,同时只保留一条相似的推文)。我使用 itertools.combinations 循环遍历所有项目,但花了很长时间(即几天)。这是我的代码:

import pandas as pd
from difflib import SequenceMatcher
import itertools
import re
import time


def similar(a, b):
    return SequenceMatcher(None, a, b).ratio()

df1=pd.read_csv("50k_TweetSheet.csv")
data = df1['text'].tolist()

orginalData = data
outList = []

data[:] = [re.sub(r"http\S+", "", s) for s in data]
data[:] = [re.sub(r"@\S+", "", s) for s in data]
data[:] = [re.sub(r"RT|rt\S+", "", s) for s in data]
data[:] = [s.replace('\r+', ' ') for s in data]
data[:] = [s.replace('\n+', ' ') for s in data]
data[:] = [s.replace(' +', ' ') for s in data]


numOfRows = len(data)

start_time = time.time()
for a, b in itertools.combinations(range(numOfRows), 2):
    if len(data[a].split()) < 4: continue
    if a in outList: continue
    similarity = similar(data[a],data[b])
    if similarity > 0.75:
        if len(data[a].split()) > len(data[b].split()):
            outList.append(b)
            print(data[a])
        else:
            outList.append(a)
            print(data[b])

有更快的方法吗?

4

0 回答 0