Question

我最近开发了一个Python程序，它在某个文档中用术语表示反向索引。我现在想要创建职位发布，例如

to, 993427:
⟨ 1, 6: ⟨7, 18, 33, 72, 86, 231⟩;

2, 5: ⟨1, 17, 74, 222, 255⟩; 4, 5: ⟨8, 16, 190, 429, 433⟩; 5, 2: ⟨363, 367⟩;

7, 3: ⟨13, 23, 191⟩; …⟩

我知道代码不完整，如上所述，我只是想实现功能。

from pprint import pprint as pp
from collections import Counter
import pprint
import re
import sys
import string
import fileinput
try: 
    reduce
except: 
    from functools import reduce
try:
    raw_input
except:
    raw_input = input


def readIn(fileglob): #Reads in multiple files and strips punctation/uppercase.
    texts, words = {}, set()
    for txtfile in (fileglob):
        with open(txtfile, 'r') as splitWords:
            txt = splitWords.read().lower().split()
            txt = str(txt)
            txt = re.findall(r'\w+', txt)
            words |= set(txt)
            texts[txtfile.split('\\')[-1]] = txt
    return texts, words

def search(indexes): # Inverted index, based off the book and the web.
    return reduce(set.intersection,
                  (index[word] for word in indexes),
                  set(texts.keys()))

def getWordBins(posOfWords):
    cnt = Counter()
   for word in posOfWords:
       cnt[posOfWords] += 1
    return cnt


def main(fileList, topWords):
    tempArray = []
    for x in range(1,len(fileList)):
        tempArray.append(fileList[x])


    texts, words = readIn(tempArray)
    index = {word:set(txt
                         for txt, wrds in texts.items() if word in wrds)
                for word in words}


    test =({k + " " + str(len(v)) + " " + str(sorted(v)) for k,v in index.items()})

    txt = readIn(fileList)
    posWord = getWordBins(txt)
    for key, value in posWord.most_common(topWords):
        print key, value


    #Writes out the information requested to a ".idx" file.
    doc = open("document.idx", "w") 
    doc.write("# INPUT DOCUMENT REFERENCE LEGEND\n")
    for fileNumber in range(1, len(fileList)):
        doc.write(str(fileNumber) + "\t" + fileList[fileNumber] + "\n")
    doc.write("# INVERTED INDEX RESULTS\n")
    tempTest = []
    for x in test:
        tempTest.append(x.split(" "))
    for x in tempTest:
        tempStr = ""
        for y in x:
            tempStr += y + "\t"
        doc.write(tempStr + "\n")
    doc.close


main(sys.argv, sys.argv)

这是我到目前为止，唯一的新功能是getWordBins函数和循环：

    txt = readIn(fileList)
    posWord = getWordBins(txt)
    for key, value in posWord.most_common(topWords):
        print key, value

现在，当我尝试运行代码时会发生什么：

Traceback (most recent call last):
  File "Intro3.py", line 82, in <module>
    main(sys.argv, sys.argv)
  File "Intro3.py", line 60, in main
    posWord = getWordBins(txt)
  File "Intro3.py", line 41, in getWordBins
    cnt[posOfWords] += 1
TypeError: unhashable type: 'dict'

很高兴收到任何关于这个令人不安的错误的指导。它不是字典，为什么错误呢？谢谢你的时间！

Answer 1

你在做什么：

cnt[posOfWords] += 1

我想你可能意味着：

cnt[word] += 1

你的readin函数也返回一个dict和一个集合，所以你的txt变量是（dict，set）

的元组

所以你的问题归结为试图使用一个持有字典作为键的元组（我怀疑是你的意图）。它对cnt[word] += 1不起作用，因为那仍然会尝试使用dict作为关键。你可能需要这样做：

txt, _ = readIn(fileList)

然后这可能会起作用：

cnt[word] += 1

Python中的位置倒置索引

1 个答案: