Question

所以我应该编写一些代码来接收一些文本行，通过删除所有非关键词，标点符号等来重新编写它们，最后打印每个关键字以及它出现在哪些行上。有一次，我的代码正在工作，似乎没有改变任何东西，我开始得到这个错误，我不知道为什么。我不是在寻找使代码更短或更短的方法，我意识到它远非理想。我想知道如何解决这个错误。

EDIT-错误在第58行，如果word不在索引中，则在createindex中：

以下是代码：

from string import *

# Program to index sentences

stopWords = [ "a", "i", "it", "am", "at", "on", "in", "to", "too", "very", \
              "of", "from", "here", "even", "the", "but", "and", "is", "my", \
              "them", "then", "this", "that", "than", "though", "so", "are" ]

punctuation = [".",",",":",";","!","?","&","'"]
stemming=["s","es","ed","er","ly","ing"]
text={}
reworkedtext={}

def inserttext(text):    #Function to insert lines of text
    linecount=1
    print "Please insert text here:"
    line = ""
    while line!=".":
        line = raw_input()
        text[linecount]=line
        linecount+=1

def reworktext(text):   #Reworks the text by removing punctuation and making everything lowercase
    for line in text:
        reworkedtext[line]=""
        for character in range(0,len(text[line])):
            if text[line][character] not in punctuation:
                reworkedtext[line]=reworkedtext[line]+lower(text[line][character])

def removestopwords(reworkedtext):   #Removes stopwords
    for line in reworkedtext:
        wordcount=0
        reworkedtext[line]=split(reworkedtext[line])
        for word in range(0,len(reworkedtext[line])):
            if reworkedtext[line][wordcount] in stopWords:
                del(reworkedtext[line][wordcount])
            else:
                wordcount+=1

def stemwords(reworkedtext):  #Stems all words
    for line in reworkedtext:
        for word in range(0,len(reworkedtext[line])):
            if reworkedtext[line][word][-2:] in stemming:
                reworkedtext[line][word]=reworkedtext[line][word][:-2]
            if reworkedtext[line][word][-3:] in stemming:
                reworkedtext[line][word]=reworkedtext[line][word][:-3]
            if reworkedtext[line][word][-1:] in stemming:
                reworkedtext[line][word]=reworkedtext[line][word][:-1]

def createindex(reworkedtext): #creates index and prints it
    linecount=1
    for line in reworkedtext:
        for word in range(0,len(reworkedtext[line])):
            if  word not in index:
                index[word]=""
                index[word]=str(line)
                linecount+=1
            elif index[word]!=str(line):
                index[word]=index[word]+", "+str(line)
    for words in index:
        print words, index[words]

inserttext(text)

reworktext(text)

removestopwords(reworkedtext)

stemwords(reworkedtext)

createindex(reworkedtext)

Answer 1

好像你忘了初始化索引词典

def createindex(reworkedtext): #creates index and prints it
    linecount=1
    index = {} # <----------- add this line and see what's what :)
    for line in reworkedtext:
        for word in range(0,len(reworkedtext[line])):
            if  word not in index:
                index[word]=""
                index[word]=str(line)
                linecount+=1
            elif index[word]!=str(line):
                index[word]=index[word]+", "+str(line)
    for words in index:
        print words, index[words]

Python - 类型'function'的参数不是可迭代的错误

1 个答案: