Question

任何输入都将非常感激。我已经被困在这一段很长一段时间了，有点绝望。下面是我的代码的一部分，它应该读取文本文件并打印关键字以及该关键字的出现次数。我创建了一个带键但没有值的字典。当我尝试添加值时，我收到此错误消息：“TypeError：list indices必须是整数或切片，而不是dict”。为这行代码生成错误：

position_term = {uat_dic[key_word], word_position}'.

我可以根据需要回答任何问题或提供其他信息。非常感谢你给予的任何帮助。

import string


def main():
 # Call a function to create the keyword frequency dictionary
 create_keyword_frequency_dictionary()

 # Call a function to calculate the keyword properties: frequency and position
 keyword_frequency, keyword_position = calculate_keyword_properties()

 # Call a function to display the results as in the Sample Output
 display_results(keyword_frequency, keyword_position)


def create_keyword_frequency_dictionary():

 # Open the uat_voc.txt file and create a dictionary where
 #   the key is the term found in the file, and the value is initialized to 0.
 # This function only initializes the dictionary.
 # Values for the keyword frequencies are set by the    calculate_keyword_properties function.

#easy to use variable name that holds the file path, can easily change  the  file location here
file_name = "/Users/ccs/Library/Mobile  Documents/com~apple~TextEdit/Documents/uat_voc.txt"
#create an empty dictionary
keyword_frequency_dictionary = []

#wrap the i/o in a try/catch statement
try:
    #open the file and load it into infile
    infile = open(file_name, 'r')
    #for each line in infile
    for line in infile:
        #take the line, slice off the \n character
        line = line[:-1]
        #create a dictionary term where the key is the word in line,  initialize value to 0
        dic_term = {line: 0}
        #add the dictionary term to the dictionary list
        keyword_frequency_dictionary.append(dic_term)

    #close the infile
    infile.close()

# Catch IO Errors, with the File Not Found error the primary possible problem to detect.
except FileNotFoundError:
    print("File not found when attempting to read", file_name)
    return None
except IOError:
    print("Error in data file when reading", file_name)
    infile = None
    infile.close()
    return None

return keyword_frequency_dictionary



def calculate_keyword_properties():

    # Open the HowBigDataIsChangingAstronomy.txt' file
    # Read each line in the file and normalize the text as in Assignment 3
    # For each word, determine if it is in the keyword_frequency dictionary, i.e, it is a keyword in the UAT vocabulary,
    #   If the word is a UAT keyword, then increment the frequency.
    # For each word, if it is the first occurrence in the file, then save its   position in a keyword_position dictionary


 # Open the HowBigDataIsChangingAstronomy.txt' file
infile = open('/Users/ccs/Library/Mobile   Documents/com~apple~TextEdit/Documents/HowBigDataIsChangingAstronomy.txt','r')

#read the entire file into clean_file and normalize (this file still has '' instead of ---) length = 2982
clean_file = remove_punctuation(infile.read())

#create empty list that will fill with words
clean_list_of_words = []

#create the keyword dictionary
uat_dic = create_keyword_frequency_dictionary()

#create the keyword_position dictionary
keyword_position_dictionary = []

print(clean_file)
print(len(clean_file))
#reparse the file and remove all '' from normalized file (length = 2972)
for line in clean_file:
    for word in line.split():
        clean_list_of_words.append(word)

print(len(clean_list_of_words))

#iterate through the clean list of words one word at a time to compare; store the word in word_position
for word_position in clean_list_of_words:
    #iterate through the dictionary so you can compare the word to each entry
    for key_word in iter(uat_dic):
        #IDK what was happening here, i think this is wrong
        list_word = clean_list_of_words.index(word_position)
        dic_word = uat_dic.index(key_word)
        #compare the word from word_position to each key value in the uat_dictionary
        if list_word == dic_word:
            #if it was a match, get the value, store it in frequency
            frequency = uat_dic.index(key_word)
            #increment frequency
            frequency+=1
            #check to see if this was the first occurance of the term
            if frequency == 1:
                #if this was the first occurrence, then store a dictionary key/value pair with word_position as the place in the document
                #uat_dic = {uat_dic[key_word], word_position}
                position_term = {uat_dic[key_word], word_position}
                #add the dictionary pair to the key word position list
                keyword_position_dictionary.append(position_term)
            #update the frequency value in the uat dictionary
            uat_dic[key_word] = frequency
        #keeps looping through for every word in the text document

#return the uat frequency dictionary and the keyword position dictionary 
return uat_dic, keyword_position_dictionary


# For each word, determine if it is in the keyword_frequency dictionary, i.e, it is a keyword in the UAT vocabulary,
#   If the word is a UAT keyword, then increment the frequency.
# For each word, if it is the first occurrence in the file, then save its position in a keyword_position dictionary

Answer 1

有时你只需要重构：

def count_word(file_name, word):
  return file(file_name).read().count(word)

这将计算文件中word的出现次数，这就是您尝试做的事情。

由于您要求计算关键字列表，所以应该这样做：

import collections # this is from the standard library
def count_word(file_name, words):
    '''
    Takes a file name and a list of words to count.
    '''
    # initialize a counter
    cnt = collections.Counter()
    # tokenize the file
    tokens = file(file_name).read().strip().split()
    for token in tokens:
        if token in words:
            # increment the counter for that token
            cnt[token] += 1
    return cnt

尝试将字频率值添加到已具有键但没有值的python字典中

1 个答案: