W Pythonie3, z istniejącego pliku .txt, który zawiera tekst / podtytuł / inny, chcę utworzyć prostą listę (bez zagnieżdżeń) istniejących słów, bez spacji i innych znaków interpunkcyjnych.

Zrobiłem to na podstawie innych żądań StackExchange

import csv

crimefile = open('she_loves_you.txt', 'r')
reader = csv.reader(crimefile)
allRows = list(reader) # result is a list with nested lists

ultimate = []
for i in allRows:
    ultimate += i # result is a list with elements longer than one word

ultimate2 = []
for i in ultimate:
    ultimate2 += i # result is a list with elements which are single letters

Mój pożądany wynik byłby podobny

['She', 'loves', 'you', 'yeah', 'yeah', 'yeah', 'She', 'loves', 'you', ...]

==================================================== ====================

Interesujące byłoby również zrozumienie, dlaczego kod (działa jako rozszerzenie powyższego):

import re
print (re.findall(r"[\w']+", ultimate))

Powoduje następujący błąd:

Traceback (most recent call last):
  File "4.4.4.csv.into.list.py", line 72, in <module>
    print (re.findall(r"[\w']+", ultimate))
  File "/usr/lib/python3.7/re.py", line 223, in findall
    return _compile(pattern, flags).findall(string)
TypeError: expected string or bytes-like object
0
hkjz 31 marzec 2020, 15:46

3 odpowiedzi

Najlepsza odpowiedź

Poniżej znajduje się pełny wynik pracy, którą wykonałem w zakresie tego pytania

import csv
import re
import json

#1 def1
#def decomposition(file):
'''
    opening the text file,
    and in 3 steps creating a list containing signle words that appears in the text file
'''

crimefile = open('she_loves_you.txt', 'r')
reader = csv.reader(crimefile)

        #step1 : list with nested lists
allRows = list(reader) # result is a list with nested lists, on which we are going to work later

        #step2 : one list, with elements longer that one word
ultimate = []
for i in allRows:
    ultimate += i

        #step3 : one list, with elements which are lenght of one word
            #print (re.findall(r"[\w']+", ultimate)) # does not work
            #print (re.findall(r"[\w']+", str(ultimate)))  # works
list_of_words = re.findall(r"[\w']+", ' '.join(ultimate)) # works even better!


#2 def2
def saving():
    '''
    #    creating/opening writable file (as a variable),
    #    and saving into it 'list of words'
    '''

    with open('she_loves_you_list.txt', 'w') as fp:
    #Save as JSON with
        json.dump(list_of_words, fp)


#3 def3
def lyric_to_frequencies(lyrics):
    '''
    #    you provide a list,
    #    and recieve a dictionary, which contain amount of unique words in this list
    '''

    myDict = {}
    for word in lyrics:
        if word in myDict:
            myDict[word] += 1
        else :
            myDict[word] = 1
    #print (myDict)
    return myDict

#4 def4
def  most_common_words(freqs):
    '''
    you provide a list of words ('freqs')
    and recieve how often they appear
    '''

    values = freqs.values()
    best = max(values) #finding biggest value very easily
    words = []
    for k in freqs : # and here we are checking which entries have biggers (best) values
        if freqs[k] == best:
            words.append(k) #just add it to the list
    print(words,best)
    return(words,best)

#5 def5
def words_often(freqs, minTimes):
    '''
    you provide a list of words ('freqs') AND minimumTimes how the word suppose to appear in file to be printed out
    and recieve how often they appear
    '''

    result = []
    done = False
    while not done :
        temp = most_common_words(freqs)
        if temp[1] >= minTimes:
            result.append(temp)
            for w in temp[0]:
                del(freqs[w])
        else:
            done = True
    return result



#1
decomposition('she_loves_you.txt')

#2
saving()

#3
lyric_to_frequencies(list_of_words)

#4
most_common_words(lyric_to_frequencies(list_of_words))

#5
words_often(lyric_to_frequencies(list_of_words), 5)
0
hkjz 9 kwiecień 2020, 11:45

Komunikat o błędzie jest całkowicie jasny "expected string or bytes-like object". Oznacza to, że Twój ultimate powinien zostać przekonwertowany na ciąg znaków (str), a kiedy sprawdzisz, że type Twojego ultimate jest obiektem list.

>>> type(ultimate)
<class 'list'>

# or 

>>> type([])
<class 'list'>

W Twoim przypadku;

print (re.findall(r"[\w']+", str(ultimate)))  # original text

# or

print (re.findall(r"[\w']+", ' '.join(ultimate)))  # joined words
0
binpy 31 marzec 2020, 12:59

Spróbuj tego:

import csv

crimefile = open('she_loves_you.txt', 'r')
reader = csv.reader(crimefile)
allRows = list(reader) # result is a list with nested lists

ultimate = []
for i in allRows:
    ultimate += i.split(" ")
0
Lambo 31 marzec 2020, 12:59