J'ai 2 fichiers python dans le même dossier utils.py
et preprocessing.py
.redéfinition de la fonction utilisé en python
J'ai deux fonctions définies dans utils.py fichier: preprocess_text, text2seq_generator
je dois utiliser ces functions
dans preprocessing.py
. Mais je reçois pas d'importer et d'avertissement disant redéfinition de la ligne preprocess_text utilisé 19
code:
utils.py
from __future__ import print_function
from collections import defaultdict
from collections import Counter
from string import punctuation
#import pdb
def filter_text(text):
return ''.join([c for c in text if c not in punctuation]).lower()
def preprocess_text(file_path_src, file_path_tar, max_feats):
f_src = open(file_path_src)
f_tar = open(file_path_tar)
vocab = defaultdict(int)
freq_src = defaultdict(int)
freq_tar = defaultdict(int)
sents_src = [line.rstrip() for line in f_src.readlines()]
sents_tar = [line.rstrip() for line in f_tar.readlines()]
for sent in sents_src:
sent = filter_text(sent)
for word in sent.split():
freq_src[word] += 1
for sent in sents_tar:
for word in sent.split():
freq_tar[word] += 1
freq_sorted_src = Counter(freq_src)
freq_sorted_src = freq_sorted_src.most_common(max_feats)
freq_sorted_tar = Counter(freq_tar)
freq_sorted_tar = freq_sorted_tar.most_common(max_feats)
freq_words_src = map(lambda x:x[0], freq_sorted_src)
freq_words_tar = map(lambda x:x[0], freq_sorted_tar)
vocab_src = dict({v:k for k, v in enumerate(freq_words_src)})
vocab_tar = dict({v:k for k, v in enumerate(freq_words_tar)})
vocab_src["UNK"] = max_feats
vocab_src["<s>"] = max_feats + 1
vocab_src["</s>"] = max_feats + 2
vocab_tar["UNK"] = max_feats
vocab_tar["<s>"] = max_feats + 1
vocab_tar["</s>"] = max_feats + 2
#pdb.set_trace()
return vocab_src, vocab_tar, sents_src, sents_tar
def text2seq_generator(vocab_src, vocab_tar, sents_src, sents_tar):
unk_key = vocab_src["UNK"]
for sent_src, sent_tar in zip(sents_src, sents_tar):
seq_src = map(lambda x:vocab_src.get(x, unk_key), filter_text(sent_src).split())
seq_tar = map(lambda x:vocab_tar.get(x, unk_key), sent_tar.split())
#pdb.set_trace()
yield seq_src, seq_tar
#vs, vt, ss, st = preprocess_text('../data/training.hi-en.en', '../data/training.hi-en.hi', 5000)
#for x,y in text2seq_generator(vs, vt, ss, st):
#print(y)
fichier preprocessing.py:
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
import codecs
import pdb
import numpy as np
from utils import preprocess_text,text2seq_generator
Erreur:
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
import codecs
import pdb
import numpy as np
from utils import preprocess_text
Traceback (most recent call last):
File "<ipython-input-8-335a30ab7871>", line 6, in <module>
from utils import preprocess_text
ImportError: cannot import name 'preprocess_text'
avertissement:
redefinition of unused preprocess_text from line 19
fichier .py d'importation et d'utiliser le function.you pourrait faire "à partir du pré-traitement des importations" –
Beaucoup d'indentation cassée dans votre code. En outre, trop de code - afficher le code minimum qui génère toujours votre erreur – vmg
@ Prakash047 toujours la même erreur – Anagha