问Keras文本预处理-将Tokenizer对象保存到文件中以进行评分

EN

import pickle

# saving
with open('tokenizer.pickle', 'wb') as handle:
    pickle.dump(tokenizer, handle, protocol=pickle.HIGHEST_PROTOCOL)

# loading
with open('tokenizer.pickle', 'rb') as handle:
    tokenizer = pickle.load(handle)

tokenizer_json = tokenizer.to_json()
with io.open('tokenizer.json', 'w', encoding='utf-8') as f:
    f.write(json.dumps(tokenizer_json, ensure_ascii=False))

with open('tokenizer.json') as f:
    data = json.load(f)
    tokenizer = tokenizer_from_json(data)

from keras.preprocessing.text import Tokenizer

docs = ["A heart that",
         "full up like",
         "a landfill",
        "no surprises",
        "and no alarms"
         "a job that slowly"
         "Bruises that",
         "You look so",
         "tired happy",
         "no alarms",
        "and no surprises"]
docs_train = docs[:7]
docs_test = docs[7:]
# EXPERIMENT 1: FIT  TOKENIZER ONLY ON TRAIN
T_1 = Tokenizer()
T_1.fit_on_texts(docs_train)  # only train set
encoded_train_1 = T_1.texts_to_sequences(docs_train)
encoded_test_1 = T_1.texts_to_sequences(docs_test)
print("result for test 1:\n%s" %(encoded_test_1,))

# EXPERIMENT 2: FIT TOKENIZER ON BOTH TRAIN + TEST
T_2 = Tokenizer()
T_2.fit_on_texts(docs)  # both train and test set
encoded_train_2 = T_2.texts_to_sequences(docs_train)
encoded_test_2 = T_2.texts_to_sequences(docs_test)
print("result for test 2:\n%s" %(encoded_test_2,))

result for test 1:
[[3], [10, 3, 9]]
result for test 2:
[[1, 19], [5, 1, 4]]