我很难生成文本分类模型

Question

我创建了一个管道，并试图使用all_train_df（附加图像）的数据生成模型，但是我得到了ValueRor：空词汇；也许文件仅包含停止单词。 所有x_train数据都是停止词...

pipeline

 import string
    from spacy.lang.en.stop_words import STOP_WORDS
    from spacy.lang.en import English

# Create our list of punctuation marks
punctuations = string.punctuation

# Create our list of stopwords
nlp = spacy.load("en_core_web_sm")
stop_words = spacy.lang.en.stop_words.STOP_WORDS

# Load English tokenizer, tagger, parser, NER and word vectors
parser = English()

# Creating our tokenizer function
def spacy_tokenizer(sentence):
    # Creating our token object, which is used to create documents with linguistic annotations.
    mytokens = parser(sentence)

    # Lemmatizing each token and converting each token into lowercase
    mytokens = [ word.lemma_.lower().strip() if word.lemma_ != "-PRON-" else word.lower_ for word in mytokens ]

    # Removing stop words
    mytokens = [ word for word in mytokens if word not in stop_words and word not in punctuations ]

    # return preprocessed list of tokens
    return mytokens


# Custom transformer using spaCy
class predictors(TransformerMixin):
    def transform(self, X, **transform_params):
        # Cleaning Text
        return [clean_text(text) for text in X]

    def fit(self, X, y=None, **fit_params):
        return self

    def get_params(self, deep=True):
        return {}

# Basic function to clean the text
def clean_text(text):
    # Removing spaces and converting text into lowercase
    return text.strip().lower()


bow_vector = CountVectorizer(tokenizer = spacy_tokenizer, ngram_range=(1,1),min_df=5, max_df=0.9, stop_words='english', lowercase=True, token_pattern='[a-zA-Z\-][a-zA-Z\-]{2,}')

“ https://i.sstatic.net/cnxfh.png” alt =“在此处输入图像说明”>