sklearn管道不工作

这对我很有效:

class GetWorldLevelSentiment(BaseEstimator, TransformerMixin):

def __init__(self):
    pass

def get_word_level_sentiment(self, word_list):
    sentiment_score = 1
    for word in word_list:
        word_sentiment = swn.senti_synsets(word)

        if len(word_sentiment) > 0:
            word_sentiment = word_sentiment[0]
        else:
            continue

        if word_sentiment.pos_score() > word_sentiment.neg_score():
            word_sentiment_score = word_sentiment.pos_score()
        elif word_sentiment.pos_score() < word_sentiment.neg_score():
            word_sentiment_score = word_sentiment.neg_score()*(-1)
        else:
            word_sentiment_score = word_sentiment.pos_score()

        print word, " " , word_sentiment_score
        if word_sentiment_score != 0:
            sentiment_score = sentiment_score * word_sentiment_score

    return sentiment_score

def transform(self, review_list, y=None):
    sentiment_score_list = list()
    for review in review_list:
        sentiment_score_list.append(self.get_word_level_sentiment(review.split()))

    return pandas.DataFrame(sentiment_score-list)

def fit(self, x, y=None):
    return self

    from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score

from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.preprocessing import StandardScaler
from sklearn import metrics
import pandas as pd

# Текстовый трансформатор
class TextTransformer(BaseEstimator, TransformerMixin):
    """
    Преобразование текстовых признаков
    """
    def __init__(self, key):
        self.key = key

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

    def transform(self, X):
        return X[self.key]

# Числовой трансформатор
class NumberTransformer(BaseEstimator, TransformerMixin):
    """
    Преобразование числовых признаков
    """
    def __init__(self, key):
        self.key = key

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

    def transform(self, X):
        return X[[self.key]]



def fit_predict(model, X_train, X_test, y_train):
    # использовать частотный векторизатор обратной частоты документа, 
    vec_tdidf = CountVectorizer(ngram_range=(2,3), max_df=0.93, min_df=0.05)

    #Текстовый признак clean 
    text = Pipeline([
                    ('transformer', TextTransformer(key='clear_text')),
                    ('vectorizer', vec_tdidf)
                    ])
    #Числовой признак word_clean_count
    word_numeric = Pipeline([
                    ('transformer', NumberTransformer(key='word_count'))
                    ])

    posting_day = Pipeline([
                    ('transformer', NumberTransformer(key='posting_day'))
                    ])
    posting_month = Pipeline([
                    ('transformer', NumberTransformer(key='posting_month'))
                    ])
    post_theme = Pipeline([
                    ('transformer', NumberTransformer(key='theme'))
                    ])
    # Объединение всех признаков
    features = FeatureUnion([('Text_Feature', text),
                             ('Num1_Feature', word_numeric),
                             ('Num3_Feature', posting_day),
                             ('Num4_Feature', posting_month),
                             ('Num6_Feature', post_theme)

                            ])

    # Классификатор
    clf = model

    # Объединение классификатора и признаков
    pipe = Pipeline([('features', features),
                     ('clf',clf)
                     ])

    # Обучение модели
    pipe_fit=pipe.fit(X_train, y_train)

    # Предсказание данных
    preds = pipe_fit.predict(X_test)

    return preds, pipe_fit