问如何将从tweet中提取的词汇、语义和弓特征组合到分类器中？

EN

train  = pd.read_csv("./av/av1/train.csv") 
test = pd.read_csv("./av/av1/test.csv")

num_chapters = len('train.csv')
fvs_lexical = np.zeros((len(train['text']), 3), np.float64)
fvs_punct = np.zeros((len(train['text']), 3), np.float64)
for e, ch_text in enumerate(train['text']):
    # note: the nltk.word_tokenize includes punctuation
    tokens = nltk.word_tokenize(ch_text.lower())
    words = word_tokenizer.tokenize(ch_text.lower())
    sentences = sentence_tokenizer.tokenize(ch_text)
    vocab = set(words)
    words_per_sentence = np.array([len(word_tokenizer.tokenize(s))
                                   for s in sentences])

# average number of words per sentence
    fvs_lexical[e, 0] = words_per_sentence.mean()
# sentence length variation
    fvs_lexical[e, 1] = words_per_sentence.std()
# apply whitening to decorrelate the features
fvs_lexical = whiten(fvs_lexical) 

#bag of wrods features
bow_vectorizer = CountVectorizer(max_df=0.90, min_df=2, max_features=1000, stop_words='english') 

vectorizer = FeatureUnion([  ("baw", bow_vectorizer), ("fvs_lexical",fvs_lexical)])
matrix = vectorizer.fit_transform(train['text'].values.astype('U'))
print "num of features: " , len(vectorizer.get_feature_names())


X =matrix.toarray()
y = np.asarray(train['label'].values.astype('U'))  

model=LogisticRegression()

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
scores = cross_val_score(model,X_train,y_train,cv=3,
  scoring='f1_micro')
y_pred = model.fit(X_train, y_train).predict(X_test)

print 'F1 score:',f1_score(y_test, y_pred, average=None) # calculating

TypeError                                 Traceback (most recent call last)
<ipython-input-87-1a69ca9a65a2> in <module>()
     24 bow_vectorizer = CountVectorizer(max_df=0.90, min_df=2, max_features=1000, stop_words='english')
     25 
---> 26 vectorizer = FeatureUnion([  ("baw", bow_vectorizer), ("fvs_lexical",fvs_lexical)])
     27 matrix = vectorizer.fit_transform(train['text'].values.astype('U'))
     28 print "num of features: " , len(vectorizer.get_feature_names())

C:\Users\AsusPc\Anaconda2\lib\site-packages\sklearn\pipeline.pyc in __init__(self, transformer_list, n_jobs, transformer_weights)
    616         self.n_jobs = n_jobs
    617         self.transformer_weights = transformer_weights
--> 618         self._validate_transformers()
    619 
    620     def get_params(self, deep=True):

C:\Users\AsusPc\Anaconda2\lib\site-packages\sklearn\pipeline.pyc in _validate_transformers(self)
    660                 raise TypeError("All estimators should implement fit and "
    661                                 "transform. '%s' (type %s) doesn't" %
--> 662                                 (t, type(t)))
    663 
    664     def _iter(self):

TypeError: All estimators should implement fit and transform. '[[1.29995156 0.         0.        ]
 [5.38551361 0.         0.        ]
 [0.37141473 0.         0.        ]
 ...
 [0.92853683 0.         0.        ]
 [1.1142442  3.52964785 0.        ]
 [1.85707366 0.         0.        ]]' (type <type 'numpy.ndarray'>) doesn't