Text embedding

from sklearn.feature_extraction.text import TfidfVectorizer
from collections import defaultdict
import numpy as np

Docs embedding

    TfidfEmbeddingVectorizer
    class TfidfEmbeddingVectorizer(object):
    def __init__(self, word2vec):
        self.word2vec = word2vec


    def transform(self, X):
        tfidf = TfidfVectorizer(analyzer = lambda x : x) 
        tfidf.fit(X) 



    max_idf = max(tfidf.idf_)



        word2weight = defaultdict(lambda : max_idf, [(w, tfidf.idf_[i]) for w, i in tfidf.vocabulary_.items()]) 

        array_list =[]
        for words in X:
            array_list.append(np.array(np.mean([self.word2vec[w]*word2weight[w] for w in words if w in self.word2vec] or [np.zeros(100)], axis = 0)))
        return(array_list)



    vec_tf_skip_gram = TfidfEmbeddingVectorizer(w2v_skip_gram)

    vec_tf_CBOW = TfidfEmbeddingVectorizer(w2v_CBOW)

skip-gram

train_tf_s = vec_tf_skip_gram.transform(text_train)
test_tf_s = vec_tf_skip_gram.transform(text_test)

CBOW

train_tf_c = vec_tf_CBOW.transform(text_train)
test_tf_c = vec_tf_CBOW.transform(text_test)

NameError                                 Traceback (most recent call last)
<ipython-input-8-58d8af0cf2a6> in <module>
     67         return(array_list)
     68 
---> 69 vec_tf_skip_gram = {TfidfEmbeddingVectorizer}'(w2v_skip_gram)
     70 vec_tf_CBOW = 'TfidfEmbeddingVectorizer'(w2v_CBOW)
     71 # skip-gram

NameError: name 'w2v_skip_gram' is not defined

and also error on w2v_CBOW too how can i fix this?

보시다 시피 vec_tf_skip_gram = {TfidfEmbeddingVectorizer}'(w2v_skip_gram)에서 name error가 나옵니다 물론 그 다음인 70 vec_tf_CBOW = 'TfidfEmbeddingVectorizer'(w2v_CBOW)에서도 error가 나오는데 어떻게 해결해야할까요?

Text embedding

from sklearn.feature_extraction.text import TfidfVectorizer
from collections import defaultdict
import numpy as np

Docs embedding

    TfidfEmbeddingVectorizer
    class TfidfEmbeddingVectorizer(object):
    def __init__(self, word2vec):
        self.word2vec = word2vec


    def transform(self, X):
        tfidf = TfidfVectorizer(analyzer = lambda x : x) 
        tfidf.fit(X) 



    max_idf = max(tfidf.idf_)



        word2weight = defaultdict(lambda : max_idf, [(w, tfidf.idf_[i]) for w, i in tfidf.vocabulary_.items()]) 

        array_list =[]
        for words in X:
            array_list.append(np.array(np.mean([self.word2vec[w]*word2weight[w] for w in words if w in self.word2vec] or [np.zeros(100)], axis = 0)))
        return(array_list)



    vec_tf_skip_gram = TfidfEmbeddingVectorizer(w2v_skip_gram)

    vec_tf_CBOW = TfidfEmbeddingVectorizer(w2v_CBOW)

skip-gram

train_tf_s = vec_tf_skip_gram.transform(text_train)
test_tf_s = vec_tf_skip_gram.transform(text_test)

CBOW

train_tf_c = vec_tf_CBOW.transform(text_train)
test_tf_c = vec_tf_CBOW.transform(text_test)

NameError                                 Traceback (most recent call last)
<ipython-input-8-58d8af0cf2a6> in <module>
     67         return(array_list)
     68 
---> 69 vec_tf_skip_gram = {TfidfEmbeddingVectorizer}'(w2v_skip_gram)
     70 vec_tf_CBOW = 'TfidfEmbeddingVectorizer'(w2v_CBOW)
     71 # skip-gram

NameError: name 'w2v_skip_gram' is not defined

and also error on w2v_CBOW too how can i fix this?

보시다 시피 vec_tf_skip_gram = {TfidfEmbeddingVectorizer}'(w2v_skip_gram)에서 name error가 나옵니다 물론 그 다음인 70 vec_tf_CBOW = 'TfidfEmbeddingVectorizer'(w2v_CBOW)에서도 error가 나오는데 어떻게 해결해야할까요?

Text embedding

from sklearn.feature_extraction.text import TfidfVectorizer from collections import defaultdict import numpy as np

Docs embedding

TfidfEmbeddingVectorizer
class TfidfEmbeddingVectorizer(object):
def __init__(self, word2vec):
    self.word2vec = word2vec


def transform(self, X):
    tfidf = TfidfVectorizer(analyzer = lambda x : x) 
    tfidf.fit(X) 



max_idf = max(tfidf.idf_)



    word2weight = defaultdict(lambda : max_idf, [(w, tfidf.idf_[i]) for w, i in tfidf.vocabulary_.items()]) 

    array_list =[]
    for words in X:
        array_list.append(np.array(np.mean([self.word2vec[w]*word2weight[w] for w in words if w in self.word2vec] or [np.zeros(100)], axis = 0)))
    return(array_list)



vec_tf_skip_gram = TfidfEmbeddingVectorizer(w2v_skip_gram)

vec_tf_CBOW = TfidfEmbeddingVectorizer(w2v_CBOW)

skip-gram

train_tf_s = vec_tf_skip_gram.transform(text_train) test_tf_s = vec_tf_skip_gram.transform(text_test)

CBOW

train_tf_c = vec_tf_CBOW.transform(text_train) test_tf_c = vec_tf_CBOW.transform(text_test)

NameError Traceback (most recent call last) in 67 return(array_list) 68 ---> 69 vec_tf_skip_gram = {TfidfEmbeddingVectorizer}'(w2v_skip_gram) 70 vec_tf_CBOW = 'TfidfEmbeddingVectorizer'(w2v_CBOW) 71 # skip-gram

NameError: name 'w2v_skip_gram' is not defined

and also error on w2v_CBOW too how can i fix this?

보시다 시피 vec_tf_skip_gram = {TfidfEmbeddingVectorizer}'(w2v_skip_gram)에서 name error가 나옵니다 물론 그 다음인 70 vec_tf_CBOW = 'TfidfEmbeddingVectorizer'(w2v_CBOW)에서도 error가 나오는데 어떻게 해결해야할까요?