def clean_text(text):

text = text.translate(string.punctuation)

text = text.lower().split()

stops = set(stopwords.words("english"))
text = [w for w in text if not w in stops]

text = " ".join(text)
text = re.sub(r"[^ws]", " ",text)
text = re.sub(r"[^A-Za-z0-9^,!./'+-=]", " ",text)

text = text.split()
lemmatizer = WordNetLemmatizer()
lemmatized_words = [lemmatizer.lemmatize(w) for w in text]
text = " ".join(lemmatized_words)


return text

data['text'] = data['text'].map(lambda x: clean_text(x))

def build_corpus(data):
"Creates a list of lists containing words from each sentence"
corpus = []
for col in ['text']:
    for sentence in data[col].iteritems():
        word_list = sentence[1].split(" ")
        corpus.append(word_list)
return corpus

corpus = build_corpus(data)

from gensim.models import word2vec
 model = word2vec.Word2Vec(corpus, size=100, window=20, min_count=20,    workers=12, sg=1)

words = list(model.wv.vocab)

tokenizer = Tokenizer()
X = corpus
tokenizer.fit_on_texts(X)
sequences = tokenizer.texts_to_sequences(X)
X = pad_sequences(sequences, maxlen=10000)

embedding_vector_size=100

vocab_size = len(tokenizer.word_index) + 1
embedding_matrix = np.zeros((vocab_size, embedding_vector_size))
for word, i in tokenizer.word_index.items():
embedding_vector = model.wv[word]
if embedding_vector is not None:
    embedding_matrix[i] = embedding_vector