from sklearn.linear_model import LogisticRegression
import multiprocessing
import pandas as pd
from gensim.models import Doc2Vec
from gensim.models.doc2vec import LabeledSentence
import multiprocessing
from sklearn import utils
from tqdm import tqdm
tqdm.pandas(desc="progress-bar")
def labelize_tweets_ug(tweets,label):
result = []
prefix = label
for i, t in zip(tweets.index, tweets):
result.append(LabeledSentence(t.split(), [prefix + '_%s' % i]))
return result
all_x = pd.concat([x_train,x_validation,x_test])
all_x_w2v = labelize_tweets_ug(all_x, 'all')
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-3-c20ffafcdd86> in <module>()
----> 1 all_x = pd.concat([x_train,x_validation,x_test])
2 all_x_w2v = labelize_tweets_ug(all_x, 'all')
NameError: name 'x_train' is not defined