positive_train_data = pd.read_csv('train_pos.tsv',sep = 't')
negative_train_data = pd.read_csv('train_neg.tsv',sep = 't')
positive_test_data = pd.read_csv('test_pos.tsv',sep = 't')
negative_test_data = pd.read_csv('test_neg.tsv',sep = 't')

positive_train_data = positive_train_data[['Text','Sentiment']]
negative_train_data = negative_train_data[['Text','Sentiment']]
positive_test_data = positive_test_data[['Text','Sentiment']]
negative_test_data = negative_test_data[['Text','Sentiment']]

train_data = pd.concat([positive_train_data,negative_train_data],ignore_index = True)
train_data = train_data.sample(frac=1).reset_index(drop=True)

test_data = pd.concat([positive_test_data,negative_test_data],ignore_index = True)
test_data = test_data.sample(frac=1).reset_index(drop=True)

data = pd.concat([positive_train_data,negative_train_data,positive_test_data,negative_test_data],ignore_index = True)
data.reset_index(drop=True,inplace=True)
x = data.Text
y = data.Sentiment
SEED = 2000


x_train, x_test, y_train1, y_test = train_test_split(x, y, test_size = 0.3, random_state = 2000)
print( "Train set has total {0} entries with {1:.2f}% negative, {2:.2f}% positive".format(len(x_train),
                                                                             (len(x_train[y_train1 == 0]) / (len(x_train)*1.))*100,
                                                                            (len(x_train[y_train1 == 1]) / (len(x_train)*1.))*100))

print ("Test set has total {0} entries with {1:.2f}% negative, {2:.2f}% positive".format(len(x_test),
                                                                             (len(x_test[y_test == 0]) / (len(x_test)*1.))*100,
                                                                            (len(x_test[y_test == 1]) / (len(x_test)*1.))*100))

tvec1 = TfidfVectorizer(max_features=10000,ngram_range=(1, 2),use_idf=1,smooth_idf=1,sublinear_tf=1,stop_words = 'english')
tvec1.fit(x_train)

x_train_tfidf = tvec1.transform(x_train)
x_test_tfidf = tvec1.transform(x_test).toarray()



model = Sequential()
model.add(Dense(500, activation='relu', input_dim=1000))
model.add(Dropout(0.25))
model.add(Dense(50,activation = 'relu'))
model.add(Dense(1, activation='sigmoid'))

model.add(Embedding(5000,64,input_length = 1000))
model.add(Conv1D(128,3,padding = 'same',))
model.add(Flatten())
model.add(Dropout(0.25))
model.add(Dense(100,activation = 'relu'))
model.add(Dropout(0.25))
model.add(Dense(1,activation='sigmoid'))