data = pd.DataFrame(columns, columns=['body', 'rating'])
reviews = pd.DataFrame([[body, rating]])
#Remove duplication
# data = pd.DataFrame.drop_duplicates(reviews)
############### Preprocessing ########
for i in range(0, len(data)):
data.iloc[i, 0] = LoadDataset_General.Emoticon_detection(data.iloc[i,
0])
data.iloc[i, 0] = LoadDataset_General.clean_raw_review(data.iloc[i, 0])
data.iloc[i, 0] = LoadDataset_General.normalizeArabic(data.iloc[i, 0])
data.iloc[i, 0] = LoadDataset_General.Elong_remove(data.iloc[i, 0])
data.iloc[i, 0] = LoadDataset_General.deNoise(data.iloc[i, 0])
data.iloc[i, 0] = LoadDataset_General.Remove_Stopwords(data.iloc[i, 0])
data.iloc[i, 0] = LoadDataset_General.Named_Entity_Recognition(
data.iloc[i, 0])
# data[i] = LoadDataset_General.Stem_word(data[i])
# data.iloc[i,0] = LoadDataset_General.Light_Stem_word(data.iloc[i,0])
# data[i] = LoadDataset_General.Get_root_word(data[i])
# random.shuffle( data )
train_size = int(len(data) * val_split)
train_texts = data.iloc[0:train_size, 0].tolist()
test_texts = data.iloc[train_size:-1, 0].tolist()
train_labels = data.iloc[0:train_size, 1].tolist()
test_labels = data.iloc[train_size:-1, 1].tolist()
num_classes = len(set(train_labels + test_labels))
tokenizer = Tokenizer(nb_words=max_features,
filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n',
split=" ")
tokenizer.fit_on_texts(train_texts)
import sklearn.feature_selection
####### Load dataset ##########
LoadDataset_General = LoadDataset_General()
datasetName = 'BBN'
(body, rating) = LoadDataset_General.Load_Data(datasetName)
############ Preprocessing ########
for i in range(0, len(body)):
body[i] = LoadDataset_General.Emoticon_detection(body[i])
body[i] = LoadDataset_General.clean_raw_review(body[i])
body[i] = LoadDataset_General.normalizeArabic(body[i])
body[i] = LoadDataset_General.Elong_remove(body[i])
body[i] = LoadDataset_General.deNoise(body[i])
body[i] = LoadDataset_General.Remove_Stopwords(body[i])
body[i] = LoadDataset_General.Named_Entity_Recognition(body[i])
# body[i] = LoadDataset_General.Stem_word(body[i])
body[i] = LoadDataset_General.Light_Stem_word(body[i])
# body[i] = LoadDataset_General.Get_root_word(body[i])
#### Load unbalanced dataset
(unbalanced_train_x, unbalanced_train_y, unbalanced_test_x, unbalanced_test_y,
unbalanced_valid_x, unbalanced_valid_y
) = LoadDataset_General.get_train_test_validation_unbalanced(
body, rating, datasetName)
d_train = np.concatenate((unbalanced_train_x, unbalanced_valid_x))
Y_train = np.concatenate((unbalanced_train_y, unbalanced_valid_y)).tolist()
Y_test = unbalanced_test_y
########## Feature Extraction using Tokenization ############
###### Counts ##########