import pandas as pd
if __name__ == "__main__":
file_x = "X.csv"
file_y = "Y_.csv"
content = pd.read_csv(file_x, encoding="utf-8")
Label = pd.read_csv(file_y, encoding="utf-8")
# content = content.as_matrix()
content = content.ix[:, 1]
content = np.array(content).ravel()
print(np.array(content).transpose().shape)
Label = Label.as_matrix()
Label = np.matrix(Label)
np.random.seed(7)
# print(Label)
content = [txt.text_cleaner(x, deep_clean=True) for x in content]
X_train, X_test, y_train, y_test = train_test_split(content,
Label,
test_size=0.1,
random_state=42)
batch_size = 256
sparse_categorical = 0
n_epochs = [100, 100, 100] ## DNN--RNN-CNN
Random_Deep = [2, 2, 2] ## DNN--RNN-CNN
RMDL.Text_Classification(X_train,
y_train,
X_test,
y_test,
batch_size=batch_size,
sparse_categorical=True,
''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' ''
import os
import numpy as np
from RMDL import text_feature_extraction as txt
from RMDL.Download import Download_WOS as WOS
from RMDL import RMDL_Text as RMDL
from sklearn.cross_validation import train_test_split
if __name__ == "__main__":
path_WOS = WOS.download_and_extract()
fname = os.path.join(path_WOS, "WebOfScience/WOS5736/X.txt")
fnamek = os.path.join(path_WOS, "WebOfScience/WOS5736/Y.txt")
with open(fname, encoding="utf-8") as f:
content = f.readlines()
content = [txt.text_cleaner(x) for x in content]
with open(fnamek) as fk:
contentk = fk.readlines()
contentk = [x.strip() for x in contentk]
Label = np.matrix(contentk, dtype=int)
Label = np.transpose(Label)
np.random.seed(7)
print(Label.shape)
X_train, X_test, y_train, y_test = train_test_split(content,
Label,
test_size=0.2,
random_state=42)
batch_size = 100
sparse_categorical = 0
n_epochs = [100, 100, 100] ## DNN--RNN-CNN
from RMDL import text_feature_extraction as txt
from keras.datasets import imdb
import numpy as np
from RMDL import RMDL_Text as RMDL
if __name__ == "__main__":
print("Load IMDB dataset....")
MAX_NB_WORDS = 75000
(X_train, y_train), (X_test,
y_test) = imdb.load_data(num_words=MAX_NB_WORDS)
print(len(X_train))
print(y_test)
word_index = imdb.get_word_index()
index_word = {v: k for k, v in word_index.items()}
X_train = [
txt.text_cleaner(' '.join(index_word.get(w) for w in x))
for x in X_train
]
X_test = [
txt.text_cleaner(' '.join(index_word.get(w) for w in x))
for x in X_test
]
X_train = np.array(X_train)
X_train = np.array(X_train).ravel()
print(X_train.shape)
X_test = np.array(X_test)
X_test = np.array(X_test).ravel()
batch_size = 100
sparse_categorical = 0
n_epochs = [500, 500, 500] ## DNN--RNN-CNN