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
Random_Deep = [3, 3, 3] ## DNN--RNN-CNN
RMDL.Text_Classification(X_train,
y_train,
X_test,
y_test,
batch_size=batch_size,
sparse_categorical=True,
random_deep=Random_Deep,
epochs=n_epochs,
no_of_classes=12)
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
Random_Deep = [3, 3, 3] ## DNN--RNN-CNN
RMDL.Text_Classification(X_train,
y_train,
X_test,
y_test,
batch_size=batch_size,
sparse_categorical=sparse_categorical,
random_deep=Random_Deep,
epochs=n_epochs)
test_labels = labels[split_data:]
#batch_size should not be very small neither too big
batch_size = 2
sparse_categorical = 0
#epoch for DNN , RNN and CNN
n_epochs = [5, 5, 5] ## DNN--RNN-CNN
Random_Deep = [3, 3, 3] ## DNN--RNN-CNN
no_of_classes = 2
RMDL.Text_Classification(np.array(train_sentences), np.array(train_labels), np.array(test_sentences),
np.array(test_labels),
batch_size=batch_size,
sparse_categorical=sparse_categorical,
random_deep=Random_Deep,
epochs=n_epochs, no_of_classes=2)
#output
#
# Found 129 unique tokens.
# (10, 500)
# Total 400000 word vectors.
# 2
# DNN 0
# <keras.optimizers.Adagrad object at 0x7f00801bbb70>
# Train on 8 samples, validate on 2 samples
# Epoch 1/5
# - 0s - loss: 0.8781 - acc: 0.5000 - val_loss: 0.1762 - val_acc: 1.0000
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=0,
shuffle=False)
batch_size = 128
n_epochs = [0, 2, 2] ## DNN--RNN-CNN
Random_Deep = [0, 1, 1] ## DNN--RNN-CNN
RMDL.Text_Classification(X_train,
y_train,
X_test,
y_test,
batch_size=batch_size,
sparse_categorical=True,
random_deep=Random_Deep,
epochs=n_epochs,
GloVe_dir="../dataset/",
GloVe_file="glove.6B.300d.txt",
EMBEDDING_DIM=300,
MAX_SEQUENCE_LENGTH=100,
MAX_NB_WORDS=50000)
