def triple_classification():
model = Sequential()
model.add(Dense(100, input_dim=w2v_dim, activation='relu'))
model.add(Dropout(0.4))
model.add(Dense(50, activation='relu'))
model.add(Dropout(0.4))
model.add(Dense(10, activation='relu'))
# model.add(Dropout(0.4))
model.add(Dense(label_categories, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy', auc])
model.fit(X_train, dummy_Y_train, shuffle=True, epochs=800, batch_size=64,
validation_split=0.2, verbose=2, callbacks=[early_stopping])
scores = model.evaluate(X_test, dummy_Y_test, batch_size=64)
print(model.metrics_names[0] + ":" + str(scores[0]) + " "
+ model.metrics_names[1] + ":" + str(scores[1]) + " "
+ model.metrics_names[2] + ":" + str(scores[2]) + " ")
score_dic = {model.metrics_names[0]: scores[0],
model.metrics_names[1]: scores[1],
model.metrics_names[2]: scores[2]}
predictions = model.predict(X_test)
confusion_matrix = conf_matrix(dummy_Y_test, predictions, label_index)
print(confusion_matrix)
return score_dic, confusion_matrix
def train_text_dense_3():
input_text = Input(shape=(100, ))
input_dense = Input(shape=(50, ))
text_out = Dense(50, input_dim=100, activation='relu')(input_text)
text_out = Dropout(0.4)(text_out)
text_out = Dense(10, activation='relu')(text_out)
# auxi_out = Dropout(0.4)(auxi_out)
# auxi_out = Dense(label_categories, activation='sigmoid', name='auxi_out')(auxi_out)
lstm_out = Dense(10, input_dim=50, activation='relu')(input_dense)
# lstm_out = Dropout(0.4)(lstm_out)
# lstm_out = Dense(10, activation='relu')(lstm_out)
# lstm_out = Dropout(0.4)(lstm_out)
# senti_out = Dense(label_categories, activation='sigmoid', name='senti_out')(senti_out)
x = keras.layers.concatenate([text_out, lstm_out])
# x = Dense(10, activation='relu')(x)
y = Dense(label_categories, activation='sigmoid')(x)
model = Model(inputs=[input_text, input_dense], outputs=y)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy', auc])
model.fit([X_train_text, X_train_dense],
dummy_Y_train,
shuffle=True,
validation_split=0.2,
epochs=300,
batch_size=256,
verbose=2)
scores_train = model.evaluate([X_train_text, X_train_dense],
dummy_Y_train,
batch_size=256)
print('result => ' + model.metrics_names[0] + ": " +
str(scores_train[0]) + " " + model.metrics_names[1] + ": " +
str(scores_train[1]) + " " + model.metrics_names[2] + ": " +
str(scores_train[2]) + " ")
scores = model.evaluate([X_test_text, X_test_dense],
dummy_Y_test,
batch_size=256)
print('result => ' + model.metrics_names[0] + ": " + str(scores[0]) +
" " + model.metrics_names[1] + ": " + str(scores[1]) + " " +
model.metrics_names[2] + ": " + str(scores[2]) + " ")
score_dic = {
model.metrics_names[0]: scores[0],
model.metrics_names[1]: scores[1],
model.metrics_names[2]: scores[2]
}
Y_predict = model.predict([X_test_text, X_test_dense])
confusion_matrix = conf_matrix(dummy_Y_test, Y_predict, label_index)
print(confusion_matrix)
print('round ' + str(train_chunk_number) + ' finished')
return score_dic, confusion_matrix
def train_text():
input = Input(shape=(w2v_dim, ))
x = Dense(300, input_dim=w2v_dim, activation='sigmoid')(input)
x = Dropout(0.4)(x)
x = Dense(200, activation='sigmoid')(x)
x = Dense(50, activation='sigmoid')(x)
x = Dense(10, activation='sigmoid')(x)
y = Dense(label_categories, activation='softmax', name='text_out')(x)
model = Model(inputs=input, outputs=y)
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy', auc])
model.fit(X_train,
dummy_Y_train,
shuffle=True,
epochs=15,
batch_size=64,
validation_split=0.2,
verbose=2,
callbacks=[early_stopping])
scores = model.evaluate(X_test, dummy_Y_test, batch_size=64)
print(model.metrics_names[0] + ":" + str(scores[0]) + " " +
model.metrics_names[1] + ":" + str(scores[1]) + " " +
model.metrics_names[2] + ":" + str(scores[2]) + " ")
score_dic = {
model.metrics_names[0]: scores[0],
model.metrics_names[1]: scores[1],
model.metrics_names[2]: scores[2]
}
predictions = model.predict(X_test)
print('general_confusion_matrix =>')
print(
print_conf_matrix(
conf_matrix(dummy_Y_test, predictions, label_index)))
# for i in range(len(dummy_Y_test)):
# print(str(i)+':')
# print(dummy_Y_test[i,:])
# if (dummy_Y_test[i,:]==np.zeros((1,2))).all():
# print(dummy_Y_test[i,:])
# print('find [0,0]')
# exit(1)
confusion_matrix, acc = get_w_acc_conf(train_chunk_number, label_index,
dummy_Y_test, predictions)
print('w_confusion_matrix =>')
print(print_conf_matrix(confusion_matrix))
print('w_acc =>', acc)
print('round ' + str(train_chunk_number) + ' finished')
return score_dic, confusion_matrix
def train_text_keywords_1():
input_text = Input(shape=(100, ))
input_keywords = Input(shape=(256, ))
input_text_senti = keras.layers.concatenate(
[input_text, input_keywords])
text_out = Dense(150, input_dim=102,
activation='relu')(input_text_senti)
text_out = Dropout(0.4)(text_out)
text_out = Dense(50, activation='relu')(text_out)
text_out = Dropout(0.4)(text_out)
text_out = Dense(10, activation='relu')(text_out)
y = Dense(label_categories, activation='sigmoid',
name='text_out')(text_out)
model = Model(inputs=[input_text, input_keywords], outputs=y)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy', auc])
model.fit([X_train_text, X_train_keywords],
dummy_Y_train,
shuffle=True,
validation_split=0.2,
epochs=400,
batch_size=512,
callbacks=[early_stopping])
scores_train = model.evaluate([X_train_text, X_train_keywords],
dummy_Y_train,
batch_size=512)
print('train_result => ' + model.metrics_names[0] + ": " +
str(scores_train[0]) + " " + model.metrics_names[1] + ": " +
str(scores_train[1]) + " " + model.metrics_names[2] + ": " +
str(scores_train[2]) + " ")
scores = model.evaluate([X_test_text, X_test_keywords],
dummy_Y_test,
batch_size=512)
print('test_result => ' + model.metrics_names[0] + ": " +
str(scores[0]) + " " + model.metrics_names[1] + ": " +
str(scores[1]) + " " + model.metrics_names[2] + ": " +
str(scores[2]) + " ")
score_dic = {
model.metrics_names[0]: scores[0],
model.metrics_names[1]: scores[1],
model.metrics_names[2]: scores[2]
}
Y_predict = model.predict([X_test_text, X_test_keywords])
confusion_matrix = conf_matrix(dummy_Y_test, Y_predict, label_index)
print(confusion_matrix)
print('round ' + str(train_chunk_number) + ' finished')
return score_dic, confusion_matrix
def train_text_cnn():
input = Input(shape=(max_count, w2v_dim, 1))
x = Conv2D(filters=16, kernel_size=(5, 100), activation='tanh')(input)
x = AveragePooling2D(pool_size=(4, 1))(x)
x = Flatten()(x)
x = Dense(100, activation='relu')(x)
x = Dense(10, activation='relu')(x)
y = Dense(label_categories, activation='tanh', name='text_out')(x)
model = Model(inputs=input, outputs=y)
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy', auc])
model.summary()
model.fit(X_train,
dummy_Y_train,
shuffle=True,
epochs=10,
batch_size=64,
validation_split=0.2,
verbose=2,
callbacks=[early_stopping])
scores = model.evaluate(X_test, dummy_Y_test, batch_size=64)
print(model.metrics_names[0] + ":" + str(scores[0]) + " " +
model.metrics_names[1] + ":" + str(scores[1]) + " " +
model.metrics_names[2] + ":" + str(scores[2]) + " ")
score_dic = {
model.metrics_names[0]: scores[0],
model.metrics_names[1]: scores[1],
model.metrics_names[2]: scores[2]
}
predictions = model.predict(X_test)
confusion_matrix = conf_matrix(dummy_Y_test, predictions, label_index)
print(confusion_matrix)
print('round ' + str(train_chunk_number) + ' finished')
return score_dic, confusion_matrix
def train_text_lstm():
input = Input(shape=(max_count, w2v_dim))
x = LSTM(256)(input)
x = Dropout(0.4)(x)
x = Dense(100, activation='tanh')(x)
x = Dense(20, activation='tanh')(x)
y = Dense(label_categories, activation='tanh', name='text_out')(x)
model = Model(inputs=input, outputs=y)
model.compile(loss='binary_crossentropy',
optimizer='sgd',
metrics=['accuracy', auc])
model.fit(X_train,
dummy_Y_train,
shuffle=True,
epochs=20,
batch_size=64,
validation_split=0.2,
verbose=2)
scores = model.evaluate(X_test, dummy_Y_test, batch_size=64)
print(model.metrics_names[0] + ":" + str(scores[0]) + " " +
model.metrics_names[1] + ":" + str(scores[1]) + " " +
model.metrics_names[2] + ":" + str(scores[2]) + " ")
score_dic = {
model.metrics_names[0]: scores[0],
model.metrics_names[1]: scores[1],
model.metrics_names[2]: scores[2]
}
predictions = model.predict(X_test)
confusion_matrix = conf_matrix(dummy_Y_test, predictions, label_index)
print(confusion_matrix)
print('round ' + str(train_chunk_number) + ' finished')
return score_dic, confusion_matrix
def train_text_keywords_2():
input_text = Input(shape=(100, ))
input_keywords = Input(shape=(256, ))
text_out = Dense(50, input_dim=100, activation='relu')(input_text)
auxi_out = Dropout(0.4)(text_out)
auxi_out = Dense(10, activation='relu')(auxi_out)
auxi_out = Dropout(0.4)(auxi_out)
auxi_out = Dense(label_categories,
activation='sigmoid',
name='auxi_out')(auxi_out)
keywords_out = Dense(50, input_dim=2,
activation='sigmoid')(input_keywords)
# keywords_out = Dropout(0.4)(keywords_out)
# keywords_out = Dense(10,activation='relu')(keywords_out)
# senti_out = Dense(label_categories, activation='sigmoid', name='senti_out')(senti_out)
x = keras.layers.concatenate([text_out, keywords_out])
x = Dense(10, activation='relu')(x)
y = Dense(label_categories, activation='sigmoid', name='final_out')(x)
model = Model(inputs=[input_text, input_keywords],
outputs=[y, auxi_out])
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy', auc])
model.fit([X_train_text, X_train_keywords],
[dummy_Y_train, dummy_Y_train],
shuffle=True,
validation_split=0.2,
epochs=350,
batch_size=64,
callbacks=[early_stopping])
scores_train = model.evaluate([X_train_text, X_train_keywords],
[dummy_Y_train, dummy_Y_train],
batch_size=512)
print('result => ' + model.metrics_names[0] + ": " +
str(scores_train[0]) + " " + model.metrics_names[1] + ": " +
str(scores_train[1]) + " " + model.metrics_names[2] + ": " +
str(scores_train[2]) + " " + model.metrics_names[3] + ": " +
str(scores_train[3]) + " " + model.metrics_names[4] + ": " +
str(scores_train[4]) + " " + model.metrics_names[5] + ": " +
str(scores_train[5]) + " " + model.metrics_names[6] + ": " +
str(scores_train[6]) + " ")
scores = model.evaluate([X_test_text, X_test_keywords],
[dummy_Y_test, dummy_Y_test],
batch_size=512)
print('result => ' + model.metrics_names[0] + ": " + str(scores[0]) +
" " + model.metrics_names[1] + ": " + str(scores[1]) + " " +
model.metrics_names[2] + ": " + str(scores[2]) + " " +
model.metrics_names[3] + ": " + str(scores[3]) + " " +
model.metrics_names[4] + ": " + str(scores[4]) + " " +
model.metrics_names[5] + ": " + str(scores[5]) + " " +
model.metrics_names[6] + ": " + str(scores[6]) + " ")
score_dic = {
model.metrics_names[0]: scores[0],
model.metrics_names[1]: scores[1],
model.metrics_names[2]: scores[2],
model.metrics_names[3]: scores[3],
model.metrics_names[4]: scores[4],
model.metrics_names[5]: scores[5],
model.metrics_names[6]: scores[6]
}
Y_predict = model.predict([X_test_text, X_test_keywords])
confusion_matrix = conf_matrix(dummy_Y_test, Y_predict[0], label_index)
print(confusion_matrix)
print('round ' + str(train_chunk_number) + ' finished')
return score_dic, confusion_matrix