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=n_epochs, 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=64,
verbose=2)
scores_train = model.evaluate([X_train_text, X_train_dense],
dummy_Y_train,
batch_size=64)
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=64)
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(50, input_dim=w2v_dim, activation='relu')(input)
x = Dropout(0.4)(x)
x = Dense(10, activation='relu')(x)
y = Dense(label_categories, activation='sigmoid', 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=n_epochs, 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_senti_2():
input_text = Input(shape=(100,))
input_senti = Input(shape=(2,))
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)
text_out = Dropout(0.4)(text_out)
auxi_out = Dense(label_categories, activation='sigmoid', name='text_out')(text_out)
senti_out = Dense(10, input_dim=2, activation='sigmoid')(input_senti)
senti_out = Dropout(0.4)(senti_out)
# senti_out = Dense(label_categories, activation='sigmoid', name='senti_out')(senti_out)
x = keras.layers.concatenate([text_out, senti_out])
y = Dense(label_categories, activation='sigmoid', name='final_out')(x)
model = Model(inputs=[input_text, input_senti], outputs=[y, auxi_out])
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy', auc])
model.fit([X_train_text, X_train_senti], [dummy_Y_train, dummy_Y_train],
shuffle=True, validation_split=0.2, epochs=350, batch_size=64)
scores_train = model.evaluate([X_train_text, X_train_senti], [dummy_Y_train, dummy_Y_train], batch_size=64)
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_senti], [dummy_Y_test, dummy_Y_test], batch_size=64)
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_senti])
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
def train_text_senti_lstm():
input_text = Input(shape=(100,))
input_senti = Input(shape=(6,))
input_lstm = Input(shape=(128,))
input_text_senti = keras.layers.concatenate([input_text,input_senti,input_lstm])
text_out = Dense(120, input_dim=234, activation='relu')(input_text_senti)
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_senti, input_lstm], outputs = y)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy', auc])
model.fit([X_train_text, X_train_senti, X_train_lstm], dummy_Y_train,shuffle=True,
validation_split=0.2, epochs=n_epochs, batch_size=64)
scores_train = model.evaluate([X_train_text, X_train_senti, X_train_lstm], dummy_Y_train, batch_size=64)
print(str(n_epochs)+' epochs, '+str(train_chunk_number)+' chunk, test_result => '
+ model.metrics_names[0] + ": " + str(scores_train[0]) + " "
+ model.metrics_names[1] + ": " + str(scores_train[1]) + " "
)
f.write(str(n_epochs)+' epochs, '+str(train_chunk_number)+' chunk, test_result => '
+ model.metrics_names[0] + ": " + str(scores_train[0]) + " "
+ model.metrics_names[1] + ": " + str(scores_train[1]) + " \n")
scores = model.evaluate([X_test_text, X_test_senti, X_test_lstm], dummy_Y_test, batch_size=64)
print(str(n_epochs)+' epochs, '+str(train_chunk_number)+' chunk, test_result => '
+ model.metrics_names[0] + ": " + str(scores[0]) + " "
+ model.metrics_names[1] + ": " + str(scores[1]) + " "
)
f.write(str(n_epochs)+' epochs, '+str(train_chunk_number)+' chunk, test_result => '
+ model.metrics_names[0] + ": " + str(scores[0]) + " "
+ model.metrics_names[1] + ": " + str(scores[1]) + " \n")
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_senti, X_test_lstm])
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():
inputs = Input(shape=(maxlen, w2v_dim, 1))
x = Conv2D(filters=32,
kernel_size=(5, 100),
activation='relu',
name='conv_out')(inputs)
x = AveragePooling2D((4, 1), name='pool_out')(x)
x = Flatten()(x)
x = Dense(50, activation='relu', name='dense_50')(x)
y = Dense(label_categories, activation='sigmoid',
name='final_out')(x)
model = Model(inputs=inputs, outputs=y)
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy', auc])
model.fit(X_train,
dummy_Y_train,
shuffle=True,
epochs=n_epochs,
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_insertdense():
# 加载lstm模型
lstm_inputs = Input(shape=(maxlen, ))
lstm_embedding = Embedding(output_dim=word2vec_dim,
input_dim=n_symbols,
mask_zero=True,
weights=[embedding_weights],
input_length=maxlen,
name='embedding_1')(lstm_inputs)
lstm_lstm = LSTM(128, name='lstm_out')(lstm_embedding)
lstm_dropout_1 = Dropout(0.5)(lstm_lstm)
lstm_dense_50 = Dense(50, activation='relu',
name='dense_50')(lstm_dropout_1)
lstm_model = Model(inputs=lstm_inputs, outputs=lstm_dense_50)
lstm_model.load_weights(path.join(path.dirname(__file__),
'sentiment_lstm.h5'),
by_name=True)
# 主要用来分类的全连接层
fcnn_inputs = Input(shape=(100, ))
fcnn_conca = keras.layers.concatenate([fcnn_inputs, lstm_dense_50])
fcnn_dense_100 = Dense(75, activation='relu')(fcnn_conca)
fcnn_dropout_1 = Dropout(0.4)(fcnn_dense_100)
fcnn_dense_20 = Dense(15, activation='relu')(fcnn_dropout_1)
fcnn_dropout_2 = Dropout(0.4)(fcnn_dense_20)
fcnn_out = Dense(label_categories,
activation='sigmoid')(fcnn_dropout_2)
model = Model(inputs=[fcnn_inputs, lstm_inputs], outputs=fcnn_out)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy', auc])
model.summary()
print('fit')
model.fit([X_train_text, X_train_lstm],
dummy_Y_train,
shuffle=True,
validation_split=0.2,
epochs=n_epochs,
batch_size=64,
verbose=1)
print('evaluate')
scores_train = model.evaluate([X_train_text, X_train_lstm],
dummy_Y_train,
batch_size=64)
print(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, train_result => ' + model.metrics_names[0] + ": " +
str(scores_train[0]) + " " + model.metrics_names[1] + ": " +
str(scores_train[1]) + " ")
f.write(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, train_result => ' + model.metrics_names[0] + ": " +
str(scores_train[0]) + " " + model.metrics_names[1] + ": " +
str(scores_train[1]) + " \n")
scores = model.evaluate([X_test_text, X_test_lstm],
dummy_Y_test,
batch_size=512)
print(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, test_result => ' + model.metrics_names[0] + ": " +
str(scores[0]) + " " + model.metrics_names[1] + ": " +
str(scores[1]) + " ")
f.write(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, test_result => ' + model.metrics_names[0] + ": " +
str(scores[0]) + " " + model.metrics_names[1] + ": " +
str(scores[1]) + " \n")
score_dic = {
model.metrics_names[0]: scores[0],
model.metrics_names[1]: scores[1]
}
Y_predict = model.predict([X_test_text, X_test_lstm])
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_insertlstm():
# 加载lstm模型
lstm_inputs = Input(shape=(maxlen, word2vec_dim))
lstm_lstm = LSTM(128, name='lstm_out')(lstm_inputs)
lstm_model = Model(inputs=lstm_inputs, outputs=lstm_lstm)
lstm_model.load_weights(path.join(path.dirname(__file__),
'smote_simJD_sentiment_lstm.h5'),
by_name=True)
print(lstm_model.get_weights())
# 主要用来分类的全连接层
fcnn_inputs = Input(shape=(100, ), name='fcnn_input')
# fcnn_dense_a = Dense(50,activation='relu')(fcnn_inputs)
# fcnn_dropout_a = Dropout(0.4)(fcnn_dense_a)
# fcnn_dense_aa = Dense(10,activation='relu')(fcnn_dropout_a)
# lstm_dense_b = Dense(50,activation='relu')(lstm_lstm)
# lstm_dropout_b = Dropout(0.4)(lstm_dense_b)
# lstm_dense_bb = Dense(10,activation='relu')(lstm_dropout_b)
fcnn_conca = keras.layers.concatenate([fcnn_inputs, lstm_lstm])
x = Dense(100, activation='relu')(fcnn_conca)
x = Dropout(0.4)(x)
x = Dense(20, activation='relu')(x)
fcnn_out = Dense(label_categories, activation='sigmoid')(x)
model = Model(inputs=[fcnn_inputs, lstm_inputs], outputs=fcnn_out)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy', auc])
model.summary()
print('fit')
model.fit([X_train_text, X_train_lstm],
dummy_Y_train,
shuffle=True,
validation_split=0.2,
epochs=n_epochs,
batch_size=64,
verbose=1)
print('evaluate')
scores_train = model.evaluate([X_train_text, X_train_lstm],
dummy_Y_train,
batch_size=64)
print(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, 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]) + " ")
f.write(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, 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]) + " \n")
scores = model.evaluate([X_test_text, X_test_lstm],
dummy_Y_test,
batch_size=512)
print(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, test_result => ' + model.metrics_names[0] + ": " +
str(scores[0]) + " " + model.metrics_names[1] + ": " +
str(scores[1]) + " " + model.metrics_names[2] + ": " +
str(scores[2]) + " ")
f.write(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, test_result => ' + model.metrics_names[0] + ": " +
str(scores[0]) + " " + model.metrics_names[1] + ": " +
str(scores[1]) + " " + model.metrics_names[2] + ": " +
str(scores[2]) + " \n")
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_lstm])
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_onlyText_cnn():
# 加载lstm模型
inputs = Input(shape=(maxlen, word2vec_dim, 1))
x = Conv2D(filters=32,
kernel_size=(5, 100),
activation='relu',
name='conv_out')(inputs)
x = AveragePooling2D((4, 1), name='pool_out')(x)
x = Flatten()(x)
x = Dense(50, activation='relu', name='dense_50')(x)
y = Dense(label_categories, activation='sigmoid')(x)
model = Model(inputs=inputs, outputs=y)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy', auc])
model.summary()
print('fit')
model.fit(X_train_cnn,
dummy_Y_train,
shuffle=True,
validation_split=0.2,
epochs=n_epochs,
batch_size=64,
verbose=1)
print('evaluate')
scores_train = model.evaluate(X_train_cnn,
dummy_Y_train,
batch_size=64)
print(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, 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]) + " ")
f.write(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, 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]) + " \n")
scores = model.evaluate(X_test_cnn, dummy_Y_test, batch_size=512)
print(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, test_result => ' + model.metrics_names[0] + ": " +
str(scores[0]) + " " + model.metrics_names[1] + ": " +
str(scores[1]) + " " + model.metrics_names[2] + ": " +
str(scores[2]) + " ")
f.write(
str(n_epochs) + ' epochs, ' + str(train_chunk_number) +
' chunk, test_result => ' + model.metrics_names[0] + ": " +
str(scores[0]) + " " + model.metrics_names[1] + ": " +
str(scores[1]) + " " + model.metrics_names[2] + ": " +
str(scores[2]) + " \n")
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_cnn)
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
