def lstm(self, path=None, name=None):
trainX = np.reshape(self.X_train,
(self.X_train.shape[0], 1, self.X_train.shape[1]))
testX = np.reshape(self.X_test,
(self.X_test.shape[0], 1, self.X_test.shape[1]))
model = Sequential()
model.add(
LSTM(32,
batch_input_shape=(1, trainX.shape[1], trainX.shape[2]),
stateful=True))
# model.add(Activation('tanh'))
model.add(Dense(1))
# model.add(Activation('linear'))
model.compile(loss='mean_squared_error', optimizer='adam')
# model.summary()
for i in range(50):
model.fit(trainX,
self.y_train,
epochs=1,
batch_size=1,
verbose=self.VERBOSE,
shuffle=False)
model.reset_states()
y_pred = model.predict(testX, batch_size=1)
y_pred = y_pred.reshape(-1)
# mae = MeanAbsoluteError()
# error = mae(self.y_test, y_predict).numpy()
# mape = MeanAbsolutePercentageError()
# error = mape(self.y_test, y_predict).numpy()
mse = MeanSquaredError()
loss_mse = mse(self.y_test, y_pred).numpy()
loss_rmse = np.sqrt(loss_mse)
mae = MeanAbsoluteError()
loss_mae = mae(self.y_test, y_pred).numpy()
mape = MeanAbsolutePercentageError()
loss_mape = mape(self.y_test, y_pred).numpy()
# msle = MeanSquaredLogarithmicError()
# loss_msle = msle(y_test, y_pred).numpy()
# print(error)
#
# plt.plot(self.y_test)
# plt.plot(y_predict)
# plt.show()
# save_info(self.y_test, y_predict, name, mape_error, self.WINDOW_SIZE, path, self.bs, self.ts)
# show_plot(self.y_test, y_predict)
return loss_rmse, loss_mae, loss_mape
def dnn(self, path=None, name=None):
model = Sequential()
print(len(self.X_train))
model.add(Dense(self.INPUT_DIM, input_shape=(self.INPUT_DIM, )))
model.add(Activation('relu'))
for i in range(7):
model.add(Dense(self.N_HIDDEN))
model.add(Activation('relu'))
model.add(Dense(1))
model.add(Activation('linear'))
model.summary()
model.compile(loss='mse',
optimizer=self.OPTIMIZER,
metrics=['accuracy'])
history = model.fit(self.X_train,
self.y_train,
epochs=self.NB_EPOCH,
verbose=self.VERBOSE)
y_pred = model.predict(self.X_test)
y_pred = y_pred.reshape(-1)
# mae = MeanAbsoluteError()
# error = mae(self.y_test, y_predict).numpy()
# print(error)
#
# mape = MeanAbsolutePercentageError()
# error = mape(self.y_test, y_predict).numpy()
#
# print(error)
#
plt.plot(self.y_test)
plt.plot(y_pred)
plt.legend(['real', 'prediction'])
plt.savefig(name + '.png')
plt.show()
r = pd.DataFrame(self.y_test)
p = pd.DataFrame(y_pred)
r.to_excel(name + '-real.xlsx')
p.to_excel(name + '-prediction.xlsx')
# mape_error = mean_absolute_percentage_error(self.y_test, y_predict)
# save_info(self.y_test, y_predict, name, mape_error, self.WINDOW_SIZE, path, self.bs, self.ts)
mse = MeanSquaredError()
loss_mse = mse(self.y_test, y_pred).numpy()
loss_rmse = np.sqrt(loss_mse)
mae = MeanAbsoluteError()
loss_mae = mae(self.y_test, y_pred).numpy()
mape = MeanAbsolutePercentageError()
loss_mape = mape(self.y_test, y_pred).numpy()
return loss_rmse, loss_mae, loss_mape
def CNN_LSTM(self, name=None):
self.X_train = self.X_train.values
self.X_test = self.X_test.values
trainX = np.reshape(self.X_train, (self.X_train.shape[0], 64, -1))
testX = np.reshape(self.X_test, (self.X_test.shape[0], 64, -1))
with tf.device('/device:CPU:0'):
model = Sequential()
input_layer = Input(shape=(64, 1))
conv1 = Conv1D(filters=32,
kernel_size=8,
strides=1,
activation='relu',
padding='same')(input_layer)
lstm1 = LSTM(32, return_sequences=True)(conv1)
output_layer = Dense(1, activation='linear')(lstm1)
model = Model(inputs=input_layer, outputs=output_layer)
# print(model.summary())
model.compile(loss='mse', optimizer='adam')
model.fit(trainX,
self.y_train,
epochs=2000,
batch_size=32,
verbose=self.VERBOSE)
y_pred = model.predict(testX, batch_size=1)
y_pred = y_pred.reshape(-1)
print(self.y_test.shape)
print(y_pred.shape)
plt.plot(self.y_test)
plt.plot(y_pred)
plt.legend(['real', 'prediction'])
plt.savefig(f'./results/{name}.png')
plt.clf()
# plt.show()
mse = MeanSquaredError()
loss_mse = mse(self.y_test, y_pred).numpy()
loss_rmse = np.sqrt(loss_mse)
mae = MeanAbsoluteError()
loss_mae = mae(self.y_test, y_pred).numpy()
mape = MeanAbsolutePercentageError()
loss_mape = mape(self.y_test, y_pred).numpy()
return loss_rmse, loss_mse, loss_mae, loss_mape
def CNN(self, name=None):
self.X_train = self.X_train.values
self.X_test = self.X_test.values
trainX = np.reshape(self.X_train, (self.X_train.shape[0], 9, -1))
testX = np.reshape(self.X_test, (self.X_test.shape[0], 9, -1))
with tf.device('/device:CPU:0'):
model = Sequential()
model.add(
Conv1D(filters=64,
kernel_size=3,
activation='relu',
input_shape=(trainX.shape[1], trainX.shape[2])))
model.add(Dropout(0.5))
# model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(loss='mse', optimizer='adam')
model.fit(trainX,
self.y_train,
epochs=2000,
batch_size=32,
verbose=self.VERBOSE)
y_pred = model.predict(testX, batch_size=1)
y_pred = y_pred.reshape(-1)
print(self.y_test.shape)
print(y_pred.shape)
plt.plot(self.y_test)
plt.plot(y_pred)
plt.legend(['real', 'prediction'])
plt.savefig(f'./results/{name}.png')
plt.clf()
# plt.show()
mse = MeanSquaredError()
loss_mse = mse(self.y_test, y_pred).numpy()
loss_rmse = np.sqrt(loss_mse)
mae = MeanAbsoluteError()
loss_mae = mae(self.y_test, y_pred).numpy()
mape = MeanAbsolutePercentageError()
loss_mape = mape(self.y_test, y_pred).numpy()
return loss_rmse, loss_mse, loss_mae, loss_mape
def lstm(self, path=None, name=None):
self.X_train = self.X_train.values
self.X_test = self.X_test.values
trainX = np.reshape(self.X_train,
(self.X_train.shape[0], 1, self.X_train.shape[1]))
testX = np.reshape(self.X_test,
(self.X_test.shape[0], 1, self.X_test.shape[1]))
model = Sequential()
model.add(
LSTM(128,
batch_input_shape=(1, trainX.shape[1], trainX.shape[2]),
stateful=True))
# model.add(Activation('tanh'))
model.add(Dense(1))
# model.add(Activation('linear'))
model.compile(loss='mean_squared_error', optimizer='adam')
model.summary()
for i in range(2000):
model.fit(trainX,
self.y_train,
epochs=1,
batch_size=1,
verbose=self.VERBOSE,
shuffle=False)
model.reset_states()
y_pred = model.predict(testX, batch_size=1)
y_pred = y_pred.reshape(-1)
plt.plot(self.y_test)
plt.plot(y_pred)
plt.legend(['real', 'prediction'])
plt.savefig(f'./results/{name}.png')
plt.clf()
# plt.show()
mse = MeanSquaredError()
loss_mse = mse(self.y_test, y_pred).numpy()
loss_rmse = np.sqrt(loss_mse)
mae = MeanAbsoluteError()
loss_mae = mae(self.y_test, y_pred).numpy()
mape = MeanAbsolutePercentageError()
loss_mape = mape(self.y_test, y_pred).numpy()
return loss_rmse, loss_mse, loss_mae, loss_mape
def lstm_with_sequence(self, path=None, name=None):
self.X_train = self.X_train.values
self.X_test = self.X_test.values
trainX = np.reshape(self.X_train, (self.X_train.shape[0], -1, 3))
testX = np.reshape(self.X_test, (self.X_test.shape[0], -1, 3))
with tf.device('/device:CPU:0'):
model = Sequential()
model.add(
LSTM(128,
activation='relu',
input_shape=(trainX.shape[1], trainX.shape[2])))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
# model.summary()
model.fit(trainX,
self.y_train,
epochs=300,
batch_size=10,
verbose=self.VERBOSE,
shuffle=False)
y_pred = model.predict(testX, batch_size=1)
y_pred = y_pred.reshape(-1)
print(self.y_test.shape)
print(y_pred.shape)
plt.plot(self.y_test)
plt.plot(y_pred)
plt.legend(['real', 'prediction'])
plt.savefig(f'./results/{name}.png')
plt.clf()
# plt.show()
mse = MeanSquaredError()
loss_mse = mse(self.y_test, y_pred).numpy()
loss_rmse = np.sqrt(loss_mse)
mae = MeanAbsoluteError()
loss_mae = mae(self.y_test, y_pred).numpy()
mape = MeanAbsolutePercentageError()
loss_mape = mape(self.y_test, y_pred).numpy()
return loss_rmse, loss_mse, loss_mae, loss_mape
def getErrors(self, predictions, test_data):
mse = MeanSquaredError()
mse_outcome = mse(np.insert(predictions, 0, self.batch_size, axis=0),
np.insert(test_data, 0, self.batch_size,
axis=0)).numpy()
mae = MeanAbsoluteError()
mae_outcome = mae(np.insert(predictions, 0, self.batch_size, axis=0),
np.insert(test_data, 0, self.batch_size,
axis=0)).numpy()
mape = MeanAbsolutePercentageError()
mape_outcome = mape(np.insert(predictions, 0, self.batch_size, axis=0),
np.insert(test_data, 0, self.batch_size,
axis=0)).numpy()
return (mse_outcome, mae_outcome, mape_outcome)
def dnn(self, path=None, name=None):
with tf.device('/device:GPU:0'):
model = Sequential()
# print(self.X_train.shape[1])
model.add(Dense(self.X_train.shape[1], input_shape=(self.X_train.shape[1],)))
model.add(Activation('relu'))
for i in range(3):
model.add(Dense(self.N_HIDDEN))
model.add(Activation('relu'))
model.add(Dense(1))
model.add(Activation('soft-max'))
model.summary()
model.compile(loss='mse',
optimizer=self.OPTIMIZER,
metrics=['accuracy'])
history = model.fit(self.X_train, self.y_train,
epochs=self.NB_EPOCH,
verbose=self.VERBOSE)
print(self.X_train)
y_pred = model.predict(self.X_test)
y_pred = y_pred.reshape(-1)
plt.plot(self.y_test)
plt.plot(y_pred)
plt.legend(['real', 'prediction'])
plt.savefig(f'./results/{name}.png')
plt.clf()
# plt.show()
mse = MeanSquaredError()
loss_mse = mse(self.y_test, y_pred).numpy()
loss_rmse = np.sqrt(loss_mse)
mae = MeanAbsoluteError()
loss_mae = mae(self.y_test, y_pred).numpy()
mape = MeanAbsolutePercentageError()
loss_mape = mape(self.y_test, y_pred).numpy()
return loss_rmse, loss_mse, loss_mae, loss_mape
def svr(self):
from sklearn.svm import SVR
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
regr = make_pipeline(SVR(C=1.0, epsilon=0.2))
regr.fit(self.X_train, self.y_train)
y_pred = regr.predict(self.X_test)
y_pred = y_pred.reshape(-1)
mse = MeanSquaredError()
loss_mse = mse(self.y_test, y_pred).numpy()
loss_rmse = np.sqrt(loss_mse)
mae = MeanAbsoluteError()
loss_mae = mae(self.y_test, y_pred).numpy()
mape = MeanAbsolutePercentageError()
loss_mape = mape(self.y_test, y_pred).numpy()
return loss_rmse, loss_mae, loss_mape
model.add(LSTM(50, return_sequences=True, activation=activation_funct))
if useDropout: model.add(Dropout(dropout))
model.add(LSTM(50, return_sequences=False, activation=activation_funct))
model.add(Dense(1, activation=activation_funct))
optimizer = RMSprop(learning_rate=learning_rate)
model.compile(optimizer=optimizer, loss=loss)
return model, scaler
learning_rate = 0.001
momentum = 0.9
# optimizer = RMSprop(learning_rate=learning_rate) created in each RNN class
loss = 'mean_absolute_percentage_error'
mape = MeanAbsolutePercentageError()
activation_funct = 'elu'
epochs = 100
batch_size = 150
dropout = 0.2
train_data_columns = ['high']
test_data_column = ['high']
day_ranges = [5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60]
def get_data(day_range):
full_apple_train = get_stock_data("AAPL", "2003-02-10", "2004-09-12")
last_59_train = full_apple_train[-(day_range - 1):]
part_apple_test = get_stock_data("AAPL", "2004-09-13", "2005-01-22")
full_apple_test = last_59_train.append(part_apple_test)
full_ibm_train = get_stock_data("IBM", "2003-02-10", "2004-09-12")
def main():
table = 'Table2'
stack = 'Stack2'
gas = 'SO2'
NN = 'LSTM'
OP = 'MVO'
data = pd.read_excel(stack + '.xlsx')
# data = data.set_index(data.iloc[:, 0])
# data = data.iloc[:, 1:]
# data = data.dropna()
# data = data.iloc[1:]
# data.to_excel('Stack2.xlsx')
W_S = data['W_S']
T = data['T']
data = data[gas]
# 250 490 737 985
may = data[:250]
june = data[250:490]
july = data[490:737]
agust = data[737:985]
september = data[985:]
may_w_s = W_S[:250]
june_w_s = W_S[250:490]
july_w_s = W_S[490:737]
agust_w_s = W_S[737:985]
september_w_s = W_S[985:]
may_t = T[:250]
june_t = T[250:490]
july_t = T[490:737]
agust_t = T[737:985]
september_t = T[985:]
d = [may, june, july, agust, september]
d_w_s = [may_w_s, june_w_s, july_w_s, agust_w_s, september_w_s]
d_t = [may_t, june_t, july_t, agust_t, september_t]
dd = ['may', 'june', 'july', 'agust', 'september']
BS = 3
TS = None
p = dict()
pp = dict()
# for i in range(5):
# dnn = DNN(d[i], BS, TS)
# rmse, mae, mape = dnn.svr()
# p[dd[i]] = [rmse, mae, mape]
# pp = pd.DataFrame(p)
# pp.to_excel('2so.xlsx')
for i in range(5):
X = d[i]
X, y = prepare_data_window(X, BS, d_w_s[i], d_t[i])
y = np.array(y)
y = y.reshape(-1, 1)
scaler_X = MinMaxScaler()
scaler_X = scaler_X.fit(X)
X = scaler_X.transform(X)
scaler_y = MinMaxScaler()
scaler_y = scaler_y.fit(y)
y = scaler_y.transform(y)
y = y.reshape(-1, 1)
# LSTM************************
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=.33,
shuffle=False)
X_train = np.reshape(X_train, (X_train.shape[0], 1, X_train.shape[1]))
X_test = np.reshape(X_test, (X_test.shape[0], 1, X_test.shape[1]))
y_train = np.array(y_train)
y_test = np.array(y_test)
y_train = y_train.flatten()
y_test = y_test.flatten()
input_shape = X_train.shape
model = Model().get_lstm(input_shape)
Wb = get_weights_and_biases(model)
Wb_flatten = flatten_weights_and_biases(Wb)
dimensions = len(Wb_flatten)
# # PSO
# pso = PSO(model, dimensions, X_train, y_train, None,
# init_weights=None, n_iteration=50)
# cost, pos = pso.PSO()
# MVO
mvo = MVO(model, dimensions, X_train, y_train)
cost, pos = mvo.MVO()
model = Model().get_lstm(input_shape)
Wb_model = unflatten_weights_and_biases(Wb, pos)
model = put_weights_and_biases(model, Wb_model)
y_pred = model.predict(X_test)
# # mse = MeanSquaredError()
# # loss = mse(y_test, y_pred).numpy()
#
# # with open(f'./Results/{file_name}', 'w') as f:
# # f.write(str(loss))
# # LSTM--------------------------------
# # ENN+++++++++++++++++++++++++++++++++
# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.33, shuffle=False)
# y_train = y_train.reshape(-1, 1)
#
# y_train = np.array(y_train)
# y_test = np.array(y_test)
#
# # y_train = y_train.flatten()
# # y_test = y_test.flatten()
#
# net = Model().get_elman(3)
# w, s = get_elman_weights(net)
#
# dimensions = len(w)
#
# # error = net.train(X_train, y_train, epochs=500, show=100, goal=0.01)
#
# # PSO
# pso_elman = PSO_ENN.PSO(net, dimensions, X_train, y_train, None,
# init_weights=None, n_iteration=50)
# cost, pos = pso_elman.PSO()
#
# # # MVO
# # mvo = MVO_ENN.MVO(net, dimensions, X_train, y_train)
# # cost, pos = mvo.MVO()
#
# net = set_elman_weights(net, pos)
#
# y_pred = net.sim(X_test)
#
# # # model = Model().get_lstm(input_shape)
# # # Wb_model = unflatten_weights_and_biases(Wb, pos)
# # # model = put_weights_and_biases(model, Wb_model)
# # # y_pred = model.predict(X_test)
#
# # ENN---------------------------------
mse = MeanSquaredError()
loss_mse = mse(y_test, y_pred).numpy()
loss_rmse = np.sqrt(loss_mse)
mae = MeanAbsoluteError()
loss_mae = mae(y_test, y_pred).numpy()
mape = MeanAbsolutePercentageError()
loss_mape = mape(y_test, y_pred).numpy()
p[dd[i]] = [loss_rmse, loss_mae, loss_mape]
file_name_real = f'{stack}_{gas}_{dd[i]}_{NN}_{OP}_real.xlsx'
file_name_pred = f'{stack}_{gas}_{dd[i]}_{NN}_{OP}_pred.xlsx'
pp[file_name_real] = y_test
pp[file_name_pred] = y_pred
# plt.plot(y_pred)
# plt.plot(y_test)
# plt.show()
p2 = pd.DataFrame(p)
p2.to_excel('2so.xlsx')
pp2 = pd.DataFrame.from_dict(pp, orient='index')
pp2 = pp2.transpose()
pp2.to_excel(f'{table}_{stack}_{gas}_{NN}_{OP}.xlsx')