LSTM(units=10, return_sequences=False, input_shape=(X_TRAIN.shape[1], 1)))
model.add(Dropout(0.1))
# model.add(LSTM(units=28, return_sequences=True))
# model.add(Dropout(0.2))
# model.add(LSTM(units=14, return_sequences=False))
# model.add(Dropout(0.2))
model.add(Dense(units=1))
# Compile and fit model
model.compile(optimizer='adam', loss='mean_squared_error')
history = model.fit(X_TRAIN,
Y_TRAIN,
validation_data=(X_TEST, Y_TEST),
epochs=EPOCHS,
batch_size=BATCH_SIZE,
shuffle=False)
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(len(loss))
# model.save(f'../saved_model/BCH_model_for_days_val_lose_{val_loss[-1]}')
# dump(sc, f'../saved_model/BCH_scaler_for_model_for_days_val_lose_{val_loss[-1]}')
model.save(f'../saved_model/BCH_model_for_days_new')
dump(sc, f'../saved_model/BCH_scaler_for_model_for_days_new')
save_info(ONE_BATCH_SIZE, BATCH_SIZE, EPOCHS, TRAIN_TEST_SPLIT_POINT, loss,
val_loss, model, 'BCH', 'days')
draw_training_and_validation_lost_plot(epochs, loss, val_loss)
model.add(
LSTM(units=12, return_sequences=False, input_shape=(X_TRAIN.shape[1], 1)))
model.add(Dropout(0.1))
# model.add(LSTM(units=16, return_sequences=True))
# model.add(Dropout(0.2))
# model.add(LSTM(units=8, return_sequences=False))
# model.add(Dropout(0.2))
model.add(Dense(units=1))
# Compile and fit model
model.compile(optimizer='adam', loss='mean_squared_error')
history = model.fit(X_TRAIN,
Y_TRAIN,
validation_data=(X_TEST, Y_TEST),
epochs=EPOCHS,
batch_size=BATCH_SIZE,
shuffle=False)
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(len(loss))
model.save(f'../saved_model/LTC_model_for_minutes_val_lose_{val_loss[-1]}')
dump(
sc,
f'../saved_model/LTC_scaler_for_model_for_minutes_val_lose_{val_loss[-1]}')
save_info(ONE_BATCH_SIZE, BATCH_SIZE, EPOCHS, TRAIN_TEST_SPLIT_POINT, loss,
val_loss, model, 'LTC', 'minutes')
draw_training_and_validation_lost_plot(epochs, loss, val_loss)
# model.add(LSTM(units=28, return_sequences=True))
# model.add(Dropout(0.2))
# model.add(LSTM(units=14, return_sequences=False))
# model.add(Dropout(0.2))
model.add(Dense(units=1))
# Compile and fit model
model.compile(optimizer='adam', loss='mean_squared_error')
history = model.fit(X_TRAIN,
Y_TRAIN,
validation_data=(X_TEST, Y_TEST),
epochs=EPOCHS,
batch_size=BATCH_SIZE,
shuffle=False)
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(len(loss))
model.save(
f'../saved_model/LTC_model_for_days_from_full_data__val_lose_{val_loss[-1]}'
)
dump(
sc,
f'../saved_model/LTC_scaler_for_model_for_full_data_days_val_lose_{val_loss[-1]}'
)
save_info(ONE_BATCH_SIZE, BATCH_SIZE, EPOCHS, TRAIN_TEST_SPLIT_POINT, loss,
val_loss, model, 'LTC', 'full_data_days')
draw_training_and_validation_lost_plot(epochs, loss, val_loss)
# model.add(LSTM(units=28, return_sequences=True))
# model.add(Dropout(0.2))
# model.add(LSTM(units=14, return_sequences=False))
# model.add(Dropout(0.2))
model.add(Dense(units=1))
# Compile and fit model
model.compile(optimizer='adam', loss='mean_squared_error')
history = model.fit(X_TRAIN,
Y_TRAIN,
validation_data=(X_TEST, Y_TEST),
epochs=EPOCHS,
batch_size=BATCH_SIZE,
shuffle=False)
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(len(loss))
model.save(
f'../saved_model/ETH_model_for_minutes_from_full_data__val_lose_{val_loss[-1]}'
)
dump(
sc,
f'../saved_model/ETH_scaler_for_model_for_full_data_minutes_val_lose_{val_loss[-1]}'
)
save_info(ONE_BATCH_SIZE, BATCH_SIZE, EPOCHS, TRAIN_TEST_SPLIT_POINT, loss,
val_loss, model, 'ETH', 'full_data_minutes')
draw_training_and_validation_lost_plot(epochs, loss, val_loss)
