Saya membuat jaringan saraf LSTM (RNN) dengan pembelajaran terawasi untuk prediksi stok data. Masalahnya adalah mengapa ia memprediksi data pelatihannya sendiri salah? (catatan: contoh yang dapat direproduksi di bawah)
Saya membuat model sederhana untuk memprediksi harga saham 5 hari ke depan:
model = Sequential()
model.add(LSTM(32, activation='sigmoid', input_shape=(x_train.shape[1], x_train.shape[2])))
model.add(Dense(y_train.shape[1]))
model.compile(optimizer='adam', loss='mse')
es = EarlyStopping(monitor='val_loss', patience=3, restore_best_weights=True)
model.fit(x_train, y_train, batch_size=64, epochs=25, validation_data=(x_test, y_test), callbacks=[es])
Hasil yang benar adalah dalam y_test
(5 nilai), jadi model melatih, melihat ke belakang 90 hari sebelumnya dan kemudian mengembalikan bobot dari yang terbaik ( val_loss=0.0030
) hasil dengan patience=3
:
Train on 396 samples, validate on 1 samples
Epoch 1/25
396/396 [==============================] - 1s 2ms/step - loss: 0.1322 - val_loss: 0.0299
Epoch 2/25
396/396 [==============================] - 0s 402us/step - loss: 0.0478 - val_loss: 0.0129
Epoch 3/25
396/396 [==============================] - 0s 397us/step - loss: 0.0385 - val_loss: 0.0178
Epoch 4/25
396/396 [==============================] - 0s 399us/step - loss: 0.0398 - val_loss: 0.0078
Epoch 5/25
396/396 [==============================] - 0s 391us/step - loss: 0.0343 - val_loss: 0.0030
Epoch 6/25
396/396 [==============================] - 0s 391us/step - loss: 0.0318 - val_loss: 0.0047
Epoch 7/25
396/396 [==============================] - 0s 389us/step - loss: 0.0308 - val_loss: 0.0043
Epoch 8/25
396/396 [==============================] - 0s 393us/step - loss: 0.0292 - val_loss: 0.0056
Hasil prediksi cukup mengagumkan, bukan?
Itu karena algoritma mengembalikan bobot terbaik dari # 5 jaman. Oke, sekarang mari kita simpan model ini ke .h5
file, mundur -10 hari dan prediksi 5 hari terakhir (pada contoh pertama kami membuat model dan memvalidasi pada 17-23 April termasuk hari libur akhir pekan, sekarang mari kita uji pada 2-8 April). Hasil:
Ini menunjukkan arah yang benar-benar salah. Seperti yang kita lihat itu karena model dilatih dan mengambil # 5 zaman terbaik untuk validasi ditetapkan pada 17-23 April, tetapi tidak pada 2-8. Jika saya mencoba melatih lebih banyak, bermain dengan zaman apa yang harus dipilih, apa pun yang saya lakukan, selalu ada banyak interval waktu di masa lalu yang memiliki prediksi salah.
Mengapa model menunjukkan hasil yang salah pada data terlatihnya sendiri? Saya melatih data, harus ingat bagaimana memprediksi data pada set ini, tetapi memprediksi salah. Apa yang saya coba:
- Gunakan kumpulan data besar dengan baris 50k +, harga saham 20 tahun, menambah lebih banyak fitur
- Buat berbagai jenis model, seperti menambahkan lebih banyak lapisan tersembunyi, ukuran batch_size yang berbeda, aktivasi lapisan yang berbeda, dropout, batchnormalisasi
- Buat callback EarlyStopping kustom, dapatkan val_loss rata-rata dari banyak set data validasi dan pilih yang terbaik
Mungkin saya melewatkan sesuatu? Apa yang bisa saya tingkatkan?
Ini adalah contoh yang sangat sederhana dan dapat direproduksi . yfinance
mengunduh data saham S&P 500.
"""python 3.7.7
tensorflow 2.1.0
keras 2.3.1"""
import numpy as np
import pandas as pd
from keras.callbacks import EarlyStopping, Callback
from keras.models import Model, Sequential, load_model
from keras.layers import Dense, Dropout, LSTM, BatchNormalization
from sklearn.preprocessing import MinMaxScaler
import plotly.graph_objects as go
import yfinance as yf
np.random.seed(4)
num_prediction = 5
look_back = 90
new_s_h5 = True # change it to False when you created model and want test on other past dates
df = yf.download(tickers="^GSPC", start='2018-05-06', end='2020-04-24', interval="1d")
data = df.filter(['Close', 'High', 'Low', 'Volume'])
# drop last N days to validate saved model on past
df.drop(df.tail(0).index, inplace=True)
print(df)
class EarlyStoppingCust(Callback):
def __init__(self, patience=0, verbose=0, validation_sets=None, restore_best_weights=False):
super(EarlyStoppingCust, self).__init__()
self.patience = patience
self.verbose = verbose
self.wait = 0
self.stopped_epoch = 0
self.restore_best_weights = restore_best_weights
self.best_weights = None
self.validation_sets = validation_sets
def on_train_begin(self, logs=None):
self.wait = 0
self.stopped_epoch = 0
self.best_avg_loss = (np.Inf, 0)
def on_epoch_end(self, epoch, logs=None):
loss_ = 0
for i, validation_set in enumerate(self.validation_sets):
predicted = self.model.predict(validation_set[0])
loss = self.model.evaluate(validation_set[0], validation_set[1], verbose = 0)
loss_ += loss
if self.verbose > 0:
print('val' + str(i + 1) + '_loss: %.5f' % loss)
avg_loss = loss_ / len(self.validation_sets)
print('avg_loss: %.5f' % avg_loss)
if self.best_avg_loss[0] > avg_loss:
self.best_avg_loss = (avg_loss, epoch + 1)
self.wait = 0
if self.restore_best_weights:
print('new best epoch = %d' % (epoch + 1))
self.best_weights = self.model.get_weights()
else:
self.wait += 1
if self.wait >= self.patience or self.params['epochs'] == epoch + 1:
self.stopped_epoch = epoch
self.model.stop_training = True
if self.restore_best_weights:
if self.verbose > 0:
print('Restoring model weights from the end of the best epoch')
self.model.set_weights(self.best_weights)
def on_train_end(self, logs=None):
print('best_avg_loss: %.5f (#%d)' % (self.best_avg_loss[0], self.best_avg_loss[1]))
def multivariate_data(dataset, target, start_index, end_index, history_size, target_size, step, single_step=False):
data = []
labels = []
start_index = start_index + history_size
if end_index is None:
end_index = len(dataset) - target_size
for i in range(start_index, end_index):
indices = range(i-history_size, i, step)
data.append(dataset[indices])
if single_step:
labels.append(target[i+target_size])
else:
labels.append(target[i:i+target_size])
return np.array(data), np.array(labels)
def transform_predicted(pr):
pr = pr.reshape(pr.shape[1], -1)
z = np.zeros((pr.shape[0], x_train.shape[2] - 1), dtype=pr.dtype)
pr = np.append(pr, z, axis=1)
pr = scaler.inverse_transform(pr)
pr = pr[:, 0]
return pr
step = 1
# creating datasets with look back
scaler = MinMaxScaler()
df_normalized = scaler.fit_transform(df.values)
dataset = df_normalized[:-num_prediction]
x_train, y_train = multivariate_data(dataset, dataset[:, 0], 0,len(dataset) - num_prediction + 1, look_back, num_prediction, step)
indices = range(len(dataset)-look_back, len(dataset), step)
x_test = np.array(dataset[indices])
x_test = np.expand_dims(x_test, axis=0)
y_test = np.expand_dims(df_normalized[-num_prediction:, 0], axis=0)
# creating past datasets to validate with EarlyStoppingCust
number_validates = 50
step_past = 5
validation_sets = [(x_test, y_test)]
for i in range(1, number_validates * step_past + 1, step_past):
indices = range(len(dataset)-look_back-i, len(dataset)-i, step)
x_t = np.array(dataset[indices])
x_t = np.expand_dims(x_t, axis=0)
y_t = np.expand_dims(df_normalized[-num_prediction-i:len(df_normalized)-i, 0], axis=0)
validation_sets.append((x_t, y_t))
if new_s_h5:
model = Sequential()
model.add(LSTM(32, return_sequences=False, activation = 'sigmoid', input_shape=(x_train.shape[1], x_train.shape[2])))
# model.add(Dropout(0.2))
# model.add(BatchNormalization())
# model.add(LSTM(units = 16))
model.add(Dense(y_train.shape[1]))
model.compile(optimizer = 'adam', loss = 'mse')
# EarlyStoppingCust is custom callback to validate each validation_sets and get average
# it takes epoch with best "best_avg" value
# es = EarlyStoppingCust(patience = 3, restore_best_weights = True, validation_sets = validation_sets, verbose = 1)
# or there is keras extension with built-in EarlyStopping, but it validates only 1 set that you pass through fit()
es = EarlyStopping(monitor = 'val_loss', patience = 3, restore_best_weights = True)
model.fit(x_train, y_train, batch_size = 64, epochs = 25, shuffle = True, validation_data = (x_test, y_test), callbacks = [es])
model.save('s.h5')
else:
model = load_model('s.h5')
predicted = model.predict(x_test)
predicted = transform_predicted(predicted)
print('predicted', predicted)
print('real', df.iloc[-num_prediction:, 0].values)
print('val_loss: %.5f' % (model.evaluate(x_test, y_test, verbose=0)))
fig = go.Figure()
fig.add_trace(go.Scatter(
x = df.index[-60:],
y = df.iloc[-60:,0],
mode='lines+markers',
name='real',
line=dict(color='#ff9800', width=1)
))
fig.add_trace(go.Scatter(
x = df.index[-num_prediction:],
y = predicted,
mode='lines+markers',
name='predict',
line=dict(color='#2196f3', width=1)
))
fig.update_layout(template='plotly_dark', hovermode='x', spikedistance=-1, hoverlabel=dict(font_size=16))
fig.update_xaxes(showspikes=True)
fig.update_yaxes(showspikes=True)
fig.show()
df.drop(df.tail(10).index, inplace=True)
, itu menunjukkan hasil buruk yang sama seperti yang saya miliki.