0 точность с LSTM

Question

Я обучил модель классификации LSTM, но получил странные результаты (точность 0). Вот мой набор данных с этапами предварительной обработки:

import pandas as pd
from sklearn.model_selection import train_test_split
import tensorflow as tf
from tensorflow import keras
import numpy as np

url = 'https://raw.githubusercontent.com/MislavSag/trademl/master/trademl/modeling/random_forest/X_TEST.csv'
X_TEST = pd.read_csv(url, sep=',')
url = 'https://raw.githubusercontent.com/MislavSag/trademl/master/trademl/modeling/random_forest/labeling_info_TEST.csv'
labeling_info_TEST = pd.read_csv(url, sep=',')


# TRAIN TEST SPLIT
X_train, X_test, y_train, y_test = train_test_split(
    X_TEST.drop(columns=['close_orig']), labeling_info_TEST['bin'],
    test_size=0.10, shuffle=False, stratify=None)


### PREPARE LSTM
x = X_train['close'].values.reshape(-1, 1)
y = y_train.values.reshape(-1, 1)
x_test = X_test['close'].values.reshape(-1, 1)
y_test = y_test.values.reshape(-1, 1)
train_val_index_split = 0.75
train_generator = keras.preprocessing.sequence.TimeseriesGenerator(
    data=x,
    targets=y,
    length=30,
    sampling_rate=1,
    stride=1,
    start_index=0,
    end_index=int(train_val_index_split*X_TEST.shape[0]),
    shuffle=False,
    reverse=False,
    batch_size=128
)
validation_generator = keras.preprocessing.sequence.TimeseriesGenerator(
    data=x,
    targets=y,
    length=30,
    sampling_rate=1,
    stride=1,
    start_index=int((train_val_index_split*X_TEST.shape[0] + 1)),
    end_index=None,  #int(train_test_index_split*X.shape[0])
    shuffle=False,
    reverse=False,
    batch_size=128
)
test_generator = keras.preprocessing.sequence.TimeseriesGenerator(
    data=x_test,
    targets=y_test,
    length=30,
    sampling_rate=1,
    stride=1,
    start_index=0,
    end_index=None,
    shuffle=False,
    reverse=False,
    batch_size=128
)

# convert generator to inmemory 3D series (if enough RAM)
def generator_to_obj(generator):
    xlist = []
    ylist = []
    for i in range(len(generator)):
        x, y = train_generator[i]
        xlist.append(x)
        ylist.append(y)
    X_train = np.concatenate(xlist, axis=0)
    y_train = np.concatenate(ylist, axis=0)
    return X_train, y_train

X_train_lstm, y_train_lstm = generator_to_obj(train_generator)
X_val_lstm, y_val_lstm = generator_to_obj(validation_generator)
X_test_lstm, y_test_lstm = generator_to_obj(test_generator)

# test for shapes
print('X and y shape train: ', X_train_lstm.shape, y_train_lstm.shape)
print('X and y shape validate: ', X_val_lstm.shape, y_val_lstm.shape)
print('X and y shape test: ', X_test_lstm.shape, y_test_lstm.shape)

, а вот моя модель с повторными версиями:

### MODEL
model = keras.models.Sequential([
        keras.layers.LSTM(124, return_sequences=True, input_shape=[None, 1]),
        keras.layers.LSTM(258),
        keras.layers.Dense(1, activation='sigmoid')
])
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
history = model.fit(X_train_lstm, y_train_lstm, epochs=10, batch_size=128,
                    validation_data=[X_val_lstm, y_val_lstm])
# history = model.fit_generator(train_generator, epochs=40, validation_data=validation_generator, verbose=1)
score, acc = model.evaluate(X_val_lstm, y_val_lstm,
                            batch_size=128)

historydf = pd.DataFrame(history.history)
historydf.head(10)

Почему я получаю точность 0?

Answer 1

Вы используете сигмовидную активацию, что означает, что ваши метки должны находиться в диапазоне от 0 до 1. Но в вашем случае метки: 1. и -1.

Просто замените -1 на 0.

for i, y in enumerate(y_train_lstm):
    if y == -1.:
        y_train_lstm[i,:] = 0. 
for i, y in enumerate(y_val_lstm):
    if y == -1.:
        y_val_lstm[i,:] = 0. 

for i, y in enumerate(y_test_lstm):
    if y == -1.:
        y_test_lstm[i,:] = 0. 

Примечание:

The signals are very close, it would be hard to distinguish them. So, probably accuracy won't be high with simple models.

After training with 0. and 1. labels,

model = keras.models.Sequential([
        keras.layers.LSTM(124, return_sequences=True, input_shape=(30, 1)),
        keras.layers.LSTM(258),
        keras.layers.Dense(1, activation='sigmoid')
])
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
history = model.fit(X_train_lstm, y_train_lstm, epochs=5, batch_size=128,
                    validation_data=(X_val_lstm, y_val_lstm))
# history = model.fit_generator(train_generator, epochs=40, validation_data=validation_generator, verbose=1)
score, acc = model.evaluate(X_val_lstm, y_val_lstm,
                            batch_size=128)

historydf = pd.DataFrame(history.history)
historydf.head(10)

Epoch 1/5
12/12 [==============================] - 5s 378ms/step - loss: 0.7386 - accuracy: 0.4990 - val_loss: 0.6959 - val_accuracy: 0.4896
Epoch 2/5
12/12 [==============================] - 4s 318ms/step - loss: 0.6947 - accuracy: 0.5133 - val_loss: 0.6959 - val_accuracy: 0.5104
Epoch 3/5
12/12 [==============================] - 4s 318ms/step - loss: 0.6941 - accuracy: 0.4895 - val_loss: 0.6930 - val_accuracy: 0.5104
Epoch 4/5
12/12 [==============================] - 4s 332ms/step - loss: 0.6946 - accuracy: 0.5269 - val_loss: 0.6946 - val_accuracy: 0.5104
Epoch 5/5
12/12 [==============================] - 4s 334ms/step - loss: 0.6931 - accuracy: 0.4901 - val_loss: 0.6929 - val_accuracy: 0.5104
3/3 [==============================] - 0s 73ms/step - loss: 0.6929 - accuracy: 0.5104

    loss    accuracy    val_loss    val_accuracy
0   0.738649    0.498980    0.695888    0.489583
1   0.694708    0.513256    0.695942    0.510417
2   0.694117    0.489463    0.692987    0.510417
3   0.694554    0.526852    0.694613    0.510417
4   0.693118    0.490143    0.692936    0.510417

Source code in colab: https://colab.research.google.com/drive/10yRf4TfGDnp_4F2HYoxPyTlF18no-8Dr?usp=sharing