Minimal Example LSTM in Keras

lstm.py

import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense
from sklearn.model_selection import train_test_split

# Generate example data (you should replace this with your data)
# Here, we create three input time series and one target time series.
# You should load your own data accordingly.
n_samples = 1000
n_timestamps = 50
n_features = 3  # Number of input time series
n_target_features = 1  # Number of target time series

# Generate random input data (you should replace this with your data)
X = np.random.rand(n_samples, n_timestamps, n_features)

# Generate random target data (you should replace this with your data)
y = np.random.rand(n_samples, n_timestamps, n_target_features)

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Define the LSTM model
model = Sequential()
model.add(LSTM(50, activation='relu', input_shape=(n_timestamps, n_features), return_sequences=True))
model.add(Dense(n_target_features))

# Compile the model
model.compile(optimizer='adam', loss='mean_squared_error')

# Train the model
model.fit(X_train, y_train, epochs=50, batch_size=32, validation_data=(X_test, y_test))

# Evaluate the model on test data
loss = model.evaluate(X_test, y_test)
print(f'Test Loss: {loss}')