Last active
September 28, 2023 07:42
-
-
Save DiogoRibeiro7/7c7c7d152f2164e88e9befcb0920f41d to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
from sklearn.model_selection import train_test_split | |
from tensorflow.keras.models import Sequential | |
from tensorflow.keras.layers import LSTM, Dense | |
def preprocess_data(X_raw): | |
""" | |
Normalize the raw data for LSTM processing. | |
Parameters: | |
X_raw (array): The raw feature set. | |
Returns: | |
array: Normalized feature set. | |
""" | |
# Min-max scaling for normalization | |
X_min = np.min(X_raw, axis=0) | |
X_max = np.max(X_raw, axis=0) | |
X_normalized = (X_raw - X_min) / (X_max - X_min) | |
return X_normalized | |
def build_lstm(input_shape): | |
""" | |
Build a Long Short-Term Memory (LSTM) model for processing EHR data. | |
Parameters: | |
input_shape (tuple): The shape of the input sequences. | |
Returns: | |
Sequential: A simple LSTM model. | |
""" | |
model = Sequential() | |
model.add(LSTM(50, input_shape=input_shape)) | |
model.add(Dense(1, activation='sigmoid')) | |
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) | |
return model | |
def train_and_evaluate_model(model, X_train, y_train, X_val, y_val): | |
""" | |
Train and evaluate the LSTM model. | |
Parameters: | |
model (Sequential): The LSTM model. | |
X_train (array): Training feature set. | |
y_train (array): Training labels. | |
X_val (array): Validation feature set. | |
y_val (array): Validation labels. | |
Returns: | |
dict: Training history. | |
""" | |
history = model.fit(X_train, y_train, epochs=10, validation_data=(X_val, y_val)) | |
return history.history | |
# Generate synthetic data for demonstration | |
X_raw = np.random.rand(100, 10, 5) # 100 samples, 10 timesteps, 5 features | |
y_raw = np.random.randint(2, size=100) # 100 labels (0 or 1) | |
# Preprocess the data | |
X_processed = preprocess_data(X_raw) | |
# Split the data into training and validation sets | |
X_train, X_val, y_train, y_val = train_test_split(X_processed, y_raw, test_size=0.2, random_state=42) | |
# Build the LSTM model | |
input_shape = (X_train.shape[1], X_train.shape[2]) | |
model = build_lstm(input_shape) | |
# Train and evaluate the model | |
history = train_and_evaluate_model(model, X_train, y_train, X_val, y_val) | |
# Output the training history | |
print("Training History:", history) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment