2.-LSTM-Model.md

@@ -67,5 +67,46 @@ model1 = Sequential([
 optimizer = Adam(learning_rate=0.001, clipvalue=1.0)
 ```
 
-**testing of different Parameters and Layers**
+
+**After testing and more debugging I have found this to have good Correlation and RMSE values. I will keep testing and train a good model for all locations**
+
+```
+def train_model(model, X_train, y_train, X_test, y_test):
+    epochs=200
+    batch_size=32
+
+    early_stopping = EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True)
+
+    # Learning rate scheduler callback
+    reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=2, min_lr=1e-6)
+
+
+    checkpoint_path = "checkpoints/model_epoch_{epoch:02d}_val_loss_{val_loss:.2f}.weights.h5"
+    checkpoint = ModelCheckpoint(
+        filepath=checkpoint_path, save_weights_only=True,
+        monitor='val_loss', mode='min', save_best_only=True, verbose=1
+    )
+
+    history = model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size,
+           validation_data=(X_test, y_test), callbacks=[checkpoint, early_stopping, reduce_lr])
+    return model, history
+
+
+modelyyx = Sequential([
+    Input(shape=(sequence_length, feature_count)),
+    Bidirectional(LSTM(128, return_sequences=True)),
+    LSTM(sequence_length) # Ensure the output shape matches y
+])
+
+histories = []
+for X_train, y_train, X_test, y_test in all_sequences:
+    optimizer = Adam(learning_rate=0.001, clipvalue=1.0)
+    modelyyx.compile(optimizer=optimizer, loss='mse')
+    print("NEW LOCATION")
+    modelyyx, history = train_model(modelyyx, X_train, y_train, X_test, y_test)
+```
+
+
+![Selection_040](uploads/477dd5d17602f6346d7f1d4d29063951/Selection_040.png)
+