fixes

2025-05-19 13:59:16 +02:00
parent 426f4d6963
commit c6defa2065
196 changed files with 18625 additions and 1 deletions
@@ -0,0 +1,127 @@
+from functools import partial
+
+from configs.feature_config import feature_config
+
+from utils.data_utils import *
+from utils.training import *
+
+from models.lstm import *
+from models.utils import *
+from models.collation import *
+
+take_every_nth = int(288 / 12)
+shift_in_hours = 12
+input_window_length = (288 // take_every_nth) * 80
+# output_window_length = (288 // take_every_nth) * 1
+output_window_length = 1
+output_window_offset = input_window_length + (288 // take_every_nth) * 0
+window_shift = int((288 // take_every_nth) / 24 * shift_in_hours)
+min_input_length_fraction_for_padding = ((288 // take_every_nth) * 4) / input_window_length
+
+max_lr = 1e-5
+batch_size = 128
+
+
+def get_lstm_run_config(
+        run_name: str,
+        run_description: str,
+        input_window_length: int,
+        output_window_length: int,
+        take_every_nth: int,
+        shift_in_hours: int,
+        output_window_offset: int,
+        batch_size: int,
+        model_parameters: dict,
+        max_lr: float,
+        num_epochs: int,
+        patience: int,
+        feature_config: dict):
+    """
+    Get the configuration for the LSTM model
+    Returns:
+        run_configuration: configuration for the LSTM model
+    """
+    base_model_config = {
+        "model_name": "lstm_regressor",
+        "version": "1.0.0",
+        "model_class": LSTMModel,
+        "feature_config": feature_config | {"ignored_features":
+            [
+                "fertility_probability",
+                "ov_over_probability",
+                # "days_relative_to_ov",
+                # "is_biphasic",
+                "ov_day",
+            ]},
+        "preprocessing": {
+            "window_shift": int((288 // take_every_nth) / 24 * shift_in_hours),
+            "take_every_nth": take_every_nth,
+            "min_input_length_fraction_for_padding": ((288 // take_every_nth) * 4) / input_window_length,
+        },
+        "batch_fn": produce_window_batches,
+        "collate_fn": simple_x_y_collate,
+        "model_creation_fn": simple_model_creation,
+        "model_save_fn": simple_model_save,
+        "model_load_fn": partial(simple_model_load, model_creation_fn=simple_model_creation),
+        "batch_loss_fn": get_model_loss,
+        "actual_fn": simple_get_y,
+        "predict_fn": simple_x_y_predict,
+        "model_parameters": {
+            **model_parameters,
+        },
+        "input_window_length": input_window_length,
+        "output_window_length": output_window_length,
+        "output_window_offset": output_window_offset,
+    }
+    base_training_config = {
+        "batch_size": batch_size,
+        "model_class": LSTMModel,
+        "learning_parameters": {
+            "learning_rate": max_lr * (batch_size / 4),
+            # "learning_rate": base_lr * (batch_size / 4),
+            "epochs": num_epochs,
+            "patience": patience,
+        },
+        "loss_functions": [
+            nn.MSELoss(),
+            nn.BCEWithLogitsLoss(),
+        ],
+        "max_grad_norm": 1.0,
+        "train_size": 0.7,
+        "val_size": 0.15,
+        "test_size": 0.15,
+    }
+    return {
+        "name": run_name,
+        "description": run_description,
+        "model_configuration": base_model_config,
+        "training_configuration": base_training_config,
+    }
+
+
+run_configuration = {
+    "item_limit": 100,
+    "runs": [
+        get_lstm_run_config(
+            run_name="lstm_regressor",
+            run_description="LSTM regressor for fertility prediction",
+            input_window_length=input_window_length,
+            output_window_length=output_window_length,
+            take_every_nth=take_every_nth,
+            shift_in_hours=shift_in_hours,
+            output_window_offset=output_window_offset,
+            batch_size=batch_size,
+            model_parameters={
+                "cnn_channels": 64,
+                "cnn_kernel_size": 3,
+                "embed_dim": 128,
+                "lstm_hidden_size": 128,
+                "num_layers": 4,
+            },
+            max_lr=max_lr,
+            num_epochs=1000,
+            patience=50,
+            feature_config=feature_config
+        )
+    ]
+}