0.10.26

prediction in DataModule fixed

Author: bartzbeielstein

pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "spotPython"
-version = "0.10.25"
+version = "0.10.26"
 authors = [
   { name="T. Bartz-Beielstein", email="tbb@bartzundbartz.de" }
 ]

src/spotPython/data/lightdatamodule.py

@@ -124,14 +124,22 @@ def setup(self, stage: Optional[str] = None) -> None:
             generator_test = torch.Generator().manual_seed(self.test_seed)
             self.data_test, _ = random_split(self.data_full, [test_size, full_train_size], generator=generator_test)
 
+        # if stage == "predict" or stage is None:
+        #     print(f"test_size, full_train_size: {test_size}, {full_train_size}")
+        #     generator_predict = torch.Generator().manual_seed(self.test_seed)
+        #     full_data_predict, _ = random_split(
+        #         self.data_full, [test_size, full_train_size], generator=generator_predict
+        #     )
+        #     # Only keep the features for prediction
+        #     self.data_predict = [x for x, _ in full_data_predict]
+
+        # Assign pred dataset for use in dataloader(s)
         if stage == "predict" or stage is None:
-            print(f"test_size, full_train_size: {test_size}, {full_train_size}")
+            # get test data aset as test_abs percent of the full dataset
             generator_predict = torch.Generator().manual_seed(self.test_seed)
-            full_data_predict, _ = random_split(
+            self.data_predict, _ = random_split(
                 self.data_full, [test_size, full_train_size], generator=generator_predict
             )
-            # Only keep the features for prediction
-            self.data_predict = [x for x, _ in full_data_predict]
 
     def train_dataloader(self) -> DataLoader:
         """
@@ -209,4 +217,4 @@ def predict_dataloader(self) -> DataLoader:
         print(f"LightDataModule: predict_dataloader(). Predict set size: {len(self.data_predict)}")
         print(f"LightDataModule: predict_dataloader(). batch_size: {self.batch_size}")
         print(f"LightDataModule: predict_dataloader(). num_workers: {self.num_workers}")
-        return DataLoader(self.data_predict, batch_size=self.batch_size, num_workers=self.num_workers)
+        return DataLoader(self.data_predict, batch_size=len(self.data_predict), num_workers=self.num_workers)

src/spotPython/light/predictmodel.py

@@ -103,8 +103,8 @@ def predict_model(config: dict, fun_control: dict) -> Tuple[float, float]:
     trainer.fit(model=model, datamodule=dm)
 
     dm.setup(stage="predict")
-    # predictions = trainer.predict(model=model, datamodule=dm)
-    predictions = trainer.predict(datamodule=dm)
+    predictions = trainer.predict(model=model, datamodule=dm)
+    # predictions = trainer.predict(datamodule=dm)
 
     # # Load the last checkpoint
     # test_result = trainer.test(datamodule=dm, ckpt_path="last")

src/spotPython/light/regression/netlightregression.py

@@ -239,6 +239,35 @@ def test_step(self, batch: tuple, batch_idx: int, prog_bar: bool = False) -> tor
         self.log("hp_metric", val_loss, prog_bar=prog_bar)
         return val_loss
 
+    def predict_step(self, batch: tuple, batch_idx: int, prog_bar: bool = False) -> torch.Tensor:
+        """
+        Performs a single prediction step.
+
+        Args:
+            batch (tuple): A tuple containing a batch of input data and labels.
+            batch_idx (int): The index of the current batch.
+            prog_bar (bool, optional): Whether to display the progress bar. Defaults to False.
+
+        Returns:
+            torch.Tensor: A tensor containing the prediction for this batch.
+        """
+        x, y = batch
+        yhat = self(x)
+        y = y.view(len(y), 1)
+        yhat = yhat.view(len(yhat), 1)
+        print(f"Predict step x: {x}")
+        print(f"Predict step y: {y}")
+        print(f"Predict step y_hat: {yhat}")
+        # pred_loss = F.mse_loss(y_hat, y)
+        # pred loss not registered
+        # self.log("pred_loss", pred_loss, prog_bar=prog_bar)
+        # self.log("hp_metric", pred_loss, prog_bar=prog_bar)
+        # MisconfigurationException: You are trying to `self.log()`
+        # but the loop's result collection is not registered yet.
+        # This is most likely because you are trying to log in a `predict` hook, but it doesn't support logging.
+        # If you want to manually log, please consider using `self.log_dict({'pred_loss': pred_loss})` instead.
+        return (x, y, yhat)
+
     def configure_optimizers(self) -> torch.optim.Optimizer:
         """
         Configures the optimizer for the model.