PVNet 5.3.11__tar.gz → 5.3.13__tar.gz

{pvnet-5.3.11 → pvnet-5.3.13}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: PVNet
-Version: 5.3.11
+Version: 5.3.13
 Summary: PVNet
 Author-email: Peter Dudfield <info@openclimatefix.org>
 Requires-Python: <3.14,>=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: ocf-data-sampler>=1.0.9
+Requires-Dist: ocf-data-sampler>=1.0.19
 Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: matplotlib

{pvnet-5.3.11 → pvnet-5.3.13}/PVNet.egg-info/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: PVNet
-Version: 5.3.11
+Version: 5.3.13
 Summary: PVNet
 Author-email: Peter Dudfield <info@openclimatefix.org>
 Requires-Python: <3.14,>=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: ocf-data-sampler>=1.0.9
+Requires-Dist: ocf-data-sampler>=1.0.19
 Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: matplotlib

{pvnet-5.3.11 → pvnet-5.3.13}/PVNet.egg-info/requires.txt

@@ -1,4 +1,4 @@
-ocf-data-sampler>=1.0.9
+ocf-data-sampler>=1.0.19
 numpy
 pandas
 matplotlib

{pvnet-5.3.11 → pvnet-5.3.13}/pvnet/datamodule.py

@@ -22,13 +22,13 @@ class PVNetDataModule(LightningDataModule):
     def __init__(
         self,
         configuration: str,
-        batch_size: int = 16,
+        train_periods: list[tuple[None | str, None | str]],
+        val_periods: list[tuple[None | str, None | str]],
+        batch_size: int,
         num_workers: int = 0,
         prefetch_factor: int | None = None,
         persistent_workers: bool = False,
         pin_memory: bool = False,
-        train_period: list[str | None] = [None, None],
-        val_period: list[str | None] = [None, None],
         seed: int | None = None,
         dataset_pickle_dir: str | None = None,
     ):
@@ -36,6 +36,10 @@ class PVNetDataModule(LightningDataModule):
 
         Args:
             configuration: Path to ocf-data-sampler configuration file.
+            train_periods: List of (start_time, end_time) tuples for the train dataset. If 
+                start_time or end_time is None, it means that there is no lower/upper bound on the 
+                time period.
+            val_periods: List of (start_time, end_time) tuples for the validation dataset.
             batch_size: Batch size.
             num_workers: Number of workers to use in multiprocess batch loading.
             prefetch_factor: Number of batches loaded in advance by each worker.
@@ -44,8 +48,6 @@ class PVNetDataModule(LightningDataModule):
                 instances alive.
             pin_memory: If True, the data loader will copy Tensors into device/CUDA pinned memory
                 before returning them.
-            train_period: Date range filter for train dataloader.
-            val_period: Date range filter for val dataloader.
             seed: Random seed used in shuffling datasets.
             dataset_pickle_dir: Directory in which the val and train set will be presaved as
                 pickle objects. Setting this speeds up instantiation of multiple workers a lot.
@@ -53,8 +55,8 @@ class PVNetDataModule(LightningDataModule):
         super().__init__()
 
         self.configuration = configuration
-        self.train_period = train_period
-        self.val_period = val_period
+        self.train_periods = train_periods
+        self.val_periods = val_periods
         self.seed = seed
         self.dataset_pickle_dir = dataset_pickle_dir
 
@@ -79,10 +81,10 @@ class PVNetDataModule(LightningDataModule):
         # shuffled once
         if stage == "fit":
             # Prepare the train dataset
-            self.train_dataset = self._get_dataset(*self.train_period)
+            self.train_dataset = self._get_dataset(self.train_periods)
 
             # Prepare and pre-shuffle the val dataset and set seed for reproducibility
-            val_dataset = self._get_dataset(*self.val_period)
+            val_dataset = self._get_dataset(self.val_periods)
 
             shuffled_indices = np.random.default_rng(seed=self.seed).permutation(len(val_dataset))
             self.val_dataset = Subset(val_dataset, shuffled_indices)
@@ -114,8 +116,8 @@ class PVNetDataModule(LightningDataModule):
                 if os.path.exists(filepath):
                     os.remove(filepath)
 
-    def _get_dataset(self, start_time: str | None, end_time: str | None) -> PVNetDataset:
-        return PVNetDataset(self.configuration, start_time=start_time, end_time=end_time)
+    def _get_dataset(self, time_periods: list[tuple[str | None, str | None]]) -> PVNetDataset:
+        return PVNetDataset(self.configuration, time_periods=time_periods)
 
     def train_dataloader(self) -> DataLoader:
         """Construct train dataloader"""

{pvnet-5.3.11 → pvnet-5.3.13}/pvnet/utils.py

@@ -98,7 +98,7 @@ def validate_batch_against_config(
     model: "BaseModel",
 ) -> None:
     """Validates tensor shapes in batch against model configuration."""
-    logger.info("Performing batch shape validation against model config.")
+    logger.info("Performing batch shape validation against model config...")
 
     # NWP validation
     if model.include_nwp:
@@ -163,7 +163,7 @@ def validate_batch_against_config(
                 f"Generation data shape mismatch: expected {expected_shape}, got {actual_shape}"
             )
 
-    logger.info("Batch shape validation successful!")
+    logger.info("Batch shape validation successful.")
 
 
 def validate_gpu_config(config: DictConfig) -> None:

{pvnet-5.3.11 → pvnet-5.3.13}/pyproject.toml

@@ -12,7 +12,7 @@ readme = {file="README.md", content-type="text/markdown"}
 requires-python = ">=3.11,<3.14"
 
 dependencies = [
-    "ocf-data-sampler>=1.0.9",
+    "ocf-data-sampler>=1.0.19",
     "numpy",
     "pandas",
     "matplotlib",

{pvnet-5.3.11 → pvnet-5.3.13}/tests/test_datamodule.py

@@ -10,6 +10,6 @@ def test_data_module(data_config_path):
         batch_size=2,
         num_workers=0,
         prefetch_factor=None,
-        train_period=[None, None],
-        val_period=[None, None],
+        train_periods=[[None, None]],
+        val_periods=[[None, None]],
     )

{pvnet-5.3.11 → pvnet-5.3.13}/tests/test_end2end.py

@@ -10,6 +10,8 @@ def test_model_trainer_fit(session_tmp_path, data_config_path, late_fusion_model
 
     datamodule = PVNetDataModule(
         configuration=data_config_path,
+        train_periods=[[None, None]],
+        val_periods=[[None, None]],
         batch_size=2,
         num_workers=2,
         prefetch_factor=None,