PVNet 3.0.37__tar.gz → 3.0.39__tar.gz

{pvnet-3.0.37 → pvnet-3.0.39}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PVNet
-Version: 3.0.37
+Version: 3.0.39
 Summary: PVNet
 Author-email: Peter Dudfield <info@openclimatefix.org>
 Description-Content-Type: text/markdown
@@ -65,12 +65,12 @@ together.
 
 ## Experiments
 
-**Link to our workshop paper coming soon**
+Our paper based on this repo was accepted into the Tackling Climate Change with Machine Learning workshop at ICLR 2024 and can be viewed [here](https://www.climatechange.ai/papers/iclr2024/46).
 
-Some very rough working notes on this model are
-[here](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA/edit?usp=sharing).
+Some slightly more structured notes on deliberate experiments we have performed with PVNet are [here](https://docs.google.com/document/d/1VumDwWd8YAfvXbOtJEv3ZJm_FHQDzrKXR0jU9vnvGQg).
 
-Some slightly more structured notes on deliberate experiments we have performed with PVNet are [here](https://docs.google.com/document/d/1VumDwWd8YAfvXbOtJEv3ZJm_FHQDzrKXR0jU9vnvGQg/edit?usp=sharing)
+Some very rough, early working notes on this model are
+[here](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA). These are now somewhat out of date.
 
 
 
@@ -200,10 +200,15 @@ Where `FULL-PATH-TO-REPO` represent the whole path to the PVNet repo on your loc
 
 ### Running the batch creation script
 
-Run the save_batches.py script to create batches with the following example arguments as:
+Run the save_batches.py script to create batches if setting parameters in the datamodule config (`streamed_batches.yaml` in this example):
 
 ```
-python scripts/save_batches.py datamodule=streamed_batches +batch_output_dir="./output" +num_train_batches=10 +num_val_batches=5
+python scripts/save_batches.py
+```
+or with the following example arguments to override config:
+
+```
+python scripts/save_batches.py datamodule=streamed_batches datamodule.batch_output_dir="./output" datamodule.num_train_batches=10 datamodule.num_val_batches=5
 ```
 
 In this function the datamodule argument looks for a config under `PVNet/configs/datamodule`. The examples here are either to use "premade_batches" or "streamed_batches".

{pvnet-3.0.37 → pvnet-3.0.39}/PVNet.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PVNet
-Version: 3.0.37
+Version: 3.0.39
 Summary: PVNet
 Author-email: Peter Dudfield <info@openclimatefix.org>
 Description-Content-Type: text/markdown
@@ -65,12 +65,12 @@ together.
 
 ## Experiments
 
-**Link to our workshop paper coming soon**
+Our paper based on this repo was accepted into the Tackling Climate Change with Machine Learning workshop at ICLR 2024 and can be viewed [here](https://www.climatechange.ai/papers/iclr2024/46).
 
-Some very rough working notes on this model are
-[here](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA/edit?usp=sharing).
+Some slightly more structured notes on deliberate experiments we have performed with PVNet are [here](https://docs.google.com/document/d/1VumDwWd8YAfvXbOtJEv3ZJm_FHQDzrKXR0jU9vnvGQg).
 
-Some slightly more structured notes on deliberate experiments we have performed with PVNet are [here](https://docs.google.com/document/d/1VumDwWd8YAfvXbOtJEv3ZJm_FHQDzrKXR0jU9vnvGQg/edit?usp=sharing)
+Some very rough, early working notes on this model are
+[here](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA). These are now somewhat out of date.
 
 
 
@@ -200,10 +200,15 @@ Where `FULL-PATH-TO-REPO` represent the whole path to the PVNet repo on your loc
 
 ### Running the batch creation script
 
-Run the save_batches.py script to create batches with the following example arguments as:
+Run the save_batches.py script to create batches if setting parameters in the datamodule config (`streamed_batches.yaml` in this example):
 
 ```
-python scripts/save_batches.py datamodule=streamed_batches +batch_output_dir="./output" +num_train_batches=10 +num_val_batches=5
+python scripts/save_batches.py
+```
+or with the following example arguments to override config:
+
+```
+python scripts/save_batches.py datamodule=streamed_batches datamodule.batch_output_dir="./output" datamodule.num_train_batches=10 datamodule.num_val_batches=5
 ```
 
 In this function the datamodule argument looks for a config under `PVNet/configs/datamodule`. The examples here are either to use "premade_batches" or "streamed_batches".

{pvnet-3.0.37 → pvnet-3.0.39}/README.md

@@ -17,12 +17,12 @@ together.
 
 ## Experiments
 
-**Link to our workshop paper coming soon**
+Our paper based on this repo was accepted into the Tackling Climate Change with Machine Learning workshop at ICLR 2024 and can be viewed [here](https://www.climatechange.ai/papers/iclr2024/46).
 
-Some very rough working notes on this model are
-[here](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA/edit?usp=sharing).
+Some slightly more structured notes on deliberate experiments we have performed with PVNet are [here](https://docs.google.com/document/d/1VumDwWd8YAfvXbOtJEv3ZJm_FHQDzrKXR0jU9vnvGQg).
 
-Some slightly more structured notes on deliberate experiments we have performed with PVNet are [here](https://docs.google.com/document/d/1VumDwWd8YAfvXbOtJEv3ZJm_FHQDzrKXR0jU9vnvGQg/edit?usp=sharing)
+Some very rough, early working notes on this model are
+[here](https://docs.google.com/document/d/1fbkfkBzp16WbnCg7RDuRDvgzInA6XQu3xh4NCjV-WDA). These are now somewhat out of date.
 
 
 
@@ -152,10 +152,15 @@ Where `FULL-PATH-TO-REPO` represent the whole path to the PVNet repo on your loc
 
 ### Running the batch creation script
 
-Run the save_batches.py script to create batches with the following example arguments as:
+Run the save_batches.py script to create batches if setting parameters in the datamodule config (`streamed_batches.yaml` in this example):
 
 ```
-python scripts/save_batches.py datamodule=streamed_batches +batch_output_dir="./output" +num_train_batches=10 +num_val_batches=5
+python scripts/save_batches.py
+```
+or with the following example arguments to override config:
+
+```
+python scripts/save_batches.py datamodule=streamed_batches datamodule.batch_output_dir="./output" datamodule.num_train_batches=10 datamodule.num_val_batches=5
 ```
 
 In this function the datamodule argument looks for a config under `PVNet/configs/datamodule`. The examples here are either to use "premade_batches" or "streamed_batches".

pvnet-3.0.39/pvnet/__init__.py

@@ -0,0 +1,2 @@
+"""PVNet"""
+__version__ = "3.0.39"

{pvnet-3.0.37 → pvnet-3.0.39}/pvnet/data/base.py

@@ -19,6 +19,7 @@ class BaseDataModule(LightningDataModule):
         test_period=[None, None],
         batch_dir=None,
         shuffle_factor=100,
+        nwp_channels=None,
     ):
         """Datamodule for training pvnet architecture.
 
@@ -38,17 +39,24 @@ class BaseDataModule(LightningDataModule):
             shuffle_factor: Number of presaved batches to be split and reshuffled to create returned
                 batches. A larger factor means on each epoch the batches will be more diverse but at
                 the cost of using more RAM.
-
+            nwp_channels: Number of NWP channels to use. If None, the all channels are used
         """
         super().__init__()
         self.configuration = configuration
         self.batch_size = batch_size
         self.batch_dir = batch_dir
         self.shuffle_factor = shuffle_factor
+        self.nwp_channels = nwp_channels
 
         if not ((batch_dir is not None) ^ (configuration is not None)):
             raise ValueError("Exactly one of `batch_dir` or `configuration` must be set.")
 
+        if (nwp_channels is not None) and (batch_dir is None):
+            raise ValueError(
+                "In order for 'nwp_channels' to work, we need batch_dir. "
+                "Otherwise the nwp channels is one in the configuration"
+            )
+
         if batch_dir is not None:
             if any([period != [None, None] for period in [train_period, val_period, test_period]]):
                 raise ValueError("Cannot set `(train/val/test)_period` with presaved batches")

{pvnet-3.0.37 → pvnet-3.0.39}/pvnet/data/wind_datamodule.py

@@ -11,6 +11,7 @@ class WindDataModule(BaseDataModule):
     """Datamodule for training windnet and using windnet pipeline in `ocf_datapipes`."""
 
     def _get_datapipe(self, start_time, end_time):
+        # TODO is this is not right, need to load full windnet pipeline
         data_pipeline = windnet_netcdf_datapipe(
             self.configuration,
             keys=["wind", "nwp", "sensor"],
@@ -28,7 +29,9 @@ class WindDataModule(BaseDataModule):
         data_pipeline = windnet_netcdf_datapipe(
             keys=["wind", "nwp", "sensor"],
             filenames=filenames,
+            nwp_channels=self.nwp_channels,
         )
+
         data_pipeline = (
             data_pipeline.batch(self.batch_size)
             .map(stack_np_examples_into_batch)

pvnet-3.0.37/pvnet/__init__.py

@@ -1,2 +0,0 @@
-"""PVNet"""
-__version__ = "3.0.37"