address PR comments

Author: jcamier

.gitignore

@@ -105,4 +105,5 @@ GFS_samples/
 GFS_TEST_RUN/
 PLACEHOLDER/
 *.zarr
-example_configuration.yaml # config file for samples adjusted for local paths
+example_configuration.yaml # config file for samples adjusted for local paths
+experiment_config.yaml

experiment_config.yaml

@@ -5,7 +5,7 @@ defaults:
   - _self_
   - trainer: default.yaml
   - model: multimodal.yaml
-  - datamodule: premade_batches.yaml
+  - datamodule: streamed_batches.yaml #
   - callbacks: default.yaml # set this to null if you don't want to use callbacks
   # - logger: null
   - logger: wandb.yaml # set logger here or use command line (e.g. `python run.py logger=wandb`)

src/open_data_pvnet/configs/PVNet_configs/config.yaml

@@ -19,8 +19,7 @@ input_data:
   gsp:
     # Path to GSP data in zarr format
     # e.g. gs://solar-pv-nowcasting-data/PV/GSP/v7/pv_gsp.zarr
-    # zarr_path: "s3://ocf-open-data-pvnet/data/uk/pvlive/v2/combined_2023_gsp.zarr"
-    zarr_path: "/Users/jacquescamier/Development/ML_AI/open-data-pvnet/gsp_2023.zarr"
+    zarr_path: "s3://ocf-open-data-pvnet/data/uk/pvlive/v2/combined_2023_gsp.zarr"
     interval_start_minutes: -60
     # Specified for intraday currently
     interval_end_minutes: 480
@@ -30,7 +29,7 @@ input_data:
     # Values after t0 are assumed as targets and cannot be dropped.
     dropout_timedeltas_minutes: []
     dropout_fraction: 0.0 # Fraction of samples with dropout
-    # public: True
+    public: True
 
   nwp:
     gfs:
@@ -39,12 +38,11 @@ input_data:
       interval_end_minutes: 540
       dropout_fraction: 0.0
       dropout_timedeltas_minutes: []
-      # zarr_path: "s3://ocf-open-data-pvnet/data/gfs/v4/2023.zarr"
-      zarr_path: "/Users/jacquescamier/Development/ML_AI/open-data-pvnet/gfs_2023.zarr"
+      zarr_path: "s3://ocf-open-data-pvnet/data/gfs/v4/2023.zarr"
       provider: "gfs"
       image_size_pixels_height: 2
       image_size_pixels_width: 2
-      # public: True
+      public: True
       channels:
         - dlwrf # downwards long-wave radiation flux
         - dswrf # downwards short-wave radiation flux

src/open_data_pvnet/configs/PVNet_configs/datamodule/configuration/example_configuration.yaml

@@ -2,7 +2,7 @@ _target_: pvnet.data.DataModule
 # Path to the data configuration yaml file. You can find examples in the configuration subdirectory
 # in configs.example/datamodule/configuration
 # Use the full local path such as: /FULL/PATH/PVNet/configs/datamodule/configuration/gcp_configuration.yaml"
-configuration: "/Users/jacquescamier/Development/ML_AI/open-data-pvnet/src/open_data_pvnet/configs/PVNet_configs/datamodule/configuration/example_configuration.yaml"
+configuration: null
 num_workers: 8
 prefetch_factor: 2
 batch_size: 8

src/open_data_pvnet/configs/PVNet_configs/datamodule/streamed_batches.yaml

@@ -6,9 +6,9 @@ wandb:
   project: "GFS_TEST_RUN"
   name: "${model_name}"
   # location to store the wandb local logs
-  save_dir: "GFS_TEST_RUN"
+  save_dir: "PLACEHOLDER"
   offline: False # set True to store all logs only locally
-  # id: null # pass correct id to resume experiment!
+  id: null # pass correct id to resume experiment!
   id: "${oc.env:WANDB_RUN_ID}"
   # entity: ""  # set to name of your wandb team or just remove it
   log_model: True