[1081][Evaluation] Use parent ruff rules (#1177)

* use ruff settings from parent

* fix code checks

* check fixes 2nd round

* reformat to line length

Author: mtar

packages/evaluate/pyproject.toml

@@ -28,58 +28,7 @@ export = "weathergen.evaluate.export_inference:export"
 
 # The linting configuration
 [tool.ruff]
-
-# Wide rows
-line-length = 100
-
-[tool.ruff.lint]
-# All disabled until the code is formatted.
-select = [
-    # pycodestyle
-    "E",
-    # Pyflakes
-    "F",
-    # pyupgrade
-    "UP",
-    # flake8-bugbear
-    "B",
-    # flake8-simplify
-    "SIM",
-    # isort
-    "I",
-    # Banned imports
-    "TID",
-    # Naming conventions
-    "N",
-    # print
-    "T201"
-]
-
-# These rules are sensible and should be enabled at a later stage.
-ignore = [
-  # "B006",
-  "B011",
-  "UP008",
-  "SIM117",
-  "SIM118",
-  "SIM102",
-  "SIM401",
-  "E501", # to be removed 
-  "E721",
-  # To ignore, not relevant for us
-  "SIM108", # in case additional norm layer supports are added in future
-  "N817", # we use heavy acronyms, e.g., allowing 'import LongModuleName as LMN' (LMN is accepted)
-  "E731", # overly restrictive and less readable code
-  "N812", # prevents us following the convention for importing torch.nn.functional as F
-]
-
-[tool.ruff.lint.flake8-tidy-imports.banned-api]
-"numpy.ndarray".msg = "Do not use 'ndarray' to describe a numpy array type, it is a function. Use numpy.typing.NDArray or numpy.typing.NDArray[np.float32] for example"
-
-[tool.ruff.format]
-# Use Unix `\n` line endings for all files
-line-ending = "lf"
-
+extend = "../../pyproject.toml"
 
 [tool.pyrefly]
 project-includes = ["src/"]

packages/evaluate/src/weathergen/evaluate/clim_utils.py

@@ -52,7 +52,8 @@ def match_climatology_time(target_datetime: pd.Timestamp, clim_data: xr.Dataset)
     # To Do: leap years and other edge cases
     if len(matching_indices) == 0:
         _logger.warning(
-            f"No matching climatology time found for {target_datetime} (DOY: {target_doy}, Hour: {target_hour})"
+            f"No matching climatology time found for {target_datetime} (DOY: {target_doy}, "
+            f"Hour: {target_hour})"
             f"Please check that climatology data and stream input data filenames match."
         )
         return None
@@ -156,8 +157,8 @@ def align_clim_data(
                 if np.any(unmatched_mask):
                     n_unmatched = np.sum(unmatched_mask)
                     raise ValueError(
-                        f"Found {n_unmatched} target coordinates with no matching climatology coordinates. "
-                        f"This will cause incorrect ACC calculations. "
+                        f"Found {n_unmatched} target coordinates with no matching climatology "
+                        f"coordinates. This will cause incorrect ACC calculations. "
                         f"Check coordinate alignment between target and climatology data."
                     )
                 # Cache the computed indices and target coords
@@ -175,8 +176,10 @@ def align_clim_data(
             except (ValueError, IndexError) as e:
                 raise ValueError(
                     f"Failed to align climatology data with target data for ACC calculation. "
-                    f"This error typically occurs when the number of points per sample varies between samples. "
-                    f"ACC metric is currently only supported for forecasting data with constant points per sample. "
+                    f"This error typically occurs when the number of points per sample varies "
+                    f"between samples. "
+                    f"ACC metric is currently only supported for forecasting data with constant "
+                    f"points per sample. "
                     f"Please ensure all samples have the same spatial coverage and grid points. "
                     f"Original error: {e}"
                 ) from e

packages/evaluate/src/weathergen/evaluate/derived_channels.py

@@ -21,9 +21,11 @@ def __init__(
         Initializes the DeriveChannels class with necessary configurations for channel derivation.
 
         Args:
-            available_channels (np.array): an array of all available channel names in the datasets (target or pred).
+            available_channels (np.array): an array of all available channel names
+            in the datasets (target or pred).
             channels (list): A list of channels of interest to be evaluated and/or plotted.
-            stream_cfg (dict): A dictionary containing the stream configuration settings for evaluation and plottings.
+            stream_cfg (dict): A dictionary containing the stream configuration settings for
+            evaluation and plottings.
 
         Returns:
             None
@@ -147,6 +149,7 @@ def get_derived_channels(
                     )
             else:
                 _logger.debug(
-                    f"Calculation of {tag} is skipped because it is included in the available channels..."
+                    f"Calculation of {tag} is skipped because it is included "
+                    "in the available channels..."
                 )
         return data_tars, data_preds, self.channels

packages/evaluate/src/weathergen/evaluate/export_inference.py

@@ -10,7 +10,9 @@
 # weathergen-common = { path = "../../../../../packages/common" }
 # weathergen = { path = "../../../../../" }
 # ///
-## Example USAGE: uv run export --run-id grwnhykd --stream ERA5 --output-dir /p/home/jusers/owens1/jureca/WeatherGen/test_output1 --format netcdf --type prediction target --fsteps 1 --samples 1
+## Example USAGE: uv run export --run-id grwnhykd --stream ERA5 \
+## --output-dir /p/home/jusers/owens1/jureca/WeatherGen/test_output1 \
+## --format netcdf --type prediction target --fsteps 1 --samples 1
 import argparse
 import logging
 import re
@@ -66,9 +68,11 @@ def find_pl(all_variables: list) -> tuple[dict[str, list[str]], list[int]]:
     """
     Find all the pressure levels for each variable using regex and returns a dictionary
     mapping variable names to their corresponding pressure levels.
+
     Parameters
     ----------
         all_variables : list of variable names with pressure levels (e.g.,'q_500','t_2m').
+
     Returns
     -------
         A tuple containing:
@@ -333,14 +337,17 @@ def output_filename(
     forecast_ref_time: np.datetime64,
 ) -> Path:
     """
-    Generate output filename based on prefix (should refer to type e.g. pred/targ), run_id, sample index, output directory, format and forecast_ref_time.
+    Generate output filename based on prefix (should refer to type e.g. pred/targ), run_id, sample
+    index, output directory, format and forecast_ref_time.
+
     Parameters
     ----------
         prefix : Prefix for file name (e.g., 'pred' or 'targ').
         run_id :Run ID to include in the filename.
         output_dir : Directory to save the output file.
         output_format : Output file format (currently only 'netcdf' supported).
         forecast_ref_time : Forecast reference time to include in the filename.
+
     Returns
     -------
         Full path to the output file.
@@ -358,9 +365,11 @@ def output_filename(
 def get_data_worker(args: tuple) -> xr.DataArray:
     """
     Worker function to retrieve data for a single sample and forecast step.
+
     Parameters
     ----------
         args : Tuple containing (sample, fstep, run_id, stream, type).
+
     Returns
     -------
         xarray DataArray for the specified sample and forecast step.
@@ -397,18 +406,30 @@ def get_data(
 
     Parameters
     ----------
-        run_id : Run ID to identify the Zarr store.
-        samples : Sample to process
-        stream : Stream name to retrieve data for (e.g., 'ERA5').
-        type : Type of data to retrieve ('target' or 'prediction').
-        fsteps : List of forecast steps to retrieve. If None, retrieves all available forecast steps.
-        channels :List of channels to retrieve. If None, retrieves all available channels.
-        n_processes : Number of parallel processes to use for data retrieval.
-        ecpoch : Epoch number to identify the Zarr store.
-        rank : Rank number to identify the Zarr store.
-        output_dir : Directory to save the NetCDF files.
-        output_format : Output file format (currently only 'netcdf' supported).
-        config : Loaded config for cf_parser function.
+        run_id : str
+            Run ID to identify the Zarr store.
+        samples : list
+            Sample to process
+        stream : str
+            Stream name to retrieve data for (e.g., 'ERA5').
+        dtype : str
+            Type of data to retrieve ('target' or 'prediction').
+        fsteps : list
+            List of forecast steps to retrieve. If None, retrieves all available forecast steps.
+        channels : list
+            List of channels to retrieve. If None, retrieves all available channels.
+        n_processes : list
+            Number of parallel processes to use for data retrieval.
+        ecpoch : int
+            Epoch number to identify the Zarr store.
+        rank : int
+            Rank number to identify the Zarr store.
+        output_dir : str
+            Directory to save the NetCDF files.
+        output_format : str
+            Output file format (currently only 'netcdf' supported).
+        config : OmegaConf
+            Loaded config for cf_parser function.
     """
     if dtype not in ["target", "prediction"]:
         raise ValueError(f"Invalid type: {dtype}. Must be 'target' or 'prediction'.")
@@ -451,7 +472,8 @@ def get_data(
                                 f"{list(set(channels) - set(existing_channels))}. Skipping them."
                             )
                         result = result.sel(channel=existing_channels)
-                    # reshape result - use adaptive function to handle both regular and Gaussian grids
+                    # reshape result - use adaptive function to handle both regular and Gaussian
+                    # grids
                     result = reshape_dataset_adaptive(result)
                     da_fs.append(result)
 
@@ -484,12 +506,14 @@ def save_sample_to_netcdf(
 ) -> None:
     """
     Uses list of pred/target xarray DataArrays to save one sample to a NetCDF file.
+
     Parameters
     ----------
     type_str : str
         Type of data ('pred' or 'targ') to include in the filename.
     dict_sample_all_steps : dict
-        Dictionary where keys is sample index and values is a list of xarray DataArrays for all the forecast steps
+        Dictionary where keys is sample index and values is a list of xarray DataArrays
+        for all the forecast steps
     fstep_hours : np.timedelta64
         Time difference between forecast steps (e.g., 6 hours).
     run_id : str
@@ -595,7 +619,8 @@ def parse_args(args: list) -> argparse.Namespace:
         type=int,
         nargs="+",
         default=None,
-        help="List of forecast steps to retrieve (e.g. 1 2 3). If not provided, retrieves all available forecast steps.",
+        help="List of forecast steps to retrieve (e.g. 1 2 3). "
+        "If not provided, retrieves all available forecast steps.",
     )
 
     parser.add_argument(
@@ -611,7 +636,8 @@ def parse_args(args: list) -> argparse.Namespace:
         type=str,
         nargs="+",
         default=None,
-        help="List of channels to retrieve (e.g., 'q_500 t_2m'). If not provided, retrieves all available channels.",
+        help="List of channels to retrieve (e.g., 'q_500 t_2m'). "
+        "If not provided, retrieves all available channels.",
     )
 
     parser.add_argument(