pypromice 1.4.0__tar.gz → 1.4.2__tar.gz

{pypromice-1.4.0/src/pypromice.egg-info → pypromice-1.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pypromice
-Version: 1.4.0
+Version: 1.4.2
 Summary: PROMICE/GC-Net data processing toolbox
 Home-page: https://github.com/GEUS-Glaciology-and-Climate/pypromice
 Author: GEUS Glaciology and Climate
@@ -15,7 +15,7 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
 Classifier: Topic :: Scientific/Engineering
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.8
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
 Requires-Dist: numpy~=1.23

{pypromice-1.4.0 → pypromice-1.4.2}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 
 setuptools.setup(
     name="pypromice",
-    version="1.4.0",
+    version="1.4.2",
     author="GEUS Glaciology and Climate",
     description="PROMICE/GC-Net data processing toolbox",
     long_description=long_description,
@@ -29,7 +29,7 @@ setuptools.setup(
     package_dir={"": "src"},
     include_package_data = True,
     packages=setuptools.find_packages(where="src"),
-    python_requires=">=3.8",
+    python_requires=">=3.10",
     package_data={
     	"pypromice.tx": ["payload_formats.csv", "payload_types.csv"],
         "pypromice.qc.percentiles": ["thresholds.csv"],

{pypromice-1.4.0 → pypromice-1.4.2}/src/pypromice/postprocess/bufr_to_csv.py

@@ -1,15 +1,22 @@
 import argparse
 from pathlib import Path
 
+import pandas as pd
+
 from pypromice.postprocess.bufr_utilities import read_bufr_file
 
 
 def main():
     parser = argparse.ArgumentParser("BUFR to CSV converter")
-    parser.add_argument("path", type=Path)
+    parser.add_argument("path", type=Path, nargs='+')
     args = parser.parse_args()
 
-    print(read_bufr_file(args.path).to_csv())
+    paths = []
+    for path in args.path:
+        paths += list(path.parent.glob(path.name))
+
+    df = pd.concat([read_bufr_file(path) for path in paths])
+    print(df.to_csv())
 
 
 if __name__ == "__main__":

{pypromice-1.4.0 → pypromice-1.4.2}/src/pypromice/process/L2toL3.py

@@ -254,6 +254,7 @@ def process_surface_height(ds, data_adjustments_dir, station_config={}):
         
         ds['z_surf_combined'] = np.maximum(ds['z_surf_combined'], ds['z_ice_surf'])
         ds['snow_height'] = np.maximum(0, ds['z_surf_combined'] - ds['z_ice_surf'])
+        ds['z_ice_surf'] = ds['z_ice_surf'].where(ds.snow_height.notnull())
     elif ds.attrs['site_type'] in ['accumulation', 'bedrock']:
         # Handle accumulation and bedrock site types
         ds['z_ice_surf'] = ('time', ds['z_surf_1'].data * np.nan)

{pypromice-1.4.0 → pypromice-1.4.2}/src/pypromice/process/aws.py

@@ -55,7 +55,15 @@ class AWS(object):
         """
         assert os.path.isfile(config_file), "cannot find " + config_file
         assert os.path.isdir(inpath), "cannot find " + inpath
-        logger.info("AWS object initialising...")
+        logger.info(
+            "AWS("
+            f"config_file={config_file},"
+            f" inpath={inpath},"
+            f" data_issues_repository={data_issues_repository},"
+            f" var_file={var_file},"
+            f" meta_file={meta_file}"
+            ")"
+        )
 
         # Load config, variables CSF standards, and L0 files
         self.config = self.loadConfig(config_file, inpath)
@@ -73,6 +81,7 @@ class AWS(object):
             l0_data_root=inpath_hash,
             data_issues=data_issues_hash,
         )
+        logger.debug('Source information: %s', source_dict)
         self.meta["source"] = json.dumps(source_dict)
 
         # Load config file

{pypromice-1.4.0 → pypromice-1.4.2}/src/pypromice/process/resample.py

@@ -32,8 +32,46 @@ def resample_dataset(ds_h, t):
     ds_d : xarray.Dataset
         L3 AWS dataset resampled to the frequency defined by t
     '''
-    df_d = ds_h.to_dataframe().resample(t).mean()
+    # Convert dataset to DataFrame
+    df_d = ds_h.to_dataframe()
     
+    # Identify non-numeric columns
+    non_numeric_cols = df_d.select_dtypes(exclude=['number']).columns
+    
+    # Log a warning and drop non-numeric columns
+    if len(non_numeric_cols) > 0:
+        for col in non_numeric_cols:
+            unique_values = df_d[col].unique()
+            logger.warning(f"Dropping column '{col}' because it is of type '{df_d[col].dtype}' and contains unique values: {unique_values}")
+
+        df_d = df_d.drop(columns=non_numeric_cols)
+    # Resample the DataFrame
+    df_d = df_d.resample(t).mean()
+
+    # taking the 10 min data and using it as instantaneous values:
+    is_10_minutes_timestamp = (ds_h.time.diff(dim='time') / np.timedelta64(1, 's') == 600)
+    if (t == '60min') and is_10_minutes_timestamp.any():
+        cols_to_update = ['p_i', 't_i', 'rh_i', 'rh_i_cor', 'wspd_i', 'wdir_i','wspd_x_i','wspd_y_i']
+        timestamp_10min = ds_h.time.where(is_10_minutes_timestamp, drop=True).to_index()
+        timestamp_round_hour = df_d.index
+        timestamp_to_update = timestamp_round_hour.intersection(timestamp_10min)
+        
+        for col in cols_to_update:
+            if col not in df_d.columns:
+                df_d[col] = np.nan
+            else:
+                # if there are already instantaneous values in the dataset
+                # we want to keep them as they are
+                # removing timestamps where there is already t_i filled from a TX file
+                missing_instantaneous = ds_h.reindex(time=timestamp_to_update)[col].isnull()
+                timestamp_to_update = timestamp_to_update[missing_instantaneous]
+            df_d.loc[timestamp_to_update, col] = ds_h.reindex(
+                time= timestamp_to_update
+                )[col.replace('_i','_u')].values
+            if col == 'p_i':
+                df_d.loc[timestamp_to_update, col] = df_d.loc[timestamp_to_update, col].values-1000
+            
+
     # recalculating wind direction from averaged directional wind speeds
     for var in ['wdir_u','wdir_l']:
         boom = var.split('_')[1]
@@ -60,9 +98,19 @@ def resample_dataset(ds_h, t):
                 if var+'_cor' in df_d.keys():
                     df_d[var+'_cor'] = (p_vap.to_series().resample(t).mean() \
                                / es_cor.to_series().resample(t).mean())*100
+    
+    # passing each variable attribute to the ressample dataset
+    vals = []
+    for c in df_d.columns:
+        if c in ds_h.data_vars:
+            vals.append(xr.DataArray(
+                data=df_d[c], dims=['time'],
+               coords={'time':df_d.index}, attrs=ds_h[c].attrs))
+        else:
+            vals.append(xr.DataArray(
+                data=df_d[c], dims=['time'],
+               coords={'time':df_d.index}, attrs=None))
             
-    vals = [xr.DataArray(data=df_d[c], dims=['time'],
-           coords={'time':df_d.index}, attrs=ds_h[c].attrs) for c in df_d.columns]
     ds_d = xr.Dataset(dict(zip(df_d.columns,vals)), attrs=ds_h.attrs)
     return ds_d
 

{pypromice-1.4.0 → pypromice-1.4.2}/src/pypromice/utilities/git.py

@@ -7,12 +7,16 @@ import logging
 logger = logging.getLogger(__name__)
 
 
-def get_commit_hash_and_check_dirty(file_path) -> str:
-    repo_path = Path(file_path).parent
+def get_commit_hash_and_check_dirty(file_path: str | Path) -> str:
+    if isinstance(file_path, str):
+        file_path = Path(file_path)
+    if file_path.is_dir():
+        repo_path = file_path
+    else:
+        repo_path = file_path.parent
 
     try:
         # Ensure the file path is relative to the repository
-        relative_file_path = os.path.relpath(file_path, repo_path)
 
         # Get the latest commit hash for the file
         commit_hash = (
@@ -25,8 +29,6 @@ def get_commit_hash_and_check_dirty(file_path) -> str:
                     "-n",
                     "1",
                     "--pretty=format:%H",
-                    #"--",
-                    #relative_file_path,
                 ],
                 stderr=subprocess.STDOUT,
             )
@@ -49,12 +51,11 @@ def get_commit_hash_and_check_dirty(file_path) -> str:
 
         if is_dirty:
             logger.warning(f"Warning: The file {file_path} is dirty compared to the last commit. {commit_hash}")
-            return 'unknown'
+            return f'{commit_hash} (dirty)'
         if commit_hash == "":
             logger.warning(f"Warning: The file {file_path} is not under version control.")
             return 'unknown'
 
-        print(f"Commit hash: {commit_hash}")
         return commit_hash
     except subprocess.CalledProcessError as e:
         logger.warning(f"Error: {e.output.decode('utf-8')}")

{pypromice-1.4.0 → pypromice-1.4.2/src/pypromice.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pypromice
-Version: 1.4.0
+Version: 1.4.2
 Summary: PROMICE/GC-Net data processing toolbox
 Home-page: https://github.com/GEUS-Glaciology-and-Climate/pypromice
 Author: GEUS Glaciology and Climate
@@ -15,7 +15,7 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
 Classifier: Topic :: Scientific/Engineering
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.8
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
 Requires-Dist: numpy~=1.23