Update docstrings

ltelab · Jun 5, 2024 · d537d98 · d537d98
1 parent 6841233
commit d537d98
Show file tree

Hide file tree

Showing 14 changed files with 126 additions and 76 deletions.
diff --git a/disdrodb/api/checks.py b/disdrodb/api/checks.py
@@ -323,7 +323,7 @@ def check_valid_campaign_dir(campaign_dir):
 
     Used to check validity of ``raw_dir`` and ``processed_dir``.
 
-    The path must be ``*/DISDRODB/<Raw/Processed>/<DATA_SOURCE>/<CAMPAIGN_NAME>``
+    The path must be ``/DISDRODB/<Raw/Processed>/<DATA_SOURCE>/<CAMPAIGN_NAME>``.
     """
     last_component = os.path.basename(campaign_dir)
     tree_components = infer_disdrodb_tree_path_components(campaign_dir)

diff --git a/disdrodb/api/configs.py b/disdrodb/api/configs.py
@@ -93,7 +93,7 @@ def read_config_file(sensor_name: str, product: str, filename: str) -> dict:
     return dictionary
 
 
-def available_sensor_names(product: str = "L0A") -> sorted:
+def available_sensor_names(product: str = "L0A") -> list:
     """Get available names of sensors.
 
     Returns

diff --git a/disdrodb/api/path.py b/disdrodb/api/path.py
@@ -396,7 +396,7 @@ def define_l0a_filename(df, processed_dir, station_name: str) -> str:
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         L0A DataFrame
     processed_dir : str
         Path of the processed directory
@@ -425,7 +425,7 @@ def define_l0b_filename(ds, processed_dir, station_name: str) -> str:
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         L0B xarray Dataset
     processed_dir : str
         Path of the processed directory
@@ -454,7 +454,7 @@ def define_l0a_filepath(df: pd.DataFrame, processed_dir: str, station_name: str)
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         L0A DataFrame.
     processed_dir : str
         Path of the processed directory.
@@ -477,7 +477,7 @@ def define_l0b_filepath(ds: xr.Dataset, processed_dir: str, station_name: str, l
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         L0B xarray Dataset.
     processed_dir : str
         Path of the processed directory.

diff --git a/disdrodb/l0/check_standards.py b/disdrodb/l0/check_standards.py
@@ -90,7 +90,7 @@ def _check_raw_fields_available(df: pd.DataFrame, sensor_name: str, verbose: boo
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Dataframe
     sensor_name : str
         Name of the sensor.
@@ -124,7 +124,7 @@ def check_l0a_column_names(df: pd.DataFrame, sensor_name: str) -> None:
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     sensor_name : str
         Name of the sensor.
@@ -165,7 +165,7 @@ def check_l0a_standards(df: pd.DataFrame, sensor_name: str, verbose: bool = True
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         L0A dataframe.
     sensor_name : str
         Name of the sensor.

diff --git a/disdrodb/l0/l0_processing.py b/disdrodb/l0/l0_processing.py
@@ -385,38 +385,29 @@ def run_l0a(
         The path should have the following structure: ``<...>/DISDRODB/Processed/<DATA_SOURCE>/<CAMPAIGN_NAME>``.
         For testing purposes, this function exceptionally accepts also a directory path simply ending
         with ``<CAMPAIGN_NAME>`` (e.g., ``/tmp/<CAMPAIGN_NAME>``).
-
     station_name : str
-    The name of the station.
-
+        The name of the station.
     glob_patterns : str
         Glob pattern to search for data files in ``<raw_dir>/data/<station_name>``.
-
     column_names : list
         Column names of the raw text file.
-
     reader_kwargs : dict
         Arguments for Pandas ``read_csv`` function to open the text file.
-
     df_sanitizer_fun : callable, optional
         Sanitizer function to format the DataFrame into DISDRODB L0A standard.
         Default is ``None``.
-
     parallel : bool, optional
         If ``True``, process the files simultaneously in multiple processes.
         The number of simultaneous processes can be customized using the ``dask.distributed.LocalCluster``.
         If ``False``, process the files sequentially in a single process.
         Default is ``False``.
-
     verbose : bool, optional
         If ``True``, print detailed processing information to the terminal.
         Default is ``False``.
-
     force : bool, optional
         If ``True``, overwrite existing data in destination directories.
         If ``False``, raise an error if data already exists in destination directories.
         Default is ``False``.
-
     debugging_mode : bool, optional
         If ``True``, reduce the amount of data to process.
         Processes only the first 100 rows of 3 raw data files.
@@ -519,33 +510,27 @@ def run_l0b(
         - The ``<CAMPAIGN_NAME>`` must semantically match between:
             - the ``raw_dir`` and ``processed_dir`` directory paths;
             - with the key ``campaign_name`` within the metadata YAML files.
-
     processed_dir : str
         The desired directory path for the processed DISDRODB L0A and L0B products.
         The path should have the following structure: ``<...>/DISDRODB/Processed/<DATA_SOURCE>/<CAMPAIGN_NAME>``.
         For testing purposes, this function exceptionally accepts also a directory path simply ending
         with ``<CAMPAIGN_NAME>`` (e.g., ``/tmp/<CAMPAIGN_NAME>``).
-
     station_name : str
         The name of the station.
-
     force : bool, optional
         If ``True``, overwrite existing data in destination directories.
         If ``False``, raise an error if data already exists in destination directories.
         Default is ``False``.
-
     verbose : bool, optional
         If ``True``, print detailed processing information to the terminal.
         Default is ``True``.
-
     parallel : bool, optional
         If ``True``, process the files simultaneously in multiple processes.
         The number of simultaneous processes can be customized using the ``dask.distributed.LocalCluster``.
         Ensure that the ``threads_per_worker`` (number of thread per process) is set to 1 to avoid HDF errors.
         Also, ensure to set the ``HDF5_USE_FILE_LOCKING`` environment variable to ``False``.
         If ``False``, process the files sequentially in a single process.
         Default is ``False``.
-
     debugging_mode : bool, optional
         If ``True``, reduce the amount of data to process.
         Only the first 3 raw data files will be processed.

diff --git a/disdrodb/l0/l0a_processing.py b/disdrodb/l0/l0a_processing.py
@@ -159,7 +159,7 @@ def remove_rows_with_missing_time(df: pd.DataFrame, verbose: bool = False):
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     verbose : bool
         Whether to verbose the processing. The default is ``False``.
@@ -193,7 +193,7 @@ def remove_duplicated_timesteps(df: pd.DataFrame, verbose: bool = False):
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     verbose : bool
         Whether to verbose the processing. The default is ``False``.
@@ -251,7 +251,7 @@ def remove_issue_timesteps(df, issue_dict, verbose=False):
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     issue_dict : dict
         Issue dictionary.
@@ -293,7 +293,7 @@ def cast_column_dtypes(df: pd.DataFrame, sensor_name: str) -> pd.DataFrame:
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     sensor_name : str
         Name of the sensor.
@@ -330,7 +330,7 @@ def coerce_corrupted_values_to_nan(df: pd.DataFrame, sensor_name: str) -> pd.Dat
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     sensor_name : str
         Name of the sensor.
@@ -361,7 +361,7 @@ def strip_string_spaces(df: pd.DataFrame, sensor_name: str) -> pd.DataFrame:
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     sensor_name : str
         Name of the sensor.
@@ -456,7 +456,7 @@ def replace_nan_flags(df, sensor_name, verbose=False):
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     sensor_name : str
         Name of the sensor.
@@ -491,7 +491,7 @@ def set_nan_outside_data_range(df, sensor_name, verbose=False):
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     sensor_name : str
         Name of the sensor.
@@ -530,7 +530,7 @@ def set_nan_invalid_values(df, sensor_name, verbose=False):
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     sensor_name : str
         Name of the sensor.
@@ -679,7 +679,7 @@ def write_l0a(
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe.
     filepath : str
         Output file path.

diff --git a/disdrodb/l0/l0b_nc_processing.py b/disdrodb/l0/l0b_nc_processing.py
@@ -141,7 +141,7 @@ def preprocess_raw_netcdf(ds, dict_names, sensor_name):
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Raw netCDF to be converted to DISDRODB standards.
     dict_names : dict
         Dictionary mapping raw netCDF variables/coordinates/dimension names
@@ -151,7 +151,7 @@ def preprocess_raw_netcdf(ds, dict_names, sensor_name):
 
     Returns
     -------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         xarray Dataset with variables compliant to DISDRODB conventions.
 
     """
@@ -185,7 +185,7 @@ def replace_custom_nan_flags(ds, dict_nan_flags, verbose=False):
 
     Parameters
     ----------
-    df : xr.Dataset
+    df  : xarray.Dataset
         Input xarray dataset
     dict_nan_flags : dict
         Dictionary with nan flags value to set as ``np.nan``.
@@ -218,7 +218,7 @@ def replace_nan_flags(ds, sensor_name, verbose):
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Input xarray dataset
     dict_nan_flags : dict
         Dictionary with nan flags value to set as np.nan
@@ -242,7 +242,7 @@ def set_nan_outside_data_range(ds, sensor_name, verbose):
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Input xarray dataset
     sensor_name : str
         Name of the sensor.
@@ -280,7 +280,7 @@ def set_nan_invalid_values(ds, sensor_name, verbose):
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Input xarray dataset
     sensor_name : str
         Name of the sensor.
@@ -323,7 +323,7 @@ def create_l0b_from_raw_nc(
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Raw xarray dataset
     dict_names : dict
         Dictionary mapping raw netCDF variables/coordinates/dimension names

diff --git a/disdrodb/l0/l0b_processing.py b/disdrodb/l0/l0b_processing.py
@@ -203,7 +203,7 @@ def retrieve_l0b_arrays(
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         Input dataframe
     sensor_name : str
         Name of the sensor
@@ -287,7 +287,7 @@ def _convert_object_variables_to_string(ds: xr.Dataset) -> xr.Dataset:
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Input dataset.
 
     Returns
@@ -306,7 +306,7 @@ def _set_variable_attributes(ds: xr.Dataset, sensor_name: str) -> xr.Dataset:
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Input dataset.
     sensor_name : str
         Name of the sensor.
@@ -431,7 +431,7 @@ def create_l0b_from_l0a(
 
     Parameters
     ----------
-    df : pd.DataFrame
+    df : pandas.DataFrame
         DISDRODB L0A dataframe.
     attrs : dict
         Station metadata.
@@ -503,7 +503,7 @@ def sanitize_encodings_dict(encoding_dict: dict, ds: xr.Dataset) -> dict:
     ----------
     encoding_dict : dict
         Dictionary containing the encoding to write DISDRODB L0B netCDFs.
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Input dataset.
 
     Returns
@@ -525,7 +525,7 @@ def rechunk_dataset(ds: xr.Dataset, encoding_dict: dict) -> xr.Dataset:
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Input xarray dataset
     encoding_dict : dict
         Dictionary containing the encoding to write the xarray dataset as a netCDF.
@@ -549,7 +549,7 @@ def set_encodings(ds: xr.Dataset, sensor_name: str) -> xr.Dataset:
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Input xarray dataset.
     sensor_name : str
         Name of the sensor.
@@ -585,7 +585,7 @@ def write_l0b(ds: xr.Dataset, filepath: str, force=False) -> None:
 
     Parameters
     ----------
-    ds : xr.Dataset
+    ds  : xarray.Dataset
         Input xarray dataset.
     filepath : str
         Output file path.