disdrodb 0.1.5__tar.gz → 0.2.1__tar.gz

{disdrodb-0.1.5 → disdrodb-0.2.1}/.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 ---
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
       - id: trailing-whitespace
       - id: end-of-file-fixer
@@ -12,17 +12,17 @@ repos:
       - id: check-ast
       - id: check-added-large-files
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.9
+    rev: v0.13.2
     hooks:
       - id: ruff
         args: [--fix]
   - repo: https://github.com/psf/black
-    rev: 25.1.0
+    rev: 25.9.0
     hooks:
       - id: black
         language_version: python3
   - repo: https://github.com/keewis/blackdoc
-    rev: v0.3.9
+    rev: v0.4.2
     hooks:
       - id: blackdoc
         additional_dependencies: ["black[jupyter]"]
@@ -38,7 +38,7 @@ repos:
         types_or: [python, markdown, rst]
         additional_dependencies: [tomli]
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.19.1
+    rev: v3.20.0
     hooks:
       - id: pyupgrade
   - repo: https://github.com/MarcoGorelli/madforhooks

{disdrodb-0.1.5 → disdrodb-0.2.1}/CONTRIBUTING.rst

@@ -118,7 +118,7 @@ Please define the name of your branch based on the scope of the contribution. Tr
 
 
 \* Guidelines for the ``<data_source>``
-- 	We use the institution name when campaign data spans more than 1 country (i.e. ARM, GPM)
+- 	We use the institution name when campaign data spans more than 1 country (i.e. ARM, NASA)
 - 	We use the country name when all campaigns (or sensor networks) are inside a given country.
 
 

{disdrodb-0.1.5/disdrodb.egg-info → disdrodb-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: disdrodb
-Version: 0.1.5
+Version: 0.2.1
 Summary: disdrodb provides tools to download, standardize, share and analyze global disdrometer data.
 Author: Gionata Ghiggi
 Project-URL: homepage, https://github.com/ltelab/disdrodb

{disdrodb-0.1.5 → disdrodb-0.2.1}/disdrodb/__init__.py

@@ -39,8 +39,6 @@ from disdrodb.configs import (
     define_configs,
     get_data_archive_dir,
     get_metadata_archive_dir,
-    get_model_options,
-    get_product_options,
     get_scattering_table_dir,
 )
 from disdrodb.data_transfer.download_data import download_archive, download_station
@@ -145,8 +143,6 @@ __all__ = [
     "generate_l2m",
     "get_data_archive_dir",
     "get_metadata_archive_dir",
-    "get_model_options",
-    "get_product_options",
     "get_reader",
     "get_scattering_table_dir",
     "get_station_reader",
@@ -177,7 +173,7 @@ __all__ = [
 ]
 
 
-__root_path__ = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))
+package_dir = os.path.dirname(os.path.realpath(__file__))
 
 
 def is_pytmatrix_available():

{disdrodb-0.1.5 → disdrodb-0.2.1}/disdrodb/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.5'
-__version_tuple__ = version_tuple = (0, 1, 5)
+__version__ = version = '0.2.1'
+__version_tuple__ = version_tuple = (0, 2, 1)
 
-__commit_id__ = commit_id = 'g71d96e131'
+__commit_id__ = commit_id = 'g0693c3a0e'

{disdrodb-0.1.5 → disdrodb-0.2.1}/disdrodb/accessor/methods.py

@@ -64,6 +64,13 @@ class DISDRODB_Base_Accessor:
 
         return get_diameter_bin_edges(self._obj)
 
+    @property
+    def velocity_bin_edges(self):
+        """Return velocity bin edges."""
+        from disdrodb.utils.manipulations import get_velocity_bin_edges
+
+        return get_velocity_bin_edges(self._obj)
+
     def regularize(self):
         """Regularize timesteps."""
         from disdrodb.utils.time import regularize_dataset
@@ -89,6 +96,12 @@ class DISDRODB_Base_Accessor:
 
         return align(self._obj, *args)
 
+    def plot_spectrum(self, **kwargs):
+        """Plot spectrum."""
+        from disdrodb.viz.plots import plot_spectrum
+
+        return plot_spectrum(self._obj, **kwargs)
+
 
 @xr.register_dataset_accessor("disdrodb")
 class DISDRODB_Dataset_Accessor(DISDRODB_Base_Accessor):
@@ -97,7 +110,7 @@ class DISDRODB_Dataset_Accessor(DISDRODB_Base_Accessor):
     def __init__(self, xarray_obj):
         super().__init__(xarray_obj)
 
-    def resample(self, accumulation_interval, rolling=True):
+    def resample(self, temporal_resolution):
         """Resample a L1 or L2 DISDRODB Product."""
         from disdrodb.l1.resampling import resample_dataset
 
@@ -105,8 +118,7 @@ class DISDRODB_Dataset_Accessor(DISDRODB_Base_Accessor):
         ds = resample_dataset(
             self._obj,
             sample_interval=sample_interval,
-            accumulation_interval=accumulation_interval,
-            rolling=rolling,
+            temporal_resolution=temporal_resolution,
         )
         return ds
 
@@ -114,7 +126,13 @@ class DISDRODB_Dataset_Accessor(DISDRODB_Base_Accessor):
         """Plot drop number concentration N(D) timeseries."""
         from disdrodb.viz.plots import plot_nd
 
-        plot_nd(self._obj, **kwargs)
+        return plot_nd(self._obj, **kwargs)
+
+    def plot_raw_and_filtered_spectra(self, **kwargs):
+        """Plot the raw and filtered spectra."""
+        from disdrodb.viz.plots import plot_raw_and_filtered_spectra
+
+        return plot_raw_and_filtered_spectra(self._obj, **kwargs)
 
 
 @xr.register_dataarray_accessor("disdrodb")

{disdrodb-0.1.5 → disdrodb-0.2.1}/disdrodb/api/checks.py

@@ -154,6 +154,16 @@ def check_rolling(rolling):
         raise TypeError("'rolling' must be a boolean.")
 
 
+def check_temporal_resolution(temporal_resolution):
+    """Check temporal resolution validity."""
+    from disdrodb.utils.time import get_sampling_information
+
+    if not isinstance(temporal_resolution, str):
+        raise TypeError("'temporal_resolution' must be a string.")
+    # If correct, the follow should not raise error
+    _ = get_sampling_information(temporal_resolution)
+
+
 def check_folder_partitioning(folder_partitioning):
     """
     Check if the given folder partitioning scheme is valid.

{disdrodb-0.1.5 → disdrodb-0.2.1}/disdrodb/api/io.py

@@ -40,6 +40,7 @@ from disdrodb.api.path import (
     define_station_dir,
 )
 from disdrodb.l0.l0_reader import define_readers_directory
+from disdrodb.utils.dict import extract_product_kwargs
 from disdrodb.utils.directories import list_files
 from disdrodb.utils.logger import (
     log_info,
@@ -117,7 +118,7 @@ def filter_by_time(filepaths, start_time=None, end_time=None):
     start_time, end_time = check_start_end_time(start_time, end_time)
 
     # -------------------------------------------------------------------------.
-    # - Retrieve start_time and end_time of GPM granules
+    # - Retrieve files start_time and end_time
     l_start_time, l_end_time = get_start_end_time_from_filepaths(filepaths)
 
     # -------------------------------------------------------------------------.
@@ -165,12 +166,9 @@ def find_files(
 
     Other Parameters
     ----------------
-    sample_interval : int, optional
-        The sampling interval in seconds of the product.
-        It must be specified only for product L2E and L2M !
-    rolling : bool, optional
-        Whether the dataset has been resampled by aggregating or rolling.
-        It must be specified only for product L2E and L2M !
+    temporal_resolution : str, optional
+        The temporal resolution of the product (e.g., "1MIN", "10MIN", "1H").
+        It must be specified only for product L1, L2E and L2M !
     model_name : str
         The model name of the statistical distribution for the DSD.
         It must be specified only for product L2M !
@@ -349,6 +347,7 @@ def open_netcdf_files(
     ds = xr.open_mfdataset(
         filepaths,
         chunks=chunks,
+        data_vars="all",
         combine="nested",
         join="outer",
         concat_dim="time",
@@ -357,7 +356,7 @@ def open_netcdf_files(
         preprocess=preprocess,
         compat="no_conflicts",
         combine_attrs="override",
-        coords="different",  # maybe minimal?
+        coords="different",  # maybe minimal? would remove lon/lat/alt?
         decode_timedelta=False,
         cache=False,
         autoclose=True,
@@ -411,21 +410,19 @@ def open_dataset(
         The name of the station.
     product : str
         The name DISDRODB product.
-    sample_interval : int, optional
-        The sampling interval in seconds of the product.
-        It must be specified only for product L2E and L2M !
-    rolling : bool, optional
-        Whether the dataset has been resampled by aggregating or rolling.
-        It must be specified only for product L2E and L2M !
-    model_name : str
-        The model name of the statistical distribution for the DSD.
-        It must be specified only for product L2M !
     debugging_mode : bool, optional
         If ``True``, it select maximum 3 files for debugging purposes.
         The default value is ``False``.
     data_archive_dir : str, optional
         The base directory of DISDRODB, expected in the format ``<...>/DISDRODB``.
         If not specified, the path specified in the DISDRODB active configuration will be used.
+    **product_kwargs : optional
+        DISDRODB product options
+        It must be specified only for product L1, L2E and L2M products !
+        For L1, L2E and L2M products, temporal_resolution is required
+        FOr L2M product, model_name is required.
+    **open_kwargs : optional
+        Additional keyword arguments passed to ``xarray.open_mfdataset()``.
 
     Returns
     -------
@@ -434,7 +431,8 @@ def open_dataset(
     """
     from disdrodb.l0.l0a_processing import read_l0a_dataframe
 
-    product_kwargs = product_kwargs if product_kwargs else {}
+    # Extract product kwargs from open_kwargs
+    product_kwargs = extract_product_kwargs(open_kwargs, product=product)
 
     # List product files
     filepaths = find_files(
@@ -478,6 +476,10 @@ def open_dataset(
         compute=compute,
         **open_kwargs,
     )
+
+    # Ensure coordinates in memory
+    # for coord in list(ds.coords):
+    #     ds[coord] = ds[coord].compute()
     return ds
 
 

{disdrodb-0.1.5 → disdrodb-0.2.1}/disdrodb/api/path.py

@@ -336,13 +336,13 @@ def define_issue_filepath(
 
 def define_config_dir(product):
     """Define the config directory path of a given DISDRODB product."""
-    from disdrodb import __root_path__
+    from disdrodb import package_dir
 
     if product.upper() in ["RAW", "L0A", "L0B"]:
         dir_name = "l0"
     else:
         raise NotImplementedError(f"Product {product} not implemented.")
-    config_dir = os.path.join(__root_path__, "disdrodb", dir_name, "configs")
+    config_dir = os.path.join(package_dir, dir_name, "configs")
     return config_dir
 
 
@@ -448,12 +448,9 @@ def define_product_dir_tree(
     ----------
     product : str
        The DISDRODB product. See ``disdrodb.available_products()``.
-    sample_interval : int, optional
-        The sampling interval in seconds of the product.
-        It must be specified only for product L2E and L2M !
-    rolling : bool, optional
-        Whether the dataset has been resampled by aggregating or rolling.
-        It must be specified only for product L2E and L2M !
+    temporal_resolution : str, optional
+        The temporal resolution of the product.
+        It must be specified only for product L1, L2E and L2M !
     model_name : str
         The custom model name of the fitted statistical distribution.
         It must be specified only for product L2M !
@@ -463,28 +460,23 @@ def define_product_dir_tree(
     data_dir : str
         Station data directory path
     """
-    from disdrodb.api.checks import check_product, check_product_kwargs, check_rolling, check_sample_interval
+    from disdrodb.api.checks import check_product, check_product_kwargs, check_temporal_resolution
 
     product = check_product(product)
     product_kwargs = check_product_kwargs(product, product_kwargs)
     if product.upper() == "RAW":
         return ""
-    if product.upper() in ["L0A", "L0B", "L0C", "L1"]:
+    if product.upper() in ["L0A", "L0B", "L0C"]:
         return ""
-    if product == "L2E":
-        rolling = product_kwargs.get("rolling")
-        sample_interval = product_kwargs.get("sample_interval")
-        check_rolling(rolling)
-        check_sample_interval(sample_interval)
-        temporal_resolution = define_temporal_resolution(seconds=sample_interval, rolling=rolling)
-        return os.path.join(temporal_resolution)
+    if product in ["L1", "L2E"]:
+        temporal_resolution = product_kwargs.get("temporal_resolution")
+        check_temporal_resolution(temporal_resolution)
+        return temporal_resolution
     # L2M if product == "L2M":
-    rolling = product_kwargs.get("rolling")
-    sample_interval = product_kwargs.get("sample_interval")
+    temporal_resolution = product_kwargs.get("temporal_resolution")
+    check_temporal_resolution(temporal_resolution)
     model_name = product_kwargs.get("model_name")
-    check_rolling(rolling)
-    check_sample_interval(sample_interval)
-    temporal_resolution = define_temporal_resolution(seconds=sample_interval, rolling=rolling)
+
     return os.path.join(model_name, temporal_resolution)
 
 
@@ -611,12 +603,9 @@ def define_data_dir(
         If not specified, the path specified in the DISDRODB active configuration will be used.
     check_exists : bool, optional
         Whether to check if the directory exists. The default value is ``False``.
-    sample_interval : int, optional
-        The sampling interval in seconds of the product.
-        It must be specified only for product L2E and L2M !
-    rolling : bool, optional
-        Whether the dataset has been resampled by aggregating or rolling.
-        It must be specified only for product L2E and L2M !
+    temporal_resolution : str, optional
+        The temporal resolution of the product.
+        It must be specified only for product L1, L2E and L2M !
     model_name : str
         The name of the fitted statistical distribution for the DSD.
         It must be specified only for product L2M !
@@ -701,11 +690,8 @@ def define_filename(
     end_time : datetime.datatime, optional
         End time.
         Required if add_time_period = True.
-    sample_interval : int, optional
-        The sampling interval in seconds of the product.
-        It must be specified only for product L0C, L1, L2E and L2M !
-    rolling : bool, optional
-        Whether the dataset has been resampled by aggregating or rolling.
+    temporal_resolution : str, optional
+        The temporal resolution of the product.
         It must be specified only for product L1, L2E and L2M !
     model_name : str
         The model name of the fitted statistical distribution for the DSD.
@@ -716,7 +702,7 @@ def define_filename(
     str
         L0B file name.
     """
-    from disdrodb.api.checks import check_product, check_product_kwargs
+    from disdrodb.api.checks import check_product, check_product_kwargs, check_temporal_resolution
 
     product = check_product(product)
     product_kwargs = check_product_kwargs(product, product_kwargs)
@@ -729,16 +715,9 @@ def define_filename(
     product_name = f"{product}"
 
     # L0C ... sample interval known only per-file
-    # L1 ... in future known a priori
-    # if product in ["L1"]:
-    #     # TODO: HACK FOR CURRENT L0C and L1 log files in create_product_logs
-    #     sample_interval = product_kwargs.get("sample_interval",  0)
-    #     temporal_resolution = define_temporal_resolution(seconds=sample_interval, rolling=False)
-    #     product_name = f"{product}.{temporal_resolution}"
-    if product in ["L2E", "L2M"]:
-        rolling = product_kwargs.get("rolling")
-        sample_interval = product_kwargs.get("sample_interval")
-        temporal_resolution = define_temporal_resolution(seconds=sample_interval, rolling=rolling)
+    if product in ["L1", "L2E", "L2M"]:
+        temporal_resolution = product_kwargs.get("temporal_resolution")
+        check_temporal_resolution(temporal_resolution)
         product_name = f"{product}.{temporal_resolution}"
     if product in ["L2M"]:
         model_name = product_kwargs.get("model_name")
@@ -828,7 +807,7 @@ def define_l0b_filename(ds, campaign_name: str, station_name: str) -> str:
 
 def define_l0c_filename(ds, campaign_name: str, station_name: str) -> str:
     """Define L0C file name."""
-    # TODO: add sample_interval as function argument    s
+    # TODO: add sample_interval as function argument
     sample_interval = int(ensure_sample_interval_in_seconds(ds["sample_interval"]).data.item())
     temporal_resolution = define_temporal_resolution(sample_interval, rolling=False)
     starting_time, ending_time = get_file_start_end_time(ds)
@@ -839,37 +818,26 @@ def define_l0c_filename(ds, campaign_name: str, station_name: str) -> str:
     return filename
 
 
-def define_l1_filename(ds, campaign_name, station_name: str) -> str:
+def define_l1_filename(ds, campaign_name, station_name: str, temporal_resolution: str) -> str:
     """Define L1 file name."""
-    # TODO: add sample_interval and rolling as function argument
-
     starting_time, ending_time = get_file_start_end_time(ds)
-    sample_interval = int(ensure_sample_interval_in_seconds(ds["sample_interval"]).data.item())
-    temporal_resolution = define_temporal_resolution(sample_interval, rolling=False)
-    starting_time, ending_time = get_file_start_end_time(ds)
-    starting_time = starting_time.strftime("%Y%m%d%H%M%S")
-    ending_time = ending_time.strftime("%Y%m%d%H%M%S")
-    version = ARCHIVE_VERSION
-    filename = f"L1.{temporal_resolution}.{campaign_name}.{station_name}.s{starting_time}.e{ending_time}.{version}.nc"
-
-    # filename = define_filename(
-    #     product="L1",
-    #     campaign_name=campaign_name,
-    #     station_name=station_name,
-    #     # Filename options
-    #     start_time=starting_time,
-    #     end_time=ending_time,
-    #     add_version=True,
-    #     add_time_period=True,
-    #     add_extension=True,
-    #     # Product options
-    #     # sample_interval=sample_interval,
-    #     # rolling=rolling,
-    # )
+    filename = define_filename(
+        product="L1",
+        campaign_name=campaign_name,
+        station_name=station_name,
+        # Filename options
+        start_time=starting_time,
+        end_time=ending_time,
+        add_version=True,
+        add_time_period=True,
+        add_extension=True,
+        # Product options
+        temporal_resolution=temporal_resolution,
+    )
     return filename
 
 
-def define_l2e_filename(ds, campaign_name: str, station_name: str, sample_interval: int, rolling: bool) -> str:
+def define_l2e_filename(ds, campaign_name: str, station_name: str, temporal_resolution: str) -> str:
     """Define L2E file name."""
     starting_time, ending_time = get_file_start_end_time(ds)
     filename = define_filename(
@@ -883,8 +851,7 @@ def define_l2e_filename(ds, campaign_name: str, station_name: str, sample_interv
         add_time_period=True,
         add_extension=True,
         # Product options
-        sample_interval=sample_interval,
-        rolling=rolling,
+        temporal_resolution=temporal_resolution,
     )
     return filename
 
@@ -893,8 +860,7 @@ def define_l2m_filename(
     ds,
     campaign_name: str,
     station_name: str,
-    sample_interval: int,
-    rolling: bool,
+    temporal_resolution: str,
     model_name: str,
 ) -> str:
     """Define L2M file name."""
@@ -910,8 +876,7 @@ def define_l2m_filename(
         add_time_period=True,
         add_extension=True,
         # Product options
-        sample_interval=sample_interval,
-        rolling=rolling,
+        temporal_resolution=temporal_resolution,
         model_name=model_name,
     )
     return filename