disdrodb 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

disdrodb/l0/readers/PWS100/FRANCE/ENPC_PWS100.py

@@ -17,12 +17,112 @@
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
 """DISDRODB reader for ENPC PWS100 raw text data."""
-import zipfile
-
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
-from disdrodb.utils.logger import log_error, log_warning
+from disdrodb.utils.logger import log_error  # , log_warning
+
+
+def read_txt_file(file, filename, logger):
+    r"""Parse a single txt file within the daily zip file.
+
+    The file starts with \\x020 and ends with \\x03\\r\\n.
+    """
+    # Read file
+    try:
+        txt = file.readline().decode("utf-8")
+    except Exception:
+        log_error(logger=logger, msg=f"{filename} is corrupted", verbose=False)
+        return None
+
+    # Check file is not empty
+    if txt == "":
+        log_error(logger=logger, msg=f"{filename} is empty", verbose=False)
+        return None
+
+    # Remove everything before \x020
+    # - At start it can appear: \x013 0 \x02PSU voltage too low 13.3\x03\r\n\
+    txt = txt.split("x020 ", 1)[-1]
+
+    # Remove everything after \\x03
+    txt = txt.split("x03", 1)[0]
+
+    # if "PSU voltage too low" in txt or "volt" in txt:
+    #     log_warning(logger=logger, msg=f"PSU voltage too low in {filename}", verbose=False)
+    #     return None
+
+    # if "Error - message" in txt:
+    #     log_warning(logger=logger, msg=f"Error message in {filename}", verbose=False)
+    #     return None
+
+    # Clean up the line
+    txt = txt.replace(" 00 ", " 0 0 ")
+    txt = txt.replace("  ", " 0 ")
+
+    # Split the cleaned line
+    buf = txt.split(" ")
+
+    # Helper to convert list of floats to comma-separated string
+    def int_list_to_str(lst):
+        return ",".join(f"{int(i)}" for i in lst)
+
+    # Try to get the drop_size distribution:
+    try:
+        drop_size_distribution = int_list_to_str(buf[29:329])  # Drop size distribution (message field 42)
+    except Exception:
+        log_error(logger, msg=f"Corrupted drop_size_distribution field in {filename}", verbose=False)
+        return None
+
+    # Try to get peak_to_pedestal_hist
+    try:
+        peak_to_pedestal_hist = int_list_to_str(buf[1498:1548])
+    except Exception:
+        log_error(
+            logger,
+            msg=f"Corrupted raw_drop_number or peak_to_pedestal_hist field in {filename}",
+            verbose=False,
+        )
+        return None
+
+    # Parse fields
+    data = {
+        "mor_visibility": float(buf[1]),  # Visibility Range (message field 20)
+        "weather_code_synop_4680": float(buf[2]),  # Present Weather Code (WMO)  (message field 21)
+        "weather_code_metar_4678": buf[3],  # Present Weather Code (METAR)  (message field 22)
+        "weather_code_nws": buf[4],  # Present Weather Code (NWS)  (message field 23)
+        "alarms": int_list_to_str(buf[5:21]),  # Alarms (message field (24))
+        "sensor_status": buf[21],  # Fault status of PWS100 (message field 25)
+        "air_temperature": float(buf[22]),  # Temperature (°C) (message field 30)
+        "relative_humidity": float(buf[23]),  # Sampled relative humidity (%) (message field 30)
+        "wetbulb_temperature": float(buf[24]),  # Average wetbulb temperature (°C)(message field 30)
+        "air_temperature_max": float(buf[25]),  # Maximum temperature (°C)(message field 31)
+        "air_temperature_min": float(buf[26]),  # Minimum temperature (°C)(message field 31)
+        "rainfall_rate": float(buf[27]),  # Precipitation rate (mm/h)(message field 40)
+        "rainfall_accumulated": float(buf[28]),  # Precipitation accumulation (mm/h)(message field 41)
+        "drop_size_distribution": drop_size_distribution,  # Drop size distribution (message field 42)
+        "average_drop_velocity": float(buf[329]),  # Average velocity (mm/s)(message field 43)
+        "average_drop_size": float(buf[330]),  # Average size (mm/h)(message field 43)
+        "type_distribution": int_list_to_str(buf[331:342]),  # Type distribution (message field 44)
+        "raw_drop_number": int_list_to_str(buf[342:1498]),  # Size/velocity spectrum (34*34) (message field 47)
+        "peak_to_pedestal_hist": (
+            peak_to_pedestal_hist  # Peak to pedestal ratio distribution histogram (message field 48)
+        ),
+    }
+
+    # Convert to single-row DataFrame
+    df = pd.DataFrame([data])
+
+    # Define datetime "time" column from filename
+    datetime_str = " ".join(filename.replace(".txt", "").split("_")[-6:])
+    df["time"] = pd.to_datetime(datetime_str, format="%Y %m %d %H %M %S")
+
+    # # Drop columns not agreeing with DISDRODB L0 standards
+    # columns_to_drop = [
+    #      "peak_to_pedestal_hist",
+    #      "type_distribution",
+    # ]
+    # df = df.drop(columns=columns_to_drop)
+    return df
 
 
 @is_documented_by(reader_generic_docstring)
@@ -31,102 +131,9 @@ def reader(
     logger=None,
 ):
     """Reader."""
+    import zipfile
 
-    ##------------------------------------------------------------------------.
-    #### Define function to read each txt file inside each daily zip file
-    def read_txt_file(file, filename, logger):  # noqa PLR0911
-        """Parse a single txt file within the daily zip file."""
-        # Read file
-        try:
-            txt = file.readline().decode("utf-8")
-        except Exception:
-            log_warning(logger=logger, msg=f"{filename} is corrupted", verbose=False)
-            return None
-
-        # Check file is not empty
-        if txt == "":
-            log_warning(logger=logger, msg=f"{filename} is empty", verbose=False)
-            return None
-
-        if "PSU voltage too low" in txt or "volt" in txt:
-            log_warning(logger=logger, msg=f"PSU voltage too low in {filename}", verbose=False)
-            return None
-
-        if "Error - message" in txt:
-            log_warning(logger=logger, msg=f"Error message in {filename}", verbose=False)
-            return None
-
-        # Clean up the line
-        txt = txt.replace(" 00 ", " 0 0 ")
-        txt = txt.replace("  ", " 0 ")
-        txt = txt[1:-8]
-
-        # Split the cleaned line
-        buf = txt.split(" ")
-
-        # Helper to convert list of floats to comma-separated string
-        def int_list_to_str(lst):
-            return ",".join(f"{int(i)}" for i in lst)
-
-        # Try to get the drop_size distribution:
-        try:
-            drop_size_distribution = int_list_to_str(buf[30:330])  # Drop size distribution (message field 42)
-        except Exception:
-            log_warning(logger, msg=f"Corrupted drop_size_distribution field in {filename}", verbose=False)
-            return None
-
-        # Try to get peak_to_pedestal_hist
-        try:
-            peak_to_pedestal_hist = int_list_to_str(buf[1499:1549])
-        except Exception:
-            log_warning(
-                logger,
-                msg=f"Corrupted raw_drop_number or peak_to_pedestal_hist field in {filename}",
-                verbose=False,
-            )
-            return None
-        # Parse fields
-        data = {
-            "mor_visibility": float(buf[2]),  # Visibility Range (message field 20)
-            "weather_code_synop_4680": float(buf[3]),  # Present Weather Code (WMO)  (message field 21)
-            "weather_code_metar_4678": buf[4],  # Present Weather Code (METAR)  (message field 22)
-            "weather_code_nws": buf[5],  # Present Weather Code (NWS)  (message field 23)
-            "alarms": int_list_to_str(buf[6:22]),  # Alarms (message field (24))
-            "sensor_status": buf[22],  # Fault status of PWS100 (message field 25)
-            "air_temperature": float(buf[23]),  # Temperature (°C) (message field 30)
-            "relative_humidity": float(buf[24]),  # Sampled relative humidity (%) (message field 30)
-            "wetbulb_temperature": float(buf[25]),  # Average wetbulb temperature (°C)(message field 30)
-            "air_temperature_max": float(buf[26]),  # Maximum temperature (°C)(message field 31)
-            "air_temperature_min": float(buf[27]),  # Minimum temperature (°C)(message field 31)
-            "rainfall_rate": float(buf[28]),  # Precipitation rate (mm/h)(message field 40)
-            "rainfall_accumulated": float(buf[29]),  # Precipitation accumulation (mm/h)(message field 41)
-            "drop_size_distribution": drop_size_distribution,  # Drop size distribution (message field 42)
-            "average_drop_velocity": float(buf[330]),  # Average velocity (mm/s)(message field 43)
-            "average_drop_size": float(buf[331]),  # Average size (mm/h)(message field 43)
-            "type_distribution": int_list_to_str(buf[332:343]),  # Type distribution (message field 44)
-            "raw_drop_number": int_list_to_str(buf[343:1499]),  # Size/velocity spectrum (34*34) (message field 47)
-            "peak_to_pedestal_hist": (
-                peak_to_pedestal_hist  # Peak to pedestal ratio distribution histogram (message field 48)
-            ),
-        }
-
-        # Convert to single-row DataFrame
-        df = pd.DataFrame([data])
-
-        # Define datetime "time" column from filename
-        datetime_str = " ".join(filename.replace(".txt", "").split("_")[-6:])
-        df["time"] = pd.to_datetime(datetime_str, format="%Y %m %d %H %M %S")
-
-        # # Drop columns not agreeing with DISDRODB L0 standards
-        # columns_to_drop = [
-        #      "peak_to_pedestal_hist",
-        #      "type_distribution",
-        # ]
-        # df = df.drop(columns=columns_to_drop)
-        return df
-
-    # ---------------------------------------------------------------------.
-    #### Iterate over all files (aka timesteps) in the daily zip archive
+    # Iterate over all files (aka timesteps) in the daily zip archive
     # - Each file contain a single timestep !
     list_df = []
     with zipfile.ZipFile(filepath, "r") as zip_ref:
@@ -146,5 +153,4 @@ def reader(
     # Concatenate all dataframes into a single one
     df = pd.concat(list_df)
 
-    # ---------------------------------------------------------------------.
     return df

disdrodb/l0/readers/PWS100/FRANCE/ENPC_PWS100_SIRTA.py

@@ -0,0 +1,151 @@
+# -----------------------------------------------------------------------------.
+# Copyright (c) 2021-2023 DISDRODB developers
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# -----------------------------------------------------------------------------.
+"""DISDRODB reader for ENPC PWS100 raw text data."""
+import zipfile
+
+import pandas as pd
+
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.utils.logger import log_error  # , log_warning
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+
+    ##------------------------------------------------------------------------.
+    #### Define function to read each txt file inside each daily zip file
+    def read_txt_file(file, filename, logger):
+        r"""Parse a single txt file within the daily zip file.
+
+        The file starts with \x020 and ends with \x03\r\r\n.
+        """
+        # Read file
+        try:
+            txt = file.readline().decode("utf-8")
+        except Exception:
+            log_error(logger=logger, msg=f"{filename} is corrupted", verbose=False)
+            return None
+
+        # Check file is not empty
+        if txt == "":
+            log_error(logger=logger, msg=f"{filename} is empty", verbose=False)
+            return None
+
+        # if "PSU voltage too low" in txt or "volt" in txt:
+        #     log_warning(logger=logger, msg=f"PSU voltage too low in {filename}", verbose=False)
+        #     return None
+
+        # if "Error - message" in txt:
+        #     log_warning(logger=logger, msg=f"Error message in {filename}", verbose=False)
+        #     return None
+
+        # Clean up the line
+        txt = txt.replace(" 00 ", " 0 0 ")
+        txt = txt.replace("  ", " 0 ")
+        txt = txt[1:-8]
+
+        # Split the cleaned line
+        buf = txt.split(" ")
+
+        # Helper to convert list of floats to comma-separated string
+        def int_list_to_str(lst):
+            return ",".join(f"{int(i)}" for i in lst)
+
+        # Try to get the drop_size distribution:
+        try:
+            drop_size_distribution = int_list_to_str(buf[30:330])  # Drop size distribution (message field 42)
+        except Exception:
+            log_error(logger, msg=f"Corrupted drop_size_distribution field in {filename}", verbose=False)
+            return None
+
+        # Try to get peak_to_pedestal_hist
+        try:
+            peak_to_pedestal_hist = int_list_to_str(buf[1499:1549])
+        except Exception:
+            log_error(
+                logger,
+                msg=f"Corrupted raw_drop_number or peak_to_pedestal_hist field in {filename}",
+                verbose=False,
+            )
+            return None
+        # Parse fields
+        data = {
+            "mor_visibility": float(buf[2]),  # Visibility Range (message field 20)
+            "weather_code_synop_4680": float(buf[3]),  # Present Weather Code (WMO)  (message field 21)
+            "weather_code_metar_4678": buf[4],  # Present Weather Code (METAR)  (message field 22)
+            "weather_code_nws": buf[5],  # Present Weather Code (NWS)  (message field 23)
+            "alarms": int_list_to_str(buf[6:22]),  # Alarms (message field (24))
+            "sensor_status": buf[22],  # Fault status of PWS100 (message field 25)
+            "air_temperature": float(buf[23]),  # Temperature (°C) (message field 30)
+            "relative_humidity": float(buf[24]),  # Sampled relative humidity (%) (message field 30)
+            "wetbulb_temperature": float(buf[25]),  # Average wetbulb temperature (°C)(message field 30)
+            "air_temperature_max": float(buf[26]),  # Maximum temperature (°C)(message field 31)
+            "air_temperature_min": float(buf[27]),  # Minimum temperature (°C)(message field 31)
+            "rainfall_rate": float(buf[28]),  # Precipitation rate (mm/h)(message field 40)
+            "rainfall_accumulated": float(buf[29]),  # Precipitation accumulation (mm/h)(message field 41)
+            "drop_size_distribution": drop_size_distribution,  # Drop size distribution (message field 42)
+            "average_drop_velocity": float(buf[330]),  # Average velocity (mm/s)(message field 43)
+            "average_drop_size": float(buf[331]),  # Average size (mm/h)(message field 43)
+            "type_distribution": int_list_to_str(buf[332:343]),  # Type distribution (message field 44)
+            "raw_drop_number": int_list_to_str(buf[343:1499]),  # Size/velocity spectrum (34*34) (message field 47)
+            "peak_to_pedestal_hist": (
+                peak_to_pedestal_hist  # Peak to pedestal ratio distribution histogram (message field 48)
+            ),
+        }
+
+        # Convert to single-row DataFrame
+        df = pd.DataFrame([data])
+
+        # Define datetime "time" column from filename
+        datetime_str = " ".join(filename.replace(".txt", "").split("_")[-6:])
+        df["time"] = pd.to_datetime(datetime_str, format="%Y %m %d %H %M %S")
+
+        # # Drop columns not agreeing with DISDRODB L0 standards
+        # columns_to_drop = [
+        #      "peak_to_pedestal_hist",
+        #      "type_distribution",
+        # ]
+        # df = df.drop(columns=columns_to_drop)
+        return df
+
+    # ---------------------------------------------------------------------.
+    #### Iterate over all files (aka timesteps) in the daily zip archive
+    # - Each file contain a single timestep !
+    list_df = []
+    with zipfile.ZipFile(filepath, "r") as zip_ref:
+        filenames = sorted(zip_ref.namelist())
+        for filename in filenames:
+            if filename.endswith(".txt"):
+                # Open file
+                with zip_ref.open(filename) as f:
+                    try:
+                        df = read_txt_file(file=f, filename=filename, logger=logger)
+                        if df is not None:
+                            list_df.append(df)
+                    except Exception as e:
+                        msg = f"An error occurred while reading {filename}. The error is: {e}."
+                        log_error(logger=logger, msg=msg, verbose=True)
+
+    # Concatenate all dataframes into a single one
+    df = pd.concat(list_df)
+
+    # ---------------------------------------------------------------------.
+    return df

disdrodb/l1/__init__.py

@@ -15,3 +15,8 @@
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
 """DISDRODB L1 module."""
+from disdrodb.l1.processing import generate_l1
+
+__all__ = [
+    "generate_l1",
+]

disdrodb/l1/fall_velocity.py

@@ -195,6 +195,7 @@ def ensure_valid_coordinates(ds, default_altitude=0, default_latitude=0, default
         The dataset with invalid coordinates replaced by default values.
 
     """
+    # TODO raise error if not present
     invalid_altitude = np.logical_or(np.isnan(ds["altitude"]), ds["altitude"] == -9999)
     ds["altitude"] = ds["altitude"].where(~invalid_altitude, default_altitude)
 
@@ -250,6 +251,12 @@ def get_raindrop_fall_velocity(diameter, method, ds_env=None):
         raise ValueError(f"{method} is an invalid fall velocity method. Valid methods: {available_methods}.")
     # Copy diameter
     diameter = diameter.copy()
+    # Initialize ds_env if None
+    # if ds_env is None:
+    #     ds_env = load_env_dataset(ds_env)
+
+    # TODO: wrapper for DISDRODB product !
+
     # Ensure valid altitude and geolocation (if missing set defaults)
     # - altitude required by Beard
     # - latitude required for gravity
@@ -258,3 +265,42 @@ def get_raindrop_fall_velocity(diameter, method, ds_env=None):
     func = dict_methods[method]
     fall_velocity = func(diameter, ds_env=ds_env) if method == "Beard1976" else func(diameter)
     return fall_velocity
+
+
+def get_dataset_fall_velocity(ds, method="Brandes2002"):
+    """Compute the fall velocity and add it to the dataset.
+
+    Parameters
+    ----------
+    ds : xarray.Dataset
+        DISDRODB L0C dataset.
+    method : str, optional
+        Method to compute fall velocity. The default method is ``"Brandes2002"``.
+
+    Returns
+    -------
+    xarray.Dataset
+        DISDRODB L0C dataset with an additional variable 'fall_velocity'.
+    """
+    from disdrodb.constants import DIAMETER_DIMENSION
+    from disdrodb.l1_env.routines import load_env_dataset
+
+    # Check if diameter dimension exists
+    if DIAMETER_DIMENSION not in ds.dims:
+        raise ValueError(f"Diameter dimension '{DIAMETER_DIMENSION}' not found in dataset dimensions.")
+
+    # Retrieve diameter values (in mm)
+    diameter_bin_center = ds["diameter_bin_center"]
+
+    # Ensure valid altitude and geolocation (if missing set defaults)
+    # TODO: MOBILE CASE !
+    default_geolocation = {"altitude": 0, "latitude": 0, "longitude": 0}
+    dataset_coords = {key: ds[key] for key in default_geolocation if key in ds}
+    default_geolocation.update(dataset_coords)
+    ds = ds.assign_coords(default_geolocation)
+
+    # TODO: deal with ENV dataset
+    ds_env = load_env_dataset(ds)
+
+    fall_velocity = get_raindrop_fall_velocity(diameter_bin_center, method=method, ds_env=ds_env)
+    return fall_velocity

disdrodb/l1/filters.py

@@ -19,6 +19,8 @@
 import numpy as np
 import xarray as xr
 
+from disdrodb.constants import DIAMETER_DIMENSION, VELOCITY_DIMENSION
+
 
 def filter_diameter_bins(ds, minimum_diameter=None, maximum_diameter=None):
     """
@@ -29,10 +31,10 @@ def filter_diameter_bins(ds, minimum_diameter=None, maximum_diameter=None):
     ds : xarray.Dataset
         The dataset containing diameter bin data.
     minimum_diameter : float, optional
-        The minimum diameter to include in the filter, in millimeters.
+        The minimum diameter to be included, in millimeters.
         Defaults to the minimum value in `ds["diameter_bin_lower"]`.
     maximum_diameter : float, optional
-        The maximum diameter to include in the filter, in millimeters.
+        The maximum diameter to be included, in millimeters.
         Defaults to the maximum value in `ds["diameter_bin_upper"]`.
 
     Returns
@@ -40,22 +42,28 @@ def filter_diameter_bins(ds, minimum_diameter=None, maximum_diameter=None):
     xarray.Dataset
         The filtered dataset containing only the specified diameter bins.
     """
+    # Put data into memory
+    ds["diameter_bin_lower"] = ds["diameter_bin_lower"].compute()
+    ds["diameter_bin_upper"] = ds["diameter_bin_upper"].compute()
+
     # Initialize default arguments
     if minimum_diameter is None:
         minimum_diameter = ds["diameter_bin_lower"].min().item()
     if maximum_diameter is None:
         maximum_diameter = ds["diameter_bin_upper"].max().item()
-    # Select valid bins
+
+    # Select bins which overlap the specified diameters
     valid_indices = np.logical_and(
-        ds["diameter_bin_lower"] >= minimum_diameter,
-        ds["diameter_bin_upper"] <= maximum_diameter,
-    )
-    ds = ds.isel({"diameter_bin_center": valid_indices})
-    # Update history
-    history = ds.attrs.get("history", "")
-    ds.attrs["history"] = (
-        history + f" Selected drops with diameters between {minimum_diameter} and {maximum_diameter} mm \n"
+        ds["diameter_bin_upper"] > minimum_diameter,
+        ds["diameter_bin_lower"] < maximum_diameter,
     )
+
+    # Select bins with diameter values entirely inside the specified min/max values
+    # valid_indices = np.logical_and(
+    #     ds["diameter_bin_lower"] >= minimum_diameter,
+    #     ds["diameter_bin_upper"] <= maximum_diameter,
+    # )
+    ds = ds.isel({DIAMETER_DIMENSION: valid_indices})
     return ds
 
 
@@ -79,22 +87,28 @@ def filter_velocity_bins(ds, minimum_velocity=0, maximum_velocity=12):
     xarray.Dataset
         The filtered dataset containing only the specified velocity bins.
     """
+    # Put data into memory
+    ds["velocity_bin_lower"] = ds["velocity_bin_lower"].compute()
+    ds["velocity_bin_upper"] = ds["velocity_bin_upper"].compute()
+
     # Initialize default arguments
     if minimum_velocity is None:
         minimum_velocity = ds["velocity_bin_lower"].min().item()
     if maximum_velocity is None:
         maximum_velocity = ds["velocity_bin_upper"].max().item()
-    # Select valid bins
+
+    # Select bins which overlap the specified velocities
     valid_indices = np.logical_and(
-        ds["velocity_bin_lower"] >= minimum_velocity,
-        ds["velocity_bin_upper"] <= maximum_velocity,
-    )
-    ds = ds.isel({"velocity_bin_center": valid_indices})
-    # Update history
-    history = ds.attrs.get("history", "")
-    ds.attrs["history"] = (
-        history + f" Selected drops with fall velocity between {minimum_velocity} and {maximum_velocity} m/s \n"
+        ds["velocity_bin_upper"] > minimum_velocity,
+        ds["velocity_bin_lower"] < maximum_velocity,
     )
+
+    # Select bins with velocity values entirely inside the specified min/max values
+    # valid_indices = np.logical_and(
+    #     ds["velocity_bin_lower"] >= minimum_velocity,
+    #     ds["velocity_bin_upper"] <= maximum_velocity,
+    # )
+    ds = ds.isel({VELOCITY_DIMENSION: valid_indices})
     return ds