disdrodb 0.1.0__py3-none-any.whl → 0.1.1__py3-none-any.whl

disdrodb/l0/readers/PARSIVEL2/FRANCE/ENPC_PARSIVEL2.py

@@ -0,0 +1,189 @@
+#!/usr/bin/env python3
+
+# -----------------------------------------------------------------------------.
+# 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 PARSIVEL2 raw text data."""
+import zipfile
+
+import numpy as np
+import pandas as pd
+
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.l0.l0a_processing import read_raw_text_file
+from disdrodb.utils.logger import log_error
+
+
+@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):
+        """Parse a single txt file within the daily zip file."""
+        ##------------------------------------------------------------------------.
+        #### Define column names
+        column_names = ["TO_PARSE"]
+
+        ##------------------------------------------------------------------------.
+        #### Define reader options
+        reader_kwargs = {}
+        # - Define delimiter
+        reader_kwargs["delimiter"] = "\\n"
+        # - Skip first row as columns names
+        # - Define encoding
+        reader_kwargs["encoding"] = "latin"  # "ISO-8859-1"
+        # - Avoid first column to become df index !!!
+        reader_kwargs["index_col"] = False
+        # - Define behaviour when encountering bad lines
+        reader_kwargs["on_bad_lines"] = "skip"
+        # - Define reader engine
+        #   - C engine is faster
+        #   - Python engine is more feature-complete
+        reader_kwargs["engine"] = "python"
+        # - Define on-the-fly decompression of on-disk data
+        #   - Available: gzip, bz2, zip
+        reader_kwargs["compression"] = "infer"
+        # - Strings to recognize as NA/NaN and replace with standard NA flags
+        #   - Already included: '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN',
+        #                       '-NaN', '-nan', '1.#IND', '1.#QNAN', '<NA>', 'N/A',
+        #                       'NA', 'NULL', 'NaN', 'n/a', 'nan', 'null'
+        reader_kwargs["na_values"] = ["na", "", "error"]
+
+        ##------------------------------------------------------------------------.
+        #### Read the data
+        df = read_raw_text_file(
+            filepath=file,
+            column_names=column_names,
+            reader_kwargs=reader_kwargs,
+            logger=logger,
+        )
+
+        ##------------------------------------------------------------------------.
+        #### Adapt the dataframe to adhere to DISDRODB L0 standards
+        # Create ID and Value columns
+        df = df["TO_PARSE"].str.split(":", expand=True, n=1)
+        df.columns = ["ID", "Value"]
+
+        # Select only rows with values
+        df = df[df["Value"].apply(lambda x: x is not None)]
+
+        # Drop rows with invalid IDs
+        valid_id_str = np.char.rjust(np.arange(0, 94).astype(str), width=2, fillchar="0")
+        df = df[df["ID"].astype(str).isin(valid_id_str)]
+
+        # Create the dataframe with each row corresponding to a timestep
+        # - Group rows based on when ID values restart
+        groups = df.groupby((df["ID"].astype(int).diff() <= 0).cumsum())
+
+        # Reshape the dataframe
+        group_dfs = []
+        for _, group in groups:
+            group_df = group.set_index("ID").T
+            group_dfs.append(group_df)
+
+        # Merge each timestep dataframe
+        # --> Missing columns are infilled by NaN
+        df = pd.concat(group_dfs, axis=0)
+
+        # Assign column names
+        column_dict = {
+            "01": "rainfall_rate_32bit",
+            "02": "rainfall_accumulated_32bit",
+            "03": "weather_code_synop_4680",
+            "04": "weather_code_synop_4677",
+            "05": "weather_code_metar_4678",
+            "06": "weather_code_nws",
+            "07": "reflectivity_32bit",
+            "08": "mor_visibility",
+            "09": "sample_interval",
+            "10": "laser_amplitude",
+            "11": "number_particles",
+            "12": "sensor_temperature",
+            # "13": "sensor_serial_number",
+            # "14": "firmware_iop",
+            # "15": "firmware_dsp",
+            "16": "sensor_heating_current",
+            "17": "sensor_battery_voltage",
+            "18": "sensor_status",
+            # "19": "start_time",
+            # "20": "sensor_time",
+            # "21": "sensor_date",
+            # "22": "station_name",
+            # "23": "station_number",
+            "24": "rainfall_amount_absolute_32bit",
+            "25": "error_code",
+            "26": "sensor_temperature_pcb",
+            "27": "sensor_temperature_receiver",
+            "28": "sensor_temperature_trasmitter",
+            "30": "rainfall_rate_16_bit_30",
+            "31": "rainfall_rate_16_bit_1200",
+            "32": "rainfall_accumulated_16bit",
+            "34": "rain_kinetic_energy",
+            "35": "snowfall_rate",
+            "90": "raw_drop_concentration",
+            "91": "raw_drop_average_velocity",
+            "93": "raw_drop_number",
+        }
+
+        df = df.rename(column_dict, axis=1)
+
+        # Keep only columns defined in the dictionary
+        df = df[list(column_dict.values())]
+
+        # 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 = [
+        #     "sensor_date",
+        #     "sensor_time",
+        # "firmware_iop",
+        # "firmware_dsp",
+        # "sensor_serial_number",
+        # "station_name",
+        # "station_number",
+        # ]
+        # 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 file:
+                    try:
+                        df = read_txt_file(file=file, filename=filename)
+                        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/l0/readers/PARSIVEL2/NCAR/PECAN_FP3.py

@@ -106,7 +106,7 @@ def reader(
     # Preprocess the raw spectrum
     # - The '<SPECTRUM>ZERO</SPECTRUM>' indicates no drops detected
     # --> "" generates an array of zeros in L0B processing
-    df["raw_drop_number"] = df["raw_drop_number"].replace("<SPECTRUM>ZERO</SPECTRUM>", "")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>ZERO</SPECTRUM>", "")
 
     # Remove <SPECTRUM> and </SPECTRUM>" acronyms from the raw_drop_number field
     df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>", "")

disdrodb/l0/readers/PARSIVEL2/NCAR/VORTEX_SE_2016_P2.py

@@ -100,7 +100,7 @@ def reader(
     # --> "" generates an array of zeros in L0B processing
     df["raw_drop_number"] = df["raw_drop_number"].astype("string")
     df["raw_drop_number"] = df["raw_drop_number"].str.strip()
-    df["raw_drop_number"] = df["raw_drop_number"].replace("<SPECTRUM>ZERO</SPECTRUM>", "")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>ZERO</SPECTRUM>", "")
 
     # Remove <SPECTRUM> and </SPECTRUM>" acronyms from the raw_drop_number field
     df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>", "")

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

@@ -0,0 +1,150 @@
+#!/usr/bin/env python3
+
+# -----------------------------------------------------------------------------.
+# 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):  # 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
+    # - 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/l0/readers/RD80/NOAA/PSL_RD80.py

@@ -0,0 +1,274 @@
+#!/usr/bin/env python3
+
+# -----------------------------------------------------------------------------.
+# 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 NOAA PSL RD80 stations."""
+import os
+
+import pandas as pd
+
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.l0.l0a_processing import read_raw_text_file
+
+
+def read_new_format(filepath, logger):
+    """Read new format."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
+    column_names = [
+        "time_interval",
+        "n1",
+        "n2",
+        "n3",
+        "n4",
+        "n5",
+        "n6",
+        "n7",
+        "n8",
+        "n9",
+        "n10",
+        "n11",
+        "n12",
+        "n13",
+        "n14",
+        "n15",
+        "n16",
+        "n17",
+        "n18",
+        "n19",
+        "n20",
+        "Dmax",
+        "RI",
+        "RA",
+        "Wg",
+        "Z",
+        "EF",
+        "N0",
+        "slope",
+        "NumDrops",
+        "SumRA",
+    ]
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # - Define delimiter
+    reader_kwargs["delimiter"] = r"\s+"
+    # Skip header
+    reader_kwargs["header"] = None
+    # Skip first row as columns names
+    reader_kwargs["skiprows"] = 2
+    # - Define encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
+    # - Avoid first column to become df index !!!
+    reader_kwargs["index_col"] = False
+    # - Define behaviour when encountering bad lines
+    reader_kwargs["on_bad_lines"] = "skip"
+    # - Define reader engine
+    #   - C engine is faster
+    #   - Python engine is more feature-complete
+    reader_kwargs["engine"] = "python"
+    # - Define on-the-fly decompression of on-disk data
+    #   - Available: gzip, bz2, zip
+    reader_kwargs["compression"] = "infer"
+    # - Strings to recognize as NA/NaN and replace with standard NA flags
+    #   - Already included: '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN',
+    #                       '-NaN', '-nan', '1.#IND', '1.#QNAN', '<NA>', 'N/A',
+    #                       'NA', 'NULL', 'NaN', 'n/a', 'nan', 'null'
+    reader_kwargs["na_values"] = ["na", "", "error"]
+
+    ##------------------------------------------------------------------------.
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
+
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+
+    # Replace -99.9900 values with NaN
+    columns_to_replace = ["Dmax", "RI", "RA", "Wg", "Z", "EF", "N0", "slope"]
+    df[columns_to_replace] = df[columns_to_replace].replace("-99.9900", "NaN")
+
+    # Replace 'Z' -Inf with NaN
+    df["Z"] = df["Z"].str.replace("-Inf", "NaN")
+
+    # Deal with time interval column
+    # - Split into start and end time
+    df_time = df["time_interval"].str.split("-", expand=True)
+    df_time.columns = ["start", "end"]
+
+    # - Convert start/end MM:SS:SSS to timedelta
+    def parse_time(t):
+        minutes, seconds, milliseconds = map(int, t.split(":"))
+        return pd.Timedelta(minutes=minutes, seconds=seconds, milliseconds=milliseconds)
+
+    df_time["start"] = df_time["start"].apply(parse_time)
+    df_time["end"] = df_time["end"].apply(parse_time)
+    # - Wrap end time if it's less than start time (i.e., crosses 60:00 boundary)
+    # --> 00:00 --> 60:00
+    df_time.loc[df_time["end"] < df_time["start"], "end"] += pd.Timedelta(minutes=60)
+
+    # Compute sample_interval in seconds as integer
+    df["sample_interval"] = (df_time["end"] - df_time["start"]).dt.total_seconds().astype(int)
+
+    # Define time
+    # - Extract date-hour
+    filename = os.path.basename(filepath)
+    if filename.startswith("lab") or filename.startswith("bao0") or filename.startswith("mdt0"):
+        date_hour_str = filename[4:11]
+    else:
+        date_hour_str = filename[3:10]
+    date_hour = pd.to_datetime(date_hour_str, format="%y%j%H")
+    df["time"] = date_hour + df_time["start"]
+
+    # Create raw_drop_number column
+    bin_columns = ["n" + str(i) for i in range(1, 21)]
+    df_arr = df[bin_columns]
+    df_raw_drop_number = df_arr.agg(";".join, axis=1)
+    df["raw_drop_number"] = df_raw_drop_number
+
+    # Remove bins columns
+    df = df.drop(columns=bin_columns)
+
+    # # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "time_interval",
+        "NumDrops",
+        "SumRA",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df
+
+
+def read_old_format(filepath, logger):
+    """Read old format."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
+    column_names = [
+        "date",
+        "time",
+        "n1",
+        "n2",
+        "n3",
+        "n4",
+        "n5",
+        "n6",
+        "n7",
+        "n8",
+        "n9",
+        "n10",
+        "n11",
+        "n12",
+        "n13",
+        "n14",
+        "n15",
+        "n16",
+        "n17",
+        "n18",
+        "n19",
+        "n20",
+        "Dmax",
+        "RI",
+        "RA",
+        "Wg",
+        "Z",
+        "EF",
+        "N0",
+        "slope",
+    ]
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # - Define delimiter
+    reader_kwargs["delimiter"] = r"\s+"
+    # Skip header
+    reader_kwargs["header"] = None
+    # Skip first row as columns names
+    reader_kwargs["skiprows"] = 1
+    # - Define encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
+    # - Avoid first column to become df index !!!
+    reader_kwargs["index_col"] = False
+    # - Define behaviour when encountering bad lines
+    reader_kwargs["on_bad_lines"] = "skip"
+    # - Define reader engine
+    #   - C engine is faster
+    #   - Python engine is more feature-complete
+    reader_kwargs["engine"] = "python"
+    # - Define on-the-fly decompression of on-disk data
+    #   - Available: gzip, bz2, zip
+    reader_kwargs["compression"] = "infer"
+    # - Strings to recognize as NA/NaN and replace with standard NA flags
+    #   - Already included: '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN',
+    #                       '-NaN', '-nan', '1.#IND', '1.#QNAN', '<NA>', 'N/A',
+    #                       'NA', 'NULL', 'NaN', 'n/a', 'nan', 'null'
+    reader_kwargs["na_values"] = ["na", "", "error"]
+
+    ##------------------------------------------------------------------------.
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
+
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+
+    # Replace -99.9900 values with NaN
+    columns_to_replace = ["Dmax", "RI", "RA", "Wg", "Z", "EF", "N0", "slope"]
+    df[columns_to_replace] = df[columns_to_replace].replace("-99.9900", "NaN")
+
+    # Replace 'Z' -Inf with NaN
+    df["Z"] = df["Z"].str.replace("-Inf", "NaN")
+
+    # Define 'time' datetime column
+    df["time"] = df["date"].astype(str) + " " + df["time"].astype(str)
+    df["time"] = pd.to_datetime(df["time"], format="%Y/%m/%d %H:%M:%S", errors="coerce")
+    df = df.drop(columns=["date"])
+
+    # Create raw_drop_number column
+    bin_columns = ["n" + str(i) for i in range(1, 21)]
+    df_arr = df[bin_columns]
+    df_raw_drop_number = df_arr.agg(";".join, axis=1)
+    df["raw_drop_number"] = df_raw_drop_number
+
+    # Remove bins columns
+    df = df.drop(columns=bin_columns)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    filename = os.path.basename(filepath)
+    # station_name = filename[0:3]
+    if filename[3] == "-":  # czc-050101-0052.txt
+        return read_old_format(filepath, logger=logger)
+    # czc2201220b20.txt
+    return read_new_format(filepath, logger=logger)

disdrodb/l0/readers/template_reader_raw_netcdf_data.py

@@ -50,7 +50,7 @@ def reader(
     sensor_name = "LPM"  # [SPECIFY HERE THE SENSOR FOR WHICH THE READER IS DESIGNED]
     ds = standardize_raw_dataset(ds=ds, dict_names=dict_names, sensor_name=sensor_name)
 
-    # Replace occureence of NaN flags with np.nan
+    # Replace occurrence of NaN flags with np.nan
     # - Define a dictionary specifying the value(s) of NaN flags for each variable
     # - The code here below is just an example that requires to be adapted !
     # - This step might not be required with your data !

disdrodb/l0/standards.py

@@ -51,8 +51,9 @@ def get_sensor_logged_variables(sensor_name: str) -> list:
 def allowed_l0_variables(sensor_name: str) -> list:
     """Get the list of allowed L0 variables for a given sensor."""
     sensor_variables = list(get_l0a_dtype(sensor_name))
-    allowed_variables = [*sensor_variables, "time", "latitude", "longitude", "altitude"]
-    # TODO: add air_temperature, relative_humidity, wind_speed, wind_direction
+    weather_variables = ["air_temperature", "relative_humidity", "wind_speed", "wind_direction"]
+    allowed_variables = [*sensor_variables, *weather_variables, "time", "latitude", "longitude", "altitude"]
+    allowed_variables = sorted(np.unique(allowed_variables).tolist())
     return allowed_variables
 
 
@@ -659,9 +660,11 @@ def get_raw_array_dims_order(sensor_name: str) -> dict:
 
     Examples
     --------
-        OTT Parsivel spectrum [v1d1 ... v1d32, v2d1, ..., v2d32]
+        OTT Parsivel spectrum [d1v1 ... d32v1, d1v2, ..., d32v2] (diameter increases first)
         --> dimension_order = ["velocity_bin_center", "diameter_bin_center"]
-        Thies LPM spectrum [v1d1 ... v20d1, v1d2, ..., v20d2]
+        Thies LPM spectrum [v1d1 ... v20d1, v1d2, ..., v20d2]  (velocity increases first)
+        --> dimension_order = ["diameter_bin_center", "velocity_bin_center"]
+        PWS 100 spectrum [d1v1 ... d1v34, d2v1, ..., d2v34] (velocity increases first)
         --> dimension_order = ["diameter_bin_center", "velocity_bin_center"]
 
     Parameters