disdrodb 0.2.0__py3-none-any.whl → 0.3.0__py3-none-any.whl

disdrodb/l0/readers/PARSIVEL2/JAPAN/PRECIP.py

@@ -0,0 +1,155 @@
+# -----------------------------------------------------------------------------.
+# Copyright (c) 2021-2026 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 Colorado State University PRECIP OTT Parsivel 2 raw data."""
+
+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
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
+    column_names = ["TO_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+
+    # - Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    # - Skip header
+    reader_kwargs["skiprows"] = 0
+
+    # - 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'] = 'xz'
+
+    # - 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", "-.-", " NA"]
+
+    ##------------------------------------------------------------------------.
+    #### 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
+    # Raise error if empty file
+    if len(df) == 0:
+        raise ValueError(f"{filepath} is empty.")
+
+    # Select only rows with expected number of delimiters
+    df = df[df["TO_PARSE"].str.count(",") == 1041]
+
+    # Raise error if no data left
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}.")
+
+    # Split into columns
+    df = df["TO_PARSE"].str.split(",", expand=True, n=17)
+
+    # Assign columns names
+    names = [
+        "date",
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "weather_code_metar_4678",
+        "weather_code_nws",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "sensor_status",
+        "rain_kinetic_energy",
+        "snowfall_rate",
+        "raw_drop_number",
+    ]
+    df.columns = names
+
+    # Add datetime time column
+    time_str = df["date"] + "-" + df["time"]
+    df["time"] = pd.to_datetime(time_str, format="%d.%m.%Y-%H:%M:%S", errors="coerce")
+
+    # Derive the raw spectrum
+    # Remove <SPECTRUM> and </SPECTRUM> prefix and suffix from the raw_drop_number field
+    df["raw_drop_number"] = df["raw_drop_number"].astype("string")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>", "")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("</SPECTRUM>", "")
+
+    # Preprocess the raw spectrum and raw_drop_average_velocity
+    # - Add 0 before every ; if ; not preceded by a digit
+    # - Example: ';;1;;' --> '0;0;1;0;'
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace(r"(?<!\d),", "0,", regex=True)
+
+    # Infill missing timesteps with raw_drop_number = 0 spectrum
+    # - Define the full time range with 30-second frequency
+    full_time_index = pd.date_range(start=df["time"].iloc[0], end=df["time"].iloc[-1], freq="30s")
+
+    # - Reindex the DataFrame to include all 30-second timesteps
+    df = df.set_index("time").reindex(full_time_index)
+
+    # - Fill missing raw_drop_number with 0
+    df["raw_drop_number"] = df["raw_drop_number"].fillna(0)
+
+    # - Restore 'time' as a column
+    df = df.rename_axis("time").reset_index()
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "date",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL2/KIT/BURKINA_FASO.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 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

disdrodb/l0/readers/PARSIVEL2/KIT/TEAMX.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 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

disdrodb/l0/readers/PARSIVEL2/KOREA/ICEPOP_MSC.py

@@ -0,0 +1,161 @@
+#!/usr/bin/env python3
+# -----------------------------------------------------------------------------.
+# Copyright (c) 2021-2026 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/>.
+# -----------------------------------------------------------------------------.
+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
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
+    column_names = ["TO_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
+
+    # - Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    # - 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
+    # 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"].astype(bool)]
+    df = df[df["Value"].apply(lambda x: x is not None)]
+
+    # Drop rows with invalid IDs
+    # - Corrupted rows
+    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 where each row corresponds to a timestep
+    df["_group"] = (df["ID"].astype(int).diff() <= 0).cumsum()
+    df = df.pivot(index="_group", columns="ID")  # noqa
+    df.columns = df.columns.get_level_values("ID")
+    df = df.reset_index(drop=True)
+
+    # 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",
+        "34": "rain_kinetic_energy",
+        "35": "snowfall_rate",
+        "90": "raw_drop_concentration",
+        "91": "raw_drop_average_velocity",
+        "93": "raw_drop_number",
+    }
+
+    # Identify missing columns and add NaN
+    expected_columns = np.array(list(column_dict.keys()))
+    missing_columns = expected_columns[np.isin(expected_columns, df.columns, invert=True)].tolist()
+    if len(missing_columns) > 0:
+        for column in missing_columns:
+            df[column] = "NaN"
+
+    # Rename columns
+    df = df.rename(column_dict, axis=1)
+
+    # Keep only columns defined in the dictionary
+    df = df[list(column_dict.values())]
+
+    # Define datetime "time" column
+    df["time"] = df["sensor_date"] + "-" + df["sensor_time"]
+    df["time"] = pd.to_datetime(df["time"], format="%d.%m.%Y-%H:%M:%S", errors="coerce")
+
+    # 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 the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL2/{NASA/GCPEX.py → KOREA/ICEPOP_UCLM.py}

@@ -1,6 +1,5 @@
-#!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 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
@@ -15,7 +14,8 @@
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
-"""This reader allows to read raw data from NASA GCPEX, OLYMPEX and IPHEX campaigns."""
+"""DISDRODB reader for University of Bergen OTT Parsivel 2 raw data."""
+
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
@@ -30,34 +30,44 @@ def reader(
     """Reader."""
     ##------------------------------------------------------------------------.
     #### Define column names
-    column_names = ["time", "TO_BE_SPLITTED"]
+    column_names = ["TO_PARSE"]
 
     ##------------------------------------------------------------------------.
     #### Define reader options
     reader_kwargs = {}
+
     # - Define delimiter
-    reader_kwargs["delimiter"] = ";"
+    reader_kwargs["delimiter"] = "\\n"
+
     # - Skip first row as columns names
     reader_kwargs["header"] = None
+
+    # - Skip header
     reader_kwargs["skiprows"] = 0
-    # - Skip file with encoding errors
-    reader_kwargs["encoding_errors"] = "ignore"
+
+    # - 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"
+    # reader_kwargs['compression'] = 'xz'
+
     # - 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", "NA", "-.-"]
+    reader_kwargs["na_values"] = ["na", "error", "-.-", " NA"]
 
     ##------------------------------------------------------------------------.
     #### Read the data
@@ -70,37 +80,47 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### Adapt the dataframe to adhere to DISDRODB L0 standards
-    # Convert time column to datetime
-    df_time = pd.to_datetime(df["time"], format="%Y%m%d%H%M%S", errors="coerce")
+    # Raise error if empty file
+    if len(df) == 0:
+        raise ValueError(f"{filepath} is empty.")
+
+    # Select only rows with expected number of delimiters
+    df = df[df["TO_PARSE"].str.count(";") == 1027]
+
+    # Check there are still valid rows
+    if len(df) == 0:
+        raise ValueError(f"No valid rows in {filepath}.")
 
-    # Split the 'TO_BE_SPLITTED' column
-    df = df["TO_BE_SPLITTED"].str.split(",", n=9, expand=True)
+    # Split into columns
+    df = df["TO_PARSE"].str.split(";", expand=True, n=4)
 
-    # Assign column names
+    # Assign columns names
     names = [
-        "station_name",
-        "sensor_status",
-        "sensor_temperature",
-        "number_particles",
-        "rainfall_rate_32bit",
-        "reflectivity_16bit",
-        "mor_visibility",
-        "weather_code_synop_4680",
-        "weather_code_synop_4677",
+        "date",
+        "time",
+        "id",
+        "unknown",
         "raw_drop_number",
     ]
     df.columns = names
 
-    # Add the time column
-    df["time"] = df_time
+    # Add datetime time column
+    time_str = df["date"] + "T" + df["time"]
+    df["time"] = pd.to_datetime(time_str, format="%Y/%m/%dT%H:%M:%S", errors="coerce")
+    df = df.drop(columns=["date"])
 
-    # Drop columns not agreeing with DISDRODB L0 standards
-    df = df.drop(columns=["station_name"])
+    # Retrieve raw spectrum
+    # - Add 0 before every , if , not preceded by a digit
+    # - Example: ',,1,,' --> '0,0,1,0,'
+    df["raw_drop_number"] = df["raw_drop_number"] + ";"
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace(r"(?<!\d);", "0;", regex=True)
 
-    # Drop rows with invalid values
-    # --> Ensure that weather_code_synop_4677 has length 2
-    # --> If a previous column is missing it will have 000
-    df = df[df["weather_code_synop_4677"].str.len() == 2]
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "id",
+        "unknown",
+    ]
+    df = df.drop(columns=columns_to_drop)
 
     # Return the dataframe adhering to DISDRODB L0 standards
     return df

disdrodb/l0/readers/PARSIVEL2/MEXICO/OH_IIUNAM_nc.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 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

disdrodb/l0/readers/PARSIVEL2/MPI/BCO_PARSIVEL2.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 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
@@ -38,11 +38,14 @@ def reader(
     # - Define delimiter
     reader_kwargs["delimiter"] = "/\n"
 
-    # Skip first row as columns names
+    # - Skip first row as columns names
     reader_kwargs["header"] = None
 
-    # Skip first 2 rows
-    reader_kwargs["skiprows"] = 1
+    # - Skip first 2 rows
+    reader_kwargs["skiprows"] = 0
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
 
     # - Avoid first column to become df index !!!
     reader_kwargs["index_col"] = False
@@ -76,12 +79,17 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### Adapt the dataframe to adhere to DISDRODB L0 standards
-    # Remove rows with invalid length
-    # df = df[df["TO_BE_PARSED"].str.len().isin([4664])]
+    # Raise error if empty file
+    if len(df) == 0:
+        raise ValueError(f"{filepath} is empty.")
 
-    # Count number of delimiters to select valid rows
+    # Select only rows with expected number of delimiters
     df = df[df["TO_BE_PARSED"].str.count(";") == 1107]
 
+    # Raise error if no data left
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}.")
+
     # Split by ; delimiter
     df = df["TO_BE_PARSED"].str.split(";", expand=True, n=19)
 
@@ -132,5 +140,4 @@ def reader(
         "sample_interval",
     ]
     df = df.drop(columns=columns_to_drop)
-
     return df

disdrodb/l0/readers/PARSIVEL2/MPI/BOWTIE.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 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
@@ -157,12 +157,17 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### Adapt the dataframe to adhere to DISDRODB L0 standards
-    # Remove rows with invalid length
-    # df = df[df["TO_BE_PARSED"].str.len().isin([4664])]
+    # Raise error if empty file
+    if len(df) == 0:
+        raise ValueError(f"{filepath} is empty.")
 
-    # Count number of delimiters to select valid rows
+    # Select only rows with expected number of delimiters
     df = df[df["TO_BE_PARSED"].str.count(";") == 1107]
 
+    # Raise error if no data left
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}.")
+
     # Split by ; delimiter
     df = df["TO_BE_PARSED"].str.split(";", expand=True, n=19)
 

disdrodb/l0/readers/PARSIVEL2/NASA/APU.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 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
@@ -44,16 +44,18 @@ def reader(
     """Reader."""
     ##------------------------------------------------------------------------.
     #### Define column names
-    column_names = ["time", "TO_BE_SPLITTED"]
+    column_names = ["TO_PARSE"]
 
     ##------------------------------------------------------------------------.
     #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
-    reader_kwargs["delimiter"] = ";"
+    reader_kwargs["delimiter"] = "//n"
     # - Skip first row as columns names
     reader_kwargs["header"] = None
     reader_kwargs["skiprows"] = 0
+    # - Define encoding
+    reader_kwargs["encoding"] = "latin-1"
     # - Skip file with encoding errors
     reader_kwargs["encoding_errors"] = "ignore"
     # - Avoid first column to become df index !!!
@@ -84,6 +86,20 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Remove rows with invalid number of separators
+    df = df[df["TO_PARSE"].str.count(";") == 1]
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}")
+
+    # Retrieve time and telegram field
+    df = df["TO_PARSE"].str.split(";", expand=True)
+    df.columns = ["time", "TO_BE_SPLITTED"]
+
+    # Remove rows with invalid number of separators
+    df = df[df["TO_BE_SPLITTED"].str.count(",") == 1033]
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}")
+
     # Convert time column to datetime
     df_time = pd.to_datetime(df["time"], format="%Y%m%d%H%M%S", errors="coerce")
 
@@ -91,7 +107,7 @@ def reader(
     df = df["TO_BE_SPLITTED"].str.split(",", n=9, expand=True)
 
     # Assign column names
-    names = [
+    columns_names = [
         "station_name",
         "sensor_status",
         "sensor_temperature",
@@ -103,7 +119,7 @@ def reader(
         "weather_code_synop_4677",
         "raw_drop_number",
     ]
-    df.columns = names
+    df.columns = columns_names
 
     # Add the time column
     df["time"] = df_time
@@ -111,10 +127,19 @@ def reader(
     # Drop columns not agreeing with DISDRODB L0 standards
     df = df.drop(columns=["station_name"])
 
+    # Remove rows with invalid raw drop number
+    # --> Occurs e.g. in UCONN apu28
+    # def mask_invalid_raw_drop_number(df)
+    #     df_split = df["raw_drop_number"].str.split(",", expand=True)
+    #     idx = np.where(np.any(df_split.astype(float) > 998, axis=1))[0]
+    #     df.loc[idx, "raw_drop_number"] = "NaN"
+    #     return df
+    df = df[df["raw_drop_number"].str.len() == 4096]
+
     # Drop rows with invalid values
     # --> Ensure that weather_code_synop_4677 has length 2
     # --> If a previous column is missing it will have 000
-    df = df[df["weather_code_synop_4677"].str.len() == 2]
+    # df = df[df["weather_code_synop_4677"].str.len() == 2]
 
     # Return the dataframe adhering to DISDRODB L0 standards
     return df

disdrodb/l0/readers/PARSIVEL2/NASA/NSSTC.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 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

disdrodb/l0/readers/PARSIVEL2/NCAR/FARM_PARSIVEL2.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
-# Copyright (c) 2021-2023 DISDRODB developers
+# Copyright (c) 2021-2026 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