disdrodb 0.1.5__py3-none-any.whl → 0.2.1__py3-none-any.whl

disdrodb/l0/readers/{LPM → LPM_V0}/BELGIUM/ULIEGE.py

@@ -88,31 +88,22 @@ def read_txt_file(file, filename, logger):
     df = df["TO_PARSE"].str.split(";", expand=True, n=43)
 
     # Assign column names
-    column_names = [
-        "id",
-        "sample_interval",
-        "weather_code_synop_4677_5min",  # or  "weather_code_synop_4680_5min",
+    names = [
+        "start_identifier",
+        "sensor_serial_number",
+        "weather_code_synop_4680_5min",
         "weather_code_metar_4678_5min",
         "precipitation_rate_5min",
-        "weather_code_synop_4677",  # or "weather_code_synop_4680",
+        "weather_code_synop_4680",
         "weather_code_metar_4678",
         "precipitation_rate",
         "precipitation_accumulated",
         "sensor_time",
-        # "mor_visibility",
-        # "reflectivity",
-        # "quality_index",
-        # "max_hail_diameter",
-        # "laser_status",
-        "dummy1",
-        "dummy2",
-        # "laser_temperature",
+        "temperature_interior",
+        "laser_temperature",
         "laser_current_average",
         "control_voltage",
         "optical_control_voltage_output",
-        # "current_heating_house",
-        # "current_heating_heads",
-        # "current_heating_carriers",
         "number_particles",
         "number_particles_internal_data",
         "number_particles_min_speed",
@@ -123,29 +114,27 @@ def read_txt_file(file, filename, logger):
         "number_particles_min_diameter_internal_data",
         "number_particles_no_hydrometeor",
         "number_particles_no_hydrometeor_internal_data",
-        # "number_particles_unknown_classification",  # ????
-        # "number_particles_unknown_classification_internal_data",
-        "number_particles_class_1",
-        "number_particles_class_1_internal_data",
-        "number_particles_class_2",
-        "number_particles_class_2_internal_data",
-        "number_particles_class_3",
-        "number_particles_class_3_internal_data",
-        "number_particles_class_4",
-        "number_particles_class_4_internal_data",
-        "number_particles_class_5",
-        "number_particles_class_5_internal_data",
-        "number_particles_class_6",
-        "number_particles_class_6_internal_data",
-        "number_particles_class_7",
-        "number_particles_class_7_internal_data",
-        "number_particles_class_8",
-        "number_particles_class_8_internal_data",
-        "number_particles_class_9",
-        "number_particles_class_9_internal_data",
+        "number_particles_unknown_classification",
+        "total_gross_volume_unknown_classification",
+        "number_particles_hail",
+        "total_gross_volume_hail",
+        "number_particles_solid_precipitation",
+        "total_gross_volume_solid_precipitation",
+        "number_particles_great_pellet",
+        "total_gross_volume_great_pellet",
+        "number_particles_small_pellet",
+        "total_gross_volume_small_pellet",
+        "number_particles_snowgrain",
+        "total_gross_volume_snowgrain",
+        "number_particles_rain",
+        "total_gross_volume_rain",
+        "number_particles_small_rain",
+        "total_gross_volume_small_rain",
+        "number_particles_drizzle",
+        "total_gross_volume_drizzle",
         "raw_drop_number",
     ]
-    df.columns = column_names
+    df.columns = names
 
     # Deal with case if there are 61 timesteps
     # - Occurs sometimes when previous hourly file miss timesteps
@@ -163,7 +152,12 @@ def read_txt_file(file, filename, logger):
     start_time = pd.to_datetime(start_time_str, format="%Y%m%d%H")
 
     # - Define timedelta based on sensor_time
+    # --> Add +24h to subsequent times when time resets
     dt = pd.to_timedelta(df["sensor_time"] + ":00").to_numpy().astype("m8[s]")
+    rollover_indices = np.where(np.diff(dt) < np.timedelta64(0, "s"))[0]
+    if rollover_indices.size > 0:
+        for idx in rollover_indices:
+            dt[idx + 1 :] += np.timedelta64(24, "h")
     dt = dt - dt[0]
 
     # - Define approximate time
@@ -173,25 +167,15 @@ def read_txt_file(file, filename, logger):
     valid_rows = dt <= np.timedelta64(3540, "s")
     df = df[valid_rows]
 
-    # Drop rows where sample interval is not 60 seconds
-    df = df[df["sample_interval"] == "000060"]
-
     # Drop rows with invalid raw_drop_number
-    # --> 440 value # 22x20
     # --> 400 here  # 20x20
     df = df[df["raw_drop_number"].astype(str).str.len() == 1599]
 
-    # Deal with old LPM version 20x20 spectrum
-    # - Add 000 in first two velocity bins
-    df["raw_drop_number"] = df["raw_drop_number"] + ";" + ";".join(["000"] * 40)
-
     # Drop columns not agreeing with DISDRODB L0 standards
     columns_to_drop = [
-        "sample_interval",
+        "start_identifier",
+        "sensor_serial_number",
         "sensor_time",
-        "dummy1",
-        "dummy2",
-        "id",
     ]
     df = df.drop(columns=columns_to_drop)
     return df

disdrodb/l0/readers/LPM_V0/ITALY/GID_LPM_V0.py

@@ -0,0 +1,240 @@
+# -----------------------------------------------------------------------------.
+# 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 GID LPM V0 sensor (TC-TO) with incorrect reported time."""
+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, log_warning
+
+
+def read_txt_file(file, filename, logger):
+    """Parse for TC-TO LPM hourly file."""
+    #### - Define raw data headers
+    column_names = ["TO_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    # - For more info: https://pandas.pydata.org/docs/reference/api/pandas.read_csv.html
+    reader_kwargs = {}
+
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+
+    # - Avoid first column to become df index !!!
+    reader_kwargs["index_col"] = False
+
+    # Since column names are expected to be passed explicitly, header is set to None
+    reader_kwargs["header"] = None
+
+    # - Number of rows to be skipped at the beginning of the file
+    reader_kwargs["skiprows"] = None
+
+    # - 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
+    # Raise error if empty file
+    if len(df) == 0:
+        raise ValueError(f"{filename} is empty.")
+
+    # Select only rows with expected number of delimiters
+    df = df[df["TO_PARSE"].str.count(";") == 442]
+
+    # Check there are still valid rows
+    if len(df) == 0:
+        raise ValueError(f"No valid rows in {filename}.")
+
+    # Split by ; delimiter (before raw drop number)
+    df = df["TO_PARSE"].str.split(";", expand=True, n=43)
+
+    # Assign column names
+    names = [
+        "start_identifier",
+        "sensor_serial_number",
+        "weather_code_synop_4680_5min",
+        "weather_code_metar_4678_5min",
+        "precipitation_rate_5min",
+        "weather_code_synop_4680",
+        "weather_code_metar_4678",
+        "precipitation_rate",
+        "precipitation_accumulated",
+        "sensor_time",
+        "temperature_interior",
+        "laser_temperature",
+        "laser_current_average",
+        "control_voltage",
+        "optical_control_voltage_output",
+        "number_particles",
+        "number_particles_internal_data",
+        "number_particles_min_speed",
+        "number_particles_min_speed_internal_data",
+        "number_particles_max_speed",
+        "number_particles_max_speed_internal_data",
+        "number_particles_min_diameter",
+        "number_particles_min_diameter_internal_data",
+        "number_particles_no_hydrometeor",
+        "number_particles_no_hydrometeor_internal_data",
+        "number_particles_unknown_classification",
+        "total_gross_volume_unknown_classification",
+        "number_particles_hail",
+        "total_gross_volume_hail",
+        "number_particles_solid_precipitation",
+        "total_gross_volume_solid_precipitation",
+        "number_particles_great_pellet",
+        "total_gross_volume_great_pellet",
+        "number_particles_small_pellet",
+        "total_gross_volume_small_pellet",
+        "number_particles_snowgrain",
+        "total_gross_volume_snowgrain",
+        "number_particles_rain",
+        "total_gross_volume_rain",
+        "number_particles_small_rain",
+        "total_gross_volume_small_rain",
+        "number_particles_drizzle",
+        "total_gross_volume_drizzle",
+        "raw_drop_number",
+    ]
+    df.columns = names
+
+    # Deal with case if there are 61 timesteps
+    # - Occurs sometimes when previous hourly file miss timesteps
+    if len(df) == 61:
+        log_warning(logger=logger, msg=f"{filename} contains 61 timesteps. Dropping the first.")
+        df = df.iloc[1:]
+
+    # Raise error if more than 60 timesteps/rows
+    n_rows = len(df)
+    if n_rows > 60:
+        raise ValueError(f"The hourly file contains {n_rows} timesteps.")
+
+    # Infer and define "time" column
+    start_time_str = filename.split(".")[0]  # '2024020200.txt'
+    start_time = pd.to_datetime(start_time_str, format="%Y%m%d%H")
+
+    # - Define timedelta based on sensor_time
+    dt = pd.to_timedelta(df["sensor_time"] + ":00").to_numpy().astype("m8[s]")
+    rollover_indices = np.where(np.diff(dt) < np.timedelta64(0, "s"))[0]
+    if rollover_indices.size > 0:
+        for idx in rollover_indices:
+            dt[idx + 1 :] += np.timedelta64(24, "h")
+    dt = dt - dt[0]
+
+    # - Define approximate time
+    df["time"] = start_time + dt
+
+    # - Keep rows where time increment is between 00 and 59 minutes
+    valid_rows = dt <= np.timedelta64(3540, "s")
+    df = df[valid_rows]
+
+    # Drop rows with invalid raw_drop_number
+    # --> 440 value # 22x20
+    df = df[df["raw_drop_number"].astype(str).str.len() == 1599]
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "sensor_time",
+        "start_identifier",
+        "sensor_serial_number",
+    ]
+    df = df.drop(columns=columns_to_drop)
+    return df
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    import zipfile
+
+    ##------------------------------------------------------------------------.
+    # filename = os.path.basename(filepath)
+    # return read_txt_file(file=filepath, filename=filename, logger=logger)
+
+    # ---------------------------------------------------------------------.
+    #### Iterate over all files (aka timesteps) in the daily zip archive
+    # - Each file contain a single timestep !
+    # list_df = []
+    # with tempfile.TemporaryDirectory() as temp_dir:
+    #     # Extract all files
+    #     unzip_file_on_terminal(filepath, temp_dir)
+
+    #     # Walk through extracted files
+    #     for root, _, files in os.walk(temp_dir):
+    #         for filename in sorted(files):
+    #             if filename.endswith(".txt"):
+    #                 full_path = os.path.join(root, filename)
+    #                 try:
+    #                     df = read_txt_file(file=full_path, 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}: {e}"
+    #                     log_error(logger=logger, msg=msg, verbose=True)
+
+    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, 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)
+
+    # Check the zip file contains at least some non.empty files
+    if len(list_df) == 0:
+        raise ValueError(f"{filepath} contains only empty files!")
+
+    # Concatenate all dataframes into a single one
+    df = pd.concat(list_df)
+
+    # ---------------------------------------------------------------------.
+    return df

disdrodb/l0/readers/PARSIVEL/BASQUECOUNTRY/EUSKALMET_OTT.py

@@ -0,0 +1,227 @@
+# -----------------------------------------------------------------------------.
+# 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 EUSKALMET OTT Parsivel raw data."""
+# import os
+# import tempfile
+# from disdrodb.utils.compression import unzip_file_on_terminal
+
+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
+
+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",  # empty
+    "06": "weather_code_nws",  # empty
+    "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",
+    "30": "rainfall_rate_16bit",
+    "31": "rainfall_rate_12bit",
+    "32": "rainfall_accumulated_16bit",
+    "90": "raw_drop_concentration",
+    "91": "raw_drop_average_velocity",
+    "93": "raw_drop_number",
+}
+
+
+def infill_missing_columns(df):
+    """Infill with NaN missing columns."""
+    columns = set(COLUMN_DICT.values())
+    for c in columns:
+        if c not in df.columns:
+            df[c] = "NaN"
+    return df
+
+
+def read_txt_file(file, filename, logger):
+    """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
+    # Empty file, raise error
+    if len(df) == 0:
+        raise ValueError(f"{filename} is empty.")
+
+    # Select rows with valid spectrum
+    # df = df[df["TO_PARSE"].str.count(";") == 1191]  # 1112
+
+    # Raise errof if corrupted file
+    if len(df) == 4:
+        raise ValueError(f"{filename} is corrupted.")
+
+    # Extract string
+    string = df["TO_PARSE"].iloc[4]
+
+    # Split into lines
+    decoded_text = string.encode().decode("unicode_escape")
+    decoded_text = decoded_text.replace("'", "").replace('"', "")
+    lines = decoded_text.split()
+
+    # Extract time
+    time_str = lines[0].split(",")[1]
+
+    # Split each line at the first colon
+    data = [line.split(":", 1) for line in lines if ":" in line]
+
+    # Create the DataFrame
+    df = pd.DataFrame(data, columns=["ID", "Value"])
+
+    # 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)]
+
+    # Select only rows with values
+    df = df[df["Value"].apply(lambda x: x is not None)]
+
+    # Reshape dataframe
+    df = df.set_index("ID").T
+
+    # Assign column names
+    df = df.rename(COLUMN_DICT, axis=1)
+
+    # Keep only columns defined in the dictionary
+    df = df.filter(items=list(COLUMN_DICT.values()))
+
+    # Infill missing columns
+    df = infill_missing_columns(df)
+
+    # Add time column ad datetime dtype
+    df["time"] = pd.to_datetime(time_str, format="%Y%m%d%H%M%S", errors="coerce")
+
+    # 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)
+    df["raw_drop_average_velocity"] = df["raw_drop_average_velocity"].str.replace(r"(?<!\d);", "0;", regex=True)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    import zipfile
+
+    # ---------------------------------------------------------------------.
+    #### Iterate over all files (aka timesteps) in the daily zip archive
+    # - Each file contain a single timestep !
+    # list_df = []
+    # with tempfile.TemporaryDirectory() as temp_dir:
+    #     # Extract all files
+    #     unzip_file_on_terminal(filepath, temp_dir)
+
+    #     # Walk through extracted files
+    #     for root, _, files in os.walk(temp_dir):
+    #         for filename in sorted(files):
+    #             if filename.endswith(".txt"):
+    #                 full_path = os.path.join(root, filename)
+    #                 try:
+    #                     df = read_txt_file(file=full_path, 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}: {e}"
+    #                     log_error(logger=logger, msg=msg, verbose=True)
+
+    list_df = []
+    with zipfile.ZipFile(filepath, "r") as zip_ref:
+        filenames = sorted(zip_ref.namelist())
+        for filename in filenames:
+            if filename.endswith(".dat"):
+                # Open file
+                with zip_ref.open(filename) as file:
+                    try:
+                        df = read_txt_file(file=file, 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)
+
+    # Check the zip file contains at least some non.empty files
+    if len(list_df) == 0:
+        raise ValueError(f"{filepath} contains only empty files!")
+
+    # Concatenate all dataframes into a single one
+    df = pd.concat(list_df)
+
+    # ---------------------------------------------------------------------.
+    return df

disdrodb/l0/readers/{PARSIVEL2 → PARSIVEL}/NASA/LPVEX.py

@@ -15,21 +15,6 @@
 # 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 APU stations.
-
-The reader allows to read raw  APU data from the following NASA campaigns:
-
-    - HYMEX
-    - IFLOODS
-    - IPHEX
-    - OLYMPEX
-    - ICEPOP
-    - IMPACTS
-    - GCPEX
-    - WFF
-
-"""
-
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
@@ -44,13 +29,13 @@ 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
@@ -84,26 +69,29 @@ 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}")
+
+    # Split the columns
+    df = df["TO_PARSE"].str.split(";", n=2, expand=True)
+
+    # Assign column names
+    df.columns = ["time", "TO_BE_SPLITTED"]
+
     # Convert time column to datetime
     df_time = pd.to_datetime(df["time"], format="%Y%m%d%H%M%S", errors="coerce")
 
     # Split the 'TO_BE_SPLITTED' column
     df = df["TO_BE_SPLITTED"].str.split(",", n=3, expand=True)
+    df.columns = ["station_id", "sensor_status", "sensor_temperature", "raw_drop_number"]
 
-    # Assign column names
-    names = [
-        "station_name",
-        "unknown",
-        "unknown2",
-        "raw_drop_number",
-    ]
-    df.columns = names
-
-    # Add the time column
+    # Add time
     df["time"] = df_time
 
     # Drop columns not agreeing with DISDRODB L0 standards
-    df = df.drop(columns=["station_name", "unknown", "unknown2"])
+    df = df.drop(columns=["station_id"])
 
     # Return the dataframe adhering to DISDRODB L0 standards
     return df

disdrodb/l0/readers/PARSIVEL/{GPM → NASA}/MC3E.py

@@ -116,7 +116,7 @@ def reader(
         return df
     # ---------------------------------------------------------
     #### Case of 1032 delimiters
-    if n_delimiters == 1033:  # (most of the files)
+    if n_delimiters == 1033:  # (most of the files ... PIERS FORMAT)
         # Select valid rows
         df = df.loc[df["TO_BE_SPLITTED"].str.count(",") == 1033]
         # Get time column