disdrodb 0.0.21__py3-none-any.whl → 0.1.0__py3-none-any.whl

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

@@ -0,0 +1,56 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+"""Reader for MEXICO OH_IIUNAM OTT PARSIVEL2 Mexico City Network."""
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.l0.l0b_nc_processing import open_raw_netcdf_file, standardize_raw_dataset
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Open the netCDF
+    ds = open_raw_netcdf_file(filepath=filepath, logger=logger)
+
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Define dictionary mapping dataset variables to select and rename
+    dict_names = {
+        ### Dimensions
+        "diameter": "diameter_bin_center",
+        "velocity": "velocity_bin_center",
+        ### Variables
+        "intensity": "rainfall_rate_32bit",
+        "rain": "rainfall_accumulated_32bit",
+        "reflectivity": "reflectivity_32bit",
+        "visibility": "mor_visibility",
+        "particles": "number_particles",
+        # "energy": "rain_kinetic_energy",   #KJ, OTT PARSIVEL2 log in J/mh
+        # "velocity_avg": only depend on time
+        # "diameter_avg": only depend on time
+        "spectrum": "raw_drop_number",
+    }
+
+    # Rename dataset variables and columns and infill missing variables
+    ds = standardize_raw_dataset(ds=ds, dict_names=dict_names, sensor_name="PARSIVEL2")
+
+    # Return the dataset adhering to DISDRODB L0B standards
+    return ds

disdrodb/l0/readers/PARSIVEL2/NCAR/PECAN_FP3.py

@@ -0,0 +1,120 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+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_SPLIT"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+
+    # - Avoid first column to become df index !!!
+    reader_kwargs["index_col"] = False
+
+    # - Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "latin1"
+
+    # - 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"
+
+    # - 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
+
+    # Remove repeated headers (with length 333)
+    df = df[df["TO_SPLIT"].str.len() != 333]
+
+    # Split into columns and assign name
+    df = df["TO_SPLIT"].str.split(",", expand=True, n=15)
+    columns = [
+        "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",
+        "rain_kinetic_energy",
+        "raw_drop_number",
+    ]
+    df.columns = columns
+
+    # Add datetime time column
+    df["time"] = df["date"] + "-" + df["time"]
+    df["time"] = pd.to_datetime(df["time"], format="%Y.%m.%d-%H:%M:%S", errors="coerce")
+    df = df.drop(columns=["date"])
+
+    # 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>", "")
+
+    # Remove <SPECTRUM> and </SPECTRUM>" acronyms from the raw_drop_number field
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>", "")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("</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"].str.replace(r"(?<!\d),", "0,", regex=True)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/{NCAR → PARSIVEL2/NCAR}/PECAN_MIPS.py

@@ -15,23 +15,20 @@
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
-from disdrodb.l0 import run_l0a
+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(
-    raw_dir,
-    processed_dir,
-    station_name,
-    # Processing options
-    force=False,
-    verbose=False,
-    parallel=False,
-    debugging_mode=False,
+    filepath,
+    logger=None,
 ):
-    ####----------------------------------------------------------------------.
-    #### - Define column names
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
     column_names = [
         "day",
         "month",
@@ -50,7 +47,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = ","
@@ -77,61 +74,45 @@ def reader(
     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’
+    #   - 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"]
 
     ##------------------------------------------------------------------------.
-    #### - Define facultative dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # Import pandas
-        import pandas as pd
-
-        # Define datetime time column
-        df["time"] = (
-            df["day"].astype(str)
-            + "-"
-            + df["month"].astype(str)
-            + "-"
-            + df["year"].astype(str)
-            + " "
-            + df["hour_minute"].astype(str)
-            + ":"
-            + df["second"].astype(str)
-        )
-        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 = [
-            "day",
-            "month",
-            "year",
-            "hour_minute",
-            "second",
-        ]
-        df = df.drop(columns=columns_to_drop)
-
-        return df
-
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in raw_dir/data/<station_name>
-    glob_patterns = "*.dat"
-
-    ####----------------------------------------------------------------------.
-    #### - Create L0A products
-    run_l0a(
-        raw_dir=raw_dir,
-        processed_dir=processed_dir,
-        station_name=station_name,
-        # Custom arguments of the reader for L0A processing
-        glob_patterns=glob_patterns,
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
         column_names=column_names,
         reader_kwargs=reader_kwargs,
-        df_sanitizer_fun=df_sanitizer_fun,
-        # Processing options
-        force=force,
-        verbose=verbose,
-        parallel=parallel,
-        debugging_mode=debugging_mode,
+        logger=logger,
     )
+
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Define datetime time column
+    df["time"] = (
+        df["day"].astype(str)
+        + "-"
+        + df["month"].astype(str)
+        + "-"
+        + df["year"].astype(str)
+        + " "
+        + df["hour_minute"].astype(str)
+        + ":"
+        + df["second"].astype(str)
+    )
+    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 = [
+        "day",
+        "month",
+        "year",
+        "hour_minute",
+        "second",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL2/NCAR/RELAMPAGO_PARSIVEL2.py

@@ -0,0 +1,181 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+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 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)
+    df.columns = df.columns.astype(str).str.pad(width=2, side="left", fillchar="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",
+        "33": "reflectivity_16bit",
+        "34": "rain_kinetic_energy",
+        "35": "snowfall_rate",
+        # 60: "number_particles_all",
+        # 61: "list_particles",
+        "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/NCAR/SNOWIE_PJ.py

@@ -0,0 +1,160 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+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"
+    # - 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=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 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",
+        "30": "rainfall_rate_16_bit_30",
+        "31": "rainfall_rate_16_bit_1200",
+        "32": "rainfall_accumulated_16bit",
+        "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
+    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)
+
+    # 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_average_velocity"] = df["raw_drop_average_velocity"].str.replace(r"(?<!\d);", "0;", regex=True)
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace(r"(?<!\d);", "0;", regex=True)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df