disdrodb 0.0.20__py3-none-any.whl → 0.1.0__py3-none-any.whl

disdrodb/l0/readers/{EPFL → PARSIVEL/EPFL}/UNIL_2022.py

@@ -15,23 +15,21 @@
 # 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
+"""Reader for UNIL 2022 campaign."""
+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,
 ):
+    """Reader."""
     ##------------------------------------------------------------------------.
-    #### - Define column names
+    #### Define column names
     column_names = [
         "id",
         "latitude",
@@ -59,7 +57,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = ";"
@@ -75,55 +73,44 @@ def reader(
     #   - 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’
+    #   - 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 dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - Convert time column to datetime with resolution in seconds
-        df["time"] = pd.to_datetime(df["time"], format="%d-%m-%Y %H:%M:%S", errors="coerce")
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Convert time column to datetime with resolution in seconds
+    df["time"] = pd.to_datetime(df["time"], format="%d-%m-%Y %H:%M:%S", errors="coerce")
 
-        # - Split TO_BE_SPLITTED columns
-        df_splitted = df["TO_BE_SPLITTED"].str.split(",", expand=True, n=1)
-        df_splitted.columns = ["datalogger_voltage", "rainfall_rate_32bit"]
-        df["rainfall_rate_32bit"] = df_splitted["rainfall_rate_32bit"]
+    # Split TO_BE_SPLITTED columns
+    df_splitted = df["TO_BE_SPLITTED"].str.split(",", expand=True, n=1)
+    df_splitted.columns = ["datalogger_voltage", "rainfall_rate_32bit"]
+    df["rainfall_rate_32bit"] = df_splitted["rainfall_rate_32bit"]
 
-        # - Drop columns not agreeing with DISDRODB L0 standards
-        columns_to_drop = [
-            "id",
-            "TO_BE_SPLITTED",
-            "datalogger_temperature",
-            "datalogger_error",
-            "latitude",
-            "longitude",
-        ]
-        df = df.drop(columns=columns_to_drop)
-        return df
+    # Remove rows with error in data reading
+    # - When datalogger error: rainfall_rate_32bit: Error in data reading!
+    df = df[df["rainfall_rate_32bit"] != "Error in data reading! 0"]
 
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in raw_dir/data/<station_name>
-    glob_patterns = "*.dat.gz"
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "id",
+        "TO_BE_SPLITTED",
+        "datalogger_temperature",
+        "datalogger_error",
+        "latitude",
+        "longitude",
+    ]
+    df = df.drop(columns=columns_to_drop)
 
-    ####----------------------------------------------------------------------.
-    #### - 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,
-        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,
-    )
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL/GPM/IFLOODS.py

@@ -0,0 +1,104 @@
+#!/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 = ["time", "TO_BE_SPLITTED"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # - Define delimiter
+    reader_kwargs["delimiter"] = ";"
+    # - Skip first row as columns names
+    reader_kwargs["header"] = None
+    # - Skip file with encoding errors
+    reader_kwargs["encoding_errors"] = "ignore"
+    # - 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", "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
+    # 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(",", expand=True, n=9)
+
+    # Assign column names
+    columns_names = [
+        "station_name",
+        "sensor_status",
+        "sensor_temperature",
+        "number_particles",
+        "rainfall_rate_32bit",
+        "reflectivity_16bit",
+        "mor_visibility",
+        "weather_code_synop_4680",
+        "weather_code_synop_4677",
+        "raw_drop_number",
+    ]
+    df.columns = columns_names
+
+    # Add the time column
+    df["time"] = df_time
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    df = df.drop(columns=["station_name"])
+
+    # 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]
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/{GPM → PARSIVEL/GPM}/LPVEX.py

@@ -15,27 +15,24 @@
 # 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,
 ):
+    """Reader."""
     ##------------------------------------------------------------------------.
-    #### - Define column names
+    #### Define column names
     column_names = ["time", "unknown", "raw_drop_number"]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = "   "
@@ -59,46 +56,30 @@ def reader(
     #   - 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’
+    #   - 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 dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # - Convert time column to datetime
-        try:
-            df["time"] = pd.to_datetime(df["time"], format="%Y %m %d %H %M %S", errors="coerce")
-        except ValueError:
-            df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
-
-        # - Drop columns not agreeing with DISDRODB L0 standards
-        df = df.drop(columns=["unknown"])
-
-        return df
-
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in raw_dir/data/<station_name>
-    glob_patterns = "*.tar"
-
-    ####----------------------------------------------------------------------.
-    #### - 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
+    # Convert time column to datetime
+    try:
+        df["time"] = pd.to_datetime(df["time"], format="%Y %m %d %H %M %S", errors="coerce")
+    except ValueError:
+        df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    df = df.drop(columns=["unknown"])
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL/GPM/MC3E.py

@@ -0,0 +1,184 @@
+#!/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 = ["time", "TO_BE_SPLITTED"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # - Define delimiter
+    reader_kwargs["delimiter"] = ";"
+    # - Skip first row as columns names
+    reader_kwargs["header"] = None
+    # - Skip file with encoding errors
+    reader_kwargs["encoding_errors"] = "ignore"
+    # - 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
+    # Convert 'time' column to datetime
+    df["time"] = pd.to_datetime(df["time"], format="%Y%m%d%H%M%S", errors="coerce")
+
+    # Count number of delimiters in the column to be parsed
+    # --> Some first rows are corrupted, so count the most frequent occurrence
+    possible_delimiters, counts = np.unique(df["TO_BE_SPLITTED"].str.count(","), return_counts=True)
+    n_delimiters = possible_delimiters[np.argmax(counts)]
+
+    # ---------------------------------------------------------
+    #### Case of 1031 delimiters
+    if n_delimiters == 1031:  # first files
+        # Select valid rows
+        df = df.loc[df["TO_BE_SPLITTED"].str.count(",") == 1031]
+        # Get time column
+        df_time = df["time"]
+        # Split the 'TO_BE_SPLITTED' column
+        df = df["TO_BE_SPLITTED"].str.split(",", expand=True, n=7)
+        # Assign column names
+        column_names = [
+            "station_name",
+            "sensor_status",
+            "sensor_temperature",
+            "reflectivity_32bit",
+            "mor_visibility",
+            "weather_code_synop_4680",
+            "weather_code_synop_4677",
+            "raw_drop_number",
+        ]
+        df.columns = column_names
+        # Add time column
+        df["time"] = df_time
+        # Remove columns not in other files
+        df = df.drop(columns="reflectivity_32bit")
+        # Add missing columns and set NaN value
+        missing_columns = [
+            "number_particles",
+            "rainfall_rate_32bit",
+            "reflectivity_16bit",
+        ]
+        for column in missing_columns:
+            df[column] = "NaN"
+        # Drop columns not agreeing with DISDRODB L0 standards
+        df = df.drop(columns=["station_name"])
+        # Return the dataframe adhering to DISDRODB L0 standards
+        return df
+    # ---------------------------------------------------------
+    #### Case of 1032 delimiters
+    if n_delimiters == 1033:  # (most of the files)
+        # Select valid rows
+        df = df.loc[df["TO_BE_SPLITTED"].str.count(",") == 1033]
+        # Get time column
+        df_time = df["time"]
+        # Split the column be parsed
+        df = df["TO_BE_SPLITTED"].str.split(",", expand=True, n=9)
+        # Assign column names
+        column_names = [
+            "station_name",
+            "sensor_status",
+            "sensor_temperature",
+            "number_particles",
+            "rainfall_rate_32bit",
+            "reflectivity_16bit",
+            "mor_visibility",
+            "weather_code_synop_4680",
+            "weather_code_synop_4677",
+            "raw_drop_number",
+        ]
+        df.columns = column_names
+        # Add time column
+        df["time"] = df_time
+        # Drop columns not agreeing with DISDRODB L0 standards
+        df = df.drop(columns=["station_name"])
+        # Return the dataframe adhering to DISDRODB L0 standards
+        return df
+
+    # ---------------------------------------------------------
+    #### Case of 1035 delimiters
+    if n_delimiters == 1035:  # APU 17 first files
+        # Select valid rows
+        df = df.loc[df["TO_BE_SPLITTED"].str.count(",") == 1035]
+        # Get time column
+        df_time = df["time"]
+        # Split the column be parsed
+        df = df["TO_BE_SPLITTED"].str.split(",", expand=True, n=11)
+        # Assign column names
+        column_names = [
+            "station_name",
+            "sensor_date",
+            "sensor_time",
+            "sensor_status",
+            "sensor_temperature",
+            "number_particles",
+            "rainfall_rate_32bit",
+            "reflectivity_16bit",
+            "mor_visibility",
+            "weather_code_synop_4680",
+            "weather_code_synop_4677",
+            "raw_drop_number",
+        ]
+        df.columns = column_names
+        # Add time column
+        df["time"] = df_time
+        # Drop columns not needed
+        df = df.drop(columns=["sensor_time", "sensor_date"])
+        # Drop columns not agreeing with DISDRODB L0 standards
+        df = df.drop(columns=["station_name"])
+        # Return the dataframe adhering to DISDRODB L0 standards
+        return df
+
+    # ---------------------------------------------------------
+    #### Undefined number of delimiters
+    # - Likely a corrupted file
+    raise ValueError(f"Unexpected number of comma delimiters: {n_delimiters} !")

disdrodb/l0/readers/PARSIVEL/NCAR/CCOPE_2015.py

@@ -0,0 +1,113 @@
+#!/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_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+
+    # 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 encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
+
+    # - 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
+    # Retrieve file start time (date hour:minute)
+    start_time = df["TO_PARSE"].iloc[0]
+    start_time = start_time[0:16]
+    start_time = pd.to_datetime(start_time, format="%m/%d/%Y %H:%M", errors="coerce")
+    df = df.iloc[1:]  # remove start_time row
+
+    # Replace heterogeneous number of spaces with ;
+    df["TO_PARSE"] = df["TO_PARSE"].str.replace(r" +", ";", regex=True)
+
+    # Split into columns and assign name
+    df = df["TO_PARSE"].str.split(";", expand=True)
+    columns = [
+        "MMSSmmm",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "reflectivity_32bit",
+        "number_particles",
+        "sensor_status",
+        "error_code",
+        "raw_drop_concentration",
+        "raw_drop_average_velocity",
+        "raw_drop_number",
+    ]
+    df.columns = columns
+
+    # Define datetime 'time' column
+    dt_minute = df["MMSSmmm"].str[0:2].astype(int).astype("<m8[m]")
+    dt_second = df["MMSSmmm"].str[2:4].astype(int).astype("<m8[s]")
+    df_time = start_time + dt_minute + dt_second
+    df["time"] = df_time
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    df = df.drop(columns=["MMSSmmm"])
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df