disdrodb 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

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

@@ -0,0 +1,109 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+"""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
+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
+    reader_kwargs["skiprows"] = 0
+    # - 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(",", n=3, expand=True)
+
+    # Assign column names
+    names = [
+        "station_name",
+        "unknown",
+        "unknown2",
+        "raw_drop_number",
+    ]
+    df.columns = names
+
+    # Add the time column
+    df["time"] = df_time
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    df = df.drop(columns=["station_name", "unknown", "unknown2"])
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

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

@@ -128,6 +128,7 @@ def reader(
     columns_to_drop = [
         "station_name",
         "station_number",
+        "sensor_serial_number",
         "firmware_iop",
         "firmware_dsp",
         "TO_SPLIT",

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

@@ -108,7 +108,7 @@ def reader(
     # --> "" generates an array of zeros in L0B processing
     df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>ZERO</SPECTRUM>", "")
 
-    # Remove <SPECTRUM> and </SPECTRUM>" acronyms from the raw_drop_number field
+    # Remove <SPECTRUM> and </SPECTRUM> prefix and suffix 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>", "")
 

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

@@ -0,0 +1,126 @@
+#!/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 the PERILS 2022 and 2023 MIPS and RADAPS files."""
+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"
+    # - Avoid first column to become df index !!!
+    reader_kwargs["index_col"] = False
+
+    # - Define behaviour when encountering bad lines
+    reader_kwargs["on_bad_lines"] = "skip"
+
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    # - 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
+    # Split and assign integrated variables names
+    df = df["TO_PARSE"].str.split(",", expand=True, n=6)
+    names = [
+        "year",
+        "doy",
+        "time",
+        "sensor_temperature",
+        "number_particles",
+        "rainfall_rate_32bit",
+        "TO_SPLIT",
+    ]
+    df.columns = names
+
+    # Derive raw drop arrays
+    def split_string(s):
+        vals = [v.strip() for v in s.split(",")]
+        c1 = ", ".join(vals[:32])
+        c2 = ", ".join(vals[32:64])
+        #    c3 = ", ".join(vals[64:])
+        series = pd.Series(
+            {
+                "raw_drop_concentration": c1,
+                "raw_drop_average_velocity": c2,
+                # "raw_drop_number": c3,
+            },
+        )
+        return series
+
+    splitted_string = df["TO_SPLIT"].apply(split_string)
+    df["raw_drop_concentration"] = splitted_string["raw_drop_concentration"]
+    df["raw_drop_average_velocity"] = splitted_string["raw_drop_average_velocity"]
+
+    # Define datetime time column
+    df["year"] = df["year"].str.replace(".0", "")
+    df["doy"] = df["doy"].str.replace(".0", "")
+    df["time"] = df["time"].str.replace(".0", "")
+    df["time"] = df["year"].astype(str) + "-" + df["doy"].astype(str) + " " + df["time"].astype(str)
+    df["time"] = pd.to_datetime(df["time"], format="%Y-%j %H%M%S", errors="coerce")
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "doy",
+        "year",
+        "TO_SPLIT",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

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

@@ -0,0 +1,165 @@
+#!/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 the PERILS 2022 and 2023 PIPS files."""
+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 = [
+        "logger_time",
+        "record_number",
+        "battery_voltage",
+        "logger_temperature",
+        "wind_direction",
+        "wind_speed",
+        "wind_flag",
+        "fast_temperature",
+        "slow_temperature",
+        "relative_humidity",
+        "pressure",
+        "compass_direction",
+        "gps_time",
+        "gps_status",
+        "gps_latitude",  # DD.DM, DM = decimal minutes/100, DD = degrees
+        "gps_latitude_hemisphere",  # N/S
+        "gps_longitude",
+        "gps_longitude_hemisphere",  # W/E
+        "gps_speed",
+        "gps_direction",
+        "gps_date",
+        "gps_magnetic_version",
+        "gps_altitude",
+        "relative_wind_direction",
+        "dew_point_temperature",
+        "rh",
+        "disdrometer_data",
+    ]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+
+    # - Define delimiter
+    reader_kwargs["delimiter"] = ","
+
+    # - 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"]
+
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    ##------------------------------------------------------------------------.
+    #### 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
+    # Drop timesteps without disdrometer data
+    df = df[~df["disdrometer_data"].isna()]
+
+    # Retrieve disdrometer data
+    df_data = df["disdrometer_data"].str.split(";", expand=True, n=11)
+
+    # Assign column names
+    column_names = [
+        "serial_number",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "reflectivity_32bit",
+        "sample_interval",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_battery_voltage",
+        "sensor_time",  # Note: logger_time is currently used !
+        "sensor_date",
+        "raw_drop_number",
+    ]
+    df_data.columns = column_names
+
+    # Add weather information
+    df_data["air_temperature"] = df["fast_temperature"]
+    df_data["relative_humidity"] = df["relative_humidity"]
+    df_data["wind_direction"] = df["wind_direction"]
+    df_data["wind_speed"] = df["wind_speed"]
+
+    # df_data["dew_point"] = df["dew_point"]
+    # df_data["air_pressure"] = df["pressure"]
+
+    # Retrieve time
+    df_time = pd.to_datetime(df["logger_time"], errors="coerce")
+
+    # Retrieve coordinates information
+    # --> Latitude in degrees_north
+    # --> Longitude in degrees_east
+    # df_lat_sign = df["gps_latitude_hemisphere"].str.replace("N", "1").str.replace("S", "-1")
+    # df_lon_sign = df["gps_longitude_hemisphere"].str.replace("E", "1").str.replace("W", "-1")
+    # df_lat_sign = df_lat_sign.astype(float)
+    # df_lon_sign = df_lon_sign.astype(float)
+    # df_lon = df["gps_longitude"].astype(float)
+    # df_lat = df["gps_latitude"].astype(float)
+    # df_lon = df_lon * df_lon_sign
+    # df_lat = df_lat * df_lat_sign
+
+    # Create dataframe
+    df = df_data
+    df["time"] = df_time
+    # df["latitude"] = df_lat
+    # df["longitude"] = df_lon
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    df = df.drop(columns=["serial_number", "sensor_time", "sensor_date", "serial_number"])
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

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

@@ -102,7 +102,7 @@ def reader(
     df["raw_drop_number"] = df["raw_drop_number"].str.strip()
     df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>ZERO</SPECTRUM>", "")
 
-    # Remove <SPECTRUM> and </SPECTRUM>" acronyms from the raw_drop_number field
+    # Remove <SPECTRUM> and </SPECTRUM> prefix and suffix 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>", "")
 

disdrodb/l0/readers/PARSIVEL2/NCAR/VORTEX_SE_2016_PIPS.py

@@ -15,6 +15,9 @@
 # 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 the PERILS 2022 and 2023 PIPS files."""
+import os
+
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
@@ -62,6 +65,7 @@ def reader(
     ##------------------------------------------------------------------------.
     #### Define reader options
     reader_kwargs = {}
+
     # - Define delimiter
     reader_kwargs["delimiter"] = ","
 
@@ -91,6 +95,8 @@ def reader(
 
     # Skip first row as columns names
     reader_kwargs["header"] = None
+    if "FMCW" in os.path.basename(filepath):
+        reader_kwargs["skiprows"] = 1
 
     ##------------------------------------------------------------------------.
     #### Read the data
@@ -135,24 +141,26 @@ def reader(
     # df_data["dew_point"] = df["dew_point"]
     # df_data["air_pressure"] = df["pressure"]
 
-    # Retrieve time and coordinates information
+    # Retrieve time
+    df_time = pd.to_datetime(df["logger_time"], errors="coerce")
+
+    # Retrieve coordinates information
     # --> Latitude in degrees_north
     # --> Longitude in degrees_east
-    df_time = pd.to_datetime(df["logger_time"], errors="coerce")
-    df_lat_sign = df["gps_latitude_hemisphere"].str.replace("N", "1").str.replace("S", "-1")
-    df_lon_sign = df["gps_longitude_hemisphere"].str.replace("E", "1").str.replace("W", "-1")
-    df_lat_sign = df_lat_sign.astype(float)
-    df_lon_sign = df_lon_sign.astype(float)
-    df_lon = df["gps_longitude"].astype(float)
-    df_lat = df["gps_latitude"].astype(float)
-    df_lon = df_lon * df_lon_sign
-    df_lat = df_lat * df_lat_sign
+    # df_lat_sign = df["gps_latitude_hemisphere"].str.replace("N", "1").str.replace("S", "-1")
+    # df_lon_sign = df["gps_longitude_hemisphere"].str.replace("E", "1").str.replace("W", "-1")
+    # df_lat_sign = df_lat_sign.astype(float)
+    # df_lon_sign = df_lon_sign.astype(float)
+    # df_lon = df["gps_longitude"].astype(float)
+    # df_lat = df["gps_latitude"].astype(float)
+    # df_lon = df_lon * df_lon_sign
+    # df_lat = df_lat * df_lat_sign
 
     # Create dataframe
     df = df_data
     df["time"] = df_time
-    df["latitude"] = df_lat
-    df["longitude"] = df_lon
+    # df["latitude"] = df_lat
+    # df["longitude"] = df_lon
 
     # Drop columns not agreeing with DISDRODB L0 standards
     df = df.drop(columns=["serial_number", "sensor_time", "sensor_date", "serial_number"])

disdrodb/l0/readers/PARSIVEL2/NETHERLANDS/DELFT_NC.py

@@ -35,6 +35,8 @@ def reader(
     #### Adapt the dataframe to adhere to DISDRODB L0 standards
     # Add time coordinate
     ds["time"] = ds["time_as_string"].astype("M8[s]")
+    ds["time"].attrs.pop("comment", None)
+    ds["time"].attrs.pop("units", None)
     ds = ds.set_coords("time")
 
     # Define dictionary mapping dataset variables to select and rename
@@ -63,5 +65,8 @@ def reader(
     # Rename dataset variables and columns and infill missing variables
     ds = standardize_raw_dataset(ds=ds, dict_names=dict_names, sensor_name="PARSIVEL2")
 
+    # Replace NaN flags
+    ds["raw_drop_number"] = ds["raw_drop_number"].where(ds["raw_drop_number"] < 65437)  # dummy flag 65437.0
+
     # Return the dataset adhering to DISDRODB L0B standards
     return ds

disdrodb/l0/readers/PARSIVEL2/SPAIN/CENER.py

@@ -0,0 +1,144 @@
+#!/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
+    # - 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
+    # Define time
+    df = df["TO_PARSE"].str.split(",", n=2, expand=True)
+    df.columns = ["date", "time", "TO_PARSE"]
+    datetime_str = df["date"] + " " + df["time"]
+    df["time"] = pd.to_datetime(datetime_str, format="%d.%m.%Y %H:%M:%S", errors="coerce")
+
+    # Identify rows with integral variables
+    df_vars = df[df["TO_PARSE"].str.len() == 94]
+
+    # Split and assign column names
+    df_data = df_vars["TO_PARSE"].str.split(",", expand=True)
+    var_names = [
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "weather_code_synop_4677",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "sensor_status",
+        "sensor_serial_number",
+        "sensor_temperature_receiver",
+        "sensor_temperature_trasmitter",
+        "snowfall_rate",
+        "rain_kinetic_energy",
+    ]
+    df_data.columns = var_names
+    df_data["time"] = df_vars["time"]
+    df_data = df_data.drop(columns="sensor_serial_number")
+
+    # Initialize empty arrays
+    # --> 0 values array produced in L0B
+    df_data["raw_drop_concentration"] = ""
+    df_data["raw_drop_average_velocity"] = ""
+    df_data["raw_drop_number"] = ""
+
+    # Identify raw spectrum
+    df_raw_spectrum = df[df["TO_PARSE"].str.len() == 4545]
+
+    # Derive raw drop arrays
+    def split_string(s):
+        vals = [v.strip() for v in s.split(",")]
+        c1 = ",".join(vals[:32])
+        c2 = ",".join(vals[32:64])
+        c3 = ",".join(vals[64].replace("r", "").split("/"))
+        series = pd.Series(
+            {
+                "raw_drop_concentration": c1,
+                "raw_drop_average_velocity": c2,
+                "raw_drop_number": c3,
+            },
+        )
+        return series
+
+    splitted_string = df_raw_spectrum["TO_PARSE"].apply(split_string)
+    df_raw_spectrum["raw_drop_concentration"] = splitted_string["raw_drop_concentration"]
+    df_raw_spectrum["raw_drop_average_velocity"] = splitted_string["raw_drop_average_velocity"]
+    df_raw_spectrum["raw_drop_number"] = splitted_string["raw_drop_number"]
+    df_raw_spectrum = df_raw_spectrum.drop(columns=["date", "TO_PARSE"])
+
+    # Add raw array
+    df = df_data.set_index("time")
+    df_raw_spectrum = df_raw_spectrum.set_index("time")
+
+    df.update(df_raw_spectrum)
+
+    # Set back time as column
+    df = df.reset_index()
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df