disdrodb 0.2.0__py3-none-any.whl → 0.2.1__py3-none-any.whl

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/NASA/LPVEX.py

@@ -29,22 +29,19 @@ def reader(
     """Reader."""
     ##------------------------------------------------------------------------.
     #### Define column names
-    column_names = ["time", "unknown", "raw_drop_number"]
+    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
     # - Skip file with encoding errors
     reader_kwargs["encoding_errors"] = "ignore"
-    # - Need for zipped raw file (NASA files)
-    reader_kwargs["zipped"] = True
-    # - Searched file into tar files
-    reader_kwargs["filename_to_read_zipped"] = "spectrum.txt"
-    # - Avoid first column to become df index
+    # - Avoid first column to become df index !!!
     reader_kwargs["index_col"] = False
     # - Define behaviour when encountering bad lines
     reader_kwargs["on_bad_lines"] = "skip"
@@ -59,7 +56,7 @@ def reader(
     #   - 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", "-.-"]
+    reader_kwargs["na_values"] = ["na", "", "error", "NA", "-.-"]
 
     ##------------------------------------------------------------------------.
     #### Read the data
@@ -72,14 +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
-    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")
+    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"]
+
+    # Add time
+    df["time"] = df_time
 
     # Drop columns not agreeing with DISDRODB L0 standards
-    df = df.drop(columns=["unknown"])
+    df = df.drop(columns=["station_id"])
 
     # Return the dataframe adhering to DISDRODB L0 standards
     return df

disdrodb/l0/readers/PARSIVEL/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

disdrodb/l0/readers/PARSIVEL2/BASQUECOUNTRY/EUSKALMET_OTT2.py

@@ -124,7 +124,7 @@ def read_txt_file(file, filename, logger):
     # Select rows with valid spectrum
     # df = df[df["TO_PARSE"].str.count(";") == 1191]  # 1112
 
-    # Raise errof if corrupted file
+    # Raise error if corrupted file
     if len(df) == 4:
         raise ValueError(f"{filename} is corrupted.")
 

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

@@ -0,0 +1,155 @@
+# -----------------------------------------------------------------------------.
+# 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 Colorado State University PRECIP OTT Parsivel 2 raw data."""
+
+import pandas as pd
+
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.l0.l0a_processing import read_raw_text_file
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
+    column_names = ["TO_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+
+    # - Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    # - Skip header
+    reader_kwargs["skiprows"] = 0
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
+
+    # - Avoid first column to become df index !!!
+    reader_kwargs["index_col"] = False
+
+    # - Define behaviour when encountering bad lines
+    reader_kwargs["on_bad_lines"] = "skip"
+
+    # - Define reader engine
+    #   - C engine is faster
+    #   - Python engine is more feature-complete
+    reader_kwargs["engine"] = "python"
+
+    # - Define on-the-fly decompression of on-disk data
+    #   - Available: gzip, bz2, zip
+    # reader_kwargs['compression'] = 'xz'
+
+    # - Strings to recognize as NA/NaN and replace with standard NA flags
+    #   - Already included: '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN',
+    #                       '-NaN', '-nan', '1.#IND', '1.#QNAN', '<NA>', 'N/A',
+    #                       'NA', 'NULL', 'NaN', 'n/a', 'nan', 'null'
+    reader_kwargs["na_values"] = ["na", "error", "-.-", " NA"]
+
+    ##------------------------------------------------------------------------.
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
+
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Raise error if empty file
+    if len(df) == 0:
+        raise ValueError(f"{filepath} is empty.")
+
+    # Select only rows with expected number of delimiters
+    df = df[df["TO_PARSE"].str.count(",") == 1041]
+
+    # Raise error if no data left
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}.")
+
+    # Split into columns
+    df = df["TO_PARSE"].str.split(",", expand=True, n=17)
+
+    # Assign columns names
+    names = [
+        "date",
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "weather_code_metar_4678",
+        "weather_code_nws",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "sensor_status",
+        "rain_kinetic_energy",
+        "snowfall_rate",
+        "raw_drop_number",
+    ]
+    df.columns = names
+
+    # Add datetime time column
+    time_str = df["date"] + "-" + df["time"]
+    df["time"] = pd.to_datetime(time_str, format="%d.%m.%Y-%H:%M:%S", errors="coerce")
+
+    # Derive the raw spectrum
+    # Remove <SPECTRUM> and </SPECTRUM> prefix and suffix from the raw_drop_number field
+    df["raw_drop_number"] = df["raw_drop_number"].astype("string")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>", "")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("</SPECTRUM>", "")
+
+    # Preprocess the raw spectrum and raw_drop_average_velocity
+    # - Add 0 before every ; if ; not preceded by a digit
+    # - Example: ';;1;;' --> '0;0;1;0;'
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace(r"(?<!\d),", "0,", regex=True)
+
+    # Infill missing timesteps with raw_drop_number = 0 spectrum
+    # - Define the full time range with 30-second frequency
+    full_time_index = pd.date_range(start=df["time"].iloc[0], end=df["time"].iloc[-1], freq="30s")
+
+    # - Reindex the DataFrame to include all 30-second timesteps
+    df = df.set_index("time").reindex(full_time_index)
+
+    # - Fill missing raw_drop_number with 0
+    df["raw_drop_number"] = df["raw_drop_number"].fillna(0)
+
+    # - Restore 'time' as a column
+    df = df.rename_axis("time").reset_index()
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "date",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

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

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

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

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

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

@@ -44,13 +44,13 @@ 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
@@ -84,6 +84,20 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Remove rows with invalid number of separators
+    df = df[df["TO_PARSE"].str.count(";") == 1]
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}")
+
+    # Retrieve time and telegram field
+    df = df["TO_PARSE"].str.split(";", expand=True)
+    df.columns = ["time", "TO_BE_SPLITTED"]
+
+    # Remove rows with invalid number of separators
+    df = df[df["TO_BE_SPLITTED"].str.count(",") == 1033]
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}")
+
     # Convert time column to datetime
     df_time = pd.to_datetime(df["time"], format="%Y%m%d%H%M%S", errors="coerce")
 
@@ -91,7 +105,7 @@ def reader(
     df = df["TO_BE_SPLITTED"].str.split(",", n=9, expand=True)
 
     # Assign column names
-    names = [
+    columns_names = [
         "station_name",
         "sensor_status",
         "sensor_temperature",
@@ -103,7 +117,7 @@ def reader(
         "weather_code_synop_4677",
         "raw_drop_number",
     ]
-    df.columns = names
+    df.columns = columns_names
 
     # Add the time column
     df["time"] = df_time
@@ -111,10 +125,19 @@ def reader(
     # Drop columns not agreeing with DISDRODB L0 standards
     df = df.drop(columns=["station_name"])
 
+    # Remove rows with invalid raw drop number
+    # --> Occurs e.g. in UCONN apu28
+    # def mask_invalid_raw_drop_number(df)
+    #     df_split = df["raw_drop_number"].str.split(",", expand=True)
+    #     idx = np.where(np.any(df_split.astype(float) > 998, axis=1))[0]
+    #     df.loc[idx, "raw_drop_number"] = "NaN"
+    #     return df
+    df = df[df["raw_drop_number"].str.len() == 4096]
+
     # Drop rows with invalid values
     # --> Ensure that weather_code_synop_4677 has length 2
     # --> If a previous column is missing it will have 000
-    df = df[df["weather_code_synop_4677"].str.len() == 2]
+    # df = df[df["weather_code_synop_4677"].str.len() == 2]
 
     # Return the dataframe adhering to DISDRODB L0 standards
     return df

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

@@ -42,7 +42,7 @@ def reader(
     # - Define encoding
     reader_kwargs["encoding"] = "ISO-8859-1"
 
-    # Skip first row as columns names
+    # - Skip first row as columns names
     reader_kwargs["header"] = None
 
     # - Avoid first column to become df index !!!