disdrodb 0.0.21__py3-none-any.whl → 0.1.1__py3-none-any.whl

disdrodb/l0/readers/PARSIVEL2/FRANCE/SIRTA_PARSIVEL2.py

@@ -0,0 +1,119 @@
+#!/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
+    # Skip the first row (header)
+    reader_kwargs["skiprows"] = 1
+    # - Define behaviour when encountering bad lines
+    reader_kwargs["on_bad_lines"] = "skip"
+    # Define encoding
+    reader_kwargs["encoding"] = "latin1"
+    # - 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
+    # The delimiter ; is used for separating both the variables and the
+    #   values of the raw spectrum. So we need to retrieve the columns
+    #   inside the sanitizer assuming a fixed number of columns.
+    df = df["TO_SPLIT"].str.split(";", expand=True, n=16)
+
+    # Define the column names
+    column_names = [
+        "date",
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "rain_kinetic_energy",
+        "snowfall_rate",
+        "weather_code_synop_4680",
+        "weather_code_metar_4678",
+        "weather_code_nws",
+        "raw_drop_number",
+    ]
+    df.columns = column_names
+
+    # Define the 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"].str.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/PARSIVEL2/GPM/GCPEX.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 = {}
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+    # Skip file with encoding errors
+    reader_kwargs["encoding_errors"] = "ignore"
+    # - 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 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
+    # Define 'time' 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=9, expand=True)
+
+    # 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 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/PARSIVEL2/GPM/NSSTC.py

@@ -0,0 +1,176 @@
+#!/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
+    # NOTE: Has to deal with changing file format after 25 feb 2011 by the documentation
+    # --> https://ghrc.nsstc.nasa.gov/pub/fieldCampaigns/gpmValidation/relatedProjects/nsstc/parsivel/doc/gpm_parsivel_nsstc_dataset.html).
+
+    # Check 'time' string length to detect corrupted rows
+    df = df[df["time"].str.len() == 14]
+
+    # 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)]
+
+    if n_delimiters == 1027:  # APU 2010
+        # Select valid rows
+        df = df.loc[df["TO_BE_SPLITTED"].str.count(",") == 1027]
+        # Get time column
+        df_time = df["time"]
+        # Split the 'TO_BE_SPLITTED' column
+        df = df["TO_BE_SPLITTED"].str.split(",", expand=True, n=3)
+        # Assign column names
+        column_names = [
+            "station_name",
+            "sensor_status",
+            "sensor_temperature",
+            "raw_drop_number",
+        ]
+        df.columns = column_names
+        # Add time column
+        df["time"] = df_time
+        # Add missing columns and set NaN value
+        missing_columns = [
+            "number_particles",
+            "rainfall_rate_32bit",
+            "reflectivity_16bit",
+            "mor_visibility",
+            "weather_code_synop_4680",
+            "weather_code_synop_4677",
+        ]
+        for column in missing_columns:
+            df[column] = "NaN"
+    elif n_delimiters == 1031:  # APU08 (2011)
+        # 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"
+    elif n_delimiters == 1033:
+        # 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
+    else:
+        # Wrong number of delimiters ... likely a corrupted file
+        raise ValueError("Unexpected number of comma delimiters !")
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    df = df.drop(columns=["station_name"])
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL2/ITALY/GID_PARSIVEL2.py

@@ -0,0 +1,32 @@
+#!/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  # noqa
+
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.l0.l0a_processing import read_raw_text_file  # noqa
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    raise NotImplementedError

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"].str.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