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

disdrodb/l0/readers/BRAZIL/CHUVA_OTT.py

@@ -1,183 +0,0 @@
-#!/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/>.
-# -----------------------------------------------------------------------------.
-from disdrodb.l0 import run_l0a
-from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
-
-
-@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,
-):
-    ##------------------------------------------------------------------------.
-    #### - 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"]
-
-    ##------------------------------------------------------------------------.
-    #### - Define dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # Import numpy and pandas
-        import numpy as np
-        import pandas as pd
-
-        # Create ID and Value columns
-        df = df["TO_PARSE"].str.split(":", expand=True, n=1)
-        df.columns = ["ID", "Value"]
-
-        # Drop rows with no values
-        df = df[df["Value"].astype(bool)]
-
-        # Convert ID to integer
-        # - First convert to numeric and if errors arise (corrupted rows), drop rows
-        df["ID"] = pd.to_numeric(df["ID"], errors="coerce")
-        df = df.dropna(subset="ID")
-        df["ID"] = df["ID"].astype(int)
-
-        # Create the dataframe with each row corresponding to a timestep
-        # - Group rows based on when ID values restart
-        groups = df.groupby((df["ID"].diff() <= 0).cumsum())
-
-        # - Reshape the dataframe
-        group_dfs = []
-        for _, group in groups:
-            group_df = group.set_index("ID").T
-            group_dfs.append(group_df)
-
-        # - Merge each timestep dataframe
-        # --> Missing columns are infilled by NaN
-        df = pd.concat(group_dfs, axis=0)
-        df.columns = df.columns.astype(str).str.pad(width=2, side="left", fillchar="0")
-
-        # Define available column names
-        column_dict = {
-            "01": "rainfall_rate_32bit",
-            "02": "rainfall_accumulated_32bit",
-            "03": "weather_code_synop_4680",
-            "04": "weather_code_synop_4677",
-            "05": "weather_code_metar_4678",
-            "06": "weather_code_nws",
-            "07": "reflectivity_32bit",
-            "08": "mor_visibility",
-            "09": "sample_interval",
-            "10": "laser_amplitude",
-            "11": "number_particles",
-            "12": "sensor_temperature",
-            # "13": "sensor_serial_number",
-            # "14": "firmware_iop",
-            # "15": "firmware_dsp",
-            "16": "sensor_heating_current",
-            "17": "sensor_battery_voltage",
-            "18": "sensor_status",
-            # "19": "start_time",
-            "20": "sensor_time",
-            "21": "sensor_date",
-            # "22": "station_name",
-            # "23": "station_number",
-            "24": "rainfall_amount_absolute_32bit",
-            "25": "error_code",
-            "30": "rainfall_rate_16_bit_30",
-            "31": "rainfall_rate_16_bit_1200",
-            "32": "rainfall_accumulated_16bit",
-            "90": "raw_drop_concentration",
-            "91": "raw_drop_average_velocity",
-            "93": "raw_drop_number",
-        }
-
-        # Identify missing columns and add NaN
-        expected_columns = np.array(list(column_dict.keys()))
-        missing_columns = expected_columns[np.isin(expected_columns, df.columns, invert=True)].tolist()
-        if len(missing_columns) > 0:
-            for column in missing_columns:
-                df[column] = "NaN"
-
-        # Rename columns
-        df = df.rename(column_dict, axis=1)
-
-        # - Keep only columns defined in the dictionary
-        df = df[list(column_dict.values())]
-
-        # - Define datetime "time" column
-        df["time"] = df["sensor_date"] + "-" + df["sensor_time"]
-        df["time"] = pd.to_datetime(df["time"], format="%d.%m.%Y-%H:%M:%S", errors="coerce")
-
-        # - Drop columns not agreeing with DISDRODB L0 standards
-        columns_to_drop = [
-            "sensor_date",
-            "sensor_time",
-            # "firmware_iop",
-            # "firmware_dsp",
-            # "sensor_serial_number",
-            # "station_name",
-            # "station_number",
-        ]
-        df = df.drop(columns=columns_to_drop)
-
-        return df
-
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "DISL*"
-
-    ####----------------------------------------------------------------------.
-    #### - 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,
-    )

disdrodb/l0/readers/BRAZIL/GOAMAZON_LPM.py

@@ -1,204 +0,0 @@
-#!/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/>.
-# -----------------------------------------------------------------------------.
-from disdrodb.l0 import run_l0a
-from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
-
-
-@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,
-):
-    ##------------------------------------------------------------------------.
-    #### - Define column names
-    column_names = ["TO_BE_PARSED"]
-
-    ##------------------------------------------------------------------------.
-    #### - 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"]
-
-    ##------------------------------------------------------------------------.
-    #### - Define dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # Count number of delimiters to identify valid rows
-        df = df[df["TO_BE_PARSED"].str.count(";") == 520]
-
-        # Split by ; delimiter
-        df = df["TO_BE_PARSED"].str.split(";", expand=True, n=79)
-
-        # Assign column names
-        column_names = [
-            "start_identifier",
-            "device_address",
-            "sensor_serial_number",
-            "sensor_date",
-            "sensor_time",
-            "weather_code_synop_4677_5min",
-            "weather_code_synop_4680_5min",
-            "weather_code_metar_4678_5min",
-            "precipitation_rate_5min",
-            "weather_code_synop_4677",
-            "weather_code_synop_4680",
-            "weather_code_metar_4678",
-            "precipitation_rate",
-            "rainfall_rate",
-            "snowfall_rate",
-            "precipitation_accumulated",
-            "mor_visibility",
-            "reflectivity",
-            "quality_index",
-            "max_hail_diameter",
-            "laser_status",
-            "static_signal",
-            "laser_temperature_analog_status",
-            "laser_temperature_digital_status",
-            "laser_current_analog_status",
-            "laser_current_digital_status",
-            "sensor_voltage_supply_status",
-            "current_heating_pane_transmitter_head_status",
-            "current_heating_pane_receiver_head_status",
-            "temperature_sensor_status",
-            "current_heating_voltage_supply_status",
-            "current_heating_house_status",
-            "current_heating_heads_status",
-            "current_heating_carriers_status",
-            "control_output_laser_power_status",
-            "reserve_status",
-            "temperature_interior",
-            "laser_temperature",
-            "laser_current_average",
-            "control_voltage",
-            "optical_control_voltage_output",
-            "sensor_voltage_supply",
-            "current_heating_pane_transmitter_head",
-            "current_heating_pane_receiver_head",
-            "temperature_ambient",
-            "current_heating_voltage_supply",
-            "current_heating_house",
-            "current_heating_heads",
-            "current_heating_carriers",
-            "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",
-            "number_particles_unknown_classification_internal_data",
-            "number_particles_class_1",
-            "number_particles_class_1_internal_data",
-            "number_particles_class_2",
-            "number_particles_class_2_internal_data",
-            "number_particles_class_3",
-            "number_particles_class_3_internal_data",
-            "number_particles_class_4",
-            "number_particles_class_4_internal_data",
-            "number_particles_class_5",
-            "number_particles_class_5_internal_data",
-            "number_particles_class_6",
-            "number_particles_class_6_internal_data",
-            "number_particles_class_7",
-            "number_particles_class_7_internal_data",
-            "number_particles_class_8",
-            "number_particles_class_8_internal_data",
-            "number_particles_class_9",
-            "number_particles_class_9_internal_data",
-            "raw_drop_number",
-        ]
-        df.columns = column_names
-
-        # Define datetime "time" column
-        df["time"] = df["sensor_date"] + "-" + df["sensor_time"]
-        df["time"] = pd.to_datetime(df["time"], format="%d.%m.%y-%H:%M:%S", errors="coerce")
-
-        # Drop row if start_identifier different than 00
-        df = df[df["start_identifier"].astype(str) == "00"]
-
-        # Clean raw_drop_number (ignore last "AC" character)
-        df["raw_drop_number"] = df["raw_drop_number"].str[:1760]
-
-        # Drop rows with invalid raw_drop_number
-        df = df[df["raw_drop_number"].astype(str).str.len() == 1760]
-
-        # - Drop columns not agreeing with DISDRODB L0 standards
-        columns_to_drop = [
-            "start_identifier",
-            "device_address",
-            "sensor_serial_number",
-            "sensor_date",
-            "sensor_time",
-        ]
-        df = df.drop(columns=columns_to_drop)
-
-        return df
-
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*/*/DISL*"  # <year>/<month>
-
-    ####----------------------------------------------------------------------.
-    #### - 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,
-    )

disdrodb/l0/readers/BRAZIL/GOAMAZON_OTT.py

@@ -1,183 +0,0 @@
-#!/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/>.
-# -----------------------------------------------------------------------------.
-from disdrodb.l0 import run_l0a
-from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
-
-
-@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,
-):
-    ##------------------------------------------------------------------------.
-    #### - 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"]
-
-    ##------------------------------------------------------------------------.
-    #### - Define dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import numpy and pandas
-        import numpy as np
-        import pandas as pd
-
-        # Create ID and Value columns
-        df = df["TO_PARSE"].str.split(":", expand=True, n=1)
-        df.columns = ["ID", "Value"]
-
-        # Drop rows with no values
-        df = df[df["Value"].astype(bool)]
-
-        # Convert ID to integer
-        # - First convert to numeric and if errors arise (corrupted rows), drop rows
-        df["ID"] = pd.to_numeric(df["ID"], errors="coerce")
-        df = df.dropna(subset="ID")
-        df["ID"] = df["ID"].astype(int)
-
-        # Create the dataframe with each row corresponding to a timestep
-        # - Group rows based on when ID values restart
-        groups = df.groupby((df["ID"].diff() <= 0).cumsum())
-
-        # - Reshape the dataframe
-        group_dfs = []
-        for _, group in groups:
-            group_df = group.set_index("ID").T
-            group_dfs.append(group_df)
-
-        # - Merge each timestep dataframe
-        # --> Missing columns are infilled by NaN
-        df = pd.concat(group_dfs, axis=0)
-        df.columns = df.columns.astype(str).str.pad(width=2, side="left", fillchar="0")
-
-        # Assign column names
-        column_dict = {
-            "01": "rainfall_rate_32bit",
-            "02": "rainfall_accumulated_32bit",
-            "03": "weather_code_synop_4680",
-            "04": "weather_code_synop_4677",
-            "05": "weather_code_metar_4678",
-            "06": "weather_code_nws",
-            "07": "reflectivity_32bit",
-            "08": "mor_visibility",
-            "09": "sample_interval",
-            "10": "laser_amplitude",
-            "11": "number_particles",
-            "12": "sensor_temperature",
-            # "13": "sensor_serial_number",
-            # "14": "firmware_iop",
-            # "15": "firmware_dsp",
-            "16": "sensor_heating_current",
-            "17": "sensor_battery_voltage",
-            "18": "sensor_status",
-            # "19": "start_time",
-            "20": "sensor_time",
-            "21": "sensor_date",
-            # "22": "station_name",
-            # "23": "station_number",
-            "24": "rainfall_amount_absolute_32bit",
-            "25": "error_code",
-            "30": "rainfall_rate_16_bit_30",
-            "31": "rainfall_rate_16_bit_1200",
-            "32": "rainfall_accumulated_16bit",
-            "90": "raw_drop_concentration",
-            "91": "raw_drop_average_velocity",
-            "93": "raw_drop_number",
-        }
-
-        # Identify missing columns and add NaN
-        expected_columns = np.array(list(column_dict.keys()))
-        missing_columns = expected_columns[np.isin(expected_columns, df.columns, invert=True)].tolist()
-        if len(missing_columns) > 0:
-            for column in missing_columns:
-                df[column] = "NaN"
-
-        # Rename columns
-        df = df.rename(column_dict, axis=1)
-
-        # - Keep only columns defined in the dictionary
-        df = df[list(column_dict.values())]
-
-        # - Define datetime "time" column
-        df["time"] = df["sensor_date"] + "-" + df["sensor_time"]
-        df["time"] = pd.to_datetime(df["time"], format="%d.%m.%Y-%H:%M:%S", errors="coerce")
-
-        # - Drop columns not agreeing with DISDRODB L0 standards
-        columns_to_drop = [
-            "sensor_date",
-            "sensor_time",
-            # "firmware_iop",
-            # "firmware_dsp",
-            # "sensor_serial_number",
-            # "station_name",
-            # "station_number",
-        ]
-        df = df.drop(columns=columns_to_drop)
-
-        return df
-
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*/*/DISL*"  # <year>/<month>
-
-    ####----------------------------------------------------------------------.
-    #### - 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,
-    )