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

disdrodb/l0/readers/LPM/NETHERLANDS/DELFT_RWANDA_LPM_NC.py

@@ -0,0 +1,103 @@
+# -----------------------------------------------------------------------------.
+# 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 RWANDA DELFT Thies LPM sensor in netCDF format."""
+
+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
+    # Add time coordinate
+    ds["time"] = ds["time"].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
+    dict_names = {
+        ### Dimensions
+        "diameter_classes": "diameter_bin_center",
+        "velocity_classes": "velocity_bin_center",
+        ### Variables
+        "weather_code_synop_4680": "weather_code_synop_4680",
+        "weather_code_synop_4677": "weather_code_synop_4677",
+        "weather_code_metar_4678": "weather_code_metar_4678",
+        "liquid_precip_intensity": "rainfall_rate",
+        "solid_precip_intensity": "snowfall_rate",
+        "all_precip_intensity": "precipitation_rate",
+        "reflectivity": "reflectivity",
+        "visibility": "mor_visibility",
+        "measurement_quality": "quality_index",
+        "maximum_diameter_hail": "max_hail_diameter",
+        "status_laser": "laser_status",
+        "status_output_laser_power": "control_output_laser_power_status",
+        "interior_temperature": "temperature_interior",
+        "temperature_of_laser_driver": "laser_temperature",
+        "mean_value_laser_current": "laser_current_average",
+        "control_voltage": "control_voltage",
+        "optical_control_output": "optical_control_voltage_output",
+        "voltage_sensor_supply": "sensor_voltage_supply",
+        "current_heating_laser_head": "current_heating_pane_transmitter_head",
+        "current_heating_receiver_head": "current_heating_pane_receiver_head",
+        "ambient_temperature": "temperature_ambient",
+        "voltage_heating_supply": "current_heating_voltage_supply",
+        "current_heating_housing": "current_heating_house",
+        "current_heating_heads": "current_heating_heads",
+        "current_heating_carriers": "current_heating_carriers",
+        "number_of_all_measured_particles": "number_particles",
+        "number_of_particles_slower_than_0.15": "number_particles_min_speed",
+        "number_of_particles_faster_than_20": "number_particles_max_speed",
+        "number_of_particles_smaller_than_0.15": "number_particles_min_diameter",
+        "number_of_particles_with_unknown_classification": "number_particles_unknown_classification",
+        "total_volume_gross_particles_unknown_classification": "number_particles_unknown_classification_internal_data",
+        "number_of_particles_class_1": "number_particles_class_1",
+        "total_volume_gross_of_class_1": "number_particles_class_1_internal_data",
+        "number_of_particles_class_2": "number_particles_class_2",
+        "total_volume_gross_of_class_2": "number_particles_class_2_internal_data",
+        "number_of_particles_class_3": "number_particles_class_3",
+        "total_volume_gross_of_class_3": "number_particles_class_3_internal_data",
+        "number_of_particles_class_4": "number_particles_class_4",
+        "total_volume_gross_of_class_4": "number_particles_class_4_internal_data",
+        "number_of_particles_class_5": "number_particles_class_5",
+        "total_volume_gross_of_class_5": "number_particles_class_5_internal_data",
+        "number_of_particles_class_6": "number_particles_class_6",
+        "total_volume_gross_of_class_6": "number_particles_class_6_internal_data",
+        "number_of_particles_class_7": "number_particles_class_7",
+        "total_volume_gross_of_class_7": "number_particles_class_7_internal_data",
+        "number_of_particles_class_8": "number_particles_class_8",
+        "total_volume_gross_of_class_8": "number_particles_class_8_internal_data",
+        "number_of_particles_class_9": "number_particles_class_9",
+        "total_volume_gross_of_class_9": "number_particles_class_9_internal_data",
+        "raw_data": "raw_drop_number",
+    }
+
+    # Rename dataset variables and columns and infill missing variables
+    ds = standardize_raw_dataset(ds=ds, dict_names=dict_names, sensor_name="LPM")
+
+    # Return the dataset adhering to DISDRODB L0B standards
+    return ds

disdrodb/l0/readers/LPM/NORWAY/HAUKELISETER_LPM.py

@@ -0,0 +1,216 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+"""DISDRODB reader for Haukeliseter Test Site LPM sensors."""
+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 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
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
+
+    # - 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=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(";").isin([520, 521])]
+
+    # Raise error if no data left
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}.")
+
+    # Retrieve most frequent number of delimiters
+    possible_delimiters, counts = np.unique(df["TO_PARSE"].str.count(";"), return_counts=True)
+    n_delimiters = possible_delimiters[np.argmax(counts)]
+
+    if n_delimiters == 520:
+        n = 79
+        columns_to_drop = ["device_address", "sensor_serial_number"]
+    else:  # n_delimiters == 521
+        n = 80
+        columns_to_drop = ["start_identifier", "device_address", "sensor_serial_number"]
+
+    # Split by ; delimiter (before raw drop number)
+    df = df["TO_PARSE"].str.split(";", expand=True, n=n)
+
+    # Assign column names
+    names = [
+        "time",
+        *columns_to_drop,
+        "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_status",
+        "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",
+        "reserved_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 = names
+
+    # Remove checksum from raw_drop_number
+    df["raw_drop_number"] = df["raw_drop_number"].str.rsplit(";", n=2, expand=True)[0]
+
+    # Define datetime "time" column
+    if n_delimiters == 520:
+        time_str = df["time"].str.extract(r"(\d{8}_\d{6})")[0]
+        df["time"] = pd.to_datetime(time_str, format="%Y%m%d_%H%M%S", errors="coerce")
+    else:
+        time_str = df["time"].str.extract(r"(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})")[0]
+        df["time"] = pd.to_datetime(time_str, format="%Y-%m-%d %H:%M:%S", errors="coerce")
+
+    # Drop rows with invalid raw_drop_number
+    df = df[df["raw_drop_number"].astype(str).str.len() == 1759]
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    variables_to_drop = [
+        *columns_to_drop,
+        "sensor_date",
+        "sensor_time",
+    ]
+    df = df.drop(columns=variables_to_drop)
+    return df

disdrodb/l0/readers/LPM/NORWAY/NMBU_LPM.py

@@ -0,0 +1,208 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+"""DISDRODB reader for NMBU BIOKLIM LPM sensor."""
+import os
+
+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 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=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(";") == 525]
+
+    # Raise error if no data left
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}.")
+
+    # Split by ; delimiter (before raw drop number)
+    df = df["TO_PARSE"].str.split(";", expand=True, n=80)
+
+    # Assign column names
+    names = [
+        "time",
+        "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_status",
+        "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",
+        "reserved_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 = names
+
+    # Remove checksum from raw_drop_number
+    df["raw_drop_number"] = df["raw_drop_number"].str.rsplit(";", n=6, expand=True)[0]
+
+    # Define datetime "time" column
+    # df["time"] = df["sensor_date"] + "-" + df["sensor_time"]
+    date_str = os.path.basename(filepath).split(".")[0]
+    time_str = date_str + "T" + df["time"]
+    df["time"] = pd.to_datetime(time_str, format="%Y-%m-%dT%H:%M:%S", errors="coerce")
+
+    # Drop row if start_identifier different than 00
+    # df = df[df["start_identifier"].astype(str) == "00"]
+
+    # Drop rows with invalid raw_drop_number
+    df = df[df["raw_drop_number"].astype(str).str.len() == 1759]
+
+    # 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