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

disdrodb/l0/readers/LPM/UK/WITHWORTH_LPM.py

@@ -0,0 +1,219 @@
+#!/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 the MANCHESTER Withworth Meteorological Observatory LPM sensor."""
+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"] = "latin"
+
+    # 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([45, 522])]
+
+    # 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)
+    # - Add a dummy row with 82 delimiters so that str.split expand also if only 45 delimiters are present
+    dummy_row = ";".join(["DUMMY"] * 82)
+    df = pd.concat([df, pd.DataFrame({"TO_PARSE": [dummy_row]})], ignore_index=True)
+    # - Split columns
+    df = df["TO_PARSE"].str.split(";", expand=True, n=81)
+    # - Drop the dummy row (last one)
+    df = df.iloc[:-1, :]
+    # - Fill empty columns
+    df.loc[:, 46:50] = df.loc[:, 46:50].fillna("NaN")
+    df.loc[:, 51:] = df.loc[:, 51:].fillna("0")
+
+    # Assign column names
+    names = [
+        "date",
+        "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
+
+    # Define 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")
+
+    # Remove checksum from raw_drop_number
+    df["raw_drop_number"] = df["raw_drop_number"].str.rsplit(";", n=2, expand=True)[0]
+
+    # Drop rows with invalid raw_drop_number
+    df = df[df["raw_drop_number"].astype(str).str.len().isin([1, 1759])]
+
+    # Drop row if start_identifier different than 00
+    # df["start_identifier"] = df["start_identifier"].astype(str).str[-2:]
+    # df = df[df["start_identifier"] == "00"]
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "start_identifier",
+        "device_address",
+        "sensor_serial_number",
+        "sensor_date",
+        "sensor_time",
+        "date",
+    ]
+    df = df.drop(columns=columns_to_drop)
+    return df

disdrodb/l0/readers/LPM/USA/CHARLESTON.py

@@ -0,0 +1,229 @@
+#!/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 CHARLESTON experiment LPM sensors."""
+import os
+
+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(";") == 520]
+
+    # 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=79)
+
+    # Assign column names
+    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_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]
+
+    # Remove corrupted characters
+    df = df.replace("°", "", regex=True)  # station N
+
+    # Keep only rows where sensor_time matches HH:MM:SS format
+    df = df[df["sensor_time"].astype(str).str.match(r"^\d{2}:\d{2}:\d{2}$")]
+
+    # Keep only rows with valid spectrum
+    df = df[df["raw_drop_number"].astype(str).str.match(r"^(?:\d{3};)*\d{3};?$")]
+    if len(df) == 0:
+        raise ValueError("Spectra is corrupted")
+
+    # Define datetime "time" column
+    # - Define start time
+    filename = os.path.basename(filepath)
+    _, delta_dt, doy, year = filename.split(".")[0].split("_")
+    start_time = pd.to_datetime(f"{year}_{doy}", format="%y_%j") + pd.to_timedelta(int(delta_dt), unit="s")
+    # - Define timedelta based on sensor_time
+    # --> Add +24h to subsequent times when time resets
+    dt = pd.to_timedelta(df["sensor_time"]).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 measurement datetime
+    df["time"] = start_time + dt
+
+    # 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 = [
+        "start_identifier",
+        "device_address",
+        "sensor_serial_number",
+        "sensor_date",
+        "sensor_time",
+    ]
+    df = df.drop(columns=variables_to_drop)
+    return df

disdrodb/l0/readers/{LPM → LPM_V0}/BELGIUM/ULIEGE.py

@@ -88,31 +88,22 @@ def read_txt_file(file, filename, logger):
     df = df["TO_PARSE"].str.split(";", expand=True, n=43)
 
     # Assign column names
-    column_names = [
-        "id",
-        "sample_interval",
-        "weather_code_synop_4677_5min",  # or  "weather_code_synop_4680_5min",
+    names = [
+        "start_identifier",
+        "sensor_serial_number",
+        "weather_code_synop_4680_5min",
         "weather_code_metar_4678_5min",
         "precipitation_rate_5min",
-        "weather_code_synop_4677",  # or "weather_code_synop_4680",
+        "weather_code_synop_4680",
         "weather_code_metar_4678",
         "precipitation_rate",
         "precipitation_accumulated",
         "sensor_time",
-        # "mor_visibility",
-        # "reflectivity",
-        # "quality_index",
-        # "max_hail_diameter",
-        # "laser_status",
-        "dummy1",
-        "dummy2",
-        # "laser_temperature",
+        "temperature_interior",
+        "laser_temperature",
         "laser_current_average",
         "control_voltage",
         "optical_control_voltage_output",
-        # "current_heating_house",
-        # "current_heating_heads",
-        # "current_heating_carriers",
         "number_particles",
         "number_particles_internal_data",
         "number_particles_min_speed",
@@ -123,29 +114,27 @@ def read_txt_file(file, filename, logger):
         "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",
+        "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 = column_names
+    df.columns = names
 
     # Deal with case if there are 61 timesteps
     # - Occurs sometimes when previous hourly file miss timesteps
@@ -163,7 +152,12 @@ def read_txt_file(file, filename, logger):
     start_time = pd.to_datetime(start_time_str, format="%Y%m%d%H")
 
     # - Define timedelta based on sensor_time
+    # --> Add +24h to subsequent times when time resets
     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
@@ -173,25 +167,15 @@ def read_txt_file(file, filename, logger):
     valid_rows = dt <= np.timedelta64(3540, "s")
     df = df[valid_rows]
 
-    # Drop rows where sample interval is not 60 seconds
-    df = df[df["sample_interval"] == "000060"]
-
     # Drop rows with invalid raw_drop_number
-    # --> 440 value # 22x20
     # --> 400 here  # 20x20
     df = df[df["raw_drop_number"].astype(str).str.len() == 1599]
 
-    # Deal with old LPM version 20x20 spectrum
-    # - Add 000 in first two velocity bins
-    df["raw_drop_number"] = df["raw_drop_number"] + ";" + ";".join(["000"] * 40)
-
     # Drop columns not agreeing with DISDRODB L0 standards
     columns_to_drop = [
-        "sample_interval",
+        "start_identifier",
+        "sensor_serial_number",
         "sensor_time",
-        "dummy1",
-        "dummy2",
-        "id",
     ]
     df = df.drop(columns=columns_to_drop)
     return df