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

disdrodb/l0/readers/{ARM → LPM/ARM}/ARM_LPM.py

@@ -16,21 +16,23 @@
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
 """Reader for ARM Thies LPM sensor."""
-from disdrodb.l0 import run_l0b_from_nc
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.l0.l0b_nc_processing import open_raw_netcdf_file, replace_custom_nan_flags, standardize_raw_dataset
 
 
 @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,
+    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
         "particle_diameter": "diameter_bin_center",
@@ -99,54 +101,30 @@ def reader(
         # 'air_temperature',
     }
 
-    # Define dataset sanitizer
-    def ds_sanitizer_fun(ds):
-        from disdrodb.l0.l0b_nc_processing import replace_custom_nan_flags
-
-        # Replace nan flags with np.nan
-        # - ARM use the -9999 flags
-        nan_flags_variables = [
-            "weather_code_synop_4677_5min",
-            "weather_code_synop_4680_5min",
-            "weather_code_synop_4680",
-            "weather_code_synop_4677",
-            "mor_visibility",
-            "quality_index",
-            "temperature_interior",
-            "laser_temperature",
-            "laser_current_average",
-            "number_particles",
-            "number_particles_min_speed",
-            "number_particles_max_speed",
-            "number_particles_min_diameter",
-            "number_particles_max_diameter",
-            "raw_drop_number",
-        ]
-        dict_nan_flags = {var: [-9999] for var in nan_flags_variables}
-        ds = replace_custom_nan_flags(ds, dict_nan_flags=dict_nan_flags)
-
-        # Return dataset
-        return ds
-
-    # Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*.nc"
-
-    ####----------------------------------------------------------------------.
-    #### - Create L0A products
-    run_l0b_from_nc(
-        raw_dir=raw_dir,
-        processed_dir=processed_dir,
-        station_name=station_name,
-        # Custom arguments of the reader
-        glob_patterns=glob_patterns,
-        dict_names=dict_names,
-        ds_sanitizer_fun=ds_sanitizer_fun,
-        # Processing options
-        force=force,
-        verbose=verbose,
-        parallel=parallel,
-        debugging_mode=debugging_mode,
-    )
+    # Rename dataset variables and columns and infill missing variables
+    ds = standardize_raw_dataset(ds=ds, dict_names=dict_names, sensor_name="LPM")
 
+    # Replace nan flags with np.nan
+    # - ARM use the -9999 flags
+    nan_flags_variables = [
+        "weather_code_synop_4677_5min",
+        "weather_code_synop_4680_5min",
+        "weather_code_synop_4680",
+        "weather_code_synop_4677",
+        "mor_visibility",
+        "quality_index",
+        "temperature_interior",
+        "laser_temperature",
+        "laser_current_average",
+        "number_particles",
+        "number_particles_min_speed",
+        "number_particles_max_speed",
+        "number_particles_min_diameter",
+        "number_particles_max_diameter",
+        "raw_drop_number",
+    ]
+    dict_nan_flags = {var: [-9999] for var in nan_flags_variables}
+    ds = replace_custom_nan_flags(ds, dict_nan_flags=dict_nan_flags, logger=logger)
 
-# -----------------------------------------------------------------.
+    # Return the dataset adhering to DISDRODB L0B standards
+    return ds

disdrodb/l0/readers/LPM/AUSTRALIA/MELBOURNE_2007_LPM.py

@@ -0,0 +1,236 @@
+#!/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 = ["TO_BE_PARSED"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "#"
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+    # Skip first 3 rows
+    reader_kwargs["skiprows"] = 2
+    # - 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"]  # NP
+
+    ##------------------------------------------------------------------------.
+    #### 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 rows with invalid length
+    # - time: 20
+    # - data: 2229
+    df = df[df["TO_BE_PARSED"].str.len().isin([20, 2229])]
+    df = df.reset_index(drop=True)
+    # Remove rows with consecutive timesteps
+    # - Keep last timestep occurrence
+    idx_timesteps = np.where(df["TO_BE_PARSED"].str.len() == 20)[0]
+    idx_without_data = np.where(np.diff(idx_timesteps) == 1)[0].flatten().astype(int)
+    idx_timesteps_without_data = idx_timesteps[idx_without_data]
+    df = df.drop(labels=idx_timesteps_without_data)
+
+    # If the last row is a timestep, remove it
+    if df["TO_BE_PARSED"].str.len().iloc[-1] == 20:
+        df = df[:-1]
+
+    # Check there are data to process
+    if len(df) == 0 or len(df) == 1:
+        raise ValueError("No data to process.")
+
+    # Retrieve time column and format in datetime64
+    df_time = df[::2]
+    df_time = df_time.reset_index(drop=True)
+    df_time = df_time["TO_BE_PARSED"].str.replace("-", "", n=1)
+    df_time = pd.to_datetime(df_time, format="%Y-%m-%d %H:%M:%S", errors="coerce")
+
+    # Retrieve data
+    df_data = df[1::2]
+    df_data = df_data.reset_index(drop=True)
+
+    if len(df_time) != len(df_data):
+        raise ValueError("Likely corrupted data. Not same number of timesteps and data.")
+
+    # Create dataframe
+    df_data["time"] = df_time.to_numpy()
+
+    # Drop rows with invalid time
+    df_data = df_data.dropna(subset="time")
+
+    # Count number of delimiters to identify valid rows
+    df_data = df_data[df_data["TO_BE_PARSED"].str.count(";") == 524]
+
+    # Split by ; delimiter
+    df = df_data["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",
+        "TO_BE_FURTHER_PROCESSED",
+    ]
+    df.columns = column_names
+
+    # Extract the last variables remained in raw_drop_number
+    df_parsed = df["TO_BE_FURTHER_PROCESSED"].str.rsplit(";", n=6, expand=True)
+    df_parsed.columns = [
+        "raw_drop_number",
+        "air_temperature",
+        "relative_humidity",
+        "wind_speed",
+        "wind_direction",
+        "checksum",
+        "dummy",
+    ]
+
+    # Assign columns to the original dataframe
+    df[df_parsed.columns] = df_parsed
+
+    # Drop row if start_identifier different than 00
+    df["time"] = df_data["time"]
+    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",
+        "TO_BE_FURTHER_PROCESSED",
+        "checksum",
+        "dummy",
+    ]
+    df = df.drop(columns=columns_to_drop)
+    return df

disdrodb/l0/readers/LPM/BRAZIL/CHUVA_LPM.py

@@ -0,0 +1,185 @@
+#!/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_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"]
+
+    ##------------------------------------------------------------------------.
+    #### 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
+    # 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")
+
+    # TODO: correct time is unavailable yet !
+
+    # Drop row if start_identifier different than 00
+    df = df[df["start_identifier"].astype(str) == "00"]
+
+    # 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() == 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