disdrodb 0.1.0__py3-none-any.whl → 0.1.2__py3-none-any.whl

disdrodb/l0/readers/LPM/ITALY/GID_LPM_W.py

@@ -0,0 +1,210 @@
+#!/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 GID LPM sensors measuring also wind."""
+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_BE_SPLITTED"]
+
+    ##------------------------------------------------------------------------.
+    #### 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
+    # Count number of delimiters to identify valid rows
+    df = df[df["TO_BE_SPLITTED"].str.count(";") == 523]
+
+    # Split by ; delimiter (before raw drop number)
+    df = df["TO_BE_SPLITTED"].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=5, expand=True)
+    df_parsed.columns = [
+        "raw_drop_number",
+        "air_temperature",
+        "relative_humidity",
+        "wind_speed",
+        "wind_direction",
+        "checksum",
+    ]
+
+    # Assign columns to the original dataframe
+    df[df_parsed.columns] = df_parsed
+
+    # 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"]
+
+    # 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",
+        "checksum",
+        "relative_humidity",  # TO DROP? ALWAYS NOT AVAILABLE?
+        "TO_BE_FURTHER_PROCESSED",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    return df

disdrodb/l0/readers/LPM/KIT/CHWALA.py

@@ -0,0 +1,225 @@
+#!/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 GID LPM sensors not measuring wind."""
+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."""
+
+    def read_txt_file(file, filename):
+        ##------------------------------------------------------------------------.
+        #### - Define raw data headers
+        column_names = ["TO_BE_SPLITTED"]
+
+        ##------------------------------------------------------------------------.
+        #### 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=file,
+            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_SPLITTED"].str.count(";") == 520]
+
+        # Split by ; delimiter (before raw drop number)
+        df = df["TO_BE_SPLITTED"].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
+
+        # 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 from file name
+        datetime_str = "".join(filename.split("_")[1:3])
+        df["time"] = pd.to_datetime(datetime_str, format="%Y%m%d%H%M", 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 the dataframe adhering to DISDRODB L0 standards
+        return df
+
+    #### TEMPORARY: to read just a single 1-min timestep
+    df = read_txt_file(file=filepath, filename=os.path.basename(filepath))
+
+    #### FUTURE: Iterate over all files (aka 1-min timesteps) in the daily zip archive
+    # - Each file contain a single timestep !
+    # list_df = []
+    # with zipfile.ZipFile(filepath, "r") as zip_ref:
+    #     filenames = sorted(zip_ref.namelist())
+    #     for filename in filenames:
+    #         if filename.endswith(".dat"):
+    #             # Open file
+    #             with zip_ref.open(filename) as file:
+    #                 try:
+    #                     df = read_txt_file(file=file, filename=filename)
+    #                     list_df.append(df)
+    #                 except Exception as e:
+    #                     msg = f"An error occurred while reading {filename}. The error is: {e}."
+    #                     log_error(logger=logger, msg=msg, verbose=True)
+
+    # Concatenate all dataframes into a single one
+    # df = pd.concat(list_df)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/LPM/SLOVENIA/ARSO.py

@@ -0,0 +1,197 @@
+#!/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 GID LPM sensors not measuring wind."""
+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
+    # Count number of delimiters to identify valid rows
+    df = df[df["TO_PARSE"].str.count(";") == 521]
+
+    # Split by ; delimiter (before raw drop number)
+    df = df["TO_PARSE"].str.split(";", expand=True, n=80)
+
+    # Assign column names
+    column_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",
+        "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
+
+    # 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
+    time = df["time"].str.extract(r"(\d{2}/\d{2}/\d{4} \d{2}:\d{2}:\d{2})")[0]
+    df["time"] = pd.to_datetime(time, format="%d/%m/%Y %H:%M:%S", errors="coerce")
+
+    # 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 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