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

disdrodb/l0/readers/PARSIVEL2/FRANCE/ENPC_PARSIVEL2.py

@@ -0,0 +1,189 @@
+#!/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 ENPC PARSIVEL2 raw text data."""
+import zipfile
+
+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
+from disdrodb.utils.logger import log_error
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+
+    ##------------------------------------------------------------------------.
+    #### Define function to read each txt file inside each daily zip file
+    def read_txt_file(file, filename):
+        """Parse a single txt file within the daily zip file."""
+        ##------------------------------------------------------------------------.
+        #### 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"]
+
+        ##------------------------------------------------------------------------.
+        #### 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
+        # Create ID and Value columns
+        df = df["TO_PARSE"].str.split(":", expand=True, n=1)
+        df.columns = ["ID", "Value"]
+
+        # Select only rows with values
+        df = df[df["Value"].apply(lambda x: x is not None)]
+
+        # Drop rows with invalid IDs
+        valid_id_str = np.char.rjust(np.arange(0, 94).astype(str), width=2, fillchar="0")
+        df = df[df["ID"].astype(str).isin(valid_id_str)]
+
+        # Create the dataframe with each row corresponding to a timestep
+        # - Group rows based on when ID values restart
+        groups = df.groupby((df["ID"].astype(int).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)
+
+        # 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",
+            "26": "sensor_temperature_pcb",
+            "27": "sensor_temperature_receiver",
+            "28": "sensor_temperature_trasmitter",
+            "30": "rainfall_rate_16_bit_30",
+            "31": "rainfall_rate_16_bit_1200",
+            "32": "rainfall_accumulated_16bit",
+            "34": "rain_kinetic_energy",
+            "35": "snowfall_rate",
+            "90": "raw_drop_concentration",
+            "91": "raw_drop_average_velocity",
+            "93": "raw_drop_number",
+        }
+
+        df = df.rename(column_dict, axis=1)
+
+        # Keep only columns defined in the dictionary
+        df = df[list(column_dict.values())]
+
+        # Define datetime "time" column from filename
+        datetime_str = " ".join(filename.replace(".txt", "").split("_")[-6:])
+        df["time"] = pd.to_datetime(datetime_str, format="%Y %m %d %H %M %S")
+
+        # # 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
+
+    # ---------------------------------------------------------------------.
+    #### Iterate over all files (aka 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(".txt"):
+                # 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 df

disdrodb/l0/readers/PARSIVEL2/KIT/BURKINA_FASO.py

@@ -0,0 +1,133 @@
+#!/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_SPLIT"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+
+    # - Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    # - Skip header
+    reader_kwargs["skiprows"] = 7
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "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'] = 'xz'
+
+    # - 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"]
+
+    ##------------------------------------------------------------------------.
+    #### 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 repeated headers (with length 301)
+    # df = df[df["TO_SPLIT"].str.len() != 301]
+
+    # Split into columns and assign name
+    df = df["TO_SPLIT"].str.split(";", expand=True, n=16)
+    columns = [
+        "date",
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "weather_code_metar_4678",
+        "weather_code_nws",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_status",
+        "sensor_battery_voltage",
+        "unknown",  # "rainfall_amount_absolute_32bit", ?
+        "error_code",
+        "raw_drop_number",
+    ]
+    df.columns = columns
+
+    # Add datetime time column
+    df["time"] = df["date"] + "-" + df["time"]
+    df["time"] = pd.to_datetime(df["time"], format="%d.%m.%Y-%H:%M:%S", errors="coerce")
+    df = df.drop(columns=["date"])
+
+    # Preprocess the raw spectrum
+    # - The '<SPECTRUM>ZERO</SPECTRUM>' indicates no drops detected
+    # --> "" generates an array of zeros in L0B processing
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>ZERO</SPECTRUM>", "")
+
+    # Remove <SPECTRUM> and </SPECTRUM>" acronyms from the raw_drop_number field
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>", "")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("</SPECTRUM>", "")
+
+    # Add 0 before every , if , not preceded by a digit
+    # Example: ',,1,,' --> '0,0,1,0,'
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace(r"(?<!\d);", "0;", regex=True)
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "unknown",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL2/NCAR/FARM_PARSIVEL2.py

@@ -0,0 +1,138 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+"""Reader for CSWR FARM disdrometer data (used in PERILS and RELAMPAGO campaign)."""
+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_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
+
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+    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"]
+
+    ##------------------------------------------------------------------------.
+    #### 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
+    # Split and assign integrated variables names
+    df = df["TO_PARSE"].str.split(",", expand=True, n=22)
+
+    names = [
+        "time",
+        "station_name",
+        "station_number",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "weather_code_synop_4677",
+        "weather_code_metar_4678",
+        "weather_code_nws",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "sample_interval",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_serial_number",
+        "firmware_iop",
+        "firmware_dsp",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "sensor_status",
+        "rain_kinetic_energy",
+        "TO_SPLIT",
+    ]
+    df.columns = names
+
+    # Derive raw drop arrays
+    def split_string(s):
+        vals = [v.strip() for v in s.split(",")]
+        c1 = ", ".join(vals[:32])
+        c2 = ", ".join(vals[32:64])
+        c3 = ", ".join(vals[64:])
+        return pd.Series({"raw_drop_concentration": c1, "raw_drop_average_velocity": c2, "raw_drop_number": c3})
+
+    splitted_string = df["TO_SPLIT"].apply(split_string)
+    df["raw_drop_concentration"] = splitted_string["raw_drop_concentration"]
+    df["raw_drop_average_velocity"] = splitted_string["raw_drop_average_velocity"]
+    df["raw_drop_number"] = splitted_string["raw_drop_number"]
+
+    # Define datetime "time" column
+    df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "station_name",
+        "station_number",
+        "firmware_iop",
+        "firmware_dsp",
+        "TO_SPLIT",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL2/NCAR/PECAN_FP3.py

@@ -106,7 +106,7 @@ def reader(
     # Preprocess the raw spectrum
     # - The '<SPECTRUM>ZERO</SPECTRUM>' indicates no drops detected
     # --> "" generates an array of zeros in L0B processing
-    df["raw_drop_number"] = df["raw_drop_number"].replace("<SPECTRUM>ZERO</SPECTRUM>", "")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>ZERO</SPECTRUM>", "")
 
     # Remove <SPECTRUM> and </SPECTRUM>" acronyms from the raw_drop_number field
     df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>", "")

disdrodb/l0/readers/PARSIVEL2/NCAR/VORTEX_SE_2016_P2.py

@@ -100,7 +100,7 @@ def reader(
     # --> "" generates an array of zeros in L0B processing
     df["raw_drop_number"] = df["raw_drop_number"].astype("string")
     df["raw_drop_number"] = df["raw_drop_number"].str.strip()
-    df["raw_drop_number"] = df["raw_drop_number"].replace("<SPECTRUM>ZERO</SPECTRUM>", "")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>ZERO</SPECTRUM>", "")
 
     # Remove <SPECTRUM> and </SPECTRUM>" acronyms from the raw_drop_number field
     df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>", "")

disdrodb/l0/readers/PARSIVEL2/NCAR/VORTEX_SE_2016_PIPS.py

@@ -126,6 +126,15 @@ def reader(
     ]
     df_data.columns = column_names
 
+    # Add weather information
+    df_data["air_temperature"] = df["fast_temperature"]
+    df_data["relative_humidity"] = df["relative_humidity"]
+    df_data["wind_direction"] = df["wind_direction"]
+    df_data["wind_speed"] = df["wind_speed"]
+
+    # df_data["dew_point"] = df["dew_point"]
+    # df_data["air_pressure"] = df["pressure"]
+
     # Retrieve time and coordinates information
     # --> Latitude in degrees_north
     # --> Longitude in degrees_east

disdrodb/l0/readers/PARSIVEL2/NETHERLANDS/DELFT_NC.py

@@ -0,0 +1,67 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+"""Reader for DELFT OTT PARSIVEL2 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_as_string"].astype("M8[s]")
+    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
+        "rainfall_rate_32bit": "rainfall_rate_32bit",
+        "weather_code_synop_4680": "weather_code_synop_4680",
+        "weather_code_synop_4677": "weather_code_synop_4677",
+        "weather_code_metar_4678": "weather_code_metar_4678",
+        "weather_code_nws": "weather_code_nws",
+        "reflectivity_32bit": "reflectivity_32bit",
+        "mor_visibility": "mor_visibility",
+        "laser_amplitude": "laser_amplitude",
+        "number_particles_validated": "number_particles",
+        "sensor_temperature": "sensor_temperature",
+        "error_code": "error_code",
+        "kinetic_energy": "rain_kinetic_energy",
+        "fieldV": "raw_drop_average_velocity",
+        "fieldN": "raw_drop_concentration",
+        "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="PARSIVEL2")
+
+    # Return the dataset adhering to DISDRODB L0B standards
+    return ds