disdrodb 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

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

@@ -0,0 +1,123 @@
+#!/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_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=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
+
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Identify groups of lines corresponding to same measurement
+    is_start = df["TO_PARSE"].str.startswith("#0#,")
+    df["observation_id"] = is_start.cumsum()
+
+    # Loop over groups and create a dataframe with a single row for each measurement
+    list_obs = []
+    for _, df_obs in df.groupby("observation_id", sort=False):
+        if len(df_obs) not in [6, 7]:
+            pass
+
+        # Remove #<id># and last comma
+        series = df_obs["TO_PARSE"].str.split(",", n=1, expand=True)[1].str.rstrip(",")
+        if len(df_obs) == 7:
+            series = series.iloc[0:6]
+
+        # Create dataframe and name columns
+        df_obs = series.to_frame().T
+        df_obs.columns = [
+            "time",
+            "TO_SPLIT1",
+            "TO_SPLIT2",
+            "raw_drop_concentration",
+            "raw_drop_average_velocity",
+            "raw_drop_number",
+        ]
+
+        # Append to the list
+        list_obs.append(df_obs)
+
+    # Concat all timesteps into a single dataframe
+    df = pd.concat(list_obs)
+
+    # Split and rename remaining variables
+    df_split1 = df["TO_SPLIT1"].str.split(",", expand=True)
+    df_split1.columns = [
+        "weather_code_synop_4680",
+        "rainfall_accumulated_32bit",
+        "rainfall_rate32bit",
+        "reflectivity_32bit",
+    ]
+    df_split2 = df["TO_SPLIT2"].str.split(",", expand=True)
+    df_split2.columns = ["parsivel_id", "sensor_serial_number", "mor_visibility", "laser_amplitude", "sensor_status"]
+
+    # Merge everything into a single dataframe
+    df = pd.concat([df, df_split1, df_split2], axis=1)
+
+    # Define time as datetime64
+    df["time"] = pd.to_datetime(df["time"], format="%d.%m.%Y %H:%M:%S", errors="coerce")
+
+    # Remove unused variables
+    df = df.drop(columns=["TO_SPLIT1", "TO_SPLIT2", "parsivel_id", "sensor_serial_number"])
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL2/{NETHERLANDS/DELFT.py → MPI/BCO_PARSIVEL2.py}

@@ -29,33 +29,42 @@ def reader(
     """Reader."""
     ##------------------------------------------------------------------------.
     #### Define column names
-    column_names = ["time", "epoch_time", "TO_BE_PARSED"]
+    column_names = ["TO_BE_PARSED"]
 
     ##------------------------------------------------------------------------.
     #### Define reader options
     reader_kwargs = {}
+
     # - Define delimiter
-    reader_kwargs["delimiter"] = ";"
-    # - Skip first row as columns names
+    reader_kwargs["delimiter"] = "/\n"
+
+    # Skip first row as columns names
     reader_kwargs["header"] = None
-    # - Avoid first column to become df index
+
+    # Skip first 2 rows
+    reader_kwargs["skiprows"] = 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 parser engine
+
+    # - 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"
-    # reader_kwargs['zipped'] = False
-    # reader_kwargs['zipped'] = True
+
     # - 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"]
+    reader_kwargs["na_values"] = ["na", "", "error", "NA"]
+
     ##------------------------------------------------------------------------.
     #### Read the data
     df = read_raw_text_file(
@@ -67,34 +76,24 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### Adapt the dataframe to adhere to DISDRODB L0 standards
-    # NOTE: Station 8 has all raw_drop_number corrupted, so it can't be used
+    # Remove rows with invalid length
+    # df = df[df["TO_BE_PARSED"].str.len().isin([4664])]
 
-    # Remove rows that have a corrupted "TO_BE_PARSED" column
-    # - PAR001, PAR002 have length 3726 (no station_name)
-    # - PAR007 have length 3736 ()
-    df = df.loc[df["TO_BE_PARSED"].astype(str).str.len() >= 3726]
-    df = df.loc[df["TO_BE_PARSED"].astype(str).str.len() <= 3736]
+    # Count number of delimiters to select valid rows
+    df = df[df["TO_BE_PARSED"].str.count(";") == 1107]
 
-    # Convert 'time' column to datetime
-    df_time = pd.to_datetime(df["time"], format="%Y%m%d-%H%M%S", errors="coerce")
-
-    # Strip values from start and end of the string
-    df["TO_BE_PARSED"] = df["TO_BE_PARSED"].str.lstrip("b'").str.rstrip("'").str.rstrip("\\r\\n'")  # noqa: B005
-
-    # Split the column 'TO_BE_PARSED'
-    df_to_parse = df["TO_BE_PARSED"].str.split(";", expand=True, n=99)
-
-    # Retrieve DISDRODB compliant columns
-    df = df_to_parse.iloc[:, 0:35]
+    # Split by ; delimiter
+    df = df["TO_BE_PARSED"].str.split(";", expand=True, n=19)
 
     # Assign column names
-    column_names = [
+    names = [
+        "date",
+        "time",
         "rainfall_rate_32bit",
         "rainfall_accumulated_32bit",
         "weather_code_synop_4680",
-        "weather_code_synop_4677",
-        "weather_code_metar_4678",
-        "weather_code_nws",
+        # "weather_code_synop_4677",
+        # "weather_code_metar_4678",
         "reflectivity_32bit",
         "mor_visibility",
         "sample_interval",
@@ -103,64 +102,35 @@ def reader(
         "sensor_temperature",
         "sensor_serial_number",
         "firmware_iop",
-        "firmware_dsp",
         "sensor_heating_current",
         "sensor_battery_voltage",
         "sensor_status",
-        "sensor_time_measurement_start",
-        "sensor_time",
-        "sensor_date",
         "station_name",
-        "station_number",
         "rainfall_amount_absolute_32bit",
         "error_code",
-        "sensor_temperature_pcb",
-        "sensor_temperature_receiver",
-        "sensor_temperature_trasmitter",
-        "rainfall_rate_16_bit_30",
-        "rainfall_rate_16_bit_1200",
-        "rainfall_accumulated_16bit",
-        "reflectivity_16bit",
-        "rain_kinetic_energy",
-        "snowfall_rate",
-        "number_particles_all",
-        # "number_particles_all_detected",
+        "ARRAY_TO_SPLIT",
     ]
-    df.columns = column_names
 
-    # Add time column
-    df["time"] = df_time
+    df.columns = names
 
-    # Retrieve raw_drop_concentration
-    df["raw_drop_concentration"] = df_to_parse.iloc[:, 35:67].apply(
-        lambda x: ",".join(x.dropna().astype(str)),
-        axis=1,
-    )
-    # Retrieve raw_drop_average_velocity
-    df["raw_drop_average_velocity"] = df_to_parse.iloc[:, 67:99].apply(
-        lambda x: ",".join(x.dropna().astype(str)),
-        axis=1,
-    )
+    # Define time in datetime format
+    time_str = df["date"] + " " + df["time"]
+    df["time"] = pd.to_datetime(time_str, format="%d.%m.%Y %H:%M:%S", errors="coerce")
 
-    # Retrieve raw_drop_number
-    df_raw_drop_number = df_to_parse.iloc[:, 99].squeeze()
-    df_raw_drop_number = df_raw_drop_number.str.replace(r"(\w{3})", r"\1,", regex=True)
-    df["raw_drop_number"] = df_raw_drop_number
+    # Add raw array
+    df["raw_drop_concentration"] = df["ARRAY_TO_SPLIT"].str[:224]
+    df["raw_drop_average_velocity"] = df["ARRAY_TO_SPLIT"].str[224:448]
+    df["raw_drop_number"] = df["ARRAY_TO_SPLIT"].str[448:]
 
     # Drop columns not agreeing with DISDRODB L0 standards
     columns_to_drop = [
-        "firmware_iop",
-        "firmware_dsp",
-        "sensor_time_measurement_start",
-        "sensor_time",
-        "sensor_date",
+        "date",
         "station_name",
-        "station_number",
-        "sensor_serial_number",
+        "firmware_iop",
+        "ARRAY_TO_SPLIT",
         "sensor_serial_number",
-        # "number_particles_all_detected",
+        "sample_interval",
     ]
     df = df.drop(columns=columns_to_drop)
 
-    # Return the dataframe adhering to DISDRODB L0 standards
     return df

disdrodb/l0/readers/PARSIVEL2/MPI/BOWTIE.py

@@ -0,0 +1,220 @@
+#!/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 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
+
+TRACKS_DICT = {
+    "M203": ("2024-08-16 02:53:21", "2024-09-24 07:59:57"),
+    "M204": ("2024-09-27 08:00:00", "2024-10-20 07:59:57"),
+    "M205": ("2024-10-23 08:00:01", "2024-11-28 13:00:01"),
+    "M206": ("2024-12-01 08:00:02", "2024-12-30 07:59:57"),
+    "M207": ("2025-01-04 08:00:01", "2025-02-11 10:25:15"),
+}
+
+
+def get_track_for_dataframe(df):
+    """Retrieve ship track identifier."""
+    df_start, df_end = df["time"].min(), df["time"].max()
+
+    overlaps = []
+    for key, (start, end) in TRACKS_DICT.items():
+        start, end = pd.to_datetime(start), pd.to_datetime(end)
+        # check if df range lies within track coverage
+        if df_start <= end and df_end >= start:
+            overlaps.append(key)
+    return overlaps
+
+
+def read_tracks_file(tracks_filepath):
+    """Read GPS master track file."""
+    df = pd.read_csv(
+        tracks_filepath,
+        names=["time", "latitude", "longitude", "flag"],
+        dtype={"time": str, "latitude": float, "longitude": float, "flag": str},
+        sep="\t",  # tab-separated
+        skiprows=1,  # skip the weird first line
+        engine="c",  # speed up reading
+    )
+    df["time"] = pd.to_datetime(df["time"])
+    return df
+
+
+def add_gps_coordinates(df, filepath):
+    """Add GPS coordinates to dataframe."""
+    # Retrieve useful tracks ids
+    tracks_ids = get_track_for_dataframe(df)
+
+    if len(tracks_ids) == 0:
+        df["latitude"] = np.nan
+        df["longitude"] = np.nan
+        return df
+
+    # Retrieve station base directory
+    station_base_dir = os.path.join(os.path.sep, *filepath.split(os.path.sep)[:-2])
+    # Define GPS files to read
+    tracks_filepaths = [os.path.join(station_base_dir, f"{tracks_id}_mastertrack.zip") for tracks_id in tracks_ids]
+    # Read GPS files
+    list_df_tracks = [read_tracks_file(fpath) for fpath in tracks_filepaths]
+    df_tracks = pd.concat(list_df_tracks)
+    df_tracks = df_tracks.dropna(subset=["time"])
+
+    # Ensure dataframes are sorted by time
+    df = df.sort_values("time")
+    df_tracks = df_tracks.sort_values("time")
+
+    # Remove bad flags
+    # df_tracks = df_tracks[df_tracks["flag"] == "1"]
+
+    # Remove flag column
+    df_tracks = df_tracks.drop(columns="flag")
+
+    # Add GPS coordinate to dataframe
+    df = pd.merge_asof(
+        df,
+        df_tracks,
+        on="time",
+        direction="nearest",
+        tolerance=pd.Timedelta("5min"),
+    )
+    return df
+
+
+@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
+    reader_kwargs["header"] = None
+
+    # Skip first 2 rows
+    reader_kwargs["skiprows"] = 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", "NA"]
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "latin1"
+
+    ##------------------------------------------------------------------------.
+    #### 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
+    # df = df[df["TO_BE_PARSED"].str.len().isin([4664])]
+
+    # Count number of delimiters to select valid rows
+    df = df[df["TO_BE_PARSED"].str.count(";") == 1107]
+
+    # Split by ; delimiter
+    df = df["TO_BE_PARSED"].str.split(";", expand=True, n=19)
+
+    # Assign column names
+    names = [
+        "date",
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        # "weather_code_synop_4677",
+        # "weather_code_metar_4678",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "sample_interval",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_serial_number",
+        "firmware_iop",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "sensor_status",
+        "station_name",
+        "rainfall_amount_absolute_32bit",
+        "error_code",
+        "ARRAY_TO_SPLIT",
+    ]
+
+    df.columns = names
+
+    # Define time in datetime format
+    time_str = df["date"] + " " + df["time"]
+    df["time"] = pd.to_datetime(time_str, format="%d.%m.%Y %H:%M:%S", errors="coerce")
+    df = df.dropna(subset=["time"])
+
+    # Add raw array
+    df["raw_drop_concentration"] = df["ARRAY_TO_SPLIT"].str[:224]
+    df["raw_drop_average_velocity"] = df["ARRAY_TO_SPLIT"].str[224:448]
+    df["raw_drop_number"] = df["ARRAY_TO_SPLIT"].str[448:]
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "date",
+        "station_name",
+        "firmware_iop",
+        "ARRAY_TO_SPLIT",
+        "sensor_serial_number",
+        "sample_interval",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Add GPS coordinates
+    df = add_gps_coordinates(df, filepath=filepath)
+    return df

disdrodb/l0/readers/PARSIVEL2/NASA/APU.py

@@ -0,0 +1,120 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+"""This reader allows to read raw data from NASA APU stations.
+
+The reader allows to read raw  APU data from the following NASA campaigns:
+
+    - HYMEX
+    - IFLOODS
+    - IPHEX
+    - OLYMPEX
+    - ICEPOP
+    - IMPACTS
+    - GCPEX
+    - WFF
+
+"""
+
+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 = ["time", "TO_BE_SPLITTED"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # - Define delimiter
+    reader_kwargs["delimiter"] = ";"
+    # - Skip first row as columns names
+    reader_kwargs["header"] = None
+    reader_kwargs["skiprows"] = 0
+    # - Skip file with encoding errors
+    reader_kwargs["encoding_errors"] = "ignore"
+    # - 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", "-.-"]
+
+    ##------------------------------------------------------------------------.
+    #### 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
+    # Convert time column to datetime
+    df_time = pd.to_datetime(df["time"], format="%Y%m%d%H%M%S", errors="coerce")
+
+    # Split the 'TO_BE_SPLITTED' column
+    df = df["TO_BE_SPLITTED"].str.split(",", n=9, expand=True)
+
+    # Assign column names
+    names = [
+        "station_name",
+        "sensor_status",
+        "sensor_temperature",
+        "number_particles",
+        "rainfall_rate_32bit",
+        "reflectivity_16bit",
+        "mor_visibility",
+        "weather_code_synop_4680",
+        "weather_code_synop_4677",
+        "raw_drop_number",
+    ]
+    df.columns = names
+
+    # Add the time column
+    df["time"] = df_time
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    df = df.drop(columns=["station_name"])
+
+    # Drop rows with invalid values
+    # --> Ensure that weather_code_synop_4677 has length 2
+    # --> If a previous column is missing it will have 000
+    df = df[df["weather_code_synop_4677"].str.len() == 2]
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df