disdrodb 0.1.5__py3-none-any.whl → 0.2.1__py3-none-any.whl

disdrodb/l0/readers/PARSIVEL2/{GPM/GCPEX.py → NORWAY/UIB.py}

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
 # Copyright (c) 2021-2023 DISDRODB developers
 #
@@ -15,7 +14,8 @@
 # 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 GCPEX, OLYMPEX and IPHEX campaigns."""
+"""DISDRODB reader for University of Bergen OTT Parsivel 2 raw data."""
+
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
@@ -30,34 +30,44 @@ def reader(
     """Reader."""
     ##------------------------------------------------------------------------.
     #### Define column names
-    column_names = ["time", "TO_BE_SPLITTED"]
+    column_names = ["TO_PARSE"]
 
     ##------------------------------------------------------------------------.
     #### Define reader options
     reader_kwargs = {}
+
     # - Define delimiter
-    reader_kwargs["delimiter"] = ";"
+    reader_kwargs["delimiter"] = "\\n"
+
     # - Skip first row as columns names
     reader_kwargs["header"] = None
+
+    # - Skip header
     reader_kwargs["skiprows"] = 0
-    # - Skip file with encoding errors
-    reader_kwargs["encoding_errors"] = "ignore"
+
+    # - 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"] = "infer"
+    # 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", "-.-"]
+    reader_kwargs["na_values"] = ["na", "error", "-.-", " NA"]
 
     ##------------------------------------------------------------------------.
     #### Read the data
@@ -70,37 +80,52 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### 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")
+    # Remove corrupted rows
+    df = df[df["TO_PARSE"].str.count(";") == 1101]
 
-    # Split the 'TO_BE_SPLITTED' column
-    df = df["TO_BE_SPLITTED"].str.split(",", n=9, expand=True)
+    # Split into columns
+    df = df["TO_PARSE"].str.split(";", expand=True, n=13)
 
-    # Assign column names
+    # Assign columns names
     names = [
-        "station_name",
-        "sensor_status",
-        "sensor_temperature",
-        "number_particles",
+        "date",
+        "time",
         "rainfall_rate_32bit",
-        "reflectivity_16bit",
-        "mor_visibility",
+        "rainfall_accumulated_32bit",
+        "snowfall_rate",
         "weather_code_synop_4680",
-        "weather_code_synop_4677",
-        "raw_drop_number",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "rain_kinetic_energy",
+        "sensor_temperature",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_battery_voltage",
+        "TO_SPLIT",
     ]
     df.columns = names
 
-    # Add the time column
-    df["time"] = df_time
+    # Sanitize date
+    date = pd.to_datetime(df["date"], format="%d.%m.%Y", errors="coerce")
+    date = date.ffill().bfill()
 
-    # Drop columns not agreeing with DISDRODB L0 standards
-    df = df.drop(columns=["station_name"])
+    # Add datetime time column
+    time_str = date.astype(str) + "T" + df["time"]
+    df["time"] = pd.to_datetime(time_str, format="%Y-%m-%dT%H:%M:%S", errors="coerce")
+    df = df.drop(columns=["date"])
+
+    # Derive raw drop arrays
+    df_split = df["TO_SPLIT"].str.split(";", expand=True)
+    df["raw_drop_concentration"] = df_split.iloc[:, :32].agg(";".join, axis=1)
+    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:64].agg(";".join, axis=1)
+    df["raw_drop_number"] = df_split.iloc[:, 64:].agg(";".join, axis=1)
+    del df_split
 
-    # 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]
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "TO_SPLIT",
+    ]
+    df = df.drop(columns=columns_to_drop)
 
     # Return the dataframe adhering to DISDRODB L0 standards
     return df

disdrodb/l0/readers/PARSIVEL2/PHILIPPINES/{PANGASA.py → PAGASA.py}

@@ -154,9 +154,12 @@ def read_txt_file(file, filename, logger):
     df["time"] = pd.to_datetime(time_str, format="%Y%m%d%H%M%S", errors="coerce")
 
     # Keep only rows with valid raw_drop_number
-    df = df[df["raw_drop_number"].str.count(";") == 1024]
-    if len(df) == 0:
-        raise ValueError("Invalid raw drop number field.")
+    invalid_data = df["raw_drop_number"].str.count(";") != 1024
+    df.loc[invalid_data, "raw_drop_number"] = "NaN"  # TODO: if number_particles = 0, could be set to "0".
+
+    # df = df[df["raw_drop_number"].str.count(";") == 1024]
+    # if len(df) == 0:
+    #     raise ValueError("Invalid raw drop number field.")
 
     # Drop columns not agreeing with DISDRODB L0 standards
     # columns_to_drop = [

disdrodb/l0/readers/PARSIVEL2/SPAIN/GRANADA.py

@@ -109,7 +109,7 @@ def reader(
     # Retrieve raw array
     df_split = df["TO_SPLIT"].str.split(",", expand=True)
     df["raw_drop_concentration"] = df_split.iloc[:, :32].agg(",".join, axis=1)
-    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:].agg(",".join, axis=1)
+    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:64].agg(",".join, axis=1)
     df["raw_drop_number"] = df_split.iloc[:, 64:].agg(",".join, axis=1)
     del df_split
 

disdrodb/l0/readers/PARSIVEL2/SWEDEN/SMHI.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/>.
+# -----------------------------------------------------------------------------.
+"""Reader for SHMI OTT Parsivel2."""
+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
+
+
+def parse_old_format(df):
+    """Reformat old format."""
+    # Remove rows with invalid number of separators
+    df = df[df["TO_PARSE"].str.count(";") == 1106]
+
+    # Split the columns
+    df = df["TO_PARSE"].str.split(";", n=18, expand=True)
+
+    # Assign column names
+    names = [
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",  # wawa
+        "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_id",
+        "rainfall_amount_absolute_32bit",
+        "error_code",
+        "TO_SPLIT",
+    ]
+
+    df.columns = names
+
+    # Derive raw arrays
+    df_split = df["TO_SPLIT"].str.split(";", expand=True)
+    df["raw_drop_concentration"] = df_split.iloc[:, :32].agg(",".join, axis=1)
+    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:64].agg(",".join, axis=1)
+    df["raw_drop_number"] = df_split.iloc[:, 64:1088].agg(",".join, axis=1)
+
+    # Ensure the time column is datetime dtype
+    df["time"] = df["time"].str[0:12] + "00"
+    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 = [
+        "sensor_serial_number",
+        "firmware_iop",
+        "station_id",
+        "TO_SPLIT",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df
+
+
+def parse_new_format(df):
+    """Reformat new format."""
+    # Remove rows with invalid number of separators
+    df = df[df["TO_PARSE"].str.count(";") == 1106]
+
+    # Split the columns
+    df = df["TO_PARSE"].str.split(";", n=18, expand=True)
+
+    # Assign column names
+    names = [
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",  # wawa
+        "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_id",
+        "rainfall_amount_absolute_32bit",
+        "error_code",
+        "TO_SPLIT",
+    ]
+
+    df.columns = names
+
+    # Derive raw arrays
+    df_split = df["TO_SPLIT"].str.split(";", expand=True)
+    df["raw_drop_concentration"] = df_split.iloc[:, :32].agg(",".join, axis=1)
+    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:64].agg(",".join, axis=1)
+    df["raw_drop_number"] = df_split.iloc[:, 64:1088].agg(",".join, axis=1)
+
+    # Add the 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 = [
+        "sensor_serial_number",
+        "firmware_iop",
+        "station_id",
+        "TO_SPLIT",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
+    column_names = ["TO_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+    # Skip file with encoding errors
+    reader_kwargs["encoding_errors"] = "ignore"
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+    # - 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
+    if df["TO_PARSE"].iloc[0].startswith("datetime_utc"):
+        # Remove header if present (2025 onward)
+        df = df.iloc[1:]
+        # Parse new format
+        return parse_new_format(df)
+    return parse_old_format(df)

disdrodb/l0/readers/{PARSIVEL/GPM/PIERS.py → PARSIVEL2/USA/CSU.py}

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # -----------------------------------------------------------------------------.
 # Copyright (c) 2021-2023 DISDRODB developers
 #
@@ -15,6 +14,8 @@
 # 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 Colorado State University OTT Parsivel 2 raw data."""
+
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
@@ -29,34 +30,44 @@ def reader(
     """Reader."""
     ##------------------------------------------------------------------------.
     #### Define column names
-    column_names = ["time", "TO_BE_SPLITTED"]
+    column_names = ["TO_PARSE"]
 
     ##------------------------------------------------------------------------.
     #### Define reader options
     reader_kwargs = {}
+
     # - Define delimiter
-    reader_kwargs["delimiter"] = ";"
+    reader_kwargs["delimiter"] = "\\n"
+
     # - Skip first row as columns names
     reader_kwargs["header"] = None
+
+    # - Skip header
     reader_kwargs["skiprows"] = 0
-    # - Skip file with encoding errors
-    reader_kwargs["encoding_errors"] = "ignore"
+
+    # - 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"] = "infer"
+    # 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", "-.-"]
+    reader_kwargs["na_values"] = ["na", "error", "-.-", " NA"]
 
     ##------------------------------------------------------------------------.
     #### Read the data
@@ -69,37 +80,59 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### 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")
+    # Remove corrupted rows
+    df = df[df["TO_PARSE"].str.count(",").isin([15, 1040])]
 
-    # Split the 'TO_BE_SPLITTED' column
-    df = df["TO_BE_SPLITTED"].str.split(",", expand=True, n=9)
+    # Split into columns
+    df["TO_PARSE"] = df["TO_PARSE"] + ",0"
+    df = df["TO_PARSE"].str.split(",", expand=True, n=16)
 
-    # Assign column names
-    columns_names = [
-        "station_name",
-        "sensor_status",
-        "sensor_temperature",
-        "number_particles",
+    # Assign columns names
+    names = [
+        "date",
+        "time",
         "rainfall_rate_32bit",
-        "reflectivity_16bit",
-        "mor_visibility",
+        "rainfall_accumulated_32bit",
         "weather_code_synop_4680",
-        "weather_code_synop_4677",
+        "weather_code_metar_4678",
+        "weather_code_nws",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "rain_kinetic_energy",
+        "snowfall_rate",
         "raw_drop_number",
     ]
-    df.columns = columns_names
+    df.columns = names
 
-    # Add the time column
-    df["time"] = df_time
+    # Add 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")
 
-    # Drop columns not agreeing with DISDRODB L0 standards
-    df = df.drop(columns=["station_name"])
+    # Derive the raw spectrum
+    # - When no drops detected, None
+    # - After conversion to string, becomes NaN
+    df["raw_drop_number"] = df["raw_drop_number"].astype("string")
+    df["raw_drop_number"] = df["raw_drop_number"].str.strip()
+
+    # Remove <SPECTRUM> and </SPECTRUM> prefix and suffix 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>,0", "")
+
+    # Preprocess the raw spectrum and raw_drop_average_velocity
+    # - 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 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]
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "date",
+    ]
+    df = df.drop(columns=columns_to_drop)
 
     # Return the dataframe adhering to DISDRODB L0 standards
     return df

disdrodb/l0/readers/PARSIVEL2/USA/{C3WE.py → CW3E.py}

@@ -15,6 +15,7 @@
 # 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 the OTT Parsivel2 sensors of the CW3E network."""
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
@@ -68,39 +69,65 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### Adapt the dataframe to adhere to DISDRODB L0 standards
-    # Define 'time' datetime
+    # Remove rows with invalid number of separators
+    df = df[df["TO_PARSE"].str.count(";").isin([1104, 1105])]
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}")
 
-    # Split the columns
-    df["TO_PARSE"].iloc[0:5].str.split(";", n=16, expand=True).iloc[0]
+    n_delimiters = int(df["TO_PARSE"].str.count(";").iloc[0])
+    if n_delimiters == 1104:
+        names = [
+            "sensor_serial_number",
+            "sensor_status",
+            "laser_amplitude",
+            "sensor_heating_current",
+            "sensor_battery_voltage",
+            "dummy_date",
+            "sensor_time",
+            "sensor_date",
+            # "sensor_temperature",
+            "number_particles",
+            "rainfall_rate_32bit",
+            "reflectivity_32bit",
+            "rainfall_accumulated_16bit",
+            "mor_visibility",
+            "weather_code_synop_4680",
+            "weather_code_synop_4677",
+            "TO_SPLIT",
+        ]
+        n = 15
+    else:
+        names = [
+            "sensor_serial_number",
+            "sensor_status",
+            "laser_amplitude",
+            "sensor_heating_current",
+            "sensor_battery_voltage",
+            "dummy_date",
+            "sensor_time",
+            "sensor_date",
+            "sensor_temperature",
+            "number_particles",
+            "rainfall_rate_32bit",
+            "reflectivity_32bit",
+            "rainfall_accumulated_16bit",
+            "mor_visibility",
+            "weather_code_synop_4680",
+            "weather_code_synop_4677",
+            "TO_SPLIT",
+        ]
+        n = 16
 
-    df = df["TO_PARSE"].str.split(";", n=16, expand=True)
+    # Split the columns
+    df = df["TO_PARSE"].str.split(";", n=n, expand=True)
 
     # Assign column names
-    names = [
-        "sensor_serial_number",
-        "sensor_status",
-        "laser_amplitude",
-        "sensor_heating_current",
-        "sensor_battery_voltage",
-        "dummy_date",
-        "sensor_time",
-        "sensor_date",
-        "sensor_temperature",
-        "number_particles",
-        "rainfall_rate_32bit",
-        "reflectivity_32bit",
-        "rainfall_accumulated_16bit",
-        "mor_visibility",
-        "weather_code_synop_4680",
-        "weather_code_synop_4677",
-        "TO_SPLIT",
-    ]
     df.columns = names
 
     # Derive raw arrays
     df_split = df["TO_SPLIT"].str.split(";", expand=True)
     df["raw_drop_concentration"] = df_split.iloc[:, :32].agg(",".join, axis=1)
-    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:].agg(",".join, axis=1)
+    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:64].agg(",".join, axis=1)
     df["raw_drop_number"] = df_split.iloc[:, 64:1088].agg(",".join, axis=1)
     df["rain_kinetic_energy"] = df_split.iloc[:, 1088]
     df["CHECK_EMPTY"] = df_split.iloc[:, 1089]