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

disdrodb/l0/readers/{EPFL → PARSIVEL/EPFL}/PLATO_2019.py

@@ -15,23 +15,20 @@
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
-from disdrodb.l0 import run_l0a
+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(
-    raw_dir,
-    processed_dir,
-    station_name,
-    # Processing options
-    force=False,
-    verbose=False,
-    parallel=False,
-    debugging_mode=False,
+    filepath,
+    logger=None,
 ):
+    """Reader."""
     ##------------------------------------------------------------------------.
-    #### - Define column names
+    #### Define column names
     column_names = [
         "date",
         "time",
@@ -52,7 +49,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define encoding
     reader_kwargs["encoding"] = "latin-1"
@@ -71,42 +68,25 @@ def reader(
     #   - 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’
+    #   - 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 dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # - Define 'time' datetime column
-        df["time"] = pd.to_datetime(df["date"] + df["time"], format="%Y%m%d%H:%M:%S")
-
-        # - Drop columns not agreeing with DISDRODB L0 standards
-        df = df.drop(columns=["date"])
-        return df
-
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*.MIS*"
-
-    ####----------------------------------------------------------------------.
-    #### - Create L0A products
-    run_l0a(
-        raw_dir=raw_dir,
-        processed_dir=processed_dir,
-        station_name=station_name,
-        # Custom arguments of the reader for L0A processing
-        glob_patterns=glob_patterns,
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
         column_names=column_names,
         reader_kwargs=reader_kwargs,
-        df_sanitizer_fun=df_sanitizer_fun,
-        # Processing options
-        force=force,
-        verbose=verbose,
-        parallel=parallel,
-        debugging_mode=debugging_mode,
+        logger=logger,
     )
+
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # - Define 'time' datetime column
+    df["time"] = pd.to_datetime(df["date"] + df["time"], format="%Y%m%d%H:%M:%S")
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    df = df.drop(columns=["date"])
+    return df

disdrodb/l0/readers/PARSIVEL/EPFL/RACLETS_2019.py

@@ -0,0 +1,140 @@
+#!/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 RACLETS 2019 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_BE_SPLITTED"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # - Define delimiter
+    reader_kwargs["delimiter"] = ";"  # Used to not split anything !
+    # - Define encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+    # - 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"] = "gzip"
+    # - 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
+    # Drop row that contains errors
+    df = df[~df["TO_BE_SPLITTED"].str.contains("Error in data reading! 0")]
+
+    # Check if file empty
+    if len(df.index) == 0:
+        raise ValueError("Error in all rows. The file has been skipped.")
+
+    # Split the column
+    df = df["TO_BE_SPLITTED"].str.split(",", expand=True, n=1111)
+
+    # Define auxiliary columns
+    column_names = [
+        "id",
+        "latitude",
+        "longitude",
+        "time",
+        "datalogger_temperature",
+        "datalogger_voltage",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "weather_code_synop_4677",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "sensor_status",
+        "rainfall_amount_absolute_32bit",
+        "error_code",
+    ]
+    df_variables = df.iloc[:, 0:20]
+    df_variables.columns = column_names
+
+    # Define raw fields
+    df_raw_drop_concentration = df.iloc[:, 20:52].agg(",".join, axis=1)
+    df_raw_drop_average_velocity = df.iloc[:, 53:85].agg(",".join, axis=1)
+    df_raw_drop_number = df.iloc[:, 86:1110].agg(",".join, axis=1)
+
+    # Combine together
+    df = df_variables
+    df["raw_drop_concentration"] = df_raw_drop_concentration
+    df["raw_drop_average_velocity"] = df_raw_drop_average_velocity
+    df["raw_drop_number"] = df_raw_drop_number
+
+    # Drop invalid rows
+    df = df.loc[df["id"].astype(str).str.len() < 10]
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "datalogger_temperature",
+        "datalogger_voltage",
+        "id",
+        "latitude",
+        "longitude",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Convert time column to datetime
+    df["time"] = pd.to_datetime(df["time"], format="%d-%m-%Y %H:%M:%S", errors="coerce")
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/{EPFL → PARSIVEL/EPFL}/RACLETS_2019_WJF.py

@@ -15,23 +15,21 @@
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
-from disdrodb.l0 import run_l0a
+"""Reader for RACLETS WJF 2019 station."""
+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(
-    raw_dir,
-    processed_dir,
-    station_name,
-    # Processing options
-    force=False,
-    verbose=False,
-    parallel=False,
-    debugging_mode=False,
+    filepath,
+    logger=None,
 ):
+    """Reader."""
     ##------------------------------------------------------------------------.
-    #### - Define column names
+    #### Define column names
     column_names = [
         "id",
         "latitude",
@@ -59,7 +57,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = ";"
@@ -77,59 +75,43 @@ def reader(
     #   - Available: gzip, bz2, zip
     reader_kwargs["compression"] = "gzip"
     # - 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’
+    #   - 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"]
 
     ##------------------------------------------------------------------------.
-    #### - Define dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # - Drop invalid rows
-        df = df.loc[df["id"].astype(str).str.len() < 10]
-
-        # - Split th 'TO_BE_SPLITTED' column
-        df_splitted = df["TO_BE_SPLITTED"].str.split(",", expand=True, n=1)
-        df_splitted.columns = ["datalogger_voltage", "rainfall_rate_32bit"]
-        df["rainfall_rate_32bit"] = df_splitted["rainfall_rate_32bit"]
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - Drop columns not agreeing with DISDRODB L0 standards
-        columns_to_drop = [
-            "id",
-            "latitude",
-            "longitude",
-            "datalogger_temperature",
-            "datalogger_error",
-            "TO_BE_SPLITTED",
-        ]
-        df = df.drop(columns=columns_to_drop)
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Drop invalid rows
+    df = df.loc[df["id"].astype(str).str.len() < 10]
 
-        # - Convert time column to datetime
-        df["time"] = pd.to_datetime(df["time"], format="%d-%m-%Y %H:%M:%S", errors="coerce")
+    # Split th 'TO_BE_SPLITTED' column
+    df_splitted = df["TO_BE_SPLITTED"].str.split(",", expand=True, n=1)
+    df_splitted.columns = ["datalogger_voltage", "rainfall_rate_32bit"]
+    df["rainfall_rate_32bit"] = df_splitted["rainfall_rate_32bit"]
 
-        return df
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "id",
+        "latitude",
+        "longitude",
+        "datalogger_temperature",
+        "datalogger_error",
+        "TO_BE_SPLITTED",
+    ]
+    df = df.drop(columns=columns_to_drop)
 
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*.dat.gz*"
+    # Convert time column to datetime
+    df["time"] = pd.to_datetime(df["time"], format="%d-%m-%Y %H:%M:%S", errors="coerce")
 
-    ####----------------------------------------------------------------------.
-    #### - Create L0A products
-    run_l0a(
-        raw_dir=raw_dir,
-        processed_dir=processed_dir,
-        station_name=station_name,
-        # Custom arguments of the reader for L0A processing
-        glob_patterns=glob_patterns,
-        column_names=column_names,
-        reader_kwargs=reader_kwargs,
-        df_sanitizer_fun=df_sanitizer_fun,
-        # Processing options
-        force=force,
-        verbose=verbose,
-        parallel=parallel,
-        debugging_mode=debugging_mode,
-    )
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/{EPFL → PARSIVEL/EPFL}/RIETHOLZBACH_2011.py

@@ -15,23 +15,21 @@
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
-from disdrodb.l0 import run_l0a
+"""Reader for RIETHOLZBACH 2011 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(
-    raw_dir,
-    processed_dir,
-    station_name,
-    # Processing options
-    force=False,
-    verbose=False,
-    parallel=False,
-    debugging_mode=False,
+    filepath,
+    logger=None,
 ):
+    """Reader."""
     ##------------------------------------------------------------------------.
-    #### - Define column names
+    #### Define column names
     column_names = [
         "time",
         "id",
@@ -58,7 +56,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = ","
@@ -74,49 +72,34 @@ def reader(
     #   - 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’
+    #   - 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 dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # - Convert time column to datetime
-        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 = [
-            "id",
-            "datalogger_temperature",
-            "datalogger_voltage",
-            "datalogger_debug",
-            "datalogger_error",
-        ]
-        df = df.drop(columns=columns_to_drop)
-        return df
-
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*.dat*"
-
-    ####----------------------------------------------------------------------.
-    #### - Create L0A products
-    run_l0a(
-        raw_dir=raw_dir,
-        processed_dir=processed_dir,
-        station_name=station_name,
-        # Custom arguments of the reader for L0A processing
-        glob_patterns=glob_patterns,
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
         column_names=column_names,
         reader_kwargs=reader_kwargs,
-        df_sanitizer_fun=df_sanitizer_fun,
-        # Processing options
-        force=force,
-        verbose=verbose,
-        parallel=parallel,
-        debugging_mode=debugging_mode,
+        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")
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "id",
+        "datalogger_temperature",
+        "datalogger_voltage",
+        "datalogger_debug",
+        "datalogger_error",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL/EPFL/SAMOYLOV_2017.py

@@ -0,0 +1,117 @@
+#!/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 SAMOYLOV 2017 campaign."""
+import numpy as np
+import pandas as pd
+
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.l0.l0a_processing import read_raw_text_file
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
+    column_names = [
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "weather_code_synop_4677",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "sensor_status",
+        "rainfall_amount_absolute_32bit",
+        "error_code",
+        "raw_drop_concentration",
+        "raw_drop_average_velocity",
+        "raw_drop_number",
+    ]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+
+    # - Define delimiter
+    reader_kwargs["delimiter"] = ";"
+
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    # - Avoid first column to become df index !!!
+    reader_kwargs["index_col"] = False
+
+    # - Define behaviour when encountering bad lines
+    reader_kwargs["on_bad_lines"] = "skip"
+
+    # - Avoid UnicodeDecodeError: 'utf-8' codec can't decode byte 0xf0
+    reader_kwargs["encoding"] = "latin-1"
+
+    # - 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"]
+
+    # Different encoding for this campaign
+    reader_kwargs["encoding"] = "latin-1"
+
+    ##------------------------------------------------------------------------.
+    #### 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
+
+    # Special parsing if 'Error in data reading' in rainfall_rate_32bit column
+    if np.any(df["rainfall_rate_32bit"].str.startswith("Error in data reading!", na=False)):
+        df["rainfall_rate_32bit"] = df["rainfall_rate_32bit"].str.replace("Error in data reading!", "")
+        df["raw_drop_number"] = df["raw_drop_average_velocity"]
+        df["raw_drop_average_velocity"] = df["raw_drop_concentration"]
+        df["raw_drop_concentration"] = df["error_code"]
+        df["error_code"] = df["rainfall_amount_absolute_32bit"].str[7:]
+        df["rainfall_amount_absolute_32bit"] = df["rainfall_amount_absolute_32bit"].str[:7]
+
+    # Convert time column to datetime
+    df["time"] = pd.to_datetime(df["time"], format="%d/%m/%Y %H:%M:%S", errors="coerce")
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df