disdrodb 0.0.21__py3-none-any.whl → 0.1.0__py3-none-any.whl

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

@@ -0,0 +1,166 @@
+#!/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 = ["time", "epoch_time", "TO_BE_PARSED"]
+
+    ##------------------------------------------------------------------------.
+    #### 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"
+    # - Define parser 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"]
+    ##------------------------------------------------------------------------.
+    #### 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
+    # NOTE: Station 8 has all raw_drop_number corrupted, so it can't be used
+
+    # 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]
+
+    # 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]
+
+    # Assign column names
+    column_names = [
+        "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",
+        "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",
+    ]
+    df.columns = column_names
+
+    # Add time column
+    df["time"] = df_time
+
+    # 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,
+    )
+
+    # 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
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "firmware_iop",
+        "firmware_dsp",
+        "sensor_time_measurement_start",
+        "sensor_time",
+        "sensor_date",
+        "station_name",
+        "station_number",
+        "sensor_serial_number",
+        "sensor_serial_number",
+        # "number_particles_all_detected",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/{NCAR/RELAMPAGO_RD80.py → RD80/BRAZIL/CHUVA_RD80.py}

@@ -16,28 +16,25 @@
 # 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",
         "sensor_status",
-        "interval",
+        "sample_interval",
         "n1",
         "n2",
         "n3",
@@ -64,7 +61,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = "\\t"
@@ -86,59 +83,38 @@ 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"]
 
     ##------------------------------------------------------------------------.
-    #### - Define dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # - Replace 'status' NaN with 0
-        df["sensor_status"] = df["sensor_status"].fillna(0)
-
-        # - Replace all ',' with '.' in RI, RA, RAT
-        df["RI"] = df["RI"].replace({",": "."}, regex=True)
-        df["RA"] = df["RA"].replace({",": "."}, regex=True)
-        df["RAT"] = df["RAT"].replace({",": "."}, regex=True)
-
-        # - Define 'time' datetime column
-        df["time"] = df["date"].astype(str) + " " + df["time"].astype(str)
-        df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
-        df = df.drop(columns=["date"])
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - Create raw_drop_number column
-        bin_columns = ["n" + str(i) for i in range(1, 21)]
-        df_arr = df[bin_columns]
-        df_raw_drop_number = df_arr.agg(";".join, axis=1)
-        df["raw_drop_number"] = df_raw_drop_number
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Replace 'status' NaN with 0
+    df["sensor_status"] = df["sensor_status"].astype(float).fillna(value=0).astype(int)
 
-        # - Remove bins columns
-        df = df.drop(columns=bin_columns)
+    # Define 'time' datetime column
+    df["time"] = df["date"].astype(str) + " " + df["time"].astype(str)
+    df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
+    df = df.drop(columns=["date"])
 
-        return df
+    # Create raw_drop_number column
+    bin_columns = ["n" + str(i) for i in range(1, 21)]
+    df_arr = df[bin_columns]
+    df_raw_drop_number = df_arr.agg(";".join, axis=1)
+    df["raw_drop_number"] = df_raw_drop_number
 
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*.txt"
+    # Remove bins columns
+    df = df.drop(columns=bin_columns)
 
-    ####----------------------------------------------------------------------.
-    #### - 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/{BRAZIL → RD80/BRAZIL}/GOAMAZON_RD80.py

@@ -16,28 +16,25 @@
 # 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",
         "sensor_status",
-        "interval",
+        "sample_interval",
         "n1",
         "n2",
         "n3",
@@ -64,7 +61,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = "\\t"
@@ -86,54 +83,38 @@ 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"]
 
     ##------------------------------------------------------------------------.
-    #### - Define dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # - Replace 'status' NaN with 0
-        df["sensor_status"] = df["sensor_status"].fillna(0)
-
-        # - Define 'time' datetime column
-        df["time"] = df["date"].astype(str) + " " + df["time"].astype(str)
-        df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
-        df = df.drop(columns=["date"])
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - Create raw_drop_number column
-        bin_columns = ["n" + str(i) for i in range(1, 21)]
-        df_arr = df[bin_columns]
-        df_raw_drop_number = df_arr.agg(";".join, axis=1)
-        df["raw_drop_number"] = df_raw_drop_number
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Replace 'status' NaN with 0
+    df["sensor_status"] = df["sensor_status"].astype(float).fillna(value=0).astype(int)
 
-        # - Remove bins columns
-        df = df.drop(columns=bin_columns)
+    # Define 'time' datetime column
+    df["time"] = df["date"].astype(str) + " " + df["time"].astype(str)
+    df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
+    df = df.drop(columns=["date"])
 
-        return df
+    # Create raw_drop_number column
+    bin_columns = ["n" + str(i) for i in range(1, 21)]
+    df_arr = df[bin_columns]
+    df_raw_drop_number = df_arr.agg(";".join, axis=1)
+    df["raw_drop_number"] = df_raw_drop_number
 
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*/*/DISL*"  # <year>/<month>
+    # Remove bins columns
+    df = df.drop(columns=bin_columns)
 
-    ####----------------------------------------------------------------------.
-    #### - 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/{NCAR → RD80/NCAR}/CINDY_2011_RD80.py

@@ -16,23 +16,20 @@
 # 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",
@@ -67,7 +64,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = "\\t"
@@ -89,54 +86,38 @@ 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"]
 
     ##------------------------------------------------------------------------.
-    #### - Define dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # - Replace 'Z' -Inf with NaN
-        df["Z"] = df["Z"].str.replace("-Inf", "NaN")
-
-        # - Define 'time' datetime column
-        df["time"] = df["date"].astype(str) + " " + df["time"].astype(str)
-        df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
-        df = df.drop(columns=["date"])
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - Create raw_drop_number column
-        bin_columns = ["n" + str(i) for i in range(1, 21)]
-        df_arr = df[bin_columns]
-        df_raw_drop_number = df_arr.agg(";".join, axis=1)
-        df["raw_drop_number"] = df_raw_drop_number
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Replace 'Z' -Inf with NaN
+    df["Z"] = df["Z"].str.replace("-Inf", "NaN")
 
-        # - Remove bins columns
-        df = df.drop(columns=bin_columns)
+    # Define 'time' datetime column
+    df["time"] = df["date"].astype(str) + " " + df["time"].astype(str)
+    df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
+    df = df.drop(columns=["date"])
 
-        return df
+    # Create raw_drop_number column
+    bin_columns = ["n" + str(i) for i in range(1, 21)]
+    df_arr = df[bin_columns]
+    df_raw_drop_number = df_arr.agg(";".join, axis=1)
+    df["raw_drop_number"] = df_raw_drop_number
 
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*.txt"
+    # Remove bins columns
+    df = df.drop(columns=bin_columns)
 
-    ####----------------------------------------------------------------------.
-    #### - 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