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

disdrodb/l0/readers/{NCAR/VORTEX_SE_2016_P1.py → PARSIVEL/NCAR/OWLES_MIPS.py}

@@ -1,11 +1,4 @@
 #!/usr/bin/env python3
-"""
-Created on Fri Feb 17 20:47:10 2023
-
-@author: ghiggi
-"""
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 # -----------------------------------------------------------------------------.
 # Copyright (c) 2021-2023 DISDRODB developers
 #
@@ -22,23 +15,20 @@ Created on Fri Feb 17 20:47:10 2023
 # 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 = [
         "day",
         "month",
@@ -57,7 +47,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = ","
@@ -68,9 +58,6 @@ def reader(
     # - Define behaviour when encountering bad lines
     reader_kwargs["on_bad_lines"] = "skip"
 
-    # - Define encoding
-    reader_kwargs["encoding"] = "ISO-8859-1"
-
     # - Define reader engine
     #   - C engine is faster
     #   - Python engine is more feature-complete
@@ -81,64 +68,51 @@ def reader(
     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"]
 
     # Skip first row as columns names
     reader_kwargs["header"] = None
 
-    ##------------------------------------------------------------------------.
-    #### - Define dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # - Define datetime 'time' column
-        df["time"] = (
-            df["day"].astype(str)
-            + "-"
-            + df["month"].astype(str)
-            + "-"
-            + df["year"].astype(str)
-            + " "
-            + df["hour_minute"].astype(str)
-            + ":"
-            + df["second"].astype(str)
-        )
-        df["time"] = pd.to_datetime(df["time"], format="%d-%m-%Y %H%M:%S")
-
-        # - Drop columns not agreeing with DISDRODB L0 standards
-        columns_to_drop = [
-            "day",
-            "month",
-            "year",
-            "hour_minute",
-            "second",
-        ]
-        df = df.drop(columns=columns_to_drop)
-
-        return df
+    # - Define encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
 
     ##------------------------------------------------------------------------.
-    #### - 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
+    # Define datetime time column
+    df["time"] = (
+        df["day"].astype(str)
+        + "-"
+        + df["month"].astype(str)
+        + "-"
+        + df["year"].astype(str)
+        + " "
+        + df["hour_minute"].astype(str)
+        + ":"
+        + df["second"].astype(str)
     )
+    df["time"] = pd.to_datetime(df["time"], format="%d-%m-%Y %H%M:%S", errors="coerce")
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "day",
+        "month",
+        "year",
+        "hour_minute",
+        "second",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL/NCAR/PECAN_MOBILE.py

@@ -0,0 +1,125 @@
+#!/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=14)
+    columns = [
+        "date",
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "laser_amplitude",
+        "sensor_temperature",
+        "weather_code_metar_4678",
+        "weather_code_nws",
+        "number_particles",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "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"].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)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/{NCAR/OWLES_MIPS.py → PARSIVEL/NCAR/PLOWS_MIPS.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,
 ):
-    ####----------------------------------------------------------------------.
-    #### - Define column names
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
     column_names = [
         "day",
         "month",
@@ -50,7 +47,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = ","
@@ -71,9 +68,9 @@ def reader(
     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"]
 
     # Skip first row as columns names
@@ -83,55 +80,39 @@ def reader(
     reader_kwargs["encoding"] = "ISO-8859-1"
 
     ##------------------------------------------------------------------------.
-    #### - Define facultative dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # Import pandas
-        import pandas as pd
-
-        # Define datetime time column
-        df["time"] = (
-            df["day"].astype(str)
-            + "-"
-            + df["month"].astype(str)
-            + "-"
-            + df["year"].astype(str)
-            + " "
-            + df["hour_minute"].astype(str)
-            + ":"
-            + df["second"].astype(str)
-        )
-        df["time"] = pd.to_datetime(df["time"], format="%d-%m-%Y %H%M:%S", errors="coerce")
-
-        # - Drop columns not agreeing with DISDRODB L0 standards
-        columns_to_drop = [
-            "day",
-            "month",
-            "year",
-            "hour_minute",
-            "second",
-        ]
-        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
+    # Define datetime 'time' column
+    df["time"] = (
+        df["day"].astype(str)
+        + "-"
+        + df["month"].astype(str)
+        + "-"
+        + df["year"].astype(str)
+        + " "
+        + df["hour_minute"].astype(str)
+        + ":"
+        + df["second"].astype(str)
+    )
+    df["time"] = pd.to_datetime(df["time"], format="%d-%m-%Y %H%M:%S", errors="coerce")
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "day",
+        "month",
+        "year",
+        "hour_minute",
+        "second",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL/NCAR/VORTEX2_2009.py

@@ -0,0 +1,114 @@
+#!/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"
+
+    # - 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 encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
+
+    # - 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"]
+
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    ##------------------------------------------------------------------------.
+    #### 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 into columns and assign name
+    df = df["TO_PARSE"].str.split(";", expand=True, n=9)
+
+    columns = [
+        "date",
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "number_particles",
+        "sensor_temperature",
+        "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"].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)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df