disdrodb 0.0.20__py3-none-any.whl → 0.1.0__py3-none-any.whl

disdrodb/l0/readers/{BRAZIL/CHUVA_RD80.py → RD80/NCAR/RELAMPAGO_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 +83,43 @@ 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)
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - 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"])
+    ##------------------------------------------------------------------------.
+    #### 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)
 
-        # - 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
+    # 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)
 
-        # - 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*"
+    # 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/template_reader_raw_netcdf_data.py

@@ -0,0 +1,62 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+"""DISDRODB reader template for raw text data."""
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.l0.l0b_nc_processing import open_raw_netcdf_file, replace_custom_nan_flags, standardize_raw_dataset
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Open the netCDF
+    ds = open_raw_netcdf_file(filepath=filepath, logger=logger)
+
+    ##---------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Define dictionary mapping dataset variables and coordinates to keep (and rename)
+    # - If the platform is moving, keep longitude, latitude and altitude
+    # - If the platform is fixed, remove longitude, latitude and altitude coordinates
+    #   --> The geolocation information must be specified in the station metadata !
+    dict_names = {
+        # Dimensions
+        "<raw_dataset_diameter_dimension>": "diameter_bin_center",  # [TO ADAPT]
+        "<raw_dataset_velocity_dimension>": "velocity_bin_center",  # [TO ADAPT]
+        # Variables
+        # - Add here other variables accepted by DISDRODB L0 standards
+        "<precipitation_spectrum>": "raw_drop_number",  # [TO ADAPT]
+    }
+
+    # Rename dataset variables and columns and infill missing variables
+    sensor_name = "LPM"  # [SPECIFY HERE THE SENSOR FOR WHICH THE READER IS DESIGNED]
+    ds = standardize_raw_dataset(ds=ds, dict_names=dict_names, sensor_name=sensor_name)
+
+    # Replace occureence of NaN flags with np.nan
+    # - Define a dictionary specifying the value(s) of NaN flags for each variable
+    # - The code here below is just an example that requires to be adapted !
+    # - This step might not be required with your data !
+    dict_nan_flags = {"<raw_drop_number>": [-9999, -999]}
+    ds = replace_custom_nan_flags(ds, dict_nan_flags=dict_nan_flags, logger=logger)
+
+    # [ADD ADDITIONAL REQUIRED CUSTOM CODE HERE]
+
+    return ds

disdrodb/l0/readers/{reader_template.py → template_reader_raw_text_data.py}

@@ -16,22 +16,18 @@
 # 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
+"""DISDRODB reader template for raw text data."""
 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."""
+    ##------------------------------------------------------------------------.
     ###########################
     #### CUSTOMIZABLE CODE ####
     ###########################
@@ -39,7 +35,7 @@ def reader(
     column_names = []  # [ADD THE COLUMN NAMES LIST HERE]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     # - For more info: https://pandas.pydata.org/docs/reference/api/pandas.read_csv.html
     reader_kwargs = {}
 
@@ -53,9 +49,9 @@ 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", " NA"]
 
     # - Define behaviour when encountering bad lines
@@ -74,36 +70,16 @@ def reader(
     reader_kwargs["skiprows"] = None
 
     ##------------------------------------------------------------------------.
-    #### - Define facultative dataframe sanitizer function for L0 processing
-    # - Enable to deal with bad raw data files
-    # - Enable to standardize raw data files to L0 standards
-
-    def df_sanitizer_fun(df):
-        # Import dask or pandas
-
-        # [ADD YOUR CUSTOM CODE HERE]
-        #             ...
-
-        return df
-
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files within raw_dir/data/<station_name>
-    glob_patterns = "*"  # [TO BE ADAPTED TO THE STATION RAW FILE NAME PATTERN]
-
-    ####----------------------------------------------------------------------.
-    #### - 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
+    # [ADD YOUR CUSTOM CODE HERE]
+
+    return df