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

disdrodb/l0/readers/PARSIVEL/CHINA/CHONGQING.py

@@ -0,0 +1,113 @@
+#!/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 CHONGQING 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 = ["TO_SPLIT"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    reader_kwargs["delimiter"] = ","
+    # - No header
+    # reader_kwargs["header"] = None
+    # - Define encoding
+    reader_kwargs["encoding"] = "latin-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"
+    # - 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", "-.-", "C" * 32]
+
+    ##------------------------------------------------------------------------.
+    #### 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 invalid rows
+    # --> C*32 that is nan
+    df = df.dropna()
+
+    # Check if there are valid data
+    if len(df) == 0:
+        raise ValueError("No data available")
+
+    # Retrieve timesteps
+    df_time = df["TO_SPLIT"].iloc[0::33]
+    df_time = pd.to_datetime(df_time, format="%Y.%m.%d;%H:%M", errors="coerce")
+    df_time = df_time.rename("time")
+    df_time = df_time.reset_index(drop=True)
+
+    # Retrieve data
+    idx = np.ones(len(df)).astype(bool)
+    idx[0::33] = False
+    df_data = df[idx]
+
+    # Check consistency (no missing rows)
+    n_expected_data_rows = int(len(df_time) * 32)
+    if len(df_data) != n_expected_data_rows:
+        raise ValueError("Not same amount of timesteps and data.")
+
+    # Replace heterogeneous number of spaces with a single space
+    df_data["TO_SPLIT"] = df_data["TO_SPLIT"].str.replace(r" +", " ", regex=True).str.strip(" ")
+
+    # Retrieve arrays
+    arr = df_data["TO_SPLIT"].str.split(" ", expand=True).to_numpy()
+    # Flatten by row and then reshape to n_timesteps x 1024
+    arr = arr.flatten(order="C").reshape(len(df_time), 1024)
+    # Then concat all the 1024 bins
+    df_arr = pd.DataFrame(arr, dtype="str")
+    df_raw_drop_number = df_arr.agg(",".join, axis=1)
+    df_raw_drop_number = df_raw_drop_number.rename("raw_drop_number")
+
+    # Create dataframe
+    df = pd.concat([df_time, df_raw_drop_number], axis=1)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/{EPFL → PARSIVEL/EPFL}/ARCTIC_2021.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 ARCTIC 2021 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 = [
         "id",
         "latitude",
@@ -59,7 +57,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = ";"
@@ -74,57 +72,42 @@ def reader(
     #   - Python engine is more feature-complete
     reader_kwargs["engine"] = "python"
     # - 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
-    # - Latitude and longitude are kept because the sensor is moving !
-
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - Drop invalid rows
-        df = df.loc[df["id"].astype(str).str.len() < 10]
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # NOTE: Latitude and longitude are kept because the sensor is moving !
 
-        # - Convert time column to datetime
-        df["time"] = pd.to_datetime(df["time"], format="%d-%m-%Y %H:%M:%S", errors="coerce")
+    # Drop invalid rows
+    df = df.loc[df["id"].astype(str).str.len() < 10]
 
-        # - Split TO_BE_SPLITTED columns
-        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"]
+    # Convert time column to datetime
+    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 = [
-            "id",
-            "TO_BE_SPLITTED",
-            "datalogger_temperature",
-            "datalogger_error",
-        ]
-        df = df.drop(columns=columns_to_drop)
-        return df
+    # Split TO_BE_SPLITTED columns
+    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"]
 
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*.log*"
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "id",
+        "TO_BE_SPLITTED",
+        "datalogger_temperature",
+        "datalogger_error",
+    ]
+    df = df.drop(columns=columns_to_drop)
 
-    ####----------------------------------------------------------------------.
-    #### - 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}/COMMON_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 COMMON 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"] = ","
@@ -76,53 +74,38 @@ 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", "NA", "-.-"]
 
     ##------------------------------------------------------------------------.
-    #### - Define dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # - Drop bad lines based on datalogger_debug column
-        bad_indexes = df[df["datalogger_debug"].str.startswith("Frame", na=False)].index
-        df = df.drop(bad_indexes)
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - Convert time column to datetime
-        df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Drop bad lines based on datalogger_debug column
+    bad_indexes = df[df["datalogger_debug"].str.startswith("Frame", na=False)].index
+    df = df.drop(bad_indexes)
 
-        # - Drop columns not agreeing with DISDRODB L0 standards
-        columns_to_drop = [
-            "datalogger_debug",
-            "datalogger_voltage",
-            "id",
-            "datalogger_temperature",
-            "datalogger_error",
-        ]
-        df = df.drop(columns=columns_to_drop)
-        return df
+    # Convert time column to datetime
+    df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
 
-    ##------------------------------------------------------------------------.
-    #### - Define glob pattern to search data files in <raw_dir>/data/<station_name>
-    glob_patterns = "*.dat*"
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "datalogger_debug",
+        "datalogger_voltage",
+        "id",
+        "datalogger_temperature",
+        "datalogger_error",
+    ]
+    df = df.drop(columns=columns_to_drop)
 
-    ####----------------------------------------------------------------------.
-    #### - 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}/DAVOS_2009_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 DAVOS 2009-2011 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"] = ","
@@ -76,49 +74,34 @@ 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_debug",
-            "datalogger_voltage",
-            "datalogger_temperature",
-            "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_debug",
+        "datalogger_voltage",
+        "datalogger_temperature",
+        "datalogger_error",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/{EPFL → PARSIVEL/EPFL}/EPFL_2009.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 EPFL 2009 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"] = ","
@@ -78,49 +76,34 @@ 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 = [
-            "datalogger_debug",
-            "datalogger_voltage",
-            "id",
-            "datalogger_temperature",
-            "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 = [
+        "datalogger_debug",
+        "datalogger_voltage",
+        "id",
+        "datalogger_temperature",
+        "datalogger_error",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df