disdrodb 0.1.4__py3-none-any.whl → 0.2.0__py3-none-any.whl

disdrodb/l0/readers/PARSIVEL2/{NASA/LPVEX.py → SPAIN/GRANADA.py}

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+
 # -----------------------------------------------------------------------------.
 # Copyright (c) 2021-2023 DISDRODB developers
 #
@@ -15,21 +16,7 @@
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 # -----------------------------------------------------------------------------.
-"""This reader allows to read raw data from NASA APU stations.
-
-The reader allows to read raw  APU data from the following NASA campaigns:
-
-    - HYMEX
-    - IFLOODS
-    - IPHEX
-    - OLYMPEX
-    - ICEPOP
-    - IMPACTS
-    - GCPEX
-    - WFF
-
-"""
-
+"""DISDRODB reader for Granada Parsivel2 raw text data."""
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
@@ -44,22 +31,22 @@ def reader(
     """Reader."""
     ##------------------------------------------------------------------------.
     #### Define column names
-    column_names = ["time", "TO_BE_SPLITTED"]
+    column_names = ["TO_PARSE"]
 
     ##------------------------------------------------------------------------.
     #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
-    reader_kwargs["delimiter"] = ";"
+    reader_kwargs["delimiter"] = "\\n"
     # - Skip first row as columns names
-    reader_kwargs["header"] = None
-    reader_kwargs["skiprows"] = 0
-    # - Skip file with encoding errors
-    reader_kwargs["encoding_errors"] = "ignore"
+    # - Define encoding
+    reader_kwargs["encoding"] = "latin"  # "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"
+    reader_kwargs["skiprows"] = 4
+
     # - Define reader engine
     #   - C engine is faster
     #   - Python engine is more feature-complete
@@ -71,11 +58,11 @@ def reader(
     #   - 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", "-.-"]
+    reader_kwargs["na_values"] = ["na", "", "error"]
 
     ##------------------------------------------------------------------------.
     #### Read the data
-    df = read_raw_text_file(
+    df_raw = read_raw_text_file(
         filepath=filepath,
         column_names=column_names,
         reader_kwargs=reader_kwargs,
@@ -84,26 +71,50 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### 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")
+    # Remove corrupted rows
+    df_raw = df_raw[df_raw["TO_PARSE"].str.count(",") == 1106]
 
-    # Split the 'TO_BE_SPLITTED' column
-    df = df["TO_BE_SPLITTED"].str.split(",", n=3, expand=True)
+    # Create ID and Value columns
+    df = df_raw["TO_PARSE"].str.split(",", expand=True, n=19)
 
-    # Assign column names
+    # Assign names
     names = [
-        "station_name",
-        "unknown",
-        "unknown2",
-        "raw_drop_number",
+        "time",
+        "id",
+        "rainfall_rate_32bit",
+        "snowfall_rate",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "rain_kinetic_energy",
+        "laser_amplitude",
+        "sensor_temperature",
+        "sensor_temperature_pcb",
+        "sensor_temperature_receiver",
+        "sensor_temperature_trasmitter",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "sensor_status",
+        "error_code",
+        "number_particles",
+        "TO_SPLIT",
     ]
     df.columns = names
 
-    # Add the time column
-    df["time"] = df_time
+    # Define datetime "time" column
+    df["time"] = df["time"].str.replace('"', "")
+    df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S")
+
+    # Retrieve raw array
+    df_split = df["TO_SPLIT"].str.split(",", expand=True)
+    df["raw_drop_concentration"] = df_split.iloc[:, :32].agg(",".join, axis=1)
+    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:64].agg(",".join, axis=1)
+    df["raw_drop_number"] = df_split.iloc[:, 64:].agg(",".join, axis=1)
+    del df_split
 
     # Drop columns not agreeing with DISDRODB L0 standards
-    df = df.drop(columns=["station_name", "unknown", "unknown2"])
+    df = df.drop(columns=["TO_SPLIT", "id"])
 
     # Return the dataframe adhering to DISDRODB L0 standards
     return df

disdrodb/l0/readers/PARSIVEL2/SWEDEN/SMHI.py

@@ -0,0 +1,189 @@
+#!/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 SHMI OTT Parsivel2."""
+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
+
+
+def parse_old_format(df):
+    """Reformat old format."""
+    # Remove rows with invalid number of separators
+    df = df[df["TO_PARSE"].str.count(";") == 1106]
+
+    # Split the columns
+    df = df["TO_PARSE"].str.split(";", n=18, expand=True)
+
+    # Assign column names
+    names = [
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",  # wawa
+        "reflectivity_32bit",
+        "mor_visibility",
+        "sample_interval",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_serial_number",
+        "firmware_iop",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "sensor_status",
+        "station_id",
+        "rainfall_amount_absolute_32bit",
+        "error_code",
+        "TO_SPLIT",
+    ]
+
+    df.columns = names
+
+    # Derive raw arrays
+    df_split = df["TO_SPLIT"].str.split(";", expand=True)
+    df["raw_drop_concentration"] = df_split.iloc[:, :32].agg(",".join, axis=1)
+    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:64].agg(",".join, axis=1)
+    df["raw_drop_number"] = df_split.iloc[:, 64:1088].agg(",".join, axis=1)
+
+    # Ensure the time column is datetime dtype
+    df["time"] = df["time"].str[0:12] + "00"
+    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 = [
+        "sensor_serial_number",
+        "firmware_iop",
+        "station_id",
+        "TO_SPLIT",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df
+
+
+def parse_new_format(df):
+    """Reformat new format."""
+    # Remove rows with invalid number of separators
+    df = df[df["TO_PARSE"].str.count(";") == 1106]
+
+    # Split the columns
+    df = df["TO_PARSE"].str.split(";", n=18, expand=True)
+
+    # Assign column names
+    names = [
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",  # wawa
+        "reflectivity_32bit",
+        "mor_visibility",
+        "sample_interval",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_temperature",
+        "sensor_serial_number",
+        "firmware_iop",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "sensor_status",
+        "station_id",
+        "rainfall_amount_absolute_32bit",
+        "error_code",
+        "TO_SPLIT",
+    ]
+
+    df.columns = names
+
+    # Derive raw arrays
+    df_split = df["TO_SPLIT"].str.split(";", expand=True)
+    df["raw_drop_concentration"] = df_split.iloc[:, :32].agg(",".join, axis=1)
+    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:64].agg(",".join, axis=1)
+    df["raw_drop_number"] = df_split.iloc[:, 64:1088].agg(",".join, axis=1)
+
+    # Add the time column
+    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 = [
+        "sensor_serial_number",
+        "firmware_iop",
+        "station_id",
+        "TO_SPLIT",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    ##------------------------------------------------------------------------.
+    #### Define column names
+    column_names = ["TO_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+    # Skip file with encoding errors
+    reader_kwargs["encoding_errors"] = "ignore"
+    # - 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 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", "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
+    if df["TO_PARSE"].iloc[0].startswith("datetime_utc"):
+        # Remove header if present (2025 onward)
+        df = df.iloc[1:]
+        # Parse new format
+        return parse_new_format(df)
+    return parse_old_format(df)

disdrodb/l0/readers/PARSIVEL2/USA/{C3WE.py → CW3E.py}

@@ -15,6 +15,7 @@
 # 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 the OTT Parsivel2 sensors of the CW3E network."""
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
@@ -68,11 +69,10 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### Adapt the dataframe to adhere to DISDRODB L0 standards
-    # Define 'time' datetime
+    # Remove rows with invalid number of separators
+    df = df[df["TO_PARSE"].str.count(";") == 1105]
 
     # Split the columns
-    df["TO_PARSE"].iloc[0:5].str.split(";", n=16, expand=True).iloc[0]
-
     df = df["TO_PARSE"].str.split(";", n=16, expand=True)
 
     # Assign column names
@@ -97,31 +97,13 @@ def reader(
     ]
     df.columns = names
 
-    # Derive raw drop arrays
-    def split_string(s):
-        vals = [v.strip() for v in s.split(";")]
-        c1 = ";".join(vals[:32])
-        c2 = ";".join(vals[32:64])
-        c3 = ";".join(vals[64:1088])
-        c4 = vals[1088]
-        c5 = vals[1089]
-        series = pd.Series(
-            {
-                "raw_drop_concentration": c1,
-                "raw_drop_average_velocity": c2,
-                "raw_drop_number": c3,
-                "rain_kinetic_energy": c4,
-                "CHECK_EMPTY": c5,
-            },
-        )
-        return series
-
-    splitted_string = df["TO_SPLIT"].apply(split_string)
-    df["raw_drop_concentration"] = splitted_string["raw_drop_concentration"]
-    df["raw_drop_average_velocity"] = splitted_string["raw_drop_average_velocity"]
-    df["raw_drop_number"] = splitted_string["raw_drop_number"]
-    df["rain_kinetic_energy"] = splitted_string["rain_kinetic_energy"]
-    df["CHECK_EMPTY"] = splitted_string["CHECK_EMPTY"]
+    # Derive raw arrays
+    df_split = df["TO_SPLIT"].str.split(";", expand=True)
+    df["raw_drop_concentration"] = df_split.iloc[:, :32].agg(",".join, axis=1)
+    df["raw_drop_average_velocity"] = df_split.iloc[:, 32:64].agg(",".join, axis=1)
+    df["raw_drop_number"] = df_split.iloc[:, 64:1088].agg(",".join, axis=1)
+    df["rain_kinetic_energy"] = df_split.iloc[:, 1088]
+    df["CHECK_EMPTY"] = df_split.iloc[:, 1089]
 
     # Ensure valid observation
     df = df[df["CHECK_EMPTY"] == ""]