disdrodb 0.1.1__py3-none-any.whl → 0.1.3__py3-none-any.whl

disdrodb/l0/readers/PARSIVEL2/KIT/TEAMX.py

@@ -0,0 +1,123 @@
+#!/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"
+    # - Skip first row as columns names
+    # - 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"
+    # - 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"]
+
+    ##------------------------------------------------------------------------.
+    #### 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
+    # Identify groups of lines corresponding to same measurement
+    is_start = df["TO_PARSE"].str.startswith("#0#,")
+    df["observation_id"] = is_start.cumsum()
+
+    # Loop over groups and create a dataframe with a single row for each measurement
+    list_obs = []
+    for _, df_obs in df.groupby("observation_id", sort=False):
+        if len(df_obs) not in [6, 7]:
+            pass
+
+        # Remove #<id># and last comma
+        series = df_obs["TO_PARSE"].str.split(",", n=1, expand=True)[1].str.rstrip(",")
+        if len(df_obs) == 7:
+            series = series.iloc[0:6]
+
+        # Create dataframe and name columns
+        df_obs = series.to_frame().T
+        df_obs.columns = [
+            "time",
+            "TO_SPLIT1",
+            "TO_SPLIT2",
+            "raw_drop_concentration",
+            "raw_drop_average_velocity",
+            "raw_drop_number",
+        ]
+
+        # Append to the list
+        list_obs.append(df_obs)
+
+    # Concat all timesteps into a single dataframe
+    df = pd.concat(list_obs)
+
+    # Split and rename remaining variables
+    df_split1 = df["TO_SPLIT1"].str.split(",", expand=True)
+    df_split1.columns = [
+        "weather_code_synop_4680",
+        "rainfall_accumulated_32bit",
+        "rainfall_rate32bit",
+        "reflectivity_32bit",
+    ]
+    df_split2 = df["TO_SPLIT2"].str.split(",", expand=True)
+    df_split2.columns = ["parsivel_id", "sensor_serial_number", "mor_visibility", "laser_amplitude", "sensor_status"]
+
+    # Merge everything into a single dataframe
+    df = pd.concat([df, df_split1, df_split2], axis=1)
+
+    # Define time as datetime64
+    df["time"] = pd.to_datetime(df["time"], format="%d.%m.%Y %H:%M:%S", errors="coerce")
+
+    # Remove unused variables
+    df = df.drop(columns=["TO_SPLIT1", "TO_SPLIT2", "parsivel_id", "sensor_serial_number"])
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL2/NASA/APU.py

@@ -0,0 +1,120 @@
+#!/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/>.
+# -----------------------------------------------------------------------------.
+"""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
+
+"""
+
+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", "TO_BE_SPLITTED"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    reader_kwargs = {}
+    # - Define delimiter
+    reader_kwargs["delimiter"] = ";"
+    # - Skip first row as columns names
+    reader_kwargs["header"] = None
+    reader_kwargs["skiprows"] = 0
+    # - Skip file with encoding errors
+    reader_kwargs["encoding_errors"] = "ignore"
+    # - 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
+    # Convert time column to datetime
+    df_time = pd.to_datetime(df["time"], format="%Y%m%d%H%M%S", errors="coerce")
+
+    # Split the 'TO_BE_SPLITTED' column
+    df = df["TO_BE_SPLITTED"].str.split(",", n=9, expand=True)
+
+    # Assign column names
+    names = [
+        "station_name",
+        "sensor_status",
+        "sensor_temperature",
+        "number_particles",
+        "rainfall_rate_32bit",
+        "reflectivity_16bit",
+        "mor_visibility",
+        "weather_code_synop_4680",
+        "weather_code_synop_4677",
+        "raw_drop_number",
+    ]
+    df.columns = names
+
+    # Add the time column
+    df["time"] = df_time
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    df = df.drop(columns=["station_name"])
+
+    # Drop rows with invalid values
+    # --> Ensure that weather_code_synop_4677 has length 2
+    # --> If a previous column is missing it will have 000
+    df = df[df["weather_code_synop_4677"].str.len() == 2]
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df

disdrodb/l0/readers/PARSIVEL2/{NETHERLANDS/DELFT.py → NCAR/FARM_PARSIVEL2.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 CSWR FARM disdrometer data (used in PERILS and RELAMPAGO campaign)."""
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
@@ -29,33 +30,43 @@ def reader(
     """Reader."""
     ##------------------------------------------------------------------------.
     #### Define column names
-    column_names = ["time", "epoch_time", "TO_BE_PARSED"]
+    column_names = ["TO_PARSE"]
 
     ##------------------------------------------------------------------------.
     #### Define reader options
     reader_kwargs = {}
+
     # - Define delimiter
-    reader_kwargs["delimiter"] = ";"
-    # - Skip first row as columns names
+    reader_kwargs["delimiter"] = "\\n"
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "ISO-8859-1"
+
+    # Skip first row as columns names
     reader_kwargs["header"] = None
-    # - Avoid first column to become df index
+    reader_kwargs["skiprows"] = 2
+
+    # - 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
+
+    # - 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"
-    # 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"]
+    reader_kwargs["na_values"] = ["na", "", "error"]
+
     ##------------------------------------------------------------------------.
     #### Read the data
     df = read_raw_text_file(
@@ -67,28 +78,13 @@ def reader(
 
     ##------------------------------------------------------------------------.
     #### 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)
+    # Split and assign integrated variables names
+    df = df["TO_PARSE"].str.split(",", expand=True, n=22)
 
-    # Retrieve DISDRODB compliant columns
-    df = df_to_parse.iloc[:, 0:35]
-
-    # Assign column names
-    column_names = [
+    names = [
+        "time",
+        "station_name",
+        "station_number",
         "rainfall_rate_32bit",
         "rainfall_accumulated_32bit",
         "weather_code_synop_4680",
@@ -107,58 +103,35 @@ def reader(
         "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",
+        "TO_SPLIT",
     ]
-    df.columns = column_names
+    df.columns = names
 
-    # Add time column
-    df["time"] = df_time
+    # 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:])
+        return pd.Series({"raw_drop_concentration": c1, "raw_drop_average_velocity": c2, "raw_drop_number": c3})
 
-    # 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,
-    )
+    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"]
 
-    # 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
+    # Define datetime "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 = [
-        "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",
+        "firmware_iop",
+        "firmware_dsp",
+        "TO_SPLIT",
     ]
     df = df.drop(columns=columns_to_drop)
 

disdrodb/l0/readers/PARSIVEL2/NCAR/PECAN_FP3.py

@@ -108,7 +108,7 @@ def reader(
     # --> "" generates an array of zeros in L0B processing
     df["raw_drop_number"] = df["raw_drop_number"].str.replace("<SPECTRUM>ZERO</SPECTRUM>", "")
 
-    # Remove <SPECTRUM> and </SPECTRUM>" acronyms from the raw_drop_number field
+    # Remove <SPECTRUM> and </SPECTRUM> prefix and suffix 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>", "")
 

disdrodb/l0/readers/PARSIVEL2/NCAR/PERILS_MIPS.py

@@ -0,0 +1,126 @@
+#!/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 the PERILS 2022 and 2023 MIPS and RADAPS files."""
+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"
+
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    # - 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"]
+
+    ##------------------------------------------------------------------------.
+    #### 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 and assign integrated variables names
+    df = df["TO_PARSE"].str.split(",", expand=True, n=6)
+    names = [
+        "year",
+        "doy",
+        "time",
+        "sensor_temperature",
+        "number_particles",
+        "rainfall_rate_32bit",
+        "TO_SPLIT",
+    ]
+    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:])
+        series = pd.Series(
+            {
+                "raw_drop_concentration": c1,
+                "raw_drop_average_velocity": c2,
+                # "raw_drop_number": c3,
+            },
+        )
+        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"]
+
+    # Define datetime time column
+    df["year"] = df["year"].str.replace(".0", "")
+    df["doy"] = df["doy"].str.replace(".0", "")
+    df["time"] = df["time"].str.replace(".0", "")
+    df["time"] = df["year"].astype(str) + "-" + df["doy"].astype(str) + " " + df["time"].astype(str)
+    df["time"] = pd.to_datetime(df["time"], format="%Y-%j %H%M%S", errors="coerce")
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "doy",
+        "year",
+        "TO_SPLIT",
+    ]
+    df = df.drop(columns=columns_to_drop)
+
+    # Return the dataframe adhering to DISDRODB L0 standards
+    return df