disdrodb 0.0.21__py3-none-any.whl → 0.1.1__py3-none-any.whl

disdrodb/l0/readers/PWS100/FRANCE/ENPC_PWS100.py

@@ -0,0 +1,150 @@
+#!/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 for ENPC PWS100 raw text data."""
+import zipfile
+
+import pandas as pd
+
+from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
+from disdrodb.utils.logger import log_error, log_warning
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+
+    ##------------------------------------------------------------------------.
+    #### Define function to read each txt file inside each daily zip file
+    def read_txt_file(file, filename, logger):  # noqa PLR0911
+        """Parse a single txt file within the daily zip file."""
+        # Read file
+        try:
+            txt = file.readline().decode("utf-8")
+        except Exception:
+            log_warning(logger=logger, msg=f"{filename} is corrupted", verbose=False)
+            return None
+
+        # Check file is not empty
+        if txt == "":
+            log_warning(logger=logger, msg=f"{filename} is empty", verbose=False)
+            return None
+
+        if "PSU voltage too low" in txt or "volt" in txt:
+            log_warning(logger=logger, msg=f"PSU voltage too low in {filename}", verbose=False)
+            return None
+
+        if "Error - message" in txt:
+            log_warning(logger=logger, msg=f"Error message in {filename}", verbose=False)
+            return None
+
+        # Clean up the line
+        txt = txt.replace(" 00 ", " 0 0 ")
+        txt = txt.replace("  ", " 0 ")
+        txt = txt[1:-8]
+
+        # Split the cleaned line
+        buf = txt.split(" ")
+
+        # Helper to convert list of floats to comma-separated string
+        def int_list_to_str(lst):
+            return ",".join(f"{int(i)}" for i in lst)
+
+        # Try to get the drop_size distribution:
+        try:
+            drop_size_distribution = int_list_to_str(buf[30:330])  # Drop size distribution (message field 42)
+        except Exception:
+            log_warning(logger, msg=f"Corrupted drop_size_distribution field in {filename}", verbose=False)
+            return None
+
+        # Try to get peak_to_pedestal_hist
+        try:
+            peak_to_pedestal_hist = int_list_to_str(buf[1499:1549])
+        except Exception:
+            log_warning(
+                logger,
+                msg=f"Corrupted raw_drop_number or peak_to_pedestal_hist field in {filename}",
+                verbose=False,
+            )
+            return None
+        # Parse fields
+        data = {
+            "mor_visibility": float(buf[2]),  # Visibility Range (message field 20)
+            "weather_code_synop_4680": float(buf[3]),  # Present Weather Code (WMO)  (message field 21)
+            "weather_code_metar_4678": buf[4],  # Present Weather Code (METAR)  (message field 22)
+            "weather_code_nws": buf[5],  # Present Weather Code (NWS)  (message field 23)
+            "alarms": int_list_to_str(buf[6:22]),  # Alarms (message field (24))
+            "sensor_status": buf[22],  # Fault status of PWS100 (message field 25)
+            "air_temperature": float(buf[23]),  # Temperature (°C) (message field 30)
+            "relative_humidity": float(buf[24]),  # Sampled relative humidity (%) (message field 30)
+            "wetbulb_temperature": float(buf[25]),  # Average wetbulb temperature (°C)(message field 30)
+            "air_temperature_max": float(buf[26]),  # Maximum temperature (°C)(message field 31)
+            "air_temperature_min": float(buf[27]),  # Minimum temperature (°C)(message field 31)
+            "rainfall_rate": float(buf[28]),  # Precipitation rate (mm/h)(message field 40)
+            "rainfall_accumulated": float(buf[29]),  # Precipitation accumulation (mm/h)(message field 41)
+            "drop_size_distribution": drop_size_distribution,  # Drop size distribution (message field 42)
+            "average_drop_velocity": float(buf[330]),  # Average velocity (mm/s)(message field 43)
+            "average_drop_size": float(buf[331]),  # Average size (mm/h)(message field 43)
+            "type_distribution": int_list_to_str(buf[332:343]),  # Type distribution (message field 44)
+            "raw_drop_number": int_list_to_str(buf[343:1499]),  # Size/velocity spectrum (34*34) (message field 47)
+            "peak_to_pedestal_hist": (
+                peak_to_pedestal_hist  # Peak to pedestal ratio distribution histogram (message field 48)
+            ),
+        }
+
+        # Convert to single-row DataFrame
+        df = pd.DataFrame([data])
+
+        # Define datetime "time" column from filename
+        datetime_str = " ".join(filename.replace(".txt", "").split("_")[-6:])
+        df["time"] = pd.to_datetime(datetime_str, format="%Y %m %d %H %M %S")
+
+        # # Drop columns not agreeing with DISDRODB L0 standards
+        # columns_to_drop = [
+        #      "peak_to_pedestal_hist",
+        #      "type_distribution",
+        # ]
+        # df = df.drop(columns=columns_to_drop)
+        return df
+
+    # ---------------------------------------------------------------------.
+    #### Iterate over all files (aka timesteps) in the daily zip archive
+    # - Each file contain a single timestep !
+    list_df = []
+    with zipfile.ZipFile(filepath, "r") as zip_ref:
+        filenames = sorted(zip_ref.namelist())
+        for filename in filenames:
+            if filename.endswith(".txt"):
+                # Open file
+                with zip_ref.open(filename) as f:
+                    try:
+                        df = read_txt_file(file=f, filename=filename, logger=logger)
+                        if df is not None:
+                            list_df.append(df)
+                    except Exception as e:
+                        msg = f"An error occurred while reading {filename}. The error is: {e}."
+                        log_error(logger=logger, msg=msg, verbose=True)
+
+    # Concatenate all dataframes into a single one
+    df = pd.concat(list_df)
+
+    # ---------------------------------------------------------------------.
+    return df

disdrodb/l0/readers/{NCAR/RELAMPAGO_RD80.py → RD80/BRAZIL/CHUVA_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"
@@ -86,59 +83,38 @@ 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"]
 
     ##------------------------------------------------------------------------.
-    #### - 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)
-
-        # - 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)
-
-        # - 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"])
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - 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
+    ##------------------------------------------------------------------------.
+    #### 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)
 
-        # - 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 = "*.txt"
+    # 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/{BRAZIL → RD80/BRAZIL}/GOAMAZON_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 +83,38 @@ 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"]
 
     ##------------------------------------------------------------------------.
-    #### - 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)
-
-        # - 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"])
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - 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
+    ##------------------------------------------------------------------------.
+    #### 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)
 
-        # - 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*"  # <year>/<month>
+    # 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/{NCAR → RD80/NCAR}/CINDY_2011_RD80.py

@@ -16,23 +16,20 @@
 # 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,
 ):
+    """Reader."""
     ##------------------------------------------------------------------------.
-    #### - Define column names
+    #### Define column names
     column_names = [
         "date",
         "time",
@@ -67,7 +64,7 @@ def reader(
     ]
 
     ##------------------------------------------------------------------------.
-    #### - Define reader options
+    #### Define reader options
     reader_kwargs = {}
     # - Define delimiter
     reader_kwargs["delimiter"] = "\\t"
@@ -89,54 +86,38 @@ 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"]
 
     ##------------------------------------------------------------------------.
-    #### - Define dataframe sanitizer function for L0 processing
-    def df_sanitizer_fun(df):
-        # - Import pandas
-        import pandas as pd
-
-        # - Replace 'Z' -Inf with NaN
-        df["Z"] = df["Z"].str.replace("-Inf", "NaN")
-
-        # - 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"])
+    #### Read the data
+    df = read_raw_text_file(
+        filepath=filepath,
+        column_names=column_names,
+        reader_kwargs=reader_kwargs,
+        logger=logger,
+    )
 
-        # - 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
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Replace 'Z' -Inf with NaN
+    df["Z"] = df["Z"].str.replace("-Inf", "NaN")
 
-        # - 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 = "*.txt"
+    # 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