disdrodb 0.1.4__py3-none-any.whl → 0.1.5__py3-none-any.whl

disdrodb/l0/readers/LPM/SLOVENIA/ARSO.py

@@ -16,19 +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/>.
 # -----------------------------------------------------------------------------.
-"""DISDRODB reader for GID LPM sensors not measuring wind."""
+"""DISDRODB reader for ARSO LPM sensors."""
 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(
+def read_SM03_telegram(
     filepath,
     logger=None,
 ):
-    """Reader."""
+    """Read SM03 telegram."""
     ##------------------------------------------------------------------------.
     #### - Define raw data headers
     column_names = ["TO_PARSE"]
@@ -77,16 +76,99 @@ def reader(
         logger=logger,
     )
 
+    ##------------------------------------------------------------------------.
+    #### Adapt the dataframe to adhere to DISDRODB L0 standards
+    # Count number of delimiters to identify valid rows
+    df = df[df["TO_PARSE"].str.count(";") == 12]
+
+    # Check there are valid rows left
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}")
+
+    # Split by ; delimiter (before raw drop number)
+    df = df["TO_PARSE"].str.split(";", expand=True)
+
+    # Assign column names
+    names = []
+    df.columns = names
+
+    # Define datetime "time" column
+    time = df[0].str[-19:]
+    df["time"] = pd.to_datetime(time, format="%d/%m/%Y %H:%M:%S", errors="coerce")
+
+    return df
+
+
+def read_SM05_telegram(
+    filepath,
+    logger=None,
+):
+    """Read SM05 telegram."""
+    ##------------------------------------------------------------------------.
+    #### - Define raw data headers
+    column_names = ["TO_PARSE"]
+
+    ##------------------------------------------------------------------------.
+    #### Define reader options
+    # - For more info: https://pandas.pydata.org/docs/reference/api/pandas.read_csv.html
+    reader_kwargs = {}
+
+    # - Define delimiter
+    reader_kwargs["delimiter"] = "\\n"
+
+    # - Avoid first column to become df index !!!
+    reader_kwargs["index_col"] = False
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "latin"
+
+    # Since column names are expected to be passed explicitly, header is set to None
+    reader_kwargs["header"] = None
+
+    # - Number of rows to be skipped at the beginning of the file
+    reader_kwargs["skiprows"] = None
+
+    # - 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
     # Count number of delimiters to identify valid rows
     df = df[df["TO_PARSE"].str.count(";") == 521]
 
+    # Check there are valid rows left
+    if len(df) == 0:
+        raise ValueError(f"No valid data in {filepath}")
+
     # Split by ; delimiter (before raw drop number)
     df = df["TO_PARSE"].str.split(";", expand=True, n=80)
 
     # Assign column names
-    column_names = [
+    names = [
         "time",
         "start_identifier",
         "device_address",
@@ -109,7 +191,7 @@ def reader(
         "quality_index",
         "max_hail_diameter",
         "laser_status",
-        "static_signal",
+        "static_signal_status",
         "laser_temperature_analog_status",
         "laser_temperature_digital_status",
         "laser_current_analog_status",
@@ -123,7 +205,7 @@ def reader(
         "current_heating_heads_status",
         "current_heating_carriers_status",
         "control_output_laser_power_status",
-        "reserve_status",
+        "reserved_status",
         "temperature_interior",
         "laser_temperature",
         "laser_current_average",
@@ -169,15 +251,16 @@ def reader(
         "number_particles_class_9_internal_data",
         "raw_drop_number",
     ]
-    df.columns = column_names
+    df.columns = names
+
+    # Define datetime "time" column
+    time_str = df["time"].str[-19:]
+    # time_str = df["time"].str.extract(r"(\d{2}/\d{2}/\d{4} \d{2}:\d{2}:\d{2})")[0]
+    df["time"] = pd.to_datetime(time_str, format="%d/%m/%Y %H:%M:%S", errors="coerce")
 
     # Remove checksum from raw_drop_number
     df["raw_drop_number"] = df["raw_drop_number"].str.rsplit(";", n=2, expand=True)[0]
 
-    # Define datetime "time" column
-    time = df["time"].str.extract(r"(\d{2}/\d{2}/\d{4} \d{2}:\d{2}:\d{2})")[0]
-    df["time"] = pd.to_datetime(time, format="%d/%m/%Y %H:%M:%S", errors="coerce")
-
     # Drop row if start_identifier different than 00
     df["start_identifier"] = df["start_identifier"].astype(str).str[-2:]
     df = df[df["start_identifier"] == "00"]
@@ -195,3 +278,15 @@ def reader(
     ]
     df = df.drop(columns=columns_to_drop)
     return df
+
+
+@is_documented_by(reader_generic_docstring)
+def reader(
+    filepath,
+    logger=None,
+):
+    """Reader."""
+    return read_SM05_telegram(
+        filepath=filepath,
+        logger=logger,
+    )

disdrodb/l0/readers/LPM/SLOVENIA/UL.py

@@ -16,7 +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/>.
 # -----------------------------------------------------------------------------.
-"""DISDRODB reader for GID LPM sensors not measuring wind."""
+"""DISDRODB reader for UL LPM sensors in Crni Vrh."""
 import pandas as pd
 
 from disdrodb.l0.l0_reader import is_documented_by, reader_generic_docstring
@@ -113,7 +113,7 @@ def reader(
         "quality_index",
         "max_hail_diameter",
         "laser_status",
-        "static_signal",
+        "static_signal_status",
         "laser_temperature_analog_status",
         "laser_temperature_digital_status",
         "laser_current_analog_status",
@@ -127,7 +127,7 @@ def reader(
         "current_heating_heads_status",
         "current_heating_carriers_status",
         "control_output_laser_power_status",
-        "reserve_status",
+        "reserved_status",
         "temperature_interior",
         "laser_temperature",
         "laser_current_average",

disdrodb/l0/readers/LPM/SWITZERLAND/INNERERIZ_LPM.py

@@ -108,7 +108,7 @@ def reader(
         "quality_index",
         "max_hail_diameter",
         "laser_status",
-        "static_signal",
+        "static_signal_status",
         "laser_temperature_analog_status",
         "laser_temperature_digital_status",
         "laser_current_analog_status",
@@ -122,7 +122,7 @@ def reader(
         "current_heating_heads_status",
         "current_heating_carriers_status",
         "control_output_laser_power_status",
-        "reserve_status",
+        "reserved_status",
         "temperature_interior",
         "laser_temperature",
         "laser_current_average",

disdrodb/l0/readers/PARSIVEL/NCAR/VORTEX2_2010.py

@@ -93,20 +93,11 @@ def reader(
     valid_id_str = np.char.rjust(np.arange(0, 94).astype(str), width=2, fillchar="0")
     df = df[df["ID"].astype(str).isin(valid_id_str)]
 
-    # Create the dataframe with each row corresponding to a timestep
-    # - Group rows based on when ID values restart
-    groups = df.groupby((df["ID"].astype(int).diff() <= 0).cumsum())
-
-    # Reshape the dataframe
-    group_dfs = []
-    for _, group in groups:
-        group_df = group.set_index("ID").T
-        group_dfs.append(group_df)
-
-    # Merge each timestep dataframe
-    # --> Missing columns are infilled by NaN
-    df = pd.concat(group_dfs, axis=0)
-    df.columns = df.columns.astype(str).str.pad(width=2, side="left", fillchar="0")
+    # Create the dataframe where each row corresponds to a timestep
+    df["_group"] = (df["ID"].astype(int).diff() <= 0).cumsum()
+    df = df.pivot(index="_group", columns="ID")  # noqa
+    df.columns = df.columns.get_level_values("ID")
+    df = df.reset_index(drop=True)
 
     # Define column names
     column_dict = {

disdrodb/l0/readers/PARSIVEL/NCAR/VORTEX2_2010_UF.py

@@ -97,20 +97,11 @@ def reader(
     if len(df) == 0:
         raise ValueError("No rows left after removing corrupted ones.")
 
-    # Create the dataframe with each row corresponding to a timestep
-    # - Group rows based on when ID values restart
-    groups = df.groupby((df["ID"].astype(int).diff() <= 0).cumsum())
-
-    # Reshape the dataframe
-    group_dfs = []
-    for _, group in groups:
-        group_df = group.set_index("ID").T
-        group_dfs.append(group_df)
-
-    # Merge each timestep dataframe
-    # --> Missing columns are infilled by NaN
-    df = pd.concat(group_dfs, axis=0)
-    df.columns = df.columns.astype(str).str.pad(width=2, side="left", fillchar="0")
+    # Create the dataframe where each row corresponds to a timestep
+    df["_group"] = (df["ID"].astype(int).diff() <= 0).cumsum()
+    df = df.pivot(index="_group", columns="ID")  # noqa
+    df.columns = df.columns.get_level_values("ID")
+    df = df.reset_index(drop=True)
 
     # Define column names
     column_dict = {

disdrodb/l0/readers/PARSIVEL/SLOVENIA/UL.py

@@ -22,12 +22,8 @@ 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."""
+def read_format1(filepath, logger):
+    """Read format F1 (before 2020)."""
     ##------------------------------------------------------------------------.
     #### Define column names
     column_names = ["TO_PARSE"]
@@ -91,8 +87,8 @@ def reader(
         "weather_code_synop_4680",
         "reflectivity_32bit",
         "mor_visibility",
-        "sensor_temperature",  # maybe
-        "laser_amplitude",  # probably
+        "sensor_temperature",
+        "laser_amplitude",
         "number_particles",
         "sensor_status",
         "sensor_heating_current",
@@ -119,3 +115,116 @@ def reader(
 
     # Return the dataframe adhering to DISDRODB L0 standards
     return df
+
+
+def read_format2(filepath, logger):
+    """Read format 2 (July 2012-April 2023)."""
+    ##------------------------------------------------------------------------.
+    #### 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 the first row (header)
+    reader_kwargs["skiprows"] = 0
+
+    # - Define encoding
+    reader_kwargs["encoding"] = "latin"
+
+    # - 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"]
+
+    # Skip first row as columns names
+    reader_kwargs["header"] = None
+
+    ##------------------------------------------------------------------------.
+    #### Read the data
+    df_raw = 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
+    # Create ID and Value columns
+    df = df_raw["TO_PARSE"].str.split(";", expand=True, n=14)
+
+    # Assign column names
+    names = [
+        "id",
+        "time",
+        "rainfall_rate_32bit",
+        "rainfall_accumulated_32bit",
+        "weather_code_synop_4680",
+        "reflectivity_32bit",
+        "mor_visibility",
+        "sensor_temperature",
+        "laser_amplitude",
+        "number_particles",
+        "sensor_status",
+        "sensor_heating_current",
+        "sensor_battery_voltage",
+        "error_code",
+        "raw_drop_number",
+    ]
+    df.columns = names
+
+    # Convert time column to datetime
+    df["time"] = pd.to_datetime(df["time"], format="%Y-%m-%d %H:%M:%S", errors="coerce")
+
+    # Preprocess the raw spectrum
+    # - Add 0 before every ; if ; not preceded by a digit
+    # Example: ';;1;;' --> '0;0;1;0;'
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace("R;", "")
+    df["raw_drop_number"] = df["raw_drop_number"].str.replace(r"(?<!\d);", "0;", regex=True)
+
+    # Drop rows with invalid spectrum
+    df = df[df["raw_drop_number"].str.count(";") == 1024]
+
+    # df["rainfall_rate_32bit"].max()
+
+    # Drop columns not agreeing with DISDRODB L0 standards
+    columns_to_drop = [
+        "id",
+    ]
+    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."""
+    if filepath.endswith("F1.dat.gz"):
+        return read_format1(filepath, logger)
+    if filepath.endswith("F2.dat.gz"):
+        return read_format2(filepath, logger)
+    raise ValueError("Unexpected filename: {os.path.basename(filepath)")

disdrodb/l0/readers/PARSIVEL2/BRAZIL/CHUVA_PARSIVEL2.py

@@ -81,20 +81,11 @@ def reader(
     valid_id_str = np.char.rjust(np.arange(0, 94).astype(str), width=2, fillchar="0")
     df = df[df["ID"].astype(str).isin(valid_id_str)]
 
-    # Create the dataframe with each row corresponding to a timestep
-    # - Group rows based on when ID values restart
-    groups = df.groupby((df["ID"].astype(int).diff() <= 0).cumsum())
-
-    # Reshape the dataframe
-    group_dfs = []
-    for _, group in groups:
-        group_df = group.set_index("ID").T
-        group_dfs.append(group_df)
-
-    # Merge each timestep dataframe
-    # --> Missing columns are infilled by NaN
-    df = pd.concat(group_dfs, axis=0)
-    df.columns = df.columns.astype(str).str.pad(width=2, side="left", fillchar="0")
+    # Create the dataframe where each row corresponds to a timestep
+    df["_group"] = (df["ID"].astype(int).diff() <= 0).cumsum()
+    df = df.pivot(index="_group", columns="ID")  # noqa
+    df.columns = df.columns.get_level_values("ID")
+    df = df.reset_index(drop=True)
 
     # Define available column names
     column_dict = {
@@ -123,9 +114,14 @@ def reader(
         # "23": "station_number",
         "24": "rainfall_amount_absolute_32bit",
         "25": "error_code",
+        # "26": "sensor_temperature_pcb",
+        # "27": "sensor_temperature_receiver",
+        # "28": "sensor_temperature_trasmitter",
         "30": "rainfall_rate_16_bit_30",
         "31": "rainfall_rate_16_bit_1200",
         "32": "rainfall_accumulated_16bit",
+        # "34": "rain_kinetic_energy",
+        # "35": "snowfall_rate",
         "90": "raw_drop_concentration",
         "91": "raw_drop_average_velocity",
         "93": "raw_drop_number",

disdrodb/l0/readers/PARSIVEL2/BRAZIL/GOAMAZON_PARSIVEL2.py

@@ -81,20 +81,11 @@ def reader(
     valid_id_str = np.char.rjust(np.arange(0, 94).astype(str), width=2, fillchar="0")
     df = df[df["ID"].astype(str).isin(valid_id_str)]
 
-    # Create the dataframe with each row corresponding to a timestep
-    # - Group rows based on when ID values restart
-    groups = df.groupby((df["ID"].astype(int).diff() <= 0).cumsum())
-
-    # Reshape the dataframe
-    group_dfs = []
-    for _, group in groups:
-        group_df = group.set_index("ID").T
-        group_dfs.append(group_df)
-
-    # Merge each timestep dataframe
-    # --> Missing columns are infilled by NaN
-    df = pd.concat(group_dfs, axis=0)
-    df.columns = df.columns.astype(str).str.pad(width=2, side="left", fillchar="0")
+    # Create the dataframe where each row corresponds to a timestep
+    df["_group"] = (df["ID"].astype(int).diff() <= 0).cumsum()
+    df = df.pivot(index="_group", columns="ID")  # noqa
+    df.columns = df.columns.get_level_values("ID")
+    df = df.reset_index(drop=True)
 
     # Assign column names
     column_dict = {
@@ -123,9 +114,14 @@ def reader(
         # "23": "station_number",
         "24": "rainfall_amount_absolute_32bit",
         "25": "error_code",
+        # "26": "sensor_temperature_pcb",
+        # "27": "sensor_temperature_receiver",
+        # "28": "sensor_temperature_trasmitter",
         "30": "rainfall_rate_16_bit_30",
         "31": "rainfall_rate_16_bit_1200",
         "32": "rainfall_accumulated_16bit",
+        # "34": "rain_kinetic_energy",
+        # "35": "snowfall_rate",
         "90": "raw_drop_concentration",
         "91": "raw_drop_average_velocity",
         "93": "raw_drop_number",

disdrodb/l0/readers/PARSIVEL2/DENMARK/DTU.py

@@ -81,20 +81,11 @@ def reader(
     valid_id_str = np.char.rjust(np.arange(0, 94).astype(str), width=2, fillchar="0")
     df = df[df["ID"].astype(str).isin(valid_id_str)]
 
-    # Create the dataframe with each row corresponding to a timestep
-    # - Group rows based on when ID values restart
-    groups = df.groupby((df["ID"].astype(int).diff() <= 0).cumsum())
-
-    # Reshape the dataframe
-    group_dfs = []
-    for _, group in groups:
-        group_df = group.set_index("ID").T
-        group_dfs.append(group_df)
-
-    # Merge each timestep dataframe
-    # --> Missing columns are infilled by NaN
-    df = pd.concat(group_dfs, axis=0)
-    df.columns = df.columns.astype(str).str.pad(width=2, side="left", fillchar="0")
+    # Create the dataframe where each row corresponds to a timestep
+    df["_group"] = (df["ID"].astype(int).diff() <= 0).cumsum()
+    df = df.pivot(index="_group", columns="ID")  # noqa
+    df.columns = df.columns.get_level_values("ID")
+    df = df.reset_index(drop=True)
 
     # Define available column names
     column_dict = {
@@ -123,6 +114,9 @@ def reader(
         # "23": "station_number",
         "24": "rainfall_amount_absolute_32bit",
         "25": "error_code",
+        # "26": "sensor_temperature_pcb",
+        # "27": "sensor_temperature_receiver",
+        # "28": "sensor_temperature_trasmitter",
         # "30": "rainfall_rate_16_bit_30",
         # "31": "rainfall_rate_16_bit_1200",
         # "32": "rainfall_accumulated_16bit",