openforis-whisp 2.0.0a6__py3-none-any.whl → 2.0.0b2__py3-none-any.whl

openforis_whisp/logger.py

@@ -1,75 +1,75 @@
-import logging
-import sys
-
-BASE_MSG_FORMAT = (
-    "[%(filename)s | %(funcName)s() | l.%(lineno)s] %(levelname)s: %(message)s"
-)
-
-
-class StdoutLogger:
-    def __init__(self, name: str, msg_format: str = BASE_MSG_FORMAT) -> None:
-        self.handler = logging.StreamHandler(sys.stdout)
-        self.handler.setFormatter(logging.Formatter(msg_format))
-        self.handler.setLevel(logging.DEBUG)
-        self.logger = logging.getLogger(name)
-        self.logger.addHandler(self.handler)
-        self.logger.propagate = False
-
-    # Add missing methods that delegate to the internal logger
-    def debug(self, message):
-        self.logger.debug(message)
-
-    def info(self, message):
-        self.logger.info(message)
-
-    def warning(self, message):
-        self.logger.warning(message)
-
-    def error(self, message):
-        self.logger.error(message)
-
-    def critical(self, message):
-        self.logger.critical(message)
-
-    def setLevel(self, level):
-        self.logger.setLevel(level)
-
-
-class FileLogger:
-    def __init__(
-        self,
-        log_filepath: str,
-        msg_format: str = BASE_MSG_FORMAT,
-        log_to_stdout: bool = True,
-    ) -> None:
-        self.handler = logging.FileHandler(log_filepath)
-        self.handler.setFormatter(logging.Formatter(msg_format))
-        self.handler.setLevel(logging.DEBUG)
-        self.logger = logging.getLogger(f"{__name__}.file_logger_{log_filepath}")
-        self.logger.addHandler(self.handler)
-        self.logger.propagate = False
-
-        if log_to_stdout:
-            self.stdout_handler = logging.StreamHandler(sys.stdout)
-            self.stdout_handler.setFormatter(logging.Formatter(msg_format))
-            self.stdout_handler.setLevel(logging.DEBUG)
-            self.logger.addHandler(self.stdout_handler)
-
-    # Add missing methods for FileLogger too
-    def debug(self, message):
-        self.logger.debug(message)
-
-    def info(self, message):
-        self.logger.info(message)
-
-    def warning(self, message):
-        self.logger.warning(message)
-
-    def error(self, message):
-        self.logger.error(message)
-
-    def critical(self, message):
-        self.logger.critical(message)
-
-    def setLevel(self, level):
-        self.logger.setLevel(level)
+import logging
+import sys
+
+BASE_MSG_FORMAT = (
+    "[%(filename)s | %(funcName)s() | l.%(lineno)s] %(levelname)s: %(message)s"
+)
+
+
+class StdoutLogger:
+    def __init__(self, name: str, msg_format: str = BASE_MSG_FORMAT) -> None:
+        self.handler = logging.StreamHandler(sys.stdout)
+        self.handler.setFormatter(logging.Formatter(msg_format))
+        self.handler.setLevel(logging.DEBUG)
+        self.logger = logging.getLogger(name)
+        self.logger.addHandler(self.handler)
+        self.logger.propagate = False
+
+    # Add missing methods that delegate to the internal logger
+    def debug(self, message):
+        self.logger.debug(message)
+
+    def info(self, message):
+        self.logger.info(message)
+
+    def warning(self, message):
+        self.logger.warning(message)
+
+    def error(self, message):
+        self.logger.error(message)
+
+    def critical(self, message):
+        self.logger.critical(message)
+
+    def setLevel(self, level):
+        self.logger.setLevel(level)
+
+
+class FileLogger:
+    def __init__(
+        self,
+        log_filepath: str,
+        msg_format: str = BASE_MSG_FORMAT,
+        log_to_stdout: bool = True,
+    ) -> None:
+        self.handler = logging.FileHandler(log_filepath)
+        self.handler.setFormatter(logging.Formatter(msg_format))
+        self.handler.setLevel(logging.DEBUG)
+        self.logger = logging.getLogger(f"{__name__}.file_logger_{log_filepath}")
+        self.logger.addHandler(self.handler)
+        self.logger.propagate = False
+
+        if log_to_stdout:
+            self.stdout_handler = logging.StreamHandler(sys.stdout)
+            self.stdout_handler.setFormatter(logging.Formatter(msg_format))
+            self.stdout_handler.setLevel(logging.DEBUG)
+            self.logger.addHandler(self.stdout_handler)
+
+    # Add missing methods for FileLogger too
+    def debug(self, message):
+        self.logger.debug(message)
+
+    def info(self, message):
+        self.logger.info(message)
+
+    def warning(self, message):
+        self.logger.warning(message)
+
+    def error(self, message):
+        self.logger.error(message)
+
+    def critical(self, message):
+        self.logger.critical(message)
+
+    def setLevel(self, level):
+        self.logger.setLevel(level)

openforis_whisp/parameters/config_runtime.py

@@ -1,44 +1,44 @@
-from pathlib import Path
-
-# output column names
-# The names need to align with whisp/parameters/lookup_context_and_metadata.csv
-geometry_area_column = "Area"  # Note: datasets.py defines this explicitly as "Area", to allow it to be a standalone script. iso2 country code. Default of "Area" aligns with the EU Traces online reporting platform.
-
-stats_unit_type_column = "Unit"  # name of unit type column in the stats tabl
-
-iso3_country_column = "Country"
-
-iso2_country_column = "ProducerCountry"  # iso2 country code. Default of "ProducerCountry" aligns with the EU Traces online reporting platform.
-
-admin_1_column = "Admin_Level_1"
-
-centroid_x_coord_column = "Centroid_lon"
-
-centroid_y_coord_column = "Centroid_lat"
-
-external_id_column = "external_id"
-
-geometry_type_column = "Geometry_type"
-
-plot_id_column = "plotId"
-
-water_flag = "In_waterbody"
-
-geometry_column = "geo"  # geometry column name, stored as a string.
-
-# reformatting numbers to decimal places (e.g. '%.3f' is 3 dp)
-geometry_area_column_formatting = "%.3f"
-
-stats_area_columns_formatting = "%.3f"
-
-stats_percent_columns_formatting = "%.1f"
-
-# lookup path - for dataset info
-DEFAULT_GEE_DATASETS_LOOKUP_TABLE_PATH = (
-    Path(__file__).parent / "lookup_gee_datasets.csv"
-)
-
-# lookup path - for dataset info
-DEFAULT_CONTEXT_LOOKUP_TABLE_PATH = (
-    Path(__file__).parent / "lookup_context_and_metadata.csv"
-)
+from pathlib import Path
+
+# output column names
+# The names need to align with whisp/parameters/lookup_context_and_metadata.csv
+geometry_area_column = "Area"  # Note: datasets.py defines this explicitly as "Area", to allow it to be a standalone script. iso2 country code. Default of "Area" aligns with the EU Traces online reporting platform.
+
+stats_unit_type_column = "Unit"  # name of unit type column in the stats tabl
+
+iso3_country_column = "Country"
+
+iso2_country_column = "ProducerCountry"  # iso2 country code. Default of "ProducerCountry" aligns with the EU Traces online reporting platform.
+
+admin_1_column = "Admin_Level_1"
+
+centroid_x_coord_column = "Centroid_lon"
+
+centroid_y_coord_column = "Centroid_lat"
+
+external_id_column = "external_id"
+
+geometry_type_column = "Geometry_type"
+
+plot_id_column = "plotId"
+
+water_flag = "In_waterbody"
+
+geometry_column = "geo"  # geometry column name, stored as a string.
+
+# reformatting numbers to decimal places (e.g. '%.3f' is 3 dp)
+geometry_area_column_formatting = "%.3f"
+
+stats_area_columns_formatting = "%.3f"
+
+stats_percent_columns_formatting = "%.1f"
+
+# lookup path - for dataset info
+DEFAULT_GEE_DATASETS_LOOKUP_TABLE_PATH = (
+    Path(__file__).parent / "lookup_gee_datasets.csv"
+)
+
+# lookup path - for dataset info
+DEFAULT_CONTEXT_LOOKUP_TABLE_PATH = (
+    Path(__file__).parent / "lookup_context_and_metadata.csv"
+)

openforis_whisp/parameters/lookup_context_and_metadata.csv

@@ -1,13 +1,13 @@
-name,order,ISO2_code,theme,theme_timber,use_for_risk,use_for_risk_timber,exclude_from_output,col_type,is_nullable,is_required,corresponding_variable
-plotId,-10,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,0,plot_id_column
-external_id,-9,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,0,external_id_column
-Area,-8,,context_and_metadata,context_and_metadata,NA,NA,0,float32,1,1,geometry_area_column
-Geometry_type,-7,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,geometry_type_column
-Country,-6,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,iso3_country_column
-ProducerCountry,-5,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,iso2_country_column
-Admin_Level_1,-4,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,admin_1_column
-Centroid_lon,-3,,context_and_metadata,context_and_metadata,NA,NA,0,float64,1,1,centroid_x_coord_column
-Centroid_lat,-2,,context_and_metadata,context_and_metadata,NA,NA,0,float64,1,1,centroid_y_coord_column
-Unit,-1,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,stats_unit_type_column
-In_waterbody,0,,context_and_metadata,context_and_metadata,NA,NA,0,bool,1,1,water_flag
-geo,9999,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,geometry_column
+name,order,ISO2_code,theme,theme_timber,use_for_risk,use_for_risk_timber,exclude_from_output,col_type,is_nullable,is_required,corresponding_variable
+plotId,-10,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,0,plot_id_column
+external_id,-9,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,0,external_id_column
+Area,-8,,context_and_metadata,context_and_metadata,NA,NA,0,float32,1,1,geometry_area_column
+Geometry_type,-7,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,geometry_type_column
+Country,-6,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,iso3_country_column
+ProducerCountry,-5,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,iso2_country_column
+Admin_Level_1,-4,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,admin_1_column
+Centroid_lon,-3,,context_and_metadata,context_and_metadata,NA,NA,0,float64,1,1,centroid_x_coord_column
+Centroid_lat,-2,,context_and_metadata,context_and_metadata,NA,NA,0,float64,1,1,centroid_y_coord_column
+Unit,-1,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,stats_unit_type_column
+In_waterbody,0,,context_and_metadata,context_and_metadata,NA,NA,0,bool,1,1,water_flag
+geo,9999,,context_and_metadata,context_and_metadata,NA,NA,0,string,1,1,geometry_column

openforis_whisp/parameters/lookup_gee_datasets.csv

@@ -163,13 +163,11 @@ GFT_planted_plantation,1900,,NA,planted_plantation_2020,0,1,0,float32,1,0,g_gft_
 IIASA_planted_plantation,1910,,NA,planted_plantation_2020,0,1,0,float32,1,0,g_iiasa_planted_prep
 TMF_regrowth_2023,2000,,NA,treecover_after_2020,0,1,0,float32,1,0,g_tmf_regrowth_prep
 ESRI_2023_TC,2010,,NA,treecover_after_2020,0,1,0,float32,1,0,g_esri_2023_tc_prep
-GLC_FCS30D_TC_2022,2020,,NA,treecover_after_2020,0,1,0,float32,1,0,g_glc_fcs30d_tc_2022_prep
 Oil_palm_2023_FDaP,2100,,NA,agri_after_2020,0,1,0,float32,1,0,g_fdap_palm_2023_prep
 Rubber_2023_FDaP,2110,,NA,agri_after_2020,0,1,0,float32,1,0,g_fdap_rubber_2023_prep
 Coffee_FDaP_2023,2111,,NA,agri_after_2020,0,1,0,float32,1,0,g_fdap_coffee_2023_prep
 Cocoa_2023_FDaP,2120,,NA,agri_after_2020,0,1,0,float32,1,0,g_fdap_cocoa_2023_prep
-ESRI_2023_crop,2130,,NA,agri_after_2020,0,1,0,float32,1,0,g_esri_2023_crop_prep
-GLC_FCS30D_crop_2022,2140,,NA,agri_after_2020,0,1,0,float32,1,0,g_glc_fcs30d_crop_2022_prep
+ESRI_crop_gain_2020_2023,2130,,NA,agri_after_2020,0,1,0,float32,1,0,g_esri_2020_2023_crop_prep
 GFW_logging_before_2020,2200,,NA,logging_concession,0,1,0,float32,1,0,g_logging_concessions_prep
 nCO_ideam_forest_2020,2310,CO,treecover,NA,1,1,0,float32,1,0,nco_ideam_forest_2020_prep
 nCO_ideam_eufo_commission_2020,2320,CO,commodities,NA,1,1,0,float32,1,0,nco_ideam_eufo_commission_2020_prep

openforis_whisp/pd_schemas.py

@@ -1,77 +1,77 @@
-import pandera as pa
-from pandera.typing import DataFrame, Series
-
-# Define a schema for validating a DataFrame related to GEE (Google Earth Engine) datasets.
-class DataLookupSchema(pa.DataFrameModel):
-
-    # Ensure the name is unique
-    name: Series[str] = pa.Field(unique=True, nullable=False)
-    order: Series[int] = pa.Field(nullable=False)
-    theme: Series[str] = pa.Field(nullable=True)
-
-    # Define fields without checks
-    use_for_risk: Series[pa.Int | bool] = pa.Field(nullable=True)
-    exclude_from_output: Series[pa.Int | bool] = pa.Field(nullable=False)
-
-    # Define col_type without checks
-    col_type: Series[str] = pa.Field(nullable=False)
-
-    is_nullable: Series[pa.Int | bool] = pa.Field(nullable=False)
-    is_required: Series[pa.Int | bool] = pa.Field(nullable=False)
-
-    corresponding_variable: Series[str] = pa.Field(nullable=True)
-
-
-# For type annotation - not used for validation yet
-data_lookup_type = DataFrame[DataLookupSchema]
-
-
-# checks (below) not working currently so using without
-
-
-# import pandera as pa
-# from pandera.typing import DataFrame, Series
-
-# # Define a schema for validating a DataFrame related to GEE (Google Earth Engine) datasets.
-# class DataLookupSchema(pa.DataFrameModel):
-
-#     # Ensure the name is unique
-#     name: Series[str] = pa.Field(unique=True, nullable=False)
-#     order: Series[int] = pa.Field(nullable=False)
-#     theme: Series[str] = pa.Field(nullable=True)
-
-#     # Restrict use_for_risk to 0 or 1, either as int or bool
-#     use_for_risk: Series[pa.Int | bool] = pa.Field(
-#         checks=pa.Check.isin([0, 1]),  # Using 'checks' keyword argument
-#         nullable=True
-#     )
-
-#     # Restrict exclude_from_input and exclude_from_output to 0 or 1
-#     exclude_from_input: Series[pa.Int | bool] = pa.Field(
-#         checks=pa.Check.isin([0, 1]),
-#         nullable=False
-#     )
-#     exclude_from_output: Series[pa.Int | bool] = pa.Field(
-#         checks=pa.Check.isin([0, 1]),
-#         nullable=False
-#     )
-
-#     # Restrict col_type to specific values
-#     col_type: Series[str] = pa.Field(
-#         checks=pa.Check.isin(['int', 'int64', 'string', 'float32', 'float64', 'bool']),
-#         nullable=False
-#     )
-
-#     is_nullable: Series[pa.Int | bool] = pa.Field(
-#         checks=pa.Check.isin([0, 1]),
-#         nullable=False
-#     )
-#     is_required: Series[pa.Int | bool] = pa.Field(
-#         checks=pa.Check.isin([0, 1]),
-#         nullable=False
-#     )
-
-#     corresponding_variable: Series[str] = pa.Field(nullable=True)
-
-# # For type annotation
-# data_lookup_type = DataFrame[DataLookupSchema]
+import pandera as pa
+from pandera.typing import DataFrame, Series
+
+# Define a schema for validating a DataFrame related to GEE (Google Earth Engine) datasets.
+class DataLookupSchema(pa.DataFrameModel):
+
+    # Ensure the name is unique
+    name: Series[str] = pa.Field(unique=True, nullable=False)
+    order: Series[int] = pa.Field(nullable=False)
+    theme: Series[str] = pa.Field(nullable=True)
+
+    # Define fields without checks
+    use_for_risk: Series[pa.Int | bool] = pa.Field(nullable=True)
+    exclude_from_output: Series[pa.Int | bool] = pa.Field(nullable=False)
+
+    # Define col_type without checks
+    col_type: Series[str] = pa.Field(nullable=False)
+
+    is_nullable: Series[pa.Int | bool] = pa.Field(nullable=False)
+    is_required: Series[pa.Int | bool] = pa.Field(nullable=False)
+
+    corresponding_variable: Series[str] = pa.Field(nullable=True)
+
+
+# For type annotation - not used for validation yet
+data_lookup_type = DataFrame[DataLookupSchema]
+
+
+# checks (below) not working currently so using without
+
+
+# import pandera as pa
+# from pandera.typing import DataFrame, Series
+
+# # Define a schema for validating a DataFrame related to GEE (Google Earth Engine) datasets.
+# class DataLookupSchema(pa.DataFrameModel):
+
+#     # Ensure the name is unique
+#     name: Series[str] = pa.Field(unique=True, nullable=False)
+#     order: Series[int] = pa.Field(nullable=False)
+#     theme: Series[str] = pa.Field(nullable=True)
+
+#     # Restrict use_for_risk to 0 or 1, either as int or bool
+#     use_for_risk: Series[pa.Int | bool] = pa.Field(
+#         checks=pa.Check.isin([0, 1]),  # Using 'checks' keyword argument
+#         nullable=True
+#     )
+
+#     # Restrict exclude_from_input and exclude_from_output to 0 or 1
+#     exclude_from_input: Series[pa.Int | bool] = pa.Field(
+#         checks=pa.Check.isin([0, 1]),
+#         nullable=False
+#     )
+#     exclude_from_output: Series[pa.Int | bool] = pa.Field(
+#         checks=pa.Check.isin([0, 1]),
+#         nullable=False
+#     )
+
+#     # Restrict col_type to specific values
+#     col_type: Series[str] = pa.Field(
+#         checks=pa.Check.isin(['int', 'int64', 'string', 'float32', 'float64', 'bool']),
+#         nullable=False
+#     )
+
+#     is_nullable: Series[pa.Int | bool] = pa.Field(
+#         checks=pa.Check.isin([0, 1]),
+#         nullable=False
+#     )
+#     is_required: Series[pa.Int | bool] = pa.Field(
+#         checks=pa.Check.isin([0, 1]),
+#         nullable=False
+#     )
+
+#     corresponding_variable: Series[str] = pa.Field(nullable=True)
+
+# # For type annotation
+# data_lookup_type = DataFrame[DataLookupSchema]