openforis-whisp 0.0.1__py3-none-any.whl

openforis_whisp/logger.py

@@ -0,0 +1,39 @@
+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
+
+
+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)

openforis_whisp/parameters/__init__.py

@@ -0,0 +1,15 @@
+"""
+!!! BAD PRACTICE, ALWAYS IMPORT YOUR MODULES EXPLICITELY !!!
+
+Module to gather all parameters.
+
+If you use a module import all the functions here you only have 1 call to make
+"""
+
+# from .config_runtime import *
+
+# from .config_asr_url_info import *
+
+# from .config_asr_credentials import *
+
+# from parameters.config_ceo import *

openforis_whisp/parameters/config_runtime.py

@@ -0,0 +1,47 @@
+from pathlib import Path
+
+# unit choice ("ha" or "percent")
+percent_or_ha = "ha"
+
+# output column names
+# The names need to align with whisp/parameters/lookup_context_and_metadata.csv
+geometry_area_column = "Area"
+
+stats_unit_type_column = "Unit"
+
+iso3_country_column = "Country"
+
+iso2_country_column = "ProducerCountry"
+
+admin_1_column = "Admin_Level_1"
+
+centroid_x_coord_column = "Centroid_lon"
+
+centroid_y_coord_column = "Centroid_lat"
+
+geo_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 = "%.0f"
+
+# 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

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

openforis_whisp/parameters/lookup_gee_datasets.csv

@@ -0,0 +1,155 @@
+name,order,theme,use_for_risk,exclude_from_output,col_type,is_nullable,is_required,corresponding_variable
+EUFO_2020,10,treecover,1,0,float32,1,0,jrc_gfc_2020_prep
+GLAD_Primary,20,treecover,1,0,float32,1,0,glad_pht_prep
+TMF_undist,30,treecover,1,0,float32,1,0,jrc_tmf_undisturbed_prep
+JAXA_FNF_2020,40,treecover,1,0,float32,1,0,jaxa_forest_prep
+GFC_TC_2020,50,treecover,1,0,float32,1,0,glad_gfc_10pc_prep
+Forest_FDaP,60,treecover,1,0,float32,1,0,glad_gfc_10pc_prep
+ESA_TC_2020,70,treecover,1,0,float32,1,0,esa_worldcover_trees_prep
+TMF_plant,80,commodities,1,0,float32,1,0,jrc_tmf_plantation_prep
+Oil_palm_Descals,90,commodities,1,0,float32,1,0,creaf_descals_palm_prep
+Oil_palm_FDaP,100,commodities,1,0,float32,1,0,fdap_palm_prep
+Cocoa_FDaP,110,commodities,1,0,float32,1,0,fdap_cocoa
+Cocoa_ETH,120,commodities,1,0,float32,1,0,eth_kalischek_cocoa_prep
+Cocoa_bnetd,130,commodities,1,0,float32,1,0,civ_ocs2020_prep
+Rubber_FDaP,140,commodities,1,0,float32,1,0,fdap_rubber_prep
+Rubber_RBGE,150,commodities,1,0,float32,1,0,rbge_rubber_prep
+WDPA,160,ancilliary,0,1,bool,1,0,wcmc_wdpa_protection_prep
+KBA,170,ancilliary,0,1,bool,1,0,birdlife_kbas_biodiversity_prep
+TMF_def_2000,180,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2001,190,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2002,200,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2003,210,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2004,220,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2005,230,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2006,240,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2007,250,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2008,260,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2009,270,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2010,280,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2011,290,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2012,300,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2013,310,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2014,320,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2015,330,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2016,340,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2017,350,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2018,360,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2019,370,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2020,380,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2021,390,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2022,400,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_def_2023,410,disturbance_before,0,0,float32,1,0,tmf_def_per_year_prep
+TMF_deg_2000,420,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2001,430,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2002,440,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2003,450,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2004,460,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2005,470,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2006,480,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2007,490,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2008,500,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2009,510,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2010,520,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2011,530,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2012,540,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2013,550,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2014,560,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2015,570,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2016,580,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2017,590,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2018,600,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2019,610,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2020,620,disturbance_before,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2021,630,disturbance_after,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2022,640,disturbance_after,0,0,float32,1,0,tmf_deg_per_year_prep
+TMF_deg_2023,650,disturbance_after,0,0,float32,1,0,tmf_deg_per_year_prep
+GFC_loss_year_2001,660,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2002,670,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2003,680,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2004,690,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2005,700,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2006,710,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2007,720,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2008,730,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2009,740,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2010,750,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2011,760,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2012,770,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2013,780,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2014,790,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2015,800,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2016,810,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2017,820,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2018,830,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2019,840,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2020,850,disturbance_before,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2021,860,disturbance_after,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2022,870,disturbance_after,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+GFC_loss_year_2023,880,disturbance_after,0,0,float32,1,0,glad_gfc_loss_per_year_prep
+RADD_year_2019,890,disturbance_before,0,0,float32,1,0,radd_year_prep
+RADD_year_2020,900,disturbance_before,0,0,float32,1,0,radd_year_prep
+RADD_year_2021,910,disturbance_after,0,0,float32,1,0,radd_year_prep
+RADD_year_2022,920,disturbance_after,0,0,float32,1,0,radd_year_prep
+RADD_year_2023,930,disturbance_after,0,0,float32,1,0,radd_year_prep
+RADD_year_2024,940,disturbance_after,0,0,float32,1,0,radd_year_prep
+RADD_year_2025,941,disturbance_after,0,0,float32,1,0,radd_year_prep
+DIST_year_2024,945,disturbance_after,0,1,float32,1,0,glad_dist_year_prep
+DIST_year_2025,946,disturbance_after,0,1,float32,1,0,glad_dist_year_prep
+ESA_fire_2001,950,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2002,960,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2003,970,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2004,980,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2005,990,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2006,1000,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2007,1010,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2008,1020,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2009,1030,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2010,1040,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2011,1050,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2012,1060,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2013,1070,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2014,1080,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2015,1090,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2016,1100,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2017,1110,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2018,1120,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2019,1130,disturbance_before,0,0,float32,1,0,esa_fire_prep
+ESA_fire_2020,1140,disturbance_before,0,0,float32,1,0,esa_fire_prep
+MODIS_fire_2000,1150,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2001,1160,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2002,1170,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2003,1180,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2004,1190,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2005,1200,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2006,1210,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2007,1220,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2008,1230,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2009,1240,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2010,1250,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2011,1260,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2012,1270,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2013,1280,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2014,1290,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2015,1300,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2016,1310,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2017,1320,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2018,1330,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2019,1340,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2020,1350,disturbance_before,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2021,1360,disturbance_after,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2022,1370,disturbance_after,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2023,1380,disturbance_after,0,0,float32,1,0,modis_fire_prep
+MODIS_fire_2024,1390,disturbance_after,0,0,float32,1,0,modis_fire_prep
+TMF_deg_before_2020,1400,disturbance_before,1,0,float32,1,0,tmf_deg_before_2020_prep
+TMF_def_before_2020,1410,disturbance_before,1,0,float32,1,0,tmf_def_before_2020_prep
+GFC_loss_before_2020,1420,disturbance_before,1,0,float32,1,0,glad_gfc_loss_before_2020_prep
+ESA_fire_before_2020,1430,disturbance_before,1,0,float32,1,0,esa_fire_before_2020_prep
+MODIS_fire_before_2020,1440,disturbance_before,1,0,float32,1,0,modis_fire_before_2020_prep
+RADD_before_2020,1450,disturbance_before,1,0,float32,1,0,radd_before_2020_prep
+TMF_deg_after_2020,1460,disturbance_after,1,0,float32,1,0,tmf_deg_after_2020_prep
+TMF_def_after_2020,1470,disturbance_after,1,0,float32,1,0,tmf_def_after_2020_prep
+GFC_loss_after_2020,1480,disturbance_after,1,0,float32,1,0,glad_gfc_loss_after_2020_prep
+MODIS_fire_after_2020,1490,disturbance_after,1,0,float32,1,0,modis_fire_after_2020_prep
+RADD_after_2020,1500,disturbance_after,1,0,float32,1,0,RADD_after_2020_prep
+DIST_after_2020,1600,disturbance_after,1,1,float32,1,0,glad_dist_after_2020_prep

openforis_whisp/pd_schemas.py

@@ -0,0 +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]