openforis-whisp 2.0.0a5__py3-none-any.whl → 2.0.0b1__py3-none-any.whl

openforis_whisp/risk.py

@@ -112,6 +112,7 @@ def whisp_risk(
     high_name: str = "yes",
     explicit_unit_type: str = None,
     national_codes: list[str] = None,  # List of ISO2 country codes to filter by
+    custom_bands_info: dict = None,  # New parameter for custom band risk info
 ) -> data_lookup_type:
     """
     Adds the EUDR (European Union Deforestation Risk) column to the DataFrame based on indicator values.
@@ -134,25 +135,43 @@ def whisp_risk(
         high_name (str, optional): Value shown in table if more than the threshold. Defaults to "yes".
         explicit_unit_type (str, optional): Override the autodetected unit type ('ha' or 'percent').
                                       If not provided, will detect from dataframe 'unit' column.
+        custom_bands_info (dict, optional): Custom band risk information. Dict format:
+            {
+                'band_name': {
+                    'theme': 'treecover',  # or 'commodities', 'disturbance_before', 'disturbance_after'
+                    'theme_timber': 'primary',  # or 'naturally_reg_2020', 'planted_plantation_2020', etc.
+                    'use_for_risk': 1,  # 0 or 1
+                    'use_for_risk_timber': 1,  # 0 or 1
+                }
+            }
+            If None, custom bands won't be included in risk calculations.
 
     Returns:
-        data_lookup_type: DataFrame with added 'EUDR_risk' column.
+        data_lookup_type: DataFrame with added risk columns.
     """
-    # Determine the unit type to use based on input data and overrid
+    # Determine the unit type
     unit_type = detect_unit_type(df, explicit_unit_type)
-
     print(f"Using unit type: {unit_type}")
 
     lookup_df_copy = lookup_gee_datasets_df.copy()
 
-    # filter by national codes (even if None - this removes all country columns unless specified)
+    # Add custom bands to lookup if provided
+    if custom_bands_info:
+        lookup_df_copy = add_custom_bands_info_to_lookup(
+            lookup_df_copy, custom_bands_info, df.columns
+        )
+        print(f"Including custom bands: {list(custom_bands_info.keys())}")
+        # print(f"appended custom bands info to lookup table")
+    if national_codes:
+        print(f"Filtering by national codes: {national_codes}")
+    # Filter by national codes
     filtered_lookup_gee_datasets_df = filter_lookup_by_country_codes(
         lookup_df=lookup_df_copy,
         filter_col="ISO2_code",
         national_codes=national_codes,
     )
 
-    # Rest of the function remains the same, but pass unit_type to add_indicators
+    # Get indicator columns (now includes custom bands)
     if ind_1_input_columns is None:
         ind_1_input_columns = get_cols_ind_01_treecover(filtered_lookup_gee_datasets_df)
     if ind_2_input_columns is None:
@@ -393,7 +412,7 @@ def add_eudr_risk_timber_col(
     """
 
     for index, row in df.iterrows():
-        # If there is a commodity in 2020 (ind_2_name) 
+        # If there is a commodity in 2020 (ind_2_name)
         # OR if there is planted-plantation in 2020 (ind_7_name) AND no agriculture in 2023 (ind_10_name), set EUDR_risk_timber to "low"
         if row[ind_2_name] == "yes" or (
             row[ind_7_name] == "yes" and row[ind_10_name] == "no"
@@ -411,7 +430,7 @@ def add_eudr_risk_timber_col(
             ind_8_name
         ] == "yes":
             df.at[index, "risk_timber"] = "high"
-        # No data yet on OWL conversion 
+        # No data yet on OWL conversion
         # If primary or naturally regenerating or planted forest in 2020 and OWL in 2023, set EUDR_risk to high
         # elif (row[ind_5_name] == "yes" or row[ind_6_name] == "yes" or row[ind_7_name] == "yes") and row[ind_10_name] == "yes":
         #    df.at[index, 'EUDR_risk_timber'] = "high"
@@ -699,7 +718,7 @@ def get_cols_ind_09_treecover_after_2020(lookup_gee_datasets_df):
     return list(
         lookup_gee_datasets_df["name"][
             (lookup_gee_datasets_df["use_for_risk_timber"] == 1)
-            & (lookup_gee_datasets_df["theme_timber"] == "treecover_post2020")
+            & (lookup_gee_datasets_df["theme_timber"] == "treecover_after_2020")
         ]
     )
 
@@ -769,3 +788,61 @@ def clamp(
 def check_range(value: float) -> None:
     if not (0 <= value <= 100):
         raise ValueError("Value must be between 0 and 100.")
+
+
+def add_custom_bands_info_to_lookup(
+    lookup_df: pd.DataFrame, custom_bands_info: dict, df_columns: list
+) -> pd.DataFrame:
+    """
+    Add custom bands to the lookup DataFrame for risk calculations.
+
+    Parameters
+    ----------
+    lookup_df : pd.DataFrame
+        Original lookup DataFrame
+    custom_bands_info : dict
+        Custom band definitions with risk info
+    df_columns : list
+        List of columns in the actual data DataFrame
+
+    Returns
+    -------
+    pd.DataFrame
+        Lookup DataFrame with custom bands added
+    """
+    custom_rows = []
+
+    for band_name, band_info in custom_bands_info.items():
+        # Only add bands that actually exist in the DataFrame
+        if band_name in df_columns:
+            custom_row = {
+                "name": band_name,  # Use the band name as provided
+                "theme": band_info.get(
+                    "theme", pd.NA
+                ),  # default to empty if not provided
+                "theme_timber": band_info.get(
+                    "theme_timber", pd.NA
+                ),  # default to empty if not provided
+                "use_for_risk": band_info.get(
+                    "use_for_risk", 0
+                ),  # default to 0 if not provided
+                "use_for_risk_timber": band_info.get(
+                    "use_for_risk_timber", 0
+                ),  # default to 0 if not provided
+                "exclude_from_output": 0,  # 0 here is so we don't exclude custom bands
+                "ISO2_code": pd.NA,  # Global, i.e., empty string, by default
+                # Add other required columns with defaults
+                "col_type": "float64",  # default to float64 if not provided
+                "is_nullable": 1,
+                "is_required": 0,
+                "order": 9999,  # Put at end unless specified otherwise
+                "corresponding_variable": pd.NA,  # not necessary for custom bands
+            }
+            custom_rows.append(custom_row)
+
+    if custom_rows:
+        custom_df = pd.DataFrame(custom_rows)
+        # Combine with original lookup
+        lookup_df = pd.concat([lookup_df, custom_df], ignore_index=True)
+
+    return lookup_df

openforis_whisp/stats.py

@@ -27,7 +27,10 @@ from .data_conversion import (
     # convert_csv_to_geojson,
     convert_df_to_geojson,
 )  # copied functions from whisp-api and geemap (accessed 2024) to avoid dependency
-from .reformat import validate_dataframe_using_lookups
+from .reformat import (
+    validate_dataframe_using_lookups,
+    validate_dataframe_using_lookups_flexible,
+)
 
 # NB functions that included "formatted" in the name apply a schema for validation and reformatting of the output dataframe. The schema is created from lookup tables.
 
@@ -38,6 +41,8 @@ def whisp_formatted_stats_geojson_to_df(
     remove_geom=False,
     national_codes=None,
     unit_type="ha",
+    whisp_image=None,
+    custom_bands=None,  # New parameter
 ) -> pd.DataFrame:
     """
         Main function for most users.
@@ -65,6 +70,15 @@ def whisp_formatted_stats_geojson_to_df(
             List of ISO2 country codes to include national datasets.
         unit_type: str, optional
             Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+        whisp_image : ee.Image, optional
+            Pre-combined multiband Earth Engine Image containing all Whisp datasets.
+            If provided, this image will be used instead of combining datasets based on national_codes.
+            If None, datasets will be combined automatically using national_codes parameter.
+        custom_bands : list or dict, optional
+            Custom band information for extra columns. Can be:
+            - List of band names: ['Aa_test', 'elevation']
+            - Dict with types: {'Aa_test': 'float64', 'elevation': 'float32'}
+            - None: preserves all extra columns automatically
 
     Returns
         -------
@@ -78,7 +92,9 @@ def whisp_formatted_stats_geojson_to_df(
         external_id_column,
         remove_geom,
         national_codes=national_codes,
-        unit_type=unit_type,  # Fixed: now it's a keyword argument
+        unit_type=unit_type,
+        whisp_image=whisp_image,
+        custom_bands=custom_bands,  # Pass through
     )
 
 
@@ -89,6 +105,7 @@ def whisp_formatted_stats_geojson_to_geojson(
     geo_column: str = "geo",
     national_codes=None,
     unit_type="ha",
+    whisp_image=None,  # New parameter
 ):
     """
     Convert a formatted GeoJSON file with a geo column into a GeoJSON file containing Whisp stats.
@@ -107,6 +124,8 @@ def whisp_formatted_stats_geojson_to_geojson(
         List of ISO2 country codes to include national datasets.
     unit_type : str, optional
         Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+    whisp_image : ee.Image, optional
+        Pre-combined multiband Earth Engine Image containing all Whisp datasets.
 
     Returns
     -------
@@ -117,6 +136,7 @@ def whisp_formatted_stats_geojson_to_geojson(
         external_id_column=external_id_column,
         national_codes=national_codes,
         unit_type=unit_type,
+        whisp_image=whisp_image,  # Pass through
     )
     # Convert the df to GeoJSON
     convert_df_to_geojson(df, output_geojson_filepath, geo_column)
@@ -131,6 +151,7 @@ def whisp_formatted_stats_ee_to_geojson(
     geo_column: str = "geo",
     national_codes=None,
     unit_type="ha",
+    whisp_image=None,  # New parameter
 ):
     """
     Convert an Earth Engine FeatureCollection to a GeoJSON file containing Whisp stats.
@@ -149,6 +170,8 @@ def whisp_formatted_stats_ee_to_geojson(
         List of ISO2 country codes to include national datasets.
     unit_type : str, optional
         Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+    whisp_image : ee.Image, optional
+        Pre-combined multiband Earth Engine Image containing all Whisp datasets.
     Returns
     -------
     None
@@ -159,6 +182,7 @@ def whisp_formatted_stats_ee_to_geojson(
         external_id_column,
         national_codes=national_codes,
         unit_type=unit_type,
+        whisp_image=whisp_image,  # Pass through
     )
 
     # Convert the df to GeoJSON
@@ -173,6 +197,8 @@ def whisp_formatted_stats_ee_to_df(
     remove_geom=False,
     national_codes=None,
     unit_type="ha",
+    whisp_image=None,
+    custom_bands=None,  # New parameter
 ) -> pd.DataFrame:
     """
     Convert a feature collection to a validated DataFrame with Whisp statistics.
@@ -189,6 +215,10 @@ def whisp_formatted_stats_ee_to_df(
         List of ISO2 country codes to include national datasets.
     unit_type : str, optional
         Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+    whisp_image : ee.Image, optional
+        Pre-combined multiband Earth Engine Image containing all Whisp datasets.
+    custom_bands : list or dict, optional
+        Custom band information for extra columns.
 
     Returns
     -------
@@ -202,11 +232,12 @@ def whisp_formatted_stats_ee_to_df(
         remove_geom,
         national_codes=national_codes,
         unit_type=unit_type,
+        whisp_image=whisp_image,
     )
 
-    # Pass national_codes to validation function to filter schema
-    validated_df = validate_dataframe_using_lookups(
-        df_stats, national_codes=national_codes
+    # Use flexible validation that handles custom bands
+    validated_df = validate_dataframe_using_lookups_flexible(
+        df_stats, national_codes=national_codes, custom_bands=custom_bands
     )
     return validated_df
 
@@ -220,6 +251,7 @@ def whisp_stats_geojson_to_df(
     remove_geom=False,
     national_codes=None,
     unit_type="ha",
+    whisp_image=None,  # New parameter
 ) -> pd.DataFrame:
     """
     Convert a GeoJSON file to a pandas DataFrame with Whisp statistics.
@@ -236,6 +268,8 @@ def whisp_stats_geojson_to_df(
         List of ISO2 country codes to include national datasets.
     unit_type : str, optional
         Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+    whisp_image : ee.Image, optional
+        Pre-combined multiband Earth Engine Image containing all Whisp datasets.
 
     Returns
     -------
@@ -250,6 +284,7 @@ def whisp_stats_geojson_to_df(
         remove_geom,
         national_codes=national_codes,
         unit_type=unit_type,
+        whisp_image=whisp_image,  # Pass through
     )
 
 
@@ -257,6 +292,7 @@ def whisp_stats_geojson_to_ee(
     input_geojson_filepath: Path | str,
     external_id_column=None,
     national_codes=None,
+    whisp_image=None,  # New parameter
 ) -> ee.FeatureCollection:
     """
     Convert a GeoJSON file to an Earth Engine FeatureCollection with Whisp statistics.
@@ -269,6 +305,8 @@ def whisp_stats_geojson_to_ee(
         The name of the external ID column, by default None.
     national_codes : list, optional
         List of ISO2 country codes to include national datasets.
+    whisp_image : ee.Image, optional
+        Pre-combined multiband Earth Engine Image containing all Whisp datasets.
 
     Returns
     -------
@@ -278,7 +316,10 @@ def whisp_stats_geojson_to_ee(
     feature_collection = convert_geojson_to_ee(str(input_geojson_filepath))
 
     return whisp_stats_ee_to_ee(
-        feature_collection, external_id_column, national_codes=national_codes
+        feature_collection,
+        external_id_column,
+        national_codes=national_codes,
+        whisp_image=whisp_image,  # Pass through
     )
 
 
@@ -288,6 +329,7 @@ def whisp_stats_geojson_to_geojson(
     external_id_column=None,
     national_codes=None,
     unit_type="ha",
+    whisp_image=None,  # New parameter
 ):
     """
     Convert a GeoJSON file to a GeoJSON object containing Whisp stats for the input ROI.
@@ -304,6 +346,8 @@ def whisp_stats_geojson_to_geojson(
         List of ISO2 country codes to include national datasets.
     unit_type : str, optional
         Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+    whisp_image : ee.Image, optional
+        Pre-combined multiband Earth Engine Image containing all Whisp datasets.
 
     Returns
     -------
@@ -318,6 +362,7 @@ def whisp_stats_geojson_to_geojson(
         external_id_column,
         national_codes=national_codes,
         unit_type=unit_type,
+        whisp_image=whisp_image,  # Pass through
     )
 
     # Convert the stats FeatureCollection to GeoJSON
@@ -333,6 +378,7 @@ def whisp_stats_geojson_to_drive(
     external_id_column=None,
     national_codes=None,
     unit_type="ha",
+    whisp_image=None,  # New parameter
 ):
     """
     Export Whisp statistics for a GeoJSON file to Google Drive.
@@ -347,6 +393,8 @@ def whisp_stats_geojson_to_drive(
         List of ISO2 country codes to include national datasets.
     unit_type : str, optional
         Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+    whisp_image : ee.Image, optional
+        Pre-combined multiband Earth Engine Image containing all Whisp datasets.
 
     Returns
     -------
@@ -364,6 +412,7 @@ def whisp_stats_geojson_to_drive(
             external_id_column,
             national_codes=national_codes,
             unit_type=unit_type,
+            whisp_image=whisp_image,  # Pass through
         )
 
     except Exception as e:
@@ -376,6 +425,7 @@ def whisp_stats_ee_to_ee(
     national_codes=None,
     unit_type="ha",
     keep_properties=None,
+    whisp_image=None,  # New parameter
 ):
     """
     Process a feature collection to get statistics for each feature.
@@ -389,6 +439,9 @@ def whisp_stats_ee_to_ee(
             - None: Remove all properties (default behavior)
             - True: Keep all properties
             - list: Keep only the specified properties
+        whisp_image (ee.Image, optional): Pre-combined multiband Earth Engine Image containing
+            all Whisp datasets. If provided, this image will be used instead of combining
+            datasets based on national_codes.
 
     Returns:
         ee.FeatureCollection: The output feature collection with statistics.
@@ -449,7 +502,10 @@ def whisp_stats_ee_to_ee(
         feature_collection = _keep_fc_properties(feature_collection, keep_properties)
 
     fc = get_stats(
-        feature_collection, national_codes=national_codes, unit_type=unit_type
+        feature_collection,
+        national_codes=national_codes,
+        unit_type=unit_type,
+        whisp_image=whisp_image,  # Pass through
     )
 
     return add_id_to_feature_collection(dataset=fc, id_name=plot_id_column)
@@ -478,6 +534,7 @@ def whisp_stats_ee_to_df(
     remove_geom=False,
     national_codes=None,
     unit_type="ha",
+    whisp_image=None,  # New parameter
 ) -> pd.DataFrame:
     """
     Convert a Google Earth Engine FeatureCollection to a pandas DataFrame and convert ISO3 to ISO2 country codes.
@@ -494,25 +551,36 @@ def whisp_stats_ee_to_df(
         List of ISO2 country codes to include national datasets.
     unit_type : str, optional
         Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+    whisp_image : ee.Image, optional
+        Pre-combined multiband Earth Engine Image containing all Whisp datasets.
 
     Returns
     -------
     df_stats : pd.DataFrame
         The dataframe containing the Whisp stats for the input ROI.
     """
+    # First, do the whisp processing to get the EE feature collection with stats
+    try:
+        stats_feature_collection = whisp_stats_ee_to_ee(
+            feature_collection,
+            external_id_column,
+            national_codes=national_codes,
+            unit_type=unit_type,
+            whisp_image=whisp_image,  # Pass through
+        )
+    except Exception as e:
+        print(f"An error occurred during Whisp stats processing: {e}")
+        raise e
+
+    # Then, convert the EE feature collection to DataFrame
     try:
         df_stats = convert_ee_to_df(
-            ee_object=whisp_stats_ee_to_ee(
-                feature_collection,
-                external_id_column,
-                national_codes=national_codes,
-                unit_type=unit_type,
-            ),
+            ee_object=stats_feature_collection,
             remove_geom=remove_geom,
         )
     except Exception as e:
         print(f"An error occurred during the conversion from EE to DataFrame: {e}")
-        return pd.DataFrame()  # Return an empty DataFrame in case of error
+        raise e
 
     try:
         df_stats = convert_iso3_to_iso2(
@@ -532,6 +600,7 @@ def whisp_stats_ee_to_drive(
     external_id_column=None,
     national_codes=None,
     unit_type="ha",
+    whisp_image=None,  # New parameter
 ):
     """
      Export Whisp statistics for a feature collection to Google Drive.
@@ -546,6 +615,8 @@ def whisp_stats_ee_to_drive(
          List of ISO2 country codes to include national datasets.
     unit_type : str, optional
          Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+    whisp_image : ee.Image, optional
+         Pre-combined multiband Earth Engine Image containing all Whisp datasets.
      Returns
      -------
      None
@@ -557,6 +628,7 @@ def whisp_stats_ee_to_drive(
                 external_id_column,
                 national_codes=national_codes,
                 unit_type=unit_type,
+                whisp_image=whisp_image,  # Pass through
             ),
             description="whisp_output_table",
             # folder="whisp_results",
@@ -574,29 +646,42 @@ def whisp_stats_ee_to_drive(
 
 
 # Get stats for a feature or feature collection
-def get_stats(feature_or_feature_col, national_codes=None, unit_type="ha"):
+def get_stats(
+    feature_or_feature_col, national_codes=None, unit_type="ha", whisp_image=None
+):
     """
-     Get stats for a feature or feature collection with optional filtering by national codes.
+    Get stats for a feature or feature collection with optional pre-combined image.
 
-     Parameters
-     ----------
-     feature_or_feature_col : ee.Feature or ee.FeatureCollection
-         The input feature or feature collection to analyze
-     national_codes : list, optional
-         List of ISO2 country codes to include national datasets
+    Parameters
+    ----------
+    feature_or_feature_col : ee.Feature or ee.FeatureCollection
+        The input feature or feature collection to analyze
+    national_codes : list, optional
+        List of ISO2 country codes to include national datasets.
+        Only used if whisp_image is None.
     unit_type : str, optional
-         Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
-     Returns
-     -------
-     ee.FeatureCollection
-         Feature collection with calculated statistics
+        Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+    whisp_image : ee.Image, optional
+        Pre-combined multiband Earth Engine Image containing all Whisp datasets.
+        If provided, this will be used instead of combining datasets based on national_codes.
+        If None, datasets will be combined automatically using national_codes parameter.
+    Returns
+    -------
+    ee.FeatureCollection
+        Feature collection with calculated statistics
     """
+
+    # Use provided image or combine datasets
+    if whisp_image is not None:
+        img_combined = whisp_image
+        print("Using provided whisp_image")
+    else:
+        img_combined = combine_datasets(national_codes=national_codes)
+        print(f"Combining datasets with national_codes: {national_codes}")
+
     # Check if the input is a Feature or a FeatureCollection
     if isinstance(feature_or_feature_col, ee.Feature):
-        # If the input is a Feature, call the server-side function for processing
-        print("feature")
-        # For a single feature, we need to combine datasets with the national_codes filter
-        img_combined = combine_datasets(national_codes=national_codes)
+        print("Processing single feature")
         output = ee.FeatureCollection(
             [
                 get_stats_feature(
@@ -605,9 +690,12 @@ def get_stats(feature_or_feature_col, national_codes=None, unit_type="ha"):
             ]
         )
     elif isinstance(feature_or_feature_col, ee.FeatureCollection):
-        # If the input is a FeatureCollection, call the server-side function for processing
+        print("Processing feature collection")
         output = get_stats_fc(
-            feature_or_feature_col, national_codes=national_codes, unit_type=unit_type
+            feature_or_feature_col,
+            national_codes=national_codes,
+            unit_type=unit_type,
+            img_combined=img_combined,  # Pass the image directly
         )
     else:
         output = "Check inputs: not an ee.Feature or ee.FeatureCollection"
@@ -615,28 +703,33 @@ def get_stats(feature_or_feature_col, national_codes=None, unit_type="ha"):
 
 
 # Get statistics for a feature collection
-def get_stats_fc(feature_col, national_codes=None, unit_type="ha"):
+def get_stats_fc(feature_col, national_codes=None, unit_type="ha", img_combined=None):
     """
-     Calculate statistics for a feature collection using Whisp datasets.
+    Calculate statistics for a feature collection using Whisp datasets.
 
-     Parameters
-     ----------
-     feature_col : ee.FeatureCollection
-         The input feature collection to analyze
-     national_codes : list, optional
-         List of ISO2 country codes (e.g., ["BR", "US"]) to include national datasets.
-         If provided, only national datasets for these countries and global datasets will be used.
-         If None (default), only global datasets will be used.
+    Parameters
+    ----------
+    feature_col : ee.FeatureCollection
+        The input feature collection to analyze
+    national_codes : list, optional
+        List of ISO2 country codes (e.g., ["BR", "US"]) to include national datasets.
+        If provided, only national datasets for these countries and global datasets will be used.
+        If None (default), only global datasets will be used.
+        Only used if img_combined is None.
     unit_type : str, optional
-         Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
-     Returns
-     -------
-     ee.FeatureCollection
-         Feature collection with calculated statistics
+        Whether to use hectares ("ha") or percentage ("percent"), by default "ha".
+    img_combined : ee.Image, optional
+        Pre-combined multiband image containing all Whisp datasets.
+        If provided, this will be used instead of combining datasets based on national_codes.
+    Returns
+    -------
+    ee.FeatureCollection
+        Feature collection with calculated statistics
     """
-    img_combined = combine_datasets(
-        national_codes=national_codes
-    )  # Pass national_codes to combine_datasets
+
+    # # Use provided image or combine datasets
+    # if img_combined is None:
+    #     img_combined = combine_datasets(national_codes=national_codes)
 
     out_feature_col = ee.FeatureCollection(
         feature_col.map(
@@ -651,6 +744,7 @@ def get_stats_fc(feature_col, national_codes=None, unit_type="ha"):
 
 
 # Get statistics for a single feature
+# Note: This function doesn't need whisp_image parameter since it already accepts img_combined directly
 
 
 def get_stats_feature(feature, img_combined, unit_type="ha"):

openforis_whisp/utils.py

@@ -4,6 +4,9 @@ import math
 import os
 import pandas as pd
 
+import urllib.request
+import os
+
 import importlib.resources as pkg_resources
 
 from dotenv import load_dotenv
@@ -152,3 +155,40 @@ class DotEnvNotFoundError(FileNotFoundError):
             "Running tests requires setting an appropriate '.env' in the root directory or in your current working "
             "directory. You may copy and edit the '.env.template' file from the root directory or from the README.",
         )
+
+
+def get_example_geojson(filename="geojson_example.geojson", cache=True):
+    """
+    Download example geojson file for testing whisp functionality.
+    
+    Parameters:
+    -----------
+    filename : str
+        Local filename to save the geojson
+    cache : bool
+        If True, cache file in user directory to avoid re-downloading
+        
+    Returns:
+    --------
+    str
+        Path to the downloaded geojson file
+    """
+    url = "https://raw.githubusercontent.com/forestdatapartnership/whisp/main/tests/fixtures/geojson_example.geojson"
+    
+    if cache:
+        cache_dir = os.path.join(os.path.expanduser("~"), ".whisp_cache")
+        os.makedirs(cache_dir, exist_ok=True)
+        filepath = os.path.join(cache_dir, filename)
+        
+        if os.path.exists(filepath):
+            return filepath
+    else:
+        filepath = filename
+    
+    try:
+        urllib.request.urlretrieve(url, filepath)
+        return filepath
+    except Exception as e:
+        raise RuntimeError(f"Failed to download example geojson: {e}")
+
+

{openforis_whisp-2.0.0a5.dist-info → openforis_whisp-2.0.0b1.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.3
 Name: openforis-whisp
-Version: 2.0.0a5
+Version: 2.0.0b1
 Summary: Whisp (What is in that plot) is an open-source solution which helps to produce relevant forest monitoring information and support compliance with deforestation-related regulations.
 License: MIT
 Keywords: whisp,geospatial,data-processing
 Author: Andy Arnell
-Author-email: and.arnell@fao.org
+Author-email: andrew.arnell@fao.org
 Requires-Python: >=3.10
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers