openforis-whisp 3.0.0a2__py3-none-any.whl → 3.0.0a3__py3-none-any.whl

openforis_whisp/reformat.py

@@ -125,7 +125,7 @@ def validate_dataframe(
     Returns:
         pd.DataFrame: The validated DataFrame with columns ordered according to the schema, or None if validation fails.
     """
-    log_missing_columns(df_stats, schema)
+    _log_missing_columns(df_stats, schema)
 
     # df_stats = df_stats.reindex(schema.columns.keys(), axis=1)
 
@@ -251,7 +251,7 @@ def create_schema_from_dataframe(schema_df: pd.DataFrame) -> pa.DataFrameSchema:
 #     return logger
 
 
-def log_missing_columns(df_stats: pd.DataFrame, template_schema: pa.DataFrameSchema):
+def _log_missing_columns(df_stats: pd.DataFrame, template_schema: pa.DataFrameSchema):
     # Initialize the logger
     logger = setup_logger(__name__)
 
@@ -675,33 +675,6 @@ def _process_custom_bands(df_extra: pd.DataFrame, custom_bands) -> pd.DataFrame:
 
 
 # Fix the duplicate logging issue
-def log_missing_columns(df_stats: pd.DataFrame, template_schema: pa.DataFrameSchema):
-    # Remove the duplicate logger creation line
-    # logger = setup_logger(__name__)  # DELETE THIS LINE
-
-    # Use the existing module-level logger (line 18: logger = StdoutLogger(__name__))
-
-    # Extract the expected columns from the DataFrameSchema
-    template_columns = list(template_schema.columns.keys())
-    df_stats_columns = df_stats.columns.tolist()
-
-    # Find missing and extra columns
-    missing_in_df = [col for col in template_columns if col not in df_stats_columns]
-    extra_in_df = [col for col in df_stats_columns if col not in template_columns]
-
-    # Log missing schema columns
-    if missing_in_df:
-        logger.warning(f"Missing expected schema columns: {missing_in_df}")
-    else:
-        logger.info("All expected schema columns found in DataFrame.")
-
-    # Log extra columns (will be preserved)
-    if extra_in_df:
-        logger.info(f"Extra columns found (will be preserved): {extra_in_df}")
-    else:
-        logger.info("No extra columns found in DataFrame.")
-
-
 def format_stats_dataframe(
     df,
     area_col="Area_sum",

openforis_whisp/stats.py

@@ -93,7 +93,6 @@ def whisp_formatted_stats_geojson_to_df_legacy(
     unit_type="ha",
     whisp_image=None,
     custom_bands=None,  # New parameter
-    validate_geometries: bool = False,
 ) -> pd.DataFrame:
     """
         Legacy function for basic Whisp stats extraction.
@@ -135,51 +134,15 @@ def whisp_formatted_stats_geojson_to_df_legacy(
             - List of band names: ['Aa_test', 'elevation']
             - Dict with types: {'Aa_test': 'float64', 'elevation': 'float32'}
             - None: preserves all extra columns automatically
-        validate_geometries : bool, optional
-            Whether to validate and fix invalid geometries, by default False.
-            Set to True to automatically fix invalid/self-intersecting polygons.
 
     Returns
         -------
         df_stats : pd.DataFrame
             The DataFrame containing the Whisp stats for the input ROI.
     """
-    # Load GeoJSON and validate geometries if requested
-    if validate_geometries:
-        import json
-        import geopandas as gpd
-        from shapely.validation import make_valid
-        import logging as py_logging
-
-        logger = py_logging.getLogger("whisp")
-
-        # Load GeoJSON file
-        with open(input_geojson_filepath, "r") as f:
-            geojson_data = json.load(f)
-
-        # Convert to GeoDataFrame
-        gdf = gpd.GeoDataFrame.from_features(geojson_data["features"])
-
-        # Validate and fix invalid geometries
-        valid_count = gdf.geometry.is_valid.sum()
-        invalid_count = len(gdf) - valid_count
-        if invalid_count > 0:
-            logger.warning(f"Fixing {invalid_count} invalid geometries")
-            gdf["geometry"] = gdf["geometry"].apply(
-                lambda g: make_valid(g) if g and not g.is_valid else g
-            )
-
-        # Pass GeoDataFrame directly to preserve CRS metadata
-        # convert_geojson_to_ee will handle:
-        # - CRS detection and conversion to WGS84 if needed
-        # - Data type sanitization (datetime, object columns)
-        # - Geometry validation and Z-coordinate stripping
-        feature_collection = convert_geojson_to_ee(
-            gdf, enforce_wgs84=True, strip_z_coords=True
-        )
-    else:
-        # Original path - no validation
-        feature_collection = convert_geojson_to_ee(str(input_geojson_filepath))
+    # Convert GeoJSON to Earth Engine FeatureCollection
+    # Note: Geometry validation/cleaning should be done before calling this function
+    feature_collection = convert_geojson_to_ee(str(input_geojson_filepath))
 
     return whisp_formatted_stats_ee_to_df(
         feature_collection,
@@ -203,8 +166,7 @@ def whisp_formatted_stats_geojson_to_df(
     mode: str = "sequential",
     batch_size: int = 10,
     max_concurrent: int = 20,
-    validate_geometries: bool = False,
-    include_geometry_audit_trail: bool = False,
+    geometry_audit_trail: bool = False,
 ) -> pd.DataFrame:
     """
     Main entry point for converting GeoJSON to Whisp statistics.
@@ -252,12 +214,7 @@ def whisp_formatted_stats_geojson_to_df(
     max_concurrent : int, optional
         Maximum concurrent EE calls for concurrent mode, by default 20.
         Only applicable for "concurrent" mode.
-    validate_geometries : bool, optional
-        Whether to validate and fix invalid geometries, by default False.
-        Set to True to automatically fix invalid/self-intersecting polygons.
-        For production workflows, it's recommended to use geometry validation and
-        cleaning tools BEFORE processing with this function.
-    include_geometry_audit_trail : bool, default True
+    geometry_audit_trail : bool, default True
         If True (default), includes audit trail columns:
         - geo_original: Original input geometry
         - geometry_type_original: Original geometry type
@@ -331,7 +288,6 @@ def whisp_formatted_stats_geojson_to_df(
             unit_type=unit_type,
             whisp_image=whisp_image,
             custom_bands=custom_bands,
-            validate_geometries=validate_geometries,
         )
     elif mode in ("concurrent", "sequential"):
         # Log info if batch_size or max_concurrent are not used in sequential mode
@@ -358,8 +314,7 @@ def whisp_formatted_stats_geojson_to_df(
             mode=mode,  # Pass mode directly (concurrent or sequential)
             batch_size=batch_size,
             max_concurrent=max_concurrent,
-            validate_geometries=validate_geometries,
-            include_geometry_audit_trail=include_geometry_audit_trail,
+            geometry_audit_trail=geometry_audit_trail,
         )
     else:
         raise ValueError(