fimeval 0.1.44__tar.gz → 0.1.46__tar.gz

{fimeval-0.1.44 → fimeval-0.1.46}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: fimeval
-Version: 0.1.44
+Version: 0.1.46
 Summary: A Framework for Automatic Evaluation of Flood Inundation Mapping Predictions Evaluation
 License: GPLv3
 Author: Surface Dynamics Modeling Lab

{fimeval-0.1.44 → fimeval-0.1.46}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "fimeval"
-version = "0.1.44"
+version = "0.1.46"
 description = "A Framework for Automatic Evaluation of Flood Inundation Mapping Predictions Evaluation"
 authors = [
     "Surface Dynamics Modeling Lab",

{fimeval-0.1.44 → fimeval-0.1.46}/src/fimeval/BuildingFootprint/evaluationwithBF.py

@@ -21,18 +21,6 @@ def Changeintogpkg(input_path, output_dir, layer_name):
         gdf.to_file(output_gpkg, driver="GPKG")
         return output_gpkg
 
-
-def Changeintogpkg(input_path, output_dir, layer_name):
-    input_path = str(input_path)
-    if input_path.endswith(".gpkg"):
-        return input_path
-    else:
-        gdf = gpd.read_file(input_path)
-        output_gpkg = os.path.join(output_dir, f"{layer_name}.gpkg")
-        gdf.to_file(output_gpkg, driver="GPKG")
-        return output_gpkg
-
-
 def GetFloodedBuildingCountInfo(
     building_fp_path,
     study_area_path,
@@ -51,8 +39,17 @@ def GetFloodedBuildingCountInfo(
     building_gdf = gpd.read_file(building_fp_gpkg)
     study_area_gdf = gpd.read_file(study_area_path)
 
-    if building_gdf.crs != study_area_gdf.crs:
-        building_gdf = building_gdf.to_crs(study_area_gdf.crs)
+    with rasterio.open(raster1_path) as src:
+        target_crs = str(src.crs)
+
+    # Reproject all GeoDataFrames to the target CRS
+    if building_gdf.crs != target_crs:
+        building_gdf = building_gdf.to_crs(target_crs)
+        print("reproject building_gdf")
+
+    if study_area_gdf.crs != target_crs:
+        study_area_gdf = study_area_gdf.to_crs(target_crs)
+        print("reproject study_area_gdf")
 
     clipped_buildings = gpd.overlay(building_gdf, study_area_gdf, how="intersection")
     clipped_buildings["centroid"] = clipped_buildings.geometry.centroid
@@ -85,7 +82,7 @@ def GetFloodedBuildingCountInfo(
                         elif pixel_value == 4:
                             centroid_counts["True Positive"] += 1
 
-    if "benchmark" in str(raster1_path).lower():
+    if "bm" in str(raster1_path).lower():
         count_centroids_in_raster(raster1_path, "Benchmark")
         count_centroids_in_raster(raster2_path, "Candidate")
     elif "candidate" in str(raster2_path).lower():
@@ -220,46 +217,32 @@ def GetFloodedBuildingCountInfo(
     print(f"Performance metrics chart is saved as PNG at {output_path}")
     fig.show()
 
-
 def process_TIFF(
     tif_files, contingency_files, building_footprint, boundary, method_path
 ):
     benchmark_path = None
-    candidate_path = []
-
-    if len(tif_files) == 2:
-        for tif_file in tif_files:
-            if "benchmark" in tif_file.name.lower():
-                benchmark_path = tif_file
-            else:
-                candidate_path.append(tif_file)
+    candidate_paths = []
 
-    elif len(tif_files) > 2:
-        for tif_file in tif_files:
-            if "benchmark" in tif_file.name.lower():
+    for tif_file in tif_files:
+        if "bm" in tif_file.name.lower() or "benchmark" in tif_file.name.lower():
+            if benchmark_path is None:
                 benchmark_path = tif_file
-                print(f"---Benchmark: {tif_file.name}---")
             else:
-                candidate_path.append(tif_file)
-
-    if benchmark_path and candidate_path:
-        for candidate in candidate_path:
+                candidate_paths.append(tif_file)
+        else:
+            candidate_paths.append(tif_file)
 
+    if benchmark_path and candidate_paths:
+        for candidate in candidate_paths:
             matching_contingency_map = None
             candidate_base_name = candidate.stem.replace("_clipped", "")
 
             for contingency_file in contingency_files:
                 if candidate_base_name in contingency_file.name:
                     matching_contingency_map = contingency_file
-                    print(
-                        f"Found matching contingency map for candidate {candidate.name}: {contingency_file.name}"
-                    )
                     break
 
             if matching_contingency_map:
-                print(
-                    f"---FIM evaluation with Building Footprint starts for {candidate.name}---"
-                )
                 GetFloodedBuildingCountInfo(
                     building_footprint,
                     boundary,
@@ -273,8 +256,11 @@ def process_TIFF(
                 print(
                     f"No matching contingency map found for candidate {candidate.name}. Skipping..."
                 )
-
-
+    elif not benchmark_path:
+        print("Warning: No benchmark file found.")
+    elif not candidate_paths:
+        print("Warning: No candidate files found.")
+        
 def find_existing_footprint(out_dir):
     gpkg_files = list(Path(out_dir).glob("*.gpkg"))
     return gpkg_files[0] if gpkg_files else None
@@ -337,7 +323,6 @@ def EvaluationWithBuildingFootprint(
                         )
                     else:
                         building_footprintMS = EX_building_footprint
-
                 process_TIFF(
                     tif_files,
                     contingency_files,

{fimeval-0.1.44 → fimeval-0.1.46}/src/fimeval/ContingencyMap/evaluationFIM.py

@@ -40,7 +40,6 @@ def evaluateFIM(
     Merged = []
     Unique = []
     FAR_values = []
-    Dice_values = []
 
     # Dynamically call the specified method
     method = globals().get(method)
@@ -255,7 +254,6 @@ def evaluateFIM(
                 FPR,
                 merged,
                 FAR,
-                Dice,
             ) = evaluationmetrics(out_image1, out_image2_resized)
 
             # Append values to the lists
@@ -275,7 +273,6 @@ def evaluateFIM(
             Merged.append(merged)
             Unique.append(unique_values)
             FAR_values.append(FAR)
-            Dice_values.append(Dice)
 
     results = {
         "CSI_values": csi_values,
@@ -294,7 +291,6 @@ def evaluateFIM(
         # 'Merged': Merged,
         #  'Unique': Unique
         "FAR_values": FAR_values,
-        "Dice_values": Dice_values,
     }
     for candidate_idx, candidate_path in enumerate(candidate_paths):
         candidate_BASENAME = os.path.splitext(os.path.basename(candidate_path))[0]

fimeval-0.1.46/src/fimeval/ContingencyMap/metrics.py

@@ -0,0 +1,43 @@
+import numpy as np
+
+
+# Get all the evaluation metrics
+def evaluationmetrics(out_image1, out_image2):
+    merged = out_image1 + out_image2
+    unique_values, counts = np.unique(merged, return_counts=True)
+    class_pixel_counts = dict(zip(unique_values, counts))
+    class_pixel_counts
+    TN = class_pixel_counts.get(1,0)
+    FP = class_pixel_counts.get(2,0)
+    FN = class_pixel_counts.get(3,0)
+    TP = class_pixel_counts.get(4,0)
+    epsilon = 1e-8
+    TPR = TP / (TP + FN+epsilon)
+    FNR = FN / (TP + FN+epsilon)
+    Acc = (TP + TN) / (TP + TN + FP + FN+epsilon)
+    Prec = TP / (TP + FP+epsilon)
+    sen = TP / (TP + FN+epsilon)
+    F1_score = 2 * (Prec * sen) / (Prec + sen+epsilon)
+    CSI = TP / (TP + FN + FP+epsilon)
+    POD = TP / (TP + FN+epsilon)
+    FPR = FP / (FP + TN+epsilon)
+    FAR = FP / (TP + FP+epsilon)
+
+    return (
+        unique_values,
+        TN,
+        FP,
+        FN,
+        TP,
+        TPR,
+        FNR,
+        Acc,
+        Prec,
+        sen,
+        CSI,
+        F1_score,
+        POD,
+        FPR,
+        merged,
+        FAR,
+    )

{fimeval-0.1.44 → fimeval-0.1.46}/src/fimeval/ContingencyMap/printcontingency.py

@@ -18,12 +18,12 @@ def getContingencyMap(raster_path, method_path):
     combined_flood = np.full_like(band1, fill_value=1, dtype=int)
 
     # Map pixel values to colors
-    combined_flood[band1 == 5] = 0
-    combined_flood[band1 == 0] = 1
-    combined_flood[band1 == 1] = 2
-    combined_flood[band1 == 2] = 3
-    combined_flood[band1 == 3] = 4
-    combined_flood[band1 == 4] = 5
+    combined_flood[band1 == 5] = 5
+    combined_flood[band1 == 0] = 0
+    combined_flood[band1 == 1] = 1
+    combined_flood[band1 == 2] = 2
+    combined_flood[band1 == 3] = 3
+    combined_flood[band1 == 4] = 4
 
     # Handle NoData explicitly, mapping it to "No Data" class (1)
     if nodata_value is not None:
@@ -42,7 +42,7 @@ def getContingencyMap(raster_path, method_path):
     ys_dd = np.array(latitudes).reshape(ys.shape)
 
     # Define the color map and normalization
-    flood_colors = ["black", "white", "grey", "green", "blue", "red"]  # 6 classes
+    flood_colors = ["white", "grey", "green", "blue", "red", "black"]  # 6 classes
     flood_cmap = mcolors.ListedColormap(flood_colors)
     flood_norm = mcolors.BoundaryNorm(
         boundaries=np.arange(-0.5, 6.5, 1), ncolors=len(flood_colors)
@@ -60,6 +60,7 @@ def getContingencyMap(raster_path, method_path):
 
     # Create legend patches
     value_labels = {
+        0: "No data",
         1: "True negative",
         2: "False positive",
         3: "False negative",

{fimeval-0.1.44 → fimeval-0.1.46}/src/fimeval/utilis.py

@@ -132,6 +132,7 @@ def MakeFIMsUniform(fim_dir, target_crs=None, target_resolution=None):
             for src_path in tif_files:
                 dst_path = processing_folder / src_path.name
                 reprojectFIMs(str(src_path), str(dst_path), target_crs)
+                compress_tif_lzw(dst_path)
         else:
             all_within_conus = all(is_within_conus(bounds_list[i], crs_list[i]) for i in range(len(bounds_list)))
 
@@ -148,7 +149,6 @@ def MakeFIMsUniform(fim_dir, target_crs=None, target_resolution=None):
         for src_path in tif_files:
             dst_path = processing_folder / src_path.name
             shutil.copy(src_path, dst_path)
-            compress_tif_lzw(dst_path)
     
     # Resolution check and resampling
     processed_tifs = list(processing_folder.glob('*.tif'))
@@ -170,7 +170,6 @@ def MakeFIMsUniform(fim_dir, target_crs=None, target_resolution=None):
                 for src_path in processed_tifs:
                     resample_to_resolution(str(src_path), target_resolution, target_resolution)
             else:
-                print("FIMs are in different resolution after projection. \n")
                 coarser_x = max(res[0] for res in resolutions)
                 coarser_y = max(res[1] for res in resolutions)
                 print(f"Using coarser resolution: X={coarser_x}, Y={coarser_y}. Resampling all FIMS to this resolution.")

fimeval-0.1.44/src/fimeval/ContingencyMap/metrics.py

@@ -1,44 +0,0 @@
-import numpy as np
-
-
-# Get all the evaluation metrics
-def evaluationmetrics(out_image1, out_image2):
-    merged = out_image1 + out_image2
-    unique_values, counts = np.unique(merged, return_counts=True)
-    class_pixel_counts = dict(zip(unique_values, counts))
-    class_pixel_counts
-    TN = class_pixel_counts[1]
-    FP = class_pixel_counts[2]
-    FN = class_pixel_counts[3]
-    TP = class_pixel_counts[4]
-    TPR = TP / (TP + FN)
-    FNR = FN / (TP + FN)
-    Acc = (TP + TN) / (TP + TN + FP + FN)
-    Prec = TP / (TP + FP)
-    sen = TP / (TP + FN)
-    F1_score = 2 * (Prec * sen) / (Prec + sen)
-    CSI = TP / (TP + FN + FP)
-    POD = TP / (TP + FN)
-    FPR = FP / (FP + TN)
-    FAR = FP / (TP + FP)
-    Dice = 2 * TP / (2 * TP + FP + FN)
-
-    return (
-        unique_values,
-        TN,
-        FP,
-        FN,
-        TP,
-        TPR,
-        FNR,
-        Acc,
-        Prec,
-        sen,
-        CSI,
-        F1_score,
-        POD,
-        FPR,
-        merged,
-        FAR,
-        Dice,
-    )