optional ground truth, required input path

swisstopo · Jul 24, 2024 · d21d8a5 · d21d8a5 · github-actions · Jul 24, 2024
1 parent 9bf677e
commit d21d8a5
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 9 deletions.
diff --git a/src/stratigraphy/benchmark/score.py b/src/stratigraphy/benchmark/score.py
@@ -251,20 +251,22 @@ def evaluate_layer_extraction(predictions: dict, number_of_truth_values: dict) -
     return _metrics, document_level_metrics
 
 
-def create_predictions_objects(predictions: dict, ground_truth_path: Path) -> tuple[dict[FilePredictions], dict]:
+def create_predictions_objects(
+    predictions: dict, ground_truth_path: Path | None
+) -> tuple[dict[FilePredictions], dict]:
     """Create predictions objects from the predictions and evaluate them against the ground truth.
 
     Args:
         predictions (dict): The predictions from the predictions.json file.
-        ground_truth_path (Path): The path to the ground truth file.
+        ground_truth_path (Path　| None): The path to the ground truth file.
 
     Returns:
         tuple[dict[FilePredictions], dict]: The predictions objects and the number of ground truth values per file.
     """
-    try:  # for inference no ground truth is available
+    if ground_truth_path and os.path.exists(ground_truth_path):  # for inference no ground truth is available
         ground_truth = GroundTruth(ground_truth_path)
         ground_truth_is_present = True
-    except FileNotFoundError:
+    else:
         logging.warning("Ground truth file not found.")
         ground_truth_is_present = False
 

diff --git a/src/stratigraphy/main.py b/src/stratigraphy/main.py
@@ -34,14 +34,15 @@
 @click.option(
     "-i",
     "--input-directory",
+    required=True,
     type=click.Path(exists=True, path_type=Path),
     help="Path to the input directory, or path to a single pdf file.",
 )
 @click.option(
     "-g",
     "--ground-truth-path",
-    type=click.Path(exists=False, path_type=Path),
-    help="Path to the ground truth file.",
+    type=click.Path(exists=True, path_type=Path),
+    help="Path to the ground truth file (optional).",
 )
 @click.option(
     "-o",
@@ -69,7 +70,7 @@
 )
 def click_pipeline(
     input_directory: Path,
-    ground_truth_path: Path,
+    ground_truth_path: Path | None,
     out_directory: Path,
     predictions_path: Path,
     skip_draw_predictions: bool = False,
@@ -84,7 +85,7 @@ def click_pipeline(
      \f
      Args:
          input_directory (Path): The directory containing the pdf files. Can also be the path to a single pdf file.
-         ground_truth_path (Path): The path to the ground truth file json file.
+         ground_truth_path (Path | None): The path to the ground truth file json file.
          out_directory (Path): The directory to store the evaluation results.
          predictions_path (Path): The path to the predictions file.
          skip_draw_predictions (bool, optional): Whether to skip drawing predictions on pdf pages. Defaults to False.
@@ -119,7 +120,7 @@ def start_pipeline(
 
     Args:
         input_directory (Path): The directory containing the pdf files. Can also be the path to a single pdf file.
-        ground_truth_path (Path): The path to the ground truth file json file.
+        ground_truth_path (Path | None): The path to the ground truth file json file.
         out_directory (Path): The directory to store the evaluation results.
         predictions_path (Path): The path to the predictions file.
         skip_draw_predictions (bool, optional): Whether to skip drawing predictions on pdf pages. Defaults to False.
File	Stmts	Miss	Cover	Missing
src/stratigraphy
__init__.py	8	1	88%	11
extract.py	188	188	0%	3–482
get_files.py	19	19	0%	3–47
line_detection.py	26	26	0%	3–76
main.py	95	95	0%	3–237
src/stratigraphy/util
boundarydepthcolumnvalidator.py	41	20	51%	47, 57, 60, 81–84, 109–127, 139–148
coordinate_extraction.py	127	7	94%	31, 62, 75–76, 80, 205, 328
dataclasses.py	32	3	91%	37–39
depthcolumn.py	194	64	67%	26, 30, 51, 57, 60–61, 85, 88, 95, 102, 110–111, 121, 138–154, 192, 229, 248–256, 267, 272, 279, 310, 315–322, 337–338, 381–423
depthcolumnentry.py	26	7	73%	12, 15, 29–30, 33, 45, 52
description_block_splitter.py	70	2	97%	24, 139
draw.py	80	80	0%	3–244
duplicate_detection.py	51	51	0%	3–146
extract_text.py	27	2	93%	38–39
find_depth_columns.py	91	6	93%	42–43, 71, 83, 176–177
find_description.py	63	28	56%	27–35, 50–63, 79–95, 172–175
geometric_line_utilities.py	86	2	98%	82, 132
interval.py	106	55	48%	24–27, 31–34, 39, 44, 47, 57–59, 99–145, 166, 171–187
language_detection.py	18	18	0%	3–45
layer_identifier_column.py	91	91	0%	3–227
line.py	49	4	92%	25, 42, 51, 98
linesquadtree.py	46	1	98%	76
plot_utils.py	43	43	0%	3–120
predictions.py	130	130	0%	3–272
textblock.py	74	8	89%	27, 51, 63, 75, 98, 119, 127, 155
util.py	40	18	55%	22, 40–47, 61–63, 87–88, 100–105
TOTAL	1821	969	47%