Make math_blob optional for regression testing

Allow datasets to be valid for regression testing without the Clojure
math_blob file. This enables testing when database access is unavailable
(e.g., when DATABASE_URL is not set).

Changes:
- DatasetInfo.is_valid now only requires votes, comments, and golden_snapshot
- Added has_clojure_reference property to check if Clojure comparison is possible
- Updated documentation to clarify math_blob is optional
- Added tests for new behavior

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[email protected]>

Author: jucor

delphi/polismath/regression/datasets.py

@@ -5,7 +5,10 @@
 directory naming: <report_id>-<name>/
 
 Required files for regression testing:
-- *-votes.csv, *-comments.csv, {report_id}_math_blob.json, golden_snapshot.json
+- *-votes.csv, *-comments.csv, golden_snapshot.json
+
+Optional files:
+- {report_id}_math_blob.json (for Clojure comparison - requires database access to download)
 """
 
 import glob
@@ -38,8 +41,13 @@ class DatasetInfo:
 
     @property
     def is_valid(self) -> bool:
-        """Has all files needed for regression testing."""
-        return all([self.has_golden, self.has_math_blob, self.has_votes, self.has_comments])
+        """Has all files needed for regression testing (math_blob is optional)."""
+        return all([self.has_golden, self.has_votes, self.has_comments])
+
+    @property
+    def has_clojure_reference(self) -> bool:
+        """Has math_blob for comparison with Clojure implementation."""
+        return self.has_math_blob
 
     @property
     def description(self) -> str:
@@ -117,6 +125,7 @@ def list_available_datasets(include_local: bool = False) -> Dict[str, dict]:
             'is_local': d.is_local,
             'has_golden': d.has_golden,
             'has_math_blob': d.has_math_blob,
+            'has_clojure_reference': d.has_clojure_reference,
         }
         for name, d in discover_datasets(include_local).items()
     }

delphi/tests/README.md

@@ -92,9 +92,11 @@ real_data/
 **Required files per dataset:**
 - `*-votes.csv` - Vote data
 - `*-comments.csv` - Comment data
-- `{report_id}_math_blob.json` - Clojure math output
 - `golden_snapshot.json` - For regression testing
 
+**Optional files:**
+- `{report_id}_math_blob.json` - Clojure math output (for Clojure comparison, requires database access)
+
 ### Running Tests with Local Datasets
 
 ```bash

delphi/tests/test_datasets.py

@@ -38,10 +38,26 @@ def test_is_valid_all_files(self):
         info = DatasetInfo("t", "r1", Path("/x"), False, True, True, True, True)
         assert info.is_valid
 
-    def test_is_valid_missing_file(self):
+    def test_is_valid_without_math_blob(self):
+        """Math blob is optional for regression testing."""
+        # has_golden=True, has_math_blob=False, has_votes=True, has_comments=True
+        info = DatasetInfo("t", "r1", Path("/x"), False, True, False, True, True)
+        assert info.is_valid
+        assert not info.has_clojure_reference
+
+    def test_is_valid_missing_required_file(self):
+        """Missing golden/votes/comments makes dataset invalid."""
+        # Missing golden
         info = DatasetInfo("t", "r1", Path("/x"), False, False, True, True, True)
         assert not info.is_valid
 
+    def test_has_clojure_reference(self):
+        """has_clojure_reference reflects math_blob presence."""
+        with_blob = DatasetInfo("t", "r1", Path("/x"), False, True, True, True, True)
+        without_blob = DatasetInfo("t", "r1", Path("/x"), False, True, False, True, True)
+        assert with_blob.has_clojure_reference
+        assert not without_blob.has_clojure_reference
+
 
 class TestCheckFiles:
     def test_all_files_exist(self, tmp_path):