Upload main.py with huggingface_hub

main.py

@@ -5,16 +5,19 @@ FastAPI + DuckDB backend serving benchmark results.
 Loads Parquet files at startup and queries them via DuckDB in-memory.
 
 Endpoints:
-    GET /api/v1/registry           - Full registry metadata
-    GET /api/v1/maxn/heatmap       - Blood x brain heatmap data
-    GET /api/v1/maxn/detail        - Per-module results for one combination
-    GET /api/v1/h2h/blood          - Blood H2H comparison
-    GET /api/v1/h2h/blood/summary  - H2H win counts
-    GET /api/v1/h2h/brain          - Brain H2H comparison
-    GET /api/v1/h2h/models         - Model H2H comparison (future)
-    GET /api/v1/temporal           - Temporal decay results
-    GET /api/v1/features           - Feature importance for a target
-    GET /api/v1/features/cross     - Cross-target feature importance
+    GET /api/v1/registry              - Full registry metadata
+    GET /api/v1/maxn/heatmap          - Blood x brain heatmap data
+    GET /api/v1/maxn/detail           - Per-module results for one combination
+    GET /api/v1/maxn/panel_summary    - One panel across all outcomes (mean/min/max)
+    GET /api/v1/maxn/outcome_summary  - One outcome across all panels (mean/min/max)
+    GET /api/v1/maxn/target_comparison - Per-panel performance for a specific target
+    GET /api/v1/h2h/blood             - Blood H2H comparison
+    GET /api/v1/h2h/blood/summary     - H2H win counts
+    GET /api/v1/h2h/brain             - Brain H2H comparison
+    GET /api/v1/h2h/models            - Model H2H comparison (future)
+    GET /api/v1/temporal              - Temporal decay results
+    GET /api/v1/features              - Feature importance for a target
+    GET /api/v1/features/cross        - Cross-target feature importance
 """
 
 import json
@@ -504,6 +507,137 @@ def feature_cross_target(
     }
 
 
+@app.get("/api/v1/maxn/panel_summary")
+def maxn_panel_summary(
+    blood: str = Query(..., description="Blood platform name"),
+    metric: str = Query("r2"),
+    covariates: str = Query("none", enum=["none", "only", "included"]),
+    model: str = Query("TabPFN"),
+):
+    """
+    Summary of one predictor panel across all outcome panels.
+    Returns mean, min, max, n_targets, and median n_samples per outcome.
+    Replaces N calls to /maxn/detail with a single query.
+    """
+    validate_metric(metric)
+    phase = covariate_phase("maxn", covariates)
+
+    rows = db.execute(f"""
+        SELECT brain_target,
+               AVG({metric}) as mean_val,
+               MIN({metric}) as min_val,
+               MAX({metric}) as max_val,
+               COUNT(*) as n_targets,
+               MEDIAN(n_samples) as n_samples
+        FROM results
+        WHERE phase = ? AND blood_platform = ? AND model = ?
+        GROUP BY brain_target
+        ORDER BY mean_val DESC
+    """, [phase, blood, model]).fetchall()
+
+    return {
+        "blood": blood,
+        "metric": metric,
+        "covariates": covariates,
+        "outcomes": [
+            {
+                "brain_target": r[0],
+                "mean": round(r[1], 4) if r[1] is not None else None,
+                "min": round(r[2], 4) if r[2] is not None else None,
+                "max": round(r[3], 4) if r[3] is not None else None,
+                "n_targets": r[4],
+                "n_samples": int(r[5]) if r[5] is not None else None,
+            }
+            for r in rows
+        ],
+    }
+
+
+@app.get("/api/v1/maxn/outcome_summary")
+def maxn_outcome_summary(
+    brain: str = Query(..., description="Brain target name"),
+    metric: str = Query("r2"),
+    covariates: str = Query("none", enum=["none", "only", "included"]),
+    model: str = Query("TabPFN"),
+):
+    """
+    Summary of one outcome panel across all predictor panels.
+    Returns mean, min, max, n_targets, and median n_samples per predictor.
+    Replaces N calls to /maxn/detail with a single query.
+    """
+    validate_metric(metric)
+    phase = covariate_phase("maxn", covariates)
+
+    rows = db.execute(f"""
+        SELECT blood_platform,
+               AVG({metric}) as mean_val,
+               MIN({metric}) as min_val,
+               MAX({metric}) as max_val,
+               COUNT(*) as n_targets,
+               MEDIAN(n_samples) as n_samples
+        FROM results
+        WHERE phase = ? AND brain_target = ? AND model = ?
+        GROUP BY blood_platform
+        ORDER BY mean_val DESC
+    """, [phase, brain, model]).fetchall()
+
+    return {
+        "brain": brain,
+        "metric": metric,
+        "covariates": covariates,
+        "predictors": [
+            {
+                "blood_platform": r[0],
+                "mean": round(r[1], 4) if r[1] is not None else None,
+                "min": round(r[2], 4) if r[2] is not None else None,
+                "max": round(r[3], 4) if r[3] is not None else None,
+                "n_targets": r[4],
+                "n_samples": int(r[5]) if r[5] is not None else None,
+            }
+            for r in rows
+        ],
+    }
+
+
+@app.get("/api/v1/maxn/target_comparison")
+def maxn_target_comparison(
+    brain: str = Query(..., description="Brain target name"),
+    target: str = Query(..., description="Specific target/module name"),
+    metric: str = Query("r2"),
+    covariates: str = Query("none", enum=["none", "only", "included"]),
+    model: str = Query("TabPFN"),
+):
+    """
+    Per-predictor performance for a specific target within an outcome panel.
+    E.g., how each blood platform predicts module m4 of bulkrnaseq_dlpfc.
+    Replaces N calls to /maxn/detail with a single query.
+    """
+    validate_metric(metric)
+    phase = covariate_phase("maxn", covariates)
+
+    rows = db.execute(f"""
+        SELECT blood_platform, {metric}, n_samples
+        FROM results
+        WHERE phase = ? AND brain_target = ? AND target = ? AND model = ?
+        ORDER BY {metric} DESC
+    """, [phase, brain, target, model]).fetchall()
+
+    return {
+        "brain": brain,
+        "target": target,
+        "metric": metric,
+        "covariates": covariates,
+        "predictors": [
+            {
+                "blood_platform": r[0],
+                "value": round(r[1], 4) if r[1] is not None else None,
+                "n_samples": r[2],
+            }
+            for r in rows
+        ],
+    }
+
+
 @app.get("/api/v1/health")
 def health():
     """Health check."""