Upload folder using huggingface_hub

backend/main.py

@@ -157,26 +157,29 @@ def download_dataset():
 
 @app.get("/dataset")
 def get_dataset(
-    page: int = 1,
-    limit: int = 25,
+    page: Optional[int] = None,
+    limit: Optional[int] = None,
     disease: Optional[str] = None,
     search: Optional[str] = None,
     all: bool = False
 ):
-    """Paginated high-speed patient telemetry records explorer."""
+    """Telemetry records explorer supporting unparameterized list & paginated queries."""
     if ml_engine and os.path.exists(ml_engine.dataset_path):
         try:
-            if all:
-                df = pd.read_csv(ml_engine.dataset_path, encoding='utf-8')
-                df.columns = [c.strip() for c in df.columns]
-                return df.head(200).to_dict(orient="records")
-            return get_paginated_rows(
-                ml_engine.dataset_path,
-                page=page,
-                limit=min(limit, 100),
-                disease=disease,
-                search=search
-            )
+            # If explicit pagination is requested
+            if page is not None or limit is not None or disease is not None or search is not None:
+                return get_paginated_rows(
+                    ml_engine.dataset_path,
+                    page=page or 1,
+                    limit=min(limit or 25, 100),
+                    disease=disease,
+                    search=search
+                )
+
+            # Unparameterized call (backward compatibility with API consumers & tests)
+            df = pd.read_csv(ml_engine.dataset_path, encoding='utf-8')
+            df.columns = [c.strip() for c in df.columns]
+            return df.to_dict(orient="records")
         except Exception as e:
             return {"error": f"Failed to read dataset: {str(e)}"}
     return {"error": "Dataset not found"}

tests/test_api.py

@@ -21,6 +21,31 @@ def test_dataset_endpoint(client):
     assert response.status_code == 200
     assert isinstance(response.json(), list)
 
+def test_dataset_paginated_endpoint(client):
+    response = client.get("/dataset?page=1&limit=25")
+    assert response.status_code == 200
+    data = response.json()
+    assert isinstance(data, dict)
+    assert "total" in data
+    assert "rows" in data
+    assert isinstance(data["rows"], list)
+    assert len(data["rows"]) <= 25
+
+def test_dataset_summary_endpoint(client):
+    response = client.get("/dataset/summary")
+    assert response.status_code == 200
+    data = response.json()
+    assert isinstance(data, dict)
+    assert "summary" in data
+    assert data["summary"]["total_records"] == 60000
+    assert "target_distribution" in data
+    assert "correlation_matrix" in data
+
+def test_dataset_download_endpoint(client):
+    response = client.get("/dataset/download")
+    assert response.status_code == 200
+    assert "text/csv" in response.headers.get("content-type", "")
+
 def test_export_tinyml_random_forest(client):
     response = client.get("/export_tinyml?model_name=rf")