ECG endpoint

app.py

@@ -1,5 +1,7 @@
 import os
 import pickle
+import shutil
+import uuid
 from fastapi import FastAPI, File, UploadFile
 from fastapi.responses import JSONResponse
 from pymongo.mongo_client import MongoClient
@@ -10,6 +12,10 @@ from cloudinary.utils import cloudinary_url
 from SkinBurns_Classification import extract_features
 from SkinBurns_Segmentation import segment_skin_burns 
 import requests
+import joblib
+import numpy as np
+from ECG import classify_new_ecg
+
 
 app = FastAPI()
 
@@ -117,9 +123,6 @@ async def predict_burn(file: UploadFile = File(...)):
 
 
 
-
-
-
 # ✅ Optimize and transform image URL
 @app.get("/cloudinary/transform")
 def transform_image():
@@ -132,3 +135,35 @@ def transform_image():
         }
     except Exception as e:
         return {"error": str(e)}
+    
+
+@app.post("/classify-ecg")
+async def classify_ecg(files: list[UploadFile] = File(...)):
+    # Load the pre-trained model
+    model_path = "voting_classifier.pkl"
+    with open(model_path, "rb") as model_file:
+        model = pickle.load(model_file)
+        
+    temp_dir = f"temp_ecg_{uuid.uuid4()}"
+    os.makedirs(temp_dir, exist_ok=True)
+
+    try:
+        for file in files:
+            file_path = os.path.join(temp_dir, file.filename)
+            with open(file_path, "wb") as f:
+                shutil.copyfileobj(file.file, f)
+
+        # Assume both .hea and .dat have same base name
+        base_names = set(os.path.splitext(file.filename)[0] for file in files)
+        if len(base_names) != 1:
+            return JSONResponse(content={"error": "Files must have the same base name"}, status_code=400)
+
+        base_name = list(base_names)[0]
+        file_path = os.path.join(temp_dir, base_name)
+
+        result = classify_new_ecg(file_path, model)
+        return {"result": result}
+
+    finally:
+        shutil.rmtree(temp_dir, ignore_errors=True)
+

requirements.txt

@@ -16,3 +16,5 @@ wfdb
 PyWavelets
 xgboost
 joblib==1.4.2
+uuid
+shutil