fix added

app.py

@@ -14,31 +14,38 @@ from sklearn.metrics import accuracy_score, f1_score
 from sklearn.model_selection import train_test_split
 
 # =========================
-# 1. DOWNLOAD DATASET
+# 1. DOWNLOAD & EXTRACT DATASET
 # =========================
 url = "https://huggingface.co/datasets/ananyakarn/DAIC_WOZ_Data/resolve/main/DAIC_WOZ_Data.zip"
 zip_path = "data.zip"
-extract_path = "DAIC_WOZ"
 
+print("Downloading dataset...")
+r = requests.get(url, stream=True)
+with open(zip_path, "wb") as f:
+    for chunk in r.iter_content(8192):
+        f.write(chunk)
 
-# 🔥 FIX: handle nested folder
-while len(os.listdir(extract_path)) == 1:
-    extract_path = os.path.join(extract_path, os.listdir(extract_path)[0])
+print("Extracting dataset...")
+with zipfile.ZipFile(zip_path, "r") as zip_ref:
+    zip_ref.extractall(".")
 
-print("Final dataset path:", extract_path)
+# =========================
+# 2. AUTO-DETECT DATASET FOLDER
+# =========================
+def find_dataset_root():
+    for root, dirs, files in os.walk("."):
+        for d in dirs:
+            if "_P" in d or "_C" in d:
+                return root
+    return None
 
-print("Folders detected:", os.listdir(extract_path)[:10])
+extract_path = find_dataset_root()
 
-if not os.path.exists(extract_path):
-    print("Downloading dataset...")
-    r = requests.get(url, stream=True)
-    with open(zip_path, "wb") as f:
-        for chunk in r.iter_content(8192):
-            f.write(chunk)
+if extract_path is None:
+    raise Exception("Dataset folders not found!")
 
-    print("Extracting dataset...")
-    with zipfile.ZipFile(zip_path, "r") as zip_ref:
-        zip_ref.extractall(extract_path)
+print("Final dataset path:", extract_path)
+print("Sample folders:", os.listdir(extract_path)[:10])
 
 # =========================
 # 2. LOAD LIGHTWEIGHT BERT