fixed error of csv file usage

app.py

@@ -51,22 +51,31 @@ from sklearn.metrics import accuracy_score, f1_score
 from sklearn.preprocessing import StandardScaler
 
 # =========================
-# 4. LOAD LABELS (AVEC CSV)
+# 4. LOAD LABELS (CORRECT)
 # =========================
 def load_labels():
     df_train = pd.read_csv("train_split_Depression_AVEC2017.csv")
     df_dev = pd.read_csv("dev_split_Depression_AVEC2017.csv")
-    df_test = pd.read_csv("test_split_Depression_AVEC2017.csv")
 
-    df = pd.concat([df_train, df_dev, df_test])
+    df = pd.concat([df_train, df_dev])
+
+    # Clean column names
+    df.columns = df.columns.str.strip()
 
     labels = {}
+
     for _, row in df.iterrows():
-        pid = str(int(row["Participant_ID"]))
-        phq = row["PHQ8_Score"]
-        label = 1 if phq >= 10 else 0
-        labels[pid] = label
+        try:
+            pid = str(int(row["Participant_ID"]))
+
+            # ✅ FINAL LABEL
+            label = int(row["PHQ8_Binary"])
+
+            labels[pid] = label
+        except:
+            continue
 
+    print("Total labels loaded:", len(labels))
     return labels
 
 labels_dict = load_labels()
@@ -129,7 +138,7 @@ def get_visual_features(folder_path):
     return np.concatenate(features)
 
 # =========================
-# 7. BUILD DATASET (ONLY VALID LABELS)
+# 7. BUILD DATASET
 # =========================
 print("\nBuilding dataset...")
 
@@ -171,7 +180,6 @@ y = np.array([d[1] for d in data])
 scaler = StandardScaler()
 X = scaler.fit_transform(X)
 
-# Split using AVEC logic (simple split for now)
 split = int(0.7 * len(X))
 X_train, X_test = X[:split], X[split:]
 y_train, y_test = y[:split], y[split:]