fixed error

app.py

@@ -14,8 +14,7 @@ import os, requests, zipfile, time
 def safe_download(url, path):
     if os.path.exists(path):
         return
-
-    for i in range(3):
+    for _ in range(3):
         try:
             r = requests.get(url, stream=True, timeout=60)
             with open(path, "wb") as f:
@@ -25,7 +24,6 @@ def safe_download(url, path):
             return
         except:
             time.sleep(3)
-
     raise Exception("Download failed")
 
 # =========================
@@ -37,14 +35,12 @@ def load_split(csv_file):
     df = pd.read_csv(csv_file)
     df.columns = df.columns.str.strip()
     split = {}
-
     for _, row in df.iterrows():
         try:
             pid = str(int(row["Participant_ID"]))
             split[pid] = int(row["PHQ8_Binary"])
         except:
             continue
-
     return split
 
 train_labels = load_split("train_split_Depression_AVEC2017.csv")
@@ -87,8 +83,16 @@ def get_paths():
 
 ALL_PATHS = get_paths()
 
-# 🔥 LIMIT DATA (IMPORTANT for HF)
-ALL_PATHS = ALL_PATHS[:12]
+# ✅ FILTER VALID PARTICIPANTS (IMPORTANT FIX)
+ALL_PATHS = [
+    p for p in ALL_PATHS
+    if os.path.basename(p).split("_")[0] in REQUIRED_IDS
+]
+
+print("Usable participants:", len(ALL_PATHS))
+
+if len(ALL_PATHS) < 10:
+    raise Exception("Too few participants extracted!")
 
 # =========================
 # 5. LIBRARIES
@@ -117,7 +121,7 @@ def load_text(folder):
     try:
         file = [f for f in os.listdir(folder) if "TRANSCRIPT" in f][0]
         df = pd.read_csv(os.path.join(folder, file))
-        return " ".join(df.iloc[:50, -1].astype(str))  # 🔥 reduced
+        return " ".join(df.iloc[:50, -1].astype(str))
     except:
         return ""
 
@@ -152,11 +156,10 @@ def get_visual(folder):
             feats.append(np.concatenate([df.mean().values, df.std().values]))
         except:
             feats.append(np.zeros(20))
-
     return np.concatenate(feats)
 
 # =========================
-# 8. BUILD
+# 8. BUILD DATA
 # =========================
 def build(labels):
     Xt, Xa, Xv, y = [], [], [], []
@@ -176,8 +179,15 @@ def build(labels):
 Xt, Xa, Xv, y_train = build(train_labels)
 Xt_test, Xa_test, Xv_test, y_test = build(dev_labels)
 
+print("Train size:", len(y_train))
+print("Test size:", len(y_test))
+
+# ✅ SAFETY CHECK
+if len(set(y_train)) < 2 or len(set(y_test)) < 2:
+    raise Exception("Dataset has only one class!")
+
 # =========================
-# 9. NORMALIZE
+# 9. NORMALIZATION
 # =========================
 sc_t, sc_a, sc_v = StandardScaler(), StandardScaler(), StandardScaler()
 
@@ -190,12 +200,14 @@ Xa_test = sc_a.transform(Xa_test)
 Xv_test = sc_v.transform(Xv_test)
 
 # =========================
-# 🔥 RANDOM FOREST (FIXED)
+# 10. RANDOM FOREST
 # =========================
 X_train_rf = np.concatenate([Xt, Xa, Xv], axis=1)
 X_test_rf = np.concatenate([Xt_test, Xa_test, Xv_test], axis=1)
 
 rf = RandomForestClassifier(n_estimators=100, max_depth=10, random_state=42)
+
+print("\nTraining Random Forest...")
 rf.fit(X_train_rf, y_train)
 
 rf_preds = rf.predict(X_test_rf)
@@ -204,7 +216,7 @@ rf_acc = accuracy_score(y_test, rf_preds)
 rf_f1 = f1_score(y_test, rf_preds)
 
 # =========================
-# 10. TORCH MODELS
+# 11. TORCH MODEL
 # =========================
 Xt = torch.tensor(Xt, dtype=torch.float32).to(device)
 Xa = torch.tensor(Xa, dtype=torch.float32).to(device)
@@ -218,25 +230,39 @@ Xv_test = torch.tensor(Xv_test, dtype=torch.float32).to(device)
 class Simple(nn.Module):
     def __init__(self, v):
         super().__init__()
-        self.net = nn.Sequential(nn.Linear(768+40+v,128), nn.ReLU(), nn.Linear(128,1))
+        self.net = nn.Sequential(
+            nn.Linear(768+40+v,128),
+            nn.ReLU(),
+            nn.Linear(128,1)
+        )
+
     def forward(self,t,a,v):
         return self.net(torch.cat([t,a,v],1))
 
 model = Simple(Xv.shape[1]).to(device)
+
 opt = torch.optim.Adam(model.parameters(), lr=1e-4)
 loss_fn = nn.BCEWithLogitsLoss()
 
-for _ in range(5):
+print("\nTraining Neural Model...")
+
+for epoch in range(5):
     opt.zero_grad()
     loss = loss_fn(model(Xt,Xa,Xv).squeeze(), yt)
     loss.backward()
     opt.step()
+    print(f"Epoch {epoch+1}, Loss: {loss.item():.4f}")
 
+# =========================
+# 12. EVALUATION
+# =========================
 with torch.no_grad():
-    preds = (torch.sigmoid(model(Xt_test,Xa_test,Xv_test).squeeze())>0.5).int().cpu().numpy()
+    preds = (torch.sigmoid(
+        model(Xt_test,Xa_test,Xv_test).squeeze()
+    ) > 0.5).int().cpu().numpy()
 
 # =========================
-# RESULTS
+# 13. RESULTS
 # =========================
 print("\n===== FINAL RESULTS =====")