Upload folder using huggingface_hub

app.py

@@ -8,14 +8,53 @@ st.set_page_config(page_title="Engine Predictive Maintenance", layout="centered"
 st.title("Engine Predictive Maintenance")
 st.write("Enter sensor values to predict whether maintenance is needed.")
 
-# Model repo (public)
 MODEL_REPO = "vinayakdnrdd/engine-pm-model"
 MODEL_FILE = "engine_pm_model.joblib"
 
+# Load model
 model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILE)
 model = joblib.load(model_path)
 
-# --- Inputs ---
+# ---- Helper: get expected input columns from sklearn Pipeline ----
+def get_expected_columns(m):
+    # Best case: pipeline has feature_names_in_
+    cols = getattr(m, "feature_names_in_", None)
+    if cols is not None:
+        return list(cols)
+
+    # Typical: pipeline.named_steps["preprocess"] has feature_names_in_
+    pre = getattr(m, "named_steps", {}).get("preprocess", None)
+    if pre is not None:
+        cols = getattr(pre, "feature_names_in_", None)
+        if cols is not None:
+            return list(cols)
+
+        # Fallback: derive from transformers definition
+        exp = []
+        try:
+            for _, _, c in pre.transformers:
+                if isinstance(c, list):
+                    exp.extend(c)
+        except Exception:
+            pass
+        # keep unique order
+        seen = set()
+        exp2 = []
+        for c in exp:
+            if c not in seen:
+                exp2.append(c); seen.add(c)
+        if exp2:
+            return exp2
+
+    # Last fallback: assume these common names
+    return ["Engine rpm", "Lub oil pressure", "Fuel pressure", "Coolant pressure", "Lub oil temp", "Coolant temp"]
+
+expected_cols = get_expected_columns(model)
+
+with st.expander("Debug (Expected input columns from model)"):
+    st.write(expected_cols)
+
+# ---- UI inputs ----
 engine_rpm = st.number_input("Engine RPM", value=1500.0)
 lub_oil_pressure = st.number_input("Lub Oil Pressure", value=2.5)
 fuel_pressure = st.number_input("Fuel Pressure", value=3.0)
@@ -23,26 +62,70 @@ coolant_pressure = st.number_input("Coolant Pressure", value=1.2)
 lub_oil_temp = st.number_input("Lub Oil Temperature", value=85.0)
 coolant_temp = st.number_input("Coolant Temperature", value=90.0)
 
+# We store inputs with MANY aliases (case-insensitive matching)
+inputs = {
+    "Engine rpm": engine_rpm,
+    "engine rpm": engine_rpm,
+    "Engine_RPM": engine_rpm,
+    "Engine_Rpm": engine_rpm,
+
+    "Lub oil pressure": lub_oil_pressure,
+    "lub oil pressure": lub_oil_pressure,
+    "Lub_Oil_Pressure": lub_oil_pressure,
+
+    "Fuel pressure": fuel_pressure,
+    "fuel pressure": fuel_pressure,
+    "Fuel_Pressure": fuel_pressure,
+
+    "Coolant pressure": coolant_pressure,
+    "coolant pressure": coolant_pressure,
+    "Coolant_Pressure": coolant_pressure,
+
+    "Lub oil temp": lub_oil_temp,
+    "lub oil temp": lub_oil_temp,
+    "Lub oil temperature": lub_oil_temp,
+    "lub oil temperature": lub_oil_temp,
+    "Lub_Oil_Temperature": lub_oil_temp,
+
+    "Coolant temp": coolant_temp,
+    "coolant temp": coolant_temp,
+    "Coolant temperature": coolant_temp,
+    "coolant temperature": coolant_temp,
+    "Coolant_Temperature": coolant_temp,
+}
+
+def find_value_for_col(colname: str):
+    # exact match
+    if colname in inputs:
+        return inputs[colname]
+    # normalized match
+    key = colname.strip().lower()
+    for k, v in inputs.items():
+        if k.strip().lower() == key:
+            return v
+    return None
+
 if st.button("Predict"):
-    # Build input with human-friendly names...
-    X = pd.DataFrame([{
-        "Engine rpm": engine_rpm,
-        "Lub oil pressure": lub_oil_pressure,
-        "Fuel pressure": fuel_pressure,
-        "Coolant pressure": coolant_pressure,
-        "Lub oil temp": lub_oil_temp,
-        "Coolant temp": coolant_temp
-    }])
-
-    # ✅ Normalize to match training (your model expects lowercase)
-    X.columns = [c.strip().lower() for c in X.columns]
-
-    # Predict
+    row = {}
+    missing = []
+    for col in expected_cols:
+        v = find_value_for_col(col)
+        if v is None:
+            missing.append(col)
+        else:
+            row[col] = v
+
+    if missing:
+        st.error("Model expects these columns but app couldn't map them:")
+        st.write(missing)
+        st.stop()
+
+    X = pd.DataFrame([row], columns=expected_cols)
+
     proba = float(model.predict_proba(X)[0, 1])
     pred = int(proba >= 0.5)
 
     st.write(f"Probability (Maintenance Needed): **{proba:.2f}**")
-
     if pred == 1:
         st.error("⚠️ Prediction: **Maintenance Needed**")
     else: