Update app.py

app.py

@@ -54,15 +54,15 @@ for col in required_columns:
     if col not in df.columns:
         raise Exception(f"❌ Column '{col}' is missing from the dataset!")
 
-# ✅ Convert "Case Problem" column to lowercase for consistency
-df["Case Problem"] = df["Case Problem"].astype(str).str.lower()
+# ✅ Convert "Case Problem" column to lowercase and remove spaces for consistency
+df["Case Problem"] = df["Case Problem"].astype(str).str.strip().str.lower()
 
-# ✅ Encode categorical variables
+# ✅ Train and save LabelEncoder to handle unseen labels correctly
 encoder = LabelEncoder()
 df["Case Problem Encoded"] = encoder.fit_transform(df["Case Problem"])
 df["Feedback Encoded"] = encoder.fit_transform(df["Feedback"])
 
-# ✅ Save encoder for later use
+# ✅ Save encoder to use it later
 joblib.dump(encoder, "case_problem_encoder.pkl")
 
 # ✅ Train Model
@@ -72,7 +72,7 @@ X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_
 model = RandomForestClassifier(n_estimators=100, random_state=42)
 model.fit(X_train, y_train)
 
-# ✅ Save model
+# ✅ Save trained model
 joblib.dump(model, "feedback_model.pkl")
 print("✅ Model trained successfully!")
 
@@ -89,8 +89,8 @@ async def predict_feedback(data: PredictionInput):
     # ✅ Load encoder
     encoder = joblib.load("case_problem_encoder.pkl")
 
-    # ✅ Convert input to lowercase to match training data
-    case_problem_lower = data.case_problem.lower()
+    # ✅ Convert input to lowercase and remove spaces
+    case_problem_lower = data.case_problem.strip().lower()
 
     # ✅ Check if input exists in training data
     if case_problem_lower not in df["Case Problem"].values:
@@ -108,13 +108,13 @@ async def predict_feedback(data: PredictionInput):
     except Exception as e:
         return {"error": str(e)}
 
-# ✅ Gradio UI with suggestions for valid categories
+# ✅ Gradio UI with better handling
 def gradio_interface(case_problem):
     if model is None:
         return "Model not trained yet."
 
     encoder = joblib.load("case_problem_encoder.pkl")
-    case_problem_lower = case_problem.lower()
+    case_problem_lower = case_problem.strip().lower()
 
     if case_problem_lower not in df["Case Problem"].values:
         valid_problems = ", ".join(df["Case Problem"].unique())