Update app.py

app.py

@@ -59,6 +59,8 @@ def predict_hb(age, workclass, education,  occupation,  race, gender, capital_ga
     # "age": [age], "workclass":[workclass], "educational-num":[education], "marital-status":[marital_status], "occupation":[occupation], 
     # "relationship":[relationship], "race":[race], "gender":[gender], "capital-gain":[capital_gain], "capital-loss":[capital_loss], 
     # "hours-per-week":[hours_per_week], "native-country":[native_country]}
+    
+    
     columns = { 
     "age": [age], "workclass":[workclass], "educational-num":[education], "occupation":[occupation],
     "race":[race], "gender":[gender], "capital-gain":[capital_gain], "capital-loss":[capital_loss], 
@@ -70,10 +72,19 @@ def predict_hb(age, workclass, education,  occupation,  race, gender, capital_ga
     #     ann_model = pickle.load(ann_model_file)
     scaler = StandardScaler()
     X = scaler.fit_transform(fixed_features)
-    hb_model = joblib.load('hdbscan_model.joblib')
-    prediction = hdbscan.approximate_predict(hb_model,fixed_features)
-    # prediction = 1
-    return f"Predicted Cluster (HDBSCAN): {prediction}"
+    
+    clusterer = hdbscan.HDBSCAN(
+    min_cluster_size=220,
+    min_samples=117,
+    metric='euclidean',
+    cluster_selection_method='eom',
+    prediction_data=True,
+    cluster_selection_epsilon=0.28479667859306007
+    )
+
+    prediction = clusterer.fit_predict(X)
+
+    return f"Predicted Cluster (HDBSCAN): {prediction[-1]}"
 
 
 def cleaning_features(data,race,hdbscan):
@@ -137,11 +148,15 @@ def cleaning_features(data,race,hdbscan):
 
     data = pca(data)
     if(hdbscan):
+        df_transformed = pd.read_csv('dataset.csv')
+        X = df_transformed.drop('income', axis=1)
+        data = pd.concat([X, data], ignore_index=True)
         data['capital-gain'] = np.log1p(data['capital-gain'])
         data['capital-loss'] = np.log1p(data['capital-loss'])
         scaler = joblib.load("robust_scaler.pkl")
         numerical_features = ['age', 'capital-gain', 'capital-loss', 'hours-per-week']
         data[numerical_features] = scaler.transform(data[numerical_features])
+        
     return data
 
 # def pca(data):