Update app.py

app.py

@@ -33,7 +33,7 @@ def predict_ann(age, workclass, education, marital_status, occupation, relations
     # prediction = 1
     return "Income >50K" if prediction == 1 else "Income <=50K"
 
-def rf_interface(age, workclass, education, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country):
+def predict_rf(age, workclass, education, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country):
     # columns = {
     # "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], 
@@ -54,6 +54,28 @@ def rf_interface(age, workclass, education, marital_status, occupation, relation
     # prediction = 1
     return "Income >50K" if prediction == 1 else "Income <=50K"
 
+def predict_hb(age, workclass, education, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country):
+    # columns = {
+    # "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 = { "0":[0],
+    "age": [age], "workclass":[workclass], "educational-num":[education], "occupation":[occupation],
+    "race":[race], "gender":[gender], "capital-gain":[capital_gain], "capital-loss":[capital_loss], 
+    "hours-per-week":[hours_per_week], "native-country":[native_country]}
+    df = pd.DataFrame(data=columns)
+    fixed_features = cleaning_features(df,race)
+    print(fixed_features)
+    # with open('ann_model.pkl', 'rb') as ann_model_file:
+    #     ann_model = pickle.load(ann_model_file)
+    scaler = StandardScaler()
+    X = scaler.fit_transform(fixed_features)
+    hb_model = pickle.load(open('hdbscan_model.pkl', 'rb'))
+    prediction = hb_model.predict(fixed_features)
+    # prediction = 1
+    return "Income >50K" if prediction == 1 else "Income <=50K"
+
+
 def cleaning_features(data,race):
     # with open('race_onehot_encoder.pkl', 'rb') as enc_file:
     #     encoder = pickle.load(enc_file)
@@ -190,10 +212,18 @@ rf_interface = gr.Interface(
     description="Predict income using a Random Forest model."
 )
 
+hb_interface = gr.Interface(
+    fn=predict_hb,
+    inputs=inputs,
+    outputs="text",
+    title="HDBScan Clustering",
+    description="Predict income using a HDBScan Clustering model."
+)
+
 
 interface = gr.TabbedInterface(
-    [ann_interface, rf_interface],
-    ["ANN Model", "Random Forest Model"]
+    [ann_interface, rf_interface,hb_interface],
+    ["ANN Model", "Random Forest Model","HDBScan Model"]
 )