Upload app.py

app.py

@@ -20,6 +20,11 @@ capital_gain = [0, 99999]
 capital_loss = [0, 4356]
 hours_per_week = [20, 60]
 
+children_count = [0, 15]
+bmi = [10, 100]
+region_option = ['southwest', 'southeast', 'northwest', 'northeast']
+smoker_option = ['yes', 'no']
+
 # Mapping for education
 education_mapping = "{'Preschool': 1, '1st-4th': 2, '5th-6th': 3, '7th-8th': 4, '9th': 5, '10th': 6, '11th': 7, '12th': 8, 'HS-grad': 9, 'Some-college': 10, 'Assoc-voc': 11, 'Assoc-acdm': 12, 'Bachelors': 13, 'Masters': 14, 'Prof-school': 15, 'Doctorate': 16}"
 education_dict = ast.literal_eval(education_mapping)
@@ -44,12 +49,12 @@ columns = ['age', 'education-num', 'sex', 'capital-gain', 'capital-loss',
         'race_Asian-Pac-Islander', 'race_Black', 'race_Other', 'race_White']
 
 # Code for SVM
-def SVM(workclass, education, marital_status, occupation, relationship, race, sex, age, capital_gain, capital_loss, hours_per_week):
-    with open('models/best_svm_OvM_Salary_Classification.pkl', 'rb') as f:
+def SVM_Salary(workclass, education, marital_status, occupation, relationship, race, sex, age, capital_gain, capital_loss, hours_per_week):
+    with open('../SVM/models/best_svm_OvM_Salary_Classification.pkl', 'rb') as f:
         loaded_model = pickle.load(f)
 
     # Loading the scaler and transform the data
-    with open('models/z-score_scaler_svm_Salary_Classification.pkl', 'rb') as f:
+    with open('../SVM/models/z-score_scaler_svm_salary_classification.pkl', 'rb') as f:
         scaler = pickle.load(f)
 
     new_data = {
@@ -105,19 +110,85 @@ def SVM(workclass, education, marital_status, occupation, relationship, race, se
 
     return "Predicted Salary Class:", salary_result
 
+def SVM_Health(age, sex, bmi, children, smoker, region):
+    with open('models/best_health_svm_OvM_Charges_Classification.pkl', 'rb') as f:
+        loaded_model = pickle.load(f)
+
+    # Loading the scaler and transform the data
+    with open('models/z-score_scaler_svm_charges_classification.pkl', 'rb') as f:
+        scaler = pickle.load(f)
+
+    #Inverting the dict to map the 'charges' values back to 'charges' labels
+    inverse_mapping_charges = {
+        0: 'Very Low (<= 5000)',
+        1: 'Low (5001 - 10000)',
+        2: 'Moderate (10001 - 15000)',
+        3: 'High (15001 - 20000)',
+        4: 'Very High (> 20001)',
+    }
+
+    new_data = {
+        'age': age,
+        'sex': sex,
+        'bmi': bmi,
+        'children': children,
+        'smoker': smoker,
+        'region': region,
+    }
+    
+    new_data = pd.DataFrame([new_data])
+
+    # Create an empty DataFrame with these columns
+    formattedDF = pd.DataFrame(columns=columns)
+
+    # Copying over the continuous columns
+    formattedDF['age'] = new_data['age']
+    formattedDF['sex'] = new_data['sex'].apply(lambda x: 1 if x == 'Male' else 0)
+    formattedDF['bmi'] = new_data['bmi']
+    formattedDF['children'] = new_data['children']
+    formattedDF['smoker'] = new_data['smoker'].apply(lambda x: 1 if x == 'Yes' else 0)
+    formattedDF['marital-status_'+new_data['marital-status']] = 1
+    formattedDF['region_'+new_data['region']] = 1
+
+
+    # Fill remaining columns with 0
+    formattedDF.fillna(0, inplace=True)
+    formattedDF = formattedDF.astype(int)
+    formattedDF = formattedDF[formattedDF.columns.intersection(columns)]
+
+    # Apply the scaler to the unseen data
+    continuous_columns = ['age', 'bmi']
+    formattedDF[continuous_columns] = scaler.transform(formattedDF[continuous_columns])
+
+    # Make predictions with the loaded model
+    prediction = loaded_model.predict(formattedDF)[0]
+    prediction = inverse_mapping_charges[prediction]
+
+    return "Predicted Charges Class:", prediction
+
+# Code for LogisticRegression
+def LogisticRegression_Salary(input_image):
+    # Task 2 logic
+    return "Task 2 Result"
+
 # Code for LogisticRegression
-def LogisticRegression(input_image):
+def LogisticRegression_Health(input_image):
     # Task 2 logic
     return "Task 2 Result"
 
 # Code for 
-def RandomForests(input_image):
+def RandomForests_Salary(input_image):
+    # Task 2 logic
+    return "Task 2 Result"
+
+# Code for 
+def RandomForests_Health(input_image):
     # Task 2 logic
     return "Task 2 Result"
 
 # interface one
 iface1 = gr.Interface(
-    fn=SVM,
+    fn=SVM_Salary,
     inputs=[
         gr.Dropdown(choices=workclass_options, label="Workclass"),
         gr.Dropdown(choices=education_option, label="Education"),
@@ -132,26 +203,59 @@ iface1 = gr.Interface(
         gr.Slider(minimum=hours_per_week[0], maximum=hours_per_week[1], step=1, label="Hours per Week"),
     ],
     outputs="text",
-    title="SVM"
+    title="SVM - Salary"
 )
 
 # interface two
 iface2 = gr.Interface(
-    fn=LogisticRegression,
+    fn=SVM_Health,
+    inputs=[
+        gr.Slider(minimum=age[0], maximum=age[1], step=1, label="Age"),
+        gr.Dropdown(choices=sex_option, label="Sex"),
+        gr.Slider(minimum=bmi[0], maximum=bmi[1], step=0.1, label="BMI"),
+        gr.Slider(minimum=children_count[0], maximum=children_count[1], step=1, label="Children"),
+        gr.Dropdown(choices=smoker_option, label="Smoker"),
+        gr.Dropdown(choices=region_option, label="Region"),
+    ],
+    outputs="text",
+    title="SVM - Health"
+)
+
+# interface three
+iface3 = gr.Interface(
+    fn=LogisticRegression_Salary,
     inputs="image",
     outputs="text",
     title="Logistic Regression"
 )
 
-# interface two
-iface3 = gr.Interface(
-    fn=RandomForests,
+# interface four
+iface4 = gr.Interface(
+    fn=LogisticRegression_Health,
+    inputs="image",
+    outputs="text",
+    title="Logistic Regression"
+)
+
+# interface five
+iface5 = gr.Interface(
+    fn=RandomForests_Salary,
+    inputs="image",
+    outputs="text",
+    title="Random Forests"
+)
+
+# interface six
+iface6 = gr.Interface(
+    fn=RandomForests_Health,
     inputs="image",
     outputs="text",
     title="Random Forests"
 )
 
-demo = gr.TabbedInterface([iface1, iface2, iface3], ["SVM - Jerome Agius", "Logistic Regression - Isaac Muscat", "Random Forests - Kyle Demicoli"])
+demo = gr.TabbedInterface([iface1, iface2, iface3, iface4, iface5, iface6], ["SVM - Jerome Agius", "SVM - Jerome Agius", 
+                                                                            "Logistic Regression - Isaac Muscat", "Logistic Regression - Isaac Muscat",
+                                                                            "Random Forests - Kyle Demicoli", "Random Forests - Kyle Demicoli"])
 
 # Run the interface
 demo.launch(share=True)