Update app.py

app.py

@@ -4,7 +4,6 @@ import numpy as np
 import pickle
 import catboost
 from sklearn.impute import SimpleImputer
-import requests
 
 # Load the saved model and unique values:
 with open("model_and_key_components.pkl", "rb") as f:
@@ -47,94 +46,90 @@ st.sidebar.markdown("**Year of Migration**: Enter the year of migration for the
 st.sidebar.markdown("**Country of Birth**: Choose the individual's birth country (e.g., United-States, Other).")
 st.sidebar.markdown("**Importance of Record**: Enter the weight of the instance (numeric value, e.g., 0.9).")
 
-# Create input fields for user input
+# Create the input fields in the order of your DataFrame
+input_data = {
+    'age': 0,  # Default values, you can change these as needed
+    'gender': unique_values['gender'][0],
+    'education': unique_values['education'][0],
+    'worker_class': unique_values['worker_class'][0],
+    'marital_status': unique_values['marital_status'][0],
+    'race': unique_values['race'][0],
+    'is_hispanic': unique_values['is_hispanic'][0],
+    'employment_commitment': unique_values['employment_commitment'][0],
+    'employment_stat': unique_values['employment_stat'][0],
+    'wage_per_hour': 0,  # Default value
+    'working_week_per_year': 0,  # Default value
+    'industry_code': 0,  # Default value
+    'industry_code_main': unique_values['industry_code_main'][0],
+    'occupation_code': 0,  # Default value
+    'occupation_code_main': unique_values['occupation_code_main'][0],
+    'total_employed': 0,  # Default value
+    'household_stat': unique_values['household_stat'][0],
+    'household_summary': unique_values['household_summary'][0],
+    'vet_benefit': 0,  # Default value
+    'tax_status': unique_values['tax_status'][0],
+    'gains': 0,  # Default value
+    'losses': 0,  # Default value
+    'stocks_status': 0,  # Default value
+    'citizenship': unique_values['citizenship'][0],
+    'mig_year': 0,
+    'country_of_birth_own': 'United-States',
+    'importance_of_record': 0.0  # Default value
+}
+
+# Create the input fields
 col1, col2, col3 = st.columns(3)
 
 with col1:
-    age = st.number_input("Age", min_value=0)
-    gender = st.selectbox("Gender", ["Male", "Female"])
-    education = st.selectbox("Education", unique_values['education'])
-    worker_class = st.selectbox("Class of Worker", unique_values['worker_class'])
-    marital_status = st.selectbox("Marital Status", unique_values['marital_status'])
-    race = st.selectbox("Race", unique_values['race'])
-    is_hispanic = st.selectbox("Hispanic Origin", unique_values['is_hispanic'])
-    employment_commitment = st.selectbox("Full/Part-Time Employment", unique_values['employment_commitment'])
-    wage_per_hour = st.number_input("Wage Per Hour", min_value=0)
+    input_data['age'] = st.number_input("Age", min_value=0, key='age')
+    input_data['gender'] = st.selectbox("Gender", unique_values['gender'], key='gender')
+    input_data['education'] = st.selectbox("Education", unique_values['education'], key='education')
+    input_data['worker_class'] = st.selectbox("Class of Worker", unique_values['worker_class'], key='worker_class')
+    input_data['marital_status'] = st.selectbox("Marital Status", unique_values['marital_status'], key='marital_status')
+    input_data['race'] = st.selectbox("Race", unique_values['race'], key='race')
+    input_data['is_hispanic'] = st.selectbox("Hispanic Origin", unique_values['is_hispanic'], key='is_hispanic')
+    input_data['employment_commitment'] = st.selectbox("Full/Part-Time Employment", unique_values['employment_commitment'], key='employment_commitment')
+    input_data['employment_stat'] = st.selectbox("Has Own Business Or Is Self Employed", unique_values['employment_stat'], key='employment_stat')
+    input_data['wage_per_hour'] = st.number_input("Wage Per Hour", min_value=0, key='wage_per_hour')
 
 with col2:
-    working_week_per_year = st.number_input("Weeks Worked Per Year", min_value=0)
-    industry_code = st.selectbox("Category Code of Industry", unique_values['industry_code'])
-    industry_code_main = st.selectbox("Major Industry Code", unique_values['industry_code_main'])
-    occupation_code = st.selectbox("Category Code of Occupation", unique_values['occupation_code'])
-    occupation_code_main = st.selectbox("Major Occupation Code", unique_values['occupation_code_main'])
-    total_employed = st.number_input("Number of Persons Worked for Employer", min_value=0)
-    household_stat = st.selectbox("Detailed Household and Family Status", unique_values['household_stat'])
-    household_summary = st.selectbox("Detailed Household Summary", unique_values['household_summary'])
-    vet_benefit = st.selectbox("Veteran Benefits", unique_values['vet_benefit'])
+    input_data['working_week_per_year'] = st.number_input("Weeks Worked Per Year", min_value=0, key='working_week_per_year')
+    input_data['industry_code'] = st.selectbox("Category Code of Industry", unique_values['industry_code'], key='industry_code')
+    input_data['industry_code_main'] = st.selectbox("Major Industry Code", unique_values['industry_code_main'], key='industry_code_main')
+    input_data['occupation_code'] = st.selectbox("Category Code of Occupation", unique_values['occupation_code'], key='occupation_code')
+    input_data['occupation_code_main'] = st.selectbox("Major Occupation Code", unique_values['occupation_code_main'], key='occupation_code_main')
+    input_data['total_employed'] = st.number_input("Number of Persons Worked for Employer", min_value=0, key='total_employed')
+    input_data['household_stat'] = st.selectbox("Detailed Household and Family Status", unique_values['household_stat'], key='household_stat')
+    input_data['household_summary'] = st.selectbox("Detailed Household Summary", unique_values['household_summary'], key='household_summary')
+    input_data['vet_benefit'] = st.selectbox("Veteran Benefits", unique_values['vet_benefit'], key='vet_benefit')
 
 with col3:
-    tax_status = st.selectbox("Tax Filer Status", unique_values['tax_status'])
-    gains = st.number_input("Gains", min_value=0)
-    losses = st.number_input("Losses", min_value=0)
-    stocks_status = st.number_input("Dividends from Stocks", min_value=0)
-    citizenship = st.selectbox("Citizenship", unique_values['citizenship'])
-    mig_year = st.selectbox("Migration Year", unique_values['mig_year'])
-    country_of_birth_own = st.selectbox("Country of Birth", unique_values['country_of_birth_own'])
-    importance_of_record = st.number_input("Importance of Record", min_value=0.0)
+    input_data['tax_status'] = st.selectbox("Tax Filer Status", unique_values['tax_status'], key='tax_status')
+    input_data['gains'] = st.number_input("Gains", min_value=0, key='gains')
+    input_data['losses'] = st.number_input("Losses", min_value=0, key='losses')
+    input_data['stocks_status'] = st.number_input("Dividends from Stocks", min_value=0, key='stocks_status')
+    input_data['citizenship'] = st.selectbox("Citizenship", unique_values['citizenship'], key='citizenship')
+    input_data['mig_year'] = st.selectbox("Migration Year", unique_values['mig_year'], key='migration_year')
+    input_data['country_of_birth_own'] = st.selectbox("Country of Birth", unique_values['country_of_birth_own'], key='country_of_birth_own')
+    input_data['importance_of_record'] = st.number_input("Importance of Record", min_value=0, key='importance_of_record')
 
-# Button to trigger prediction
+# Button to make predictions
 if st.button("Predict"):
-    # Create a dictionary of user input
-    user_input = {
-        "age": int(age),
-        "gender": gender,
-        "education": education,
-        "worker_class": worker_class,
-        "marital_status": marital_status,
-        "race": race,
-        "is_hispanic": is_hispanic,
-        "employment_commitment": employment_commitment,
-        "wage_per_hour": int(wage_per_hour),
-        "working_week_per_year": int(working_week_per_year),
-        "industry_code": int(industry_code),
-        "industry_code_main": industry_code_main,
-        "occupation_code": int(occupation_code),
-        "occupation_code_main": occupation_code_main,
-        "total_employed": int(total_employed),
-        "household_stat": household_stat,
-        "household_summary": household_summary,
-        "vet_benefit": int(vet_benefit),
-        "tax_status": tax_status,
-        "gains": int(gains),
-        "losses": int(losses),
-        "stocks_status": int(stocks_status),
-        "citizenship": citizenship,
-        "mig_year": int(mig_year),
-        "country_of_birth_own": country_of_birth_own,
-        "importance_of_record": float(importance_of_record)
-    }
+    # Transform the input data to a DataFrame for prediction
+    input_df = pd.DataFrame([input_data])
 
-    # Send a POST request to the FastAPI server
-    response = requests.post("https://rasmodev-income-prediction-fastapi.hf.space/predict/", json=user_input)
-    
+    # Make predictions
+    prediction = dt_model.predict(input_df)
+    prediction_proba = dt_model.predict_proba(input_df)
 
-    # Check if the request was successful
-    if response.status_code == 200:
-        prediction_data = response.json()
-        
-        # Display prediction result to the user
-        st.subheader("Prediction Result")
-    
-        # Determine income prediction and format message
-        if prediction_data['income_prediction'] == "Income over $50K":
-            st.success("This individual is predicted to have an income of over $50K.")
-        else:
-            st.error("This individual is predicted to have an income of under $50K")
-        
-        # Display prediction probability
-        st.subheader("Prediction Probability")
-        probability = prediction_data['prediction_probability']
-        st.write(f"The probability of the individual having an income over $50K is: {probability:.2f}")
+    # Display prediction result
+    st.subheader("Prediction")
+    if prediction[0] == 1:
+        st.success("This individual is predicted to have an income of over $50K.")
     else:
-        st.error("Error: Unable to get prediction")
+        st.error("This individual is predicted to have an income of under $50K")
+
+    # Show prediction probability
+    st.subheader("Prediction Probability")
+    st.write(f"The probability of the individual having an income over $50K is: {prediction_proba[0][1]:.2f}")