streamlit app

app.py

@@ -0,0 +1,136 @@
+import pandas as pd
+import streamlit as st
+import numpy as np
+import pickle
+import catboost
+from sklearn.impute import SimpleImputer
+
+
+
+# Load the saved model and unique values:
+with open("model_and_key_components.pkl", "rb") as f:
+    components = pickle.load(f)
+
+# Extract the individual components
+dt_model = components["model"]
+unique_values = components["unique_values"]
+
+
+st.image("https://pbs.twimg.com/media/DywhyJiXgAIUZej?format=jpg&name=medium")
+st.title("Income Prediction App")
+
+# Sidebar with input field descriptions
+st.sidebar.header("Description of the Required Input Fields")
+st.sidebar.markdown("**Age**: Enter the age of the individual (e.g., 25, 42, 57).")
+st.sidebar.markdown("**Gender**: Select the gender of the individual (e.g., Male, Female).")
+st.sidebar.markdown("**Education**: Choose the highest education level of the individual (e.g., Bachelors Degree, High School Graduate, Masters Degree).")
+st.sidebar.markdown("**Worker Class**: Select the class of worker for the individual (e.g., Private, Government, Self-employed).")
+st.sidebar.markdown("**Marital Status**: Choose the marital status of the individual (e.g., Married, Never married, Divorced).")
+st.sidebar.markdown("**Race**: Select the race of the individual (e.g., White, Black, Asian-Pac-Islander).")
+st.sidebar.markdown("**Hispanic Origin**: Choose the Hispanic origin of the individual (e.g., Mexican, Puerto Rican, Cuban).")
+st.sidebar.markdown("**Full/Part-Time Employment**: Select the employment status as full-time or part-time (e.g., Full-time schedules, Part-time schedules).")
+st.sidebar.markdown("**Wage Per Hour**: Enter the wage per hour of the individual (numeric value, e.g., 20.50).")
+st.sidebar.markdown("**Weeks Worked Per Year**: Specify the number of weeks the individual worked in a year (numeric value, e.g., 45).")
+st.sidebar.markdown("**Industry Code**: Choose the category code of the industry where the individual works (e.g., Category 1, Category 2).")
+st.sidebar.markdown("**Major Industry Code**: Select the major industry code of the individual's work (e.g., Industry A, Industry B).")
+st.sidebar.markdown("**Occupation Code**: Choose the category code of the occupation of the individual (e.g., Category X, Category Y).")
+st.sidebar.markdown("**Major Occupation Code**: Select the major occupation code of the individual (e.g., Occupation 1, Occupation 2).")
+st.sidebar.markdown("**Total Employed**: Specify the number of persons worked for the employer (numeric value, e.g., 3, 5).")
+st.sidebar.markdown("**Household Stat**: Choose the detailed household and family status of the individual (e.g., Single, Married-civilian spouse present).")
+st.sidebar.markdown("**Household Summary**: Select the detailed household summary (e.g., Child under 18 never married, Spouse of householder).")
+st.sidebar.markdown("**Veteran Benefits**: Choose whether the individual receives veteran benefits (Yes or No).")
+st.sidebar.markdown("**Tax Filer Status**: Select the tax filer status of the individual (e.g., Single, Joint both 65+).")
+st.sidebar.markdown("**Gains**: Specify any gains the individual has (numeric value, e.g., 1500.0).")
+st.sidebar.markdown("**Losses**: Specify any losses the individual has (numeric value, e.g., 300.0).")
+st.sidebar.markdown("**Dividends from Stocks**: Specify any dividends from stocks for the individual (numeric value, e.g., 120.5).")
+st.sidebar.markdown("**Citizenship**: Select the citizenship status of the individual (e.g., Native, Foreign Born- Not a citizen of U S).")
+st.sidebar.markdown("**Year of Migration**: Enter the year of migration for the individual (numeric value, e.g., 2005).")
+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 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:
+    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:
+    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:
+    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 make predictions
+if st.button("Predict"):
+    # Transform the input data to a DataFrame for prediction
+    input_df = pd.DataFrame([input_data])
+
+    # Make predictions
+    prediction = dt_model.predict(input_df)
+    prediction_proba = dt_model.predict_proba(input_df)
+
+    # 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("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}")