app.py

import streamlit as st
import pandas as pd
import joblib
from enum import Enum
from pydantic import BaseModel, Field, confloat, constr, conlist, ValidationError
from typing import Optional

# Load the model
model = joblib.load('lgb_model_main.joblib')

categorical_features = [
    'NAME_CONTRACT_TYPE',
    'CODE_GENDER',
    'NAME_INCOME_TYPE',
    'NAME_EDUCATION_TYPE',
    'NAME_FAMILY_STATUS',
    'OCCUPATION_TYPE',
    'ORGANIZATION_TYPE',
]

class ContractType(str, Enum):
    Cash_loans = "Cash loans"
    Revolving_loans = "Revolving loans"

class Gender(str, Enum):
    Male = "M"
    Female = "F"
    XNA = "XNA"

class IncomeType(str, Enum):
    Working = "Working"
    Other = "Other"
    Commercial_associate = "Commercial associate"
    Pensioner = "Pensioner"

class EducationType(str, Enum):
    Other = "Other"
    Higher_education = "Higher education"
    Secondary = "Secondary / secondary special"

class FamilyStatus(str, Enum):
    Civil_marriage = "Civil marriage"
    Married = "Married"
    Single = "Single / not married"
    Other = "Other"

class OccupationType(str, Enum):
    Laborers = "Laborers"
    Sales_staff = "Sales staff"
    Core_staff = "Core staff"
    Managers = "Managers"
    Drivers = "Drivers"
    Other = "Other"

class OrganizationType(str, Enum):
    Business_Entity = "Business Entity Type 3"
    Other = "Other"
    XNA = "XNA"
    Self_employed = "Self-employed"

class PredictionInput(BaseModel):
    AMT_INCOME_TOTAL: confloat(ge=0)
    AMT_CREDIT: confloat(ge=0)
    REGION_POPULATION_RELATIVE: confloat(ge=0)
    DAYS_REGISTRATION: int
    DAYS_BIRTH: int
    DAYS_ID_PUBLISH: int
    FLAG_WORK_PHONE: int
    FLAG_PHONE: int
    REGION_RATING_CLIENT_W_CITY: int
    REG_CITY_NOT_WORK_CITY: int
    FLAG_DOCUMENT_3: int
    NAME_CONTRACT_TYPE: ContractType
    CODE_GENDER: Gender
    FLAG_OWN_CAR: int
    NAME_INCOME_TYPE: IncomeType
    NAME_EDUCATION_TYPE: EducationType
    NAME_FAMILY_STATUS: FamilyStatus
    OCCUPATION_TYPE: OccupationType
    ORGANIZATION_TYPE: OrganizationType
    CREDIT_ACTIVE_Active_count_Bureau: Optional[int] = None
    CREDIT_ACTIVE_Closed_count_Bureau: Optional[int] = None
    DAYS_CREDIT_Bureau: Optional[int] = None
    AMT_INSTALMENT_mean_HCredit_installments: Optional[int] = None
    DAYS_INSTALMENT_mean_HCredit_installments: Optional[int] = None
    NUM_INSTALMENT_NUMBER_mean_HCredit_installments: Optional[int] = None
    NUM_INSTALMENT_VERSION_mean_HCredit_installments: Optional[int] = None
    NAME_CONTRACT_STATUS_Active_count_pos_cash: Optional[int] = None
    NAME_CONTRACT_STATUS_Completed_count_pos_cash: Optional[int] = None
    SK_DPD_DEF_pos_cash: Optional[int] = None
    NAME_CONTRACT_STATUS_Refused_count_HCredit_PApp: Optional[int] = None
    NAME_GOODS_CATEGORY_Other_count_HCredit_PApp: Optional[int] = None
    NAME_PORTFOLIO_Cash_count_HCredit_PApp: Optional[int] = None
    NAME_PRODUCT_TYPE_walk_in_count_HCredit_PApp: Optional[int] = None
    NAME_SELLER_INDUSTRY_Other_count_HCredit_PApp: Optional[int] = None
    NAME_YIELD_GROUP_high_count_HCredit_PApp: Optional[int] = None
    NAME_YIELD_GROUP_low_action_count_HCredit_PApp: Optional[int] = None
    AMT_CREDIT_HCredit_PApp: Optional[int] = None
    SELLERPLACE_AREA_HCredit_PApp: Optional[int] = None

def make_prediction(input_data: dict):
    try:
        # Convert dictionary to a pandas DataFrame
        input_df = pd.DataFrame([input_data])

        # Convert categorical features to 'category' type
        for feature in categorical_features:
            input_df[feature] = input_df[feature].astype('category')

        # Make predictions using the loaded model
        predictions = model.predict_proba(input_df, categorical_feature=categorical_features)[:, 1]

        # Placeholder response for demonstration
        response = {"Probability for this credit to be defaulted is: ": predictions[0]}  # Extract the probability for class 1

        return response
    except Exception as e:
        return {"error": str(e)}

def main():
    st.title("Credit Default Prediction")

    st.header("Input Data")
    with st.form(key='input_form'):
        AMT_INCOME_TOTAL = st.number_input("AMT_INCOME_TOTAL", min_value=0.0, format="%f")
        AMT_CREDIT = st.number_input("AMT_CREDIT", min_value=0.0, format="%f")
        REGION_POPULATION_RELATIVE = st.number_input("REGION_POPULATION_RELATIVE", min_value=0.0, format="%f")
        DAYS_REGISTRATION = st.number_input("DAYS_REGISTRATION", min_value=-100000, max_value=100000, format="%d")
        DAYS_BIRTH = st.number_input("DAYS_BIRTH", min_value=-100000, max_value=100000, format="%d")
        DAYS_ID_PUBLISH = st.number_input("DAYS_ID_PUBLISH", min_value=-100000, max_value=100000, format="%d")
        FLAG_WORK_PHONE = st.number_input("FLAG_WORK_PHONE", min_value=0, max_value=1, format="%d")
        FLAG_PHONE = st.number_input("FLAG_PHONE", min_value=0, max_value=1, format="%d")
        REGION_RATING_CLIENT_W_CITY = st.number_input("REGION_RATING_CLIENT_W_CITY", min_value=0, max_value=10, format="%d")
        REG_CITY_NOT_WORK_CITY = st.number_input("REG_CITY_NOT_WORK_CITY", min_value=0, max_value=1, format="%d")
        FLAG_DOCUMENT_3 = st.number_input("FLAG_DOCUMENT_3", min_value=0, max_value=1, format="%d")
        NAME_CONTRACT_TYPE = st.selectbox("NAME_CONTRACT_TYPE", list(ContractType))
        CODE_GENDER = st.selectbox("CODE_GENDER", list(Gender))
        FLAG_OWN_CAR = st.number_input("FLAG_OWN_CAR", min_value=0, max_value=1, format="%d")
        NAME_INCOME_TYPE = st.selectbox("NAME_INCOME_TYPE", list(IncomeType))
        NAME_EDUCATION_TYPE = st.selectbox("NAME_EDUCATION_TYPE", list(EducationType))
        NAME_FAMILY_STATUS = st.selectbox("NAME_FAMILY_STATUS", list(FamilyStatus))
        OCCUPATION_TYPE = st.selectbox("OCCUPATION_TYPE", list(OccupationType))
        ORGANIZATION_TYPE = st.selectbox("ORGANIZATION_TYPE", list(OrganizationType))

        CREDIT_ACTIVE_Active_count_Bureau = st.number_input("CREDIT_ACTIVE_Active_count_Bureau", min_value=0, format="%d", value=0)
        CREDIT_ACTIVE_Closed_count_Bureau = st.number_input("CREDIT_ACTIVE_Closed_count_Bureau", min_value=0, format="%d", value=0)
        DAYS_CREDIT_Bureau = st.number_input("DAYS_CREDIT_Bureau", min_value=-100000, max_value=100000, format="%d", value=0)
        AMT_INSTALMENT_mean_HCredit_installments = st.number_input("AMT_INSTALMENT_mean_HCredit_installments", min_value=0, format="%f", value=0.0)
        DAYS_INSTALMENT_mean_HCredit_installments = st.number_input("DAYS_INSTALMENT_mean_HCredit_installments", min_value=-100000, max_value=100000, format="%d", value=0)
        NUM_INSTALMENT_NUMBER_mean_HCredit_installments = st.number_input("NUM_INSTALMENT_NUMBER_mean_HCredit_installments", min_value=0, format="%d", value=0)
        NUM_INSTALMENT_VERSION_mean_HCredit_installments = st.number_input("NUM_INSTALMENT_VERSION_mean_HCredit_installments", min_value=0, format="%d", value=0)
        NAME_CONTRACT_STATUS_Active_count_pos_cash = st.number_input("NAME_CONTRACT_STATUS_Active_count_pos_cash", min_value=0, format="%d", value=0)
        NAME_CONTRACT_STATUS_Completed_count_pos_cash = st.number_input("NAME_CONTRACT_STATUS_Completed_count_pos_cash", min_value=0, format="%d", value=0)
        SK_DPD_DEF_pos_cash = st.number_input("SK_DPD_DEF_pos_cash", min_value=0, format="%d", value=0)
        NAME_CONTRACT_STATUS_Refused_count_HCredit_PApp = st.number_input("NAME_CONTRACT_STATUS_Refused_count_HCredit_PApp", min_value=0, format="%d", value=0)
        NAME_GOODS_CATEGORY_Other_count_HCredit_PApp = st.number_input("NAME_GOODS_CATEGORY_Other_count_HCredit_PApp", min_value=0, format="%d", value=0)
        NAME_PORTFOLIO_Cash_count_HCredit_PApp = st.number_input("NAME_PORTFOLIO_Cash_count_HCredit_PApp", min_value=0, format="%d", value=0)
        NAME_PRODUCT_TYPE_walk_in_count_HCredit_PApp = st.number_input("NAME_PRODUCT_TYPE_walk_in_count_HCredit_PApp", min_value=0, format="%d", value=0)
        NAME_SELLER_INDUSTRY_Other_count_HCredit_PApp = st.number_input("NAME_SELLER_INDUSTRY_Other_count_HCredit_PApp", min_value=0, format="%d", value=0)
        NAME_YIELD_GROUP_high_count_HCredit_PApp = st.number_input("NAME_YIELD_GROUP_high_count_HCredit_PApp", min_value=0, format="%d", value=0)
        NAME_YIELD_GROUP_low_action_count_HCredit_PApp = st.number_input("NAME_YIELD_GROUP_low_action_count_HCredit_PApp", min_value=0, format="%d", value=0)
        AMT_CREDIT_HCredit_PApp = st.number_input("AMT_CREDIT_HCredit_PApp", min_value=0, format="%f", value=0.0)
        SELLERPLACE_AREA_HCredit_PApp = st.number_input("SELLERPLACE_AREA_HCredit_PApp", min_value=0, format="%d", value=0)

        submit_button = st.form_submit_button(label='Predict')

    if submit_button:
        input_data = {
            "AMT_INCOME_TOTAL": AMT_INCOME_TOTAL,
            "AMT_CREDIT": AMT_CREDIT,
            "REGION_POPULATION_RELATIVE": REGION_POPULATION_RELATIVE,
            "DAYS_REGISTRATION": DAYS_REGISTRATION,
            "DAYS_BIRTH": DAYS_BIRTH,
            "DAYS_ID_PUBLISH": DAYS_ID_PUBLISH,
            "FLAG_WORK_PHONE": FLAG_WORK_PHONE,
            "FLAG_PHONE": FLAG_PHONE,
            "REGION_RATING_CLIENT_W_CITY": REGION_RATING_CLIENT_W_CITY,
            "REG_CITY_NOT_WORK_CITY": REG_CITY_NOT_WORK_CITY,
            "FLAG_DOCUMENT_3": FLAG_DOCUMENT_3,
            "NAME_CONTRACT_TYPE": NAME_CONTRACT_TYPE,
            "CODE_GENDER": CODE_GENDER,
            "FLAG_OWN_CAR": FLAG_OWN_CAR,
            "NAME_INCOME_TYPE": NAME_INCOME_TYPE,
            "NAME_EDUCATION_TYPE": NAME_EDUCATION_TYPE,
            "NAME_FAMILY_STATUS": NAME_FAMILY_STATUS,
            "OCCUPATION_TYPE": OCCUPATION_TYPE,
            "ORGANIZATION_TYPE": ORGANIZATION_TYPE,
            "CREDIT_ACTIVE_Active_count_Bureau": CREDIT_ACTIVE_Active_count_Bureau,
            "CREDIT_ACTIVE_Closed_count_Bureau": CREDIT_ACTIVE_Closed_count_Bureau,
            "DAYS_CREDIT_Bureau": DAYS_CREDIT_Bureau,
            "AMT_INSTALMENT_mean_HCredit_installments": AMT_INSTALMENT_mean_HCredit_installments,
            "DAYS_INSTALMENT_mean_HCredit_installments": DAYS_INSTALMENT_mean_HCredit_installments,
            "NUM_INSTALMENT_NUMBER_mean_HCredit_installments": NUM_INSTALMENT_NUMBER_mean_HCredit_installments,
            "NUM_INSTALMENT_VERSION_mean_HCredit_installments": NUM_INSTALMENT_VERSION_mean_HCredit_installments,
            "NAME_CONTRACT_STATUS_Active_count_pos_cash": NAME_CONTRACT_STATUS_Active_count_pos_cash,
            "NAME_CONTRACT_STATUS_Completed_count_pos_cash": NAME_CONTRACT_STATUS_Completed_count_pos_cash,
            "SK_DPD_DEF_pos_cash": SK_DPD_DEF_pos_cash,
            "NAME_CONTRACT_STATUS_Refused_count_HCredit_PApp": NAME_CONTRACT_STATUS_Refused_count_HCredit_PApp,
            "NAME_GOODS_CATEGORY_Other_count_HCredit_PApp": NAME_GOODS_CATEGORY_Other_count_HCredit_PApp,
            "NAME_PORTFOLIO_Cash_count_HCredit_PApp": NAME_PORTFOLIO_Cash_count_HCredit_PApp,
            "NAME_PRODUCT_TYPE_walk_in_count_HCredit_PApp": NAME_PRODUCT_TYPE_walk_in_count_HCredit_PApp,
            "NAME_SELLER_INDUSTRY_Other_count_HCredit_PApp": NAME_SELLER_INDUSTRY_Other_count_HCredit_PApp,
            "NAME_YIELD_GROUP_high_count_HCredit_PApp": NAME_YIELD_GROUP_high_count_HCredit_PApp,
            "NAME_YIELD_GROUP_low_action_count_HCredit_PApp": NAME_YIELD_GROUP_low_action_count_HCredit_PApp,
            "AMT_CREDIT_HCredit_PApp": AMT_CREDIT_HCredit_PApp,
            "SELLERPLACE_AREA_HCredit_PApp": SELLERPLACE_AREA_HCredit_PApp
        }

        try:
            input_data_validated = PredictionInput(**input_data)
            prediction = make_prediction(input_data_validated.dict())
            st.write(prediction)
        except ValidationError as e:
            st.error(f"Validation error: {e}")

if __name__ == "__main__":
    main()