Upload 4 files

app.py

@@ -0,0 +1,47 @@
+import joblib
+import pandas as pd
+import streamlit as st 
+
+
+model = joblib.load('model.joblib')
+unique_values = joblib.load('unique_values.joblib')
+    
+unique_education =  unique_values["education"]
+unique_self_employed =  unique_values["self_employed"]
+
+
+def main():
+    st.title("Loan Approve Prediction")
+
+    with st.form("questionaire"):
+        education = st.selectbox("Education", unique_education)
+        self_employed = st.selectbox("Self Employed", unique_self_employed)
+        no_of_dependents = st.slider("Number of Dependents", min_value=0 ,max_value=10)
+        income_annum = st.slider("Income Per Year",min_value=200000, max_value=1000000)
+        loan_amount = st.slider("Loan Amount", min_value=300000, max_value=40000000)
+        loan_term = st.slider("Loan Term (Year)", min_value=2, max_value=20)
+        cibil_score = st.slider("CIBIL Score", min_value=300, max_value=900)
+        residential_assets_value = st.slider("Residential Assets Value", min_value=-100000, max_value=30000000)
+        commercial_assets_value = st.slider("Commercial Assets Value", min_value=0,max_value=20000000)
+        luxury_assets_value = st.slider("Luxury Assets Value", min_value=0,max_value=50000000)
+        bank_asset_value = st.slider("Bank Assets Value", min_value=0,max_value=20000000)
+
+        clicked = st.form_submit_button("Loan Approve Prediction")
+        if clicked:
+            result=model.predict(pd.DataFrame({"no_of_dependents": [no_of_dependents],
+                                               "education": [education],
+                                               "self_employed": [self_employed],
+                                               "income_annum": [income_annum],
+                                               "loan_amount": [loan_amount],
+                                               "loan_term": [loan_term],
+                                               "cibil_score": [cibil_score],
+                                               "residential_assets_value": [residential_assets_value],
+                                               "commercial_assets_value": [commercial_assets_value],
+                                               "luxury_assets_value": [luxury_assets_value],
+                                               "bank_asset_value": [bank_asset_value]
+                                              }))
+            result = 'Approved' if result[0] == 1 else 'Declined'
+            st.success('The prediction of loan approval is  {}'.format(result))
+
+if __name__=='__main__':
+    main()

model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aee062cc8cdde4d12a54b73a643d93be3e38f5e60597bce004015eb36e48c24
+size 9662

requirements.txt

@@ -0,0 +1,5 @@
+joblib
+pandas
+scikit-learn== 1.6.1
+LightGBM==1.13.1
+altair<5

unique_values.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6664a7ab1d9d9f7bce93db3a7b97600ffae7eef2d3e52289a325aaaf0e0c9c6c
+size 742