add all files

app.py

@@ -0,0 +1,54 @@
+import pandas as pd
+import streamlit as st
+import numpy as np
+import joblib
+import warnings
+warnings.filterwarnings("ignore")
+
+model = joblib.load("model.pkl")
+scaler = joblib.load("scaler.pkl")
+col = joblib.load("columns.pkl")
+
+st.set_page_config(page_title="Insurance charges prediction",page_icon="🪙")
+
+st.title("Insurance charges prediction 📜💸")
+
+age = st.slider("Age",17,100,50)
+sex = st.selectbox("Gender",["female","male"])
+bmi = st.slider("BMI",1.0,30.0,10.0)
+chid = st.number_input("Children",0,10,2)
+smo = st.selectbox("Smoker",["yes","no"])
+reg = st.selectbox("Region",['southwest', 'southeast', 'northwest', 'northeast'])
+# reg = st.selectbox("Region",[0,1])
+bmi_cat = st.selectbox("BMI categor obese",[0,1])
+
+if(sex == "female"):
+    sex = 1
+else:
+    sex = 0
+if(smo == "yes"):
+    smo = 1
+else:
+    smo = 0
+if(reg == "southeast"):
+    reg = 1
+else:
+    reg = 0
+
+if st.button("predic"):
+    user_df = pd.DataFrame([{
+        "age":age,
+        "is_female":sex,
+        "bmi":bmi,
+        "children":chid,
+        "is_smoker" :smo,
+        "region_southeast":reg,
+        "bmi_category_Obese":bmi_cat
+    }]) 
+    c = ["age","bmi","children"]
+    user_df[c] = scaler.transform(user_df[c])
+    prediction = model.predict(user_df)[0]
+    pred = round(prediction,2)
+    # print(prediction)
+    st.success(f"Your insurance charges prediction is ₹ {pred}")
+

columns.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb30a212025bd870582199c083d178a53807c0aab166246f68fec1316c3f523
+size 103

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:320122568bd155ac54ff454a04997b481a27ff48575c4660ffae6d1d300ce328
+size 1009

scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99dbf247a2c4e8be343712fdcdfd26c2594f280f14264e2a0d24dae788686bad
+size 943