Update app.py

app.py

@@ -1,64 +1,27 @@
-import streamlit as st
-import pickle
+mport streamlit as st
 import pandas as pd
+import joblib
 
-# Load the trained models
-rf_fullstk = pickle.load(open('rf_hacathon_fullstk.pkl', 'rb'))
-rf_prodengg = pickle.load(open('rf_hacathon_prodengg.pkl', 'rb'))
-rf_mkt = pickle.load(open('rf_hacathon_mkt.pkl', 'rb'))
+# Load the pre-trained model
 
-# Define the function for prediction
-def predict_placement(degree_p, internship, DSA, java, management, leadership, communication, sales, model):
-    data = pd.DataFrame({
-        'degree_p': degree_p,
-        'internship': internship,
-        'DSA': DSA,
-        'java': java,
-        'management': management,
-        'leadership': leadership,
-        'communication': communication,
-        'sales': sales
-    }, index=[0])
-    prediction = model.predict(data)[0]
-    probability = model.predict_proba(data)[0][1]
-    return prediction, probability
-
-# Create the Streamlit app
-def main():
-    st.title("Placement Prediction App")
-    st.sidebar.title("Options")
-    options = ["Full Stack Engineer", "Marketing", "Production Engineer"]
-    job_role = st.sidebar.selectbox("Select Job Role", options)
-
-    degree_p = st.slider("Degree Percentage", 0, 100, 50)
-    internship = st.radio("Internship", ["Yes", "No"])
-    DSA = st.radio("DSA Knowledge", [0, 1])
-    java = st.radio("Java Knowledge", [0, 1])
+# Define the input widgets
+age = st.slider('Age', 18, 99, 25)
+gender = st.selectbox('Gender', ['Male', 'Female'])
+smoker = st.selectbox('Smoker', ['Yes', 'No'])
+region = st.selectbox('Region', ['Northeast', 'Northwest', 'Southeast', 'Southwest'])
+bmi = st.number_input('BMI', min_value=10.0, max_value=50.0, step=0.1)
 
-    if job_role == "Full Stack Engineer":
-        management = st.slider("Management Skills", 0, 5, 0)
-        leadership = st.slider("Leadership Skills", 0, 5, 0)
-        communication = st.slider("Communication Skills", 0, 5, 0)
-        sales = st.slider("Sales Skills", 0, 5, 0)
-        prediction, probability = predict_placement(degree_p, internship, DSA, java, management, leadership, communication, sales, rf_fullstk)
-    elif job_role == "Marketing":
-        management = st.slider("Management Skills", 0, 5, 0)
-        leadership = st.slider("Leadership Skills", 0, 5, 0)
-        DSA = st.slider("DSA Knowledge", 0, 5, 0)
-        java = st.slider("Java Knowledge", 0, 5, 0)
-        prediction, probability = predict_placement(degree_p, internship, DSA, java, management, leadership, communication, sales, rf_mkt)
-    elif job_role == "Production Engineer":
-        communication = st.slider("Communication Skills", 0, 5, 0)
-        sales = st.slider("Sales Skills", 0, 5, 0)
-        management = st.slider("Management Skills", 0, 5, 0)
-        leadership = st.slider("Leadership Skills", 0, 5, 0)
-        prediction, probability = predict_placement(degree_p, internship, DSA, java, management, leadership, communication, sales, rf_prodengg)
-
-    if prediction == 1:
-        st.success("Placed")
-        st.success(f"You will be placed with a probability of {probability:.2f}")
-    else:
-        st.warning("Not Placed")
+# Define a function to make the prediction
+def predict(age, gender, smoker, region, bmi):
+    data = pd.DataFrame({'age': [age],
+                         'sex': [gender],
+                         'smoker': [smoker],
+                         'region': [region],
+                         'bmi': [bmi]})
+    prediction = model.predict(data)[0]
+    return prediction
 
-if __name__ == '__main__':
-    main()
+# Call the predict function and display the result
+if st.button('Predict'):
+    result = predict(age, gender, smoker, region, bmi)
+    st.write('The predicted insurance cost is $', round(result, 2))