Update app.py

app.py

@@ -1,33 +1,57 @@
 import streamlit as st
 import pandas as pd
+import joblib  # Import joblib for loading the classifier
+
+# Define a dictionary to map user-friendly labels to integers
+labels_to_int = {
+    "Female": 0,
+    "Male": 1,
+    "Yes": 1,
+    "No": 0,
+    "Never worked": 0,
+    "Children": 1,
+    "Government job": 2,
+    "Self-employed": 3,
+    "Private": 4,
+    "Urban": 0,
+    "Rural": 1,
+    "No Stroke": 0,
+    "Stroke": 1,
+    "ever had": 1,
+    "never had": 0,
+    "married": 1,
+    "single": 0,
+    "never smoked": 0,
+    "smokes": 1
+}
 
 st.title("Data Collection Form")
 
 sex = st.radio("Sex", ["Female", "Male"])
 age = st.number_input("Age", min_value=0)
-hypertension = st.selectbox("Do you have hypertension?", [0, 1])
-heart_disease = st.selectbox("Do you have heart disease?", [0, 1])
-ever_married = st.selectbox("Have you ever been married?", [0, 1])
+hypertension = st.selectbox("Do you have hypertension?", ["No", "Yes"])
+heart_disease = st.selectbox("Do you have heart disease?", ["No", "Yes"])
+ever_married = st.selectbox("Have you ever been married?", ["No", "Yes"])
 work_type = st.selectbox("What is your work type?", ["Never worked", "Children", "Government job", "Self-employed", "Private"])
 residence_type = st.selectbox("What is your residence type?", ["Urban", "Rural"])
 avg_glucose_level = st.number_input("Average Glucose Level", min_value=0.0)
 bmi = st.number_input("BMI", min_value=0.0)
-smoking_status = st.selectbox("What is your smoking status?", [0, 1])
+smoking_status = st.selectbox("What is your smoking status?", ["never smoked", "smokes"])
 
 submit_button = st.button("Submit")
 
 if submit_button:
     data = {
-        "sex": 1 if sex == "Male" else 0,
+        "sex": labels_to_int[sex],
         "age": age,
-        "hypertension": ["ever had", "never had"].index(hypertension),
-        "heart_disease": ["ever had", "never had"].index(heart_disease),
-        "ever_married": ["married","single"].index(ever_married),
-        "work_type": ["Never worked", "Children", "Government job", "Self-employed", "Private"].index(work_type),
-        "residence_type": ["Urban", "Rural"].index(residence_type),
+        "hypertension": labels_to_int[hypertension],
+        "heart_disease": labels_to_int[heart_disease],
+        "ever_married": labels_to_int[ever_married],
+        "work_type": labels_to_int[work_type],
+        "residence_type": labels_to_int[residence_type],
         "avg_glucose_level": avg_glucose_level,
         "bmi": bmi,
-        "smoking_status": ["never smoked", "smokes"].index(smoking_status)
+        "smoking_status": labels_to_int[smoking_status]
     }
 
     df = pd.DataFrame([data])