import streamlit as st
import requests

# -----------------------------
# Page Configuration
# -----------------------------
st.set_page_config(
    page_title="ExtraaLearn | Lead Conversion Predictor",
    page_icon="🎓",
    layout="centered"
)

# -----------------------------
# App Header
# -----------------------------
st.title("🎓 ExtraaLearn Lead Conversion Prediction")
st.markdown(
    """
    This application predicts whether a **lead is likely to convert**
    into a **paid customer** based on their interaction and engagement data.
    """
)

st.divider()

# -----------------------------
# Lead Details Input
# -----------------------------
st.subheader("📋 Lead Information")

lead_id = st.text_input("Lead ID")

age = st.number_input("Age", min_value=18, max_value=70, value=30)

current_occupation = st.selectbox(
    "Current Occupation",
    ["Professional", "Unemployed", "Student"]
)

first_interaction = st.selectbox(
    "First Interaction Channel",
    ["Website", "Mobile App"]
)

profile_completed = st.selectbox(
    "Profile Completion Level",
    ["Low", "Medium", "High"]
)

website_visits = st.number_input(
    "Number of Website Visits",
    min_value=0,
    value=5
)

time_spent_on_website = st.number_input(
    "Total Time Spent on Website (seconds)",
    min_value=0,
    value=600
)

page_views_per_visit = st.number_input(
    "Average Page Views per Visit",
    min_value=0.0,
    value=3.0
)

last_activity = st.selectbox(
    "Last Activity Type",
    ["Email Activity", "Phone Activity", "Website Activity"]
)

st.subheader("📣 Marketing Touchpoints")

print_media_type1 = st.selectbox(
    "Seen Newspaper Advertisement?",
    ["No", "Yes"]
)

print_media_type2 = st.selectbox(
    "Seen Magazine Advertisement?",
    ["No", "Yes"]
)

digital_media = st.selectbox(
    "Seen Digital Advertisement?",
    ["No", "Yes"]
)

educational_channels = st.selectbox(
    "Heard via Educational Channels?",
    ["No", "Yes"]
)

referral = st.selectbox(
    "Heard via Referral?",
    ["No", "Yes"]
)

# -----------------------------
# Prepare Payload
# -----------------------------
payload = {
    "ID": lead_id,
    "age": age,
    "current_occupation": current_occupation,
    "first_interaction": first_interaction,
    "profile_completed": profile_completed,
    "website_visits": website_visits,
    "time_spent_on_website": time_spent_on_website,
    "page_views_per_visit": page_views_per_visit,
    "last_activity": last_activity,
    "print_media_type1": 1 if print_media_type1 == "Yes" else 0,
    "print_media_type2": 1 if print_media_type2 == "Yes" else 0,
    "digital_media": 1 if digital_media == "Yes" else 0,
    "educational_channels": 1 if educational_channels == "Yes" else 0,
    "referral": 1 if referral == "Yes" else 0
}

# -----------------------------
# Prediction Button
# -----------------------------
if st.button("🔍 Predict Lead Conversion", type="primary"):
    try:
        response = requests.post(
            "https://ankitasml-extraalearn.hf.space/v1/predict",
            json=payload,
            timeout=10
        )

        if response.status_code == 200:
            result = response.json()

            prediction = result["prediction"]
            probability = result["probability"]

            st.divider()
            st.subheader("📊 Prediction Result")

            if prediction == 1:
                st.success(
                    f"✅ **Lead is likely to convert**\n\n"
                    f"📈 Conversion Probability: **{probability*100:.2f}%**"
                )
            else:
                st.warning(
                    f"⚠️ **Lead is unlikely to convert**\n\n"
                    f"📉 Conversion Probability: **{probability*100:.2f}%**"
                )

        else:
            st.error("❌ API Error: Unable to fetch prediction.")

    except Exception as e:
        st.error(f"🚨 Connection Error: {e}")

# -----------------------------
# Footer
# -----------------------------
st.divider()
st.caption("🔐 Internal Use | ExtraaLearn Lead Analytics")