import streamlit as st
import pandas as pd
import numpy as np
import math
import matplotlib.pyplot as plt
import numpy_financial as npf
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
from reportlab.lib.pagesizes import A4
from reportlab.lib.styles import getSampleStyleSheet

# ===============================
# PAGE CONFIG
# ===============================
st.set_page_config(layout="wide")
st.title("🇵🇰 AI Solar Intelligence Platform (Ultra Premium)")

# ===============================
# ADVANCED CONFIG
# ===============================

SYSTEM_LOSSES = 0.20
DEMAND_FACTOR_INDUSTRIAL = 0.75

CITY_IRRADIANCE_INDEX = {
    "Karachi": 6.2,
    "Lahore": 5.5,
    "Islamabad": 5.2,
    "Peshawar": 5.6,
    "Quetta": 6.5,
}

# Pricing
PANEL_COST_PER_WATT = 55
INSTALLATION_COST_PER_WATT = 35
BATTERY_COST_5KWH = 95000

# Appliance Database (Expanded)
LOAD_LIBRARY = {
    "Home": {
        "Lighting": 60,
        "Fans": 400,
        "Fridge": 200,
        "AC": 1500
    },
    "Industrial": {
        "Motors": 5000,
        "Compressors": 8000,
        "CNC Machines": 2000
    }
}

# ===============================
# AI RECOMMENDATION ENGINE
# ===============================

def ai_solar_recommendation(load_kw, sunlight):
    optimal_system = (load_kw / sunlight) * 1.2
    return round(optimal_system, 2)

def financial_projection(cost, daily_kwh):
    cashflows = []
    for year in range(1, 26):
        price_escalation = (1 + 0.07) ** year
        savings = daily_kwh * 30 * 55 * price_escalation
        cashflows.append(savings * 12)

    npv = npf.npv(0.05, [-cost] + cashflows)
    irr = npf.irr([-cost] + cashflows)

    payback = next((i for i, cf in enumerate(np.cumsum(cashflows), 1)
                    if cf >= cost), None)

    return cashflows, npv, irr, payback, np.cumsum(cashflows)

# ===============================
# USER INPUT LAYER
# ===============================

user_type = st.selectbox(
    "Select Client Type",
    ["Homeowner", "Commercial Business", "Industrial Investor"]
)

city = st.selectbox("Select City", list(CITY_IRRADIANCE_INDEX.keys()))
sunlight = CITY_IRRADIANCE_INDEX[city]

# Load Selection
if user_type == "Homeowner":
    load_choice = st.multiselect(
        "Select Home Loads",
        ["Lighting", "Fans", "Fridge", "AC"]
    )
elif user_type == "Commercial Business":
    load_choice = st.multiselect(
        "Select Business Loads",
        ["Lighting", "Computers", "AC", "Machinery"]
    )
else:
    load_choice = st.multiselect(
        "Select Industrial Loads",
        ["Motors", "Compressors", "CNC Machines"]
    )

hours = st.slider("Daily Usage Hours", 1, 24, 8)

# ===============================
# CALCULATIONS
# ===============================

if st.button("🚀 Run AI Solar Analysis"):

    if len(load_choice) == 0:
        st.error("Please select at least one load")
    else:

        # Load estimation
        load_watts = 0

        for item in load_choice:
            if item in ["Lighting", "Fans"]:
                load_watts += 200
            elif item == "Fridge":
                load_watts += 200
            elif item == "AC":
                load_watts += 1500
            elif item in ["Motors", "Compressors", "CNC Machines"]:
                load_watts += 3000

        daily_kwh = (load_watts * hours) / 1000
        daily_kwh = daily_kwh / (1 - SYSTEM_LOSSES)

        # AI Recommendation
        system_kw = ai_solar_recommendation(daily_kwh, sunlight)

        system_cost = system_kw * 1000 * (PANEL_COST_PER_WATT + INSTALLATION_COST_PER_WATT)

        # Financials
        cashflows, npv, irr, payback, cumulative = financial_projection(system_cost, daily_kwh)

        # Results Display
        st.subheader("📊 AI Analysis Results")

        st.write(f"Recommended Solar System Size: {system_kw} kW")
        st.write(f"Daily Energy Consumption: {round(daily_kwh,2)} kWh")
        st.write(f"Estimated Installation Cost: PKR {round(system_cost):,}")
        st.write(f"NPV (25 Years): PKR {round(npv,2):,}")
        st.write(f"IRR: {round(irr*100,2)} %")
        st.write(f"Payback Period: {payback} Years")

        # Charts
        st.subheader("📈 Investment Growth Projection")

        plt.figure(figsize=(10,4))
        plt.plot(range(1,26), cumulative)
        plt.axhline(system_cost, linestyle="--")
        st.pyplot(plt)

        # WhatsApp Style Summary
        st.subheader("📱 Proposal Summary")

        summary_text = f"""
        Solar Proposal Summary

        City: {city}
        Recommended System: {system_kw} kW
        Cost Estimate: PKR {round(system_cost):,}
        Payback Period: {payback} Years
        IRR: {round(irr*100,2)}%
        """

        st.text_area("Copy for WhatsApp / Proposal", summary_text, height=200)