app.py

import streamlit as st
import pandas as pd
import google.generativeai as genai
import os
from io import StringIO
import csv
from dotenv import load_dotenv


import streamlit as st
import pandas as pd
import google.generativeai as genai
import os
from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()

# Set page configuration first
st.set_page_config(page_title="AI-based Solar Project Estimation Tool", layout="centered")

# Initialize Gemini with the API key loaded from the .env file
api_key = os.getenv("GOOGLE_API_KEY")
if api_key:
    genai.configure(api_key=api_key)
else:
    st.error("API key is missing. Please set the GOOGLE_API_KEY environment variable.")

model = genai.GenerativeModel("gemini-1.5-flash")

# Load solar data
@st.cache_data
def load_data():
    df = pd.read_csv('https://huggingface.co/spaces/MLDeveloper/AI_based_Solar_Project_Estimation_Tool/resolve/main/solar_data_india_2024.csv')
    return df

df = load_data()

# UI - Form for user input
st.title("AI-based Solar Project Estimation Tool")
st.write("### Enter Your Details Below:")

with st.form("solar_form"):
    state_options = df['State'].dropna().unique()
    
    location = st.selectbox("Select your State", options=sorted(state_options))
    roof_size = st.number_input("Enter your roof size (in sq meters)", min_value=1)
    electricity_bill = st.number_input("Enter your monthly electricity bill (₹)", min_value=0)
    
    submitted = st.form_submit_button("Get Estimate")

# Build the prompt for Gemini
def build_prompt(location, roof_size, electricity_bill, ghi, solar_cost_per_kw):
    prompt = f"""
    Estimate the solar system for the location '{location}' based on the following details:
    - Roof size: {roof_size} sq meters
    - Monthly electricity bill: ₹{electricity_bill}
    - Average GHI (solar radiation) for {location}: {ghi} kWh/m²/day
    - Solar system cost per kW in {location}: ₹{solar_cost_per_kw}
    Provide the following:
    1. Estimated solar system size in kW
    2. Estimated daily solar output in kWh
    3. Total system cost in ₹
    4. Monthly savings in ₹
    5. Payback period in years
    """
    return prompt

# Generate the solar project estimate via Gemini
if submitted and location and roof_size > 0 and electricity_bill >= 0:
    state_data = df[df['State'].str.contains(location, case=False)].iloc[0]
    
    if state_data is not None:
        ghi = state_data['Avg_GHI (kWh/m²/day)']
        Solar_Cost_per_kW (₹) = state_data['Solar_Cost_per_kW (₹)']
        
        prompt_text = build_prompt(location, roof_size, electricity_bill, ghi, solar_cost_per_kw)
        
        # Call Gemini API once for all the batch generation
        with st.spinner("Generating solar estimate with Gemini..."):
            response = model.generate_content(prompt_text)
        
        # Display structured output with only the requested points
        st.subheader("Solar Project Estimate")
        
        # Break down the response into structured points
        estimated_data = response.text.strip().split("\n")
        
        # Extract the values for solar system size, cost, savings, and payback period
        values = []
        for point in estimated_data:
            if "solar system size" in point.lower() or "total system cost" in point.lower() or "monthly savings" in point.lower() or "payback period" in point.lower():
                # Extract the values and append to the list
                values.append(point.strip())
        
        # Display the values in 4 lines as requested
        if len(values) == 4:
            st.write(f"1. {values[0]}")
            st.write(f"2. {values[1]}")
            st.write(f"3. {values[2]}")
            st.write(f"4. {values[3]}")
    else:
        st.error("Sorry, the location entered does not match any available data.")
else:
    st.warning("Please fill out all fields to see your solar project estimate.")