utils/data_loader.py

import yfinance as yf
import pandas as pd
import streamlit as st
import requests
import json
from datetime import datetime, timedelta

# 🌟 Deepseek API Configuration
DEEPSEEK_API_KEY = "sk-d52b48c40d494fb88acee4e20e881240"
DEEPSEEK_API_URL = "https://api.deepseek.com/v1/analyze"

# 🛠 Cache timeout set to 10 minutes (600 seconds) to reduce API calls
@st.cache_data(ttl=600)
def load_nifty50_symbols():
    """Load Nifty 50 and additional stocks categorized by sectors"""
    symbols = {
        "IT": ["TCS.NS", "INFY.NS", "HCLTECH.NS", "TECHM.NS", "WIPRO.NS", "MPHASIS.NS", "LTIM.NS"],
        "Banking & Finance": [
            "HDFCBANK.NS", "ICICIBANK.NS", "SBIN.NS", "AXISBANK.NS", "KOTAKBANK.NS",
            "BAJFINANCE.NS", "BAJAJFINSV.NS", "HDFC.NS", "INDUSINDBK.NS", "IDFCFIRSTB.NS", "PNB.NS"
        ],
        "Energy & Oil": ["RELIANCE.NS", "ONGC.NS", "POWERGRID.NS", "NTPC.NS", "BPCL.NS", "GAIL.NS", "IOC.NS"],
        "Automobile": ["TATAMOTORS.NS", "M&M.NS", "MARUTI.NS", "HEROMOTOCO.NS", "EICHERMOT.NS", "TVSMOTOR.NS"],
        "Consumer Goods": ["HINDUNILVR.NS", "ITC.NS", "NESTLEIND.NS", "BRITANNIA.NS", "TITAN.NS", "DABUR.NS"],
        "Metals & Mining": ["TATASTEEL.NS", "HINDALCO.NS", "JSWSTEEL.NS", "COALINDIA.NS", "NMDC.NS"],
        "Pharmaceuticals": ["SUNPHARMA.NS", "DRREDDY.NS", "CIPLA.NS", "DIVISLAB.NS", "LUPIN.NS"],
        "Infrastructure & Realty": ["LT.NS", "ADANIPORTS.NS", "ULTRACEMCO.NS", "SHREECEM.NS", "DLF.NS", "IRCTC.NS"],
        "Telecom": ["BHARTIARTL.NS", "IDEA.NS", "RELIANCE.NS"],
        "Others": ["ASIANPAINT.NS", "HDFCLIFE.NS", "SBILIFE.NS", "UPL.NS", "ADANIENT.NS", "DMART.NS"]
    }
    return symbols

@st.cache_data(ttl=600)
def fetch_stock_data(symbol, period='1y', interval="1d"):
    """Fetch stock data from Yahoo Finance"""
    try:
        stock = yf.Ticker(symbol)
        data = stock.history(period=period, interval=interval)
        return data
    except Exception as e:
        st.error(f"⚠️ Error fetching data for {symbol}: {str(e)}")
        return None

@st.cache_data(ttl=600)
def get_stock_info(symbol):
    """Get stock information"""
    try:
        stock = yf.Ticker(symbol)
        info = stock.info
        return {
            'name': info.get('longName', symbol),
            'sector': info.get('sector', 'N/A'),
            'market_cap': info.get('marketCap', 0),
            'pe_ratio': info.get('trailingPE', 0),
            'volume': info.get('volume', 0),
            'recommendation': info.get('recommendationKey', 'N/A'),
            'target_price': info.get('targetMeanPrice', 0)
        }
    except Exception as e:
        st.error(f"⚠️ Error fetching info for {symbol}: {str(e)}")
        return None

def analyze_with_deepseek(stock_symbol, data):
    """Send stock data to Deepseek AI for analysis and prediction"""
    try:
        if data is None or data.empty:
            return "⚠️ No data available for analysis."
        
        # Prepare payload
        payload = {
            "api_key": DEEPSEEK_API_KEY,
            "stock_symbol": stock_symbol,
            "historical_data": data.to_dict(orient="records"),
        }

        headers = {
            "Content-Type": "application/json"
        }

        response = requests.post(DEEPSEEK_API_URL, headers=headers, data=json.dumps(payload))
        response_data = response.json()

        if response.status_code == 200:
            return response_data.get("prediction", "No prediction available.")
        else:
            return f"⚠️ Error: {response_data.get('error', 'Unknown error occurred')}"
    
    except Exception as e:
        return f"⚠️ Deepseek API Error: {str(e)}"

def process_uploaded_file(uploaded_file):
    """Process uploaded CSV/Excel file"""
    try:
        if uploaded_file.name.endswith('.csv'):
            df = pd.read_csv(uploaded_file)
        elif uploaded_file.name.endswith(('.xls', '.xlsx')):
            df = pd.read_excel(uploaded_file)
        else:
            raise ValueError("⚠️ Unsupported file format")

        # Ensure required columns exist
        required_columns = ['Date', 'Open', 'High', 'Low', 'Close', 'Volume']
        if not all(col in df.columns for col in required_columns):
            raise ValueError("⚠️ Missing required columns")

        # Convert Date column to datetime
        df['Date'] = pd.to_datetime(df['Date'])
        return df
    except Exception as e:
        st.error(f"⚠️ Error processing file: {str(e)}")
        return None

def get_stock_suggestions(data):
    """Generate stock suggestions based on technical indicators and Deepseek AI"""
    try:
        # Simple moving averages
        data['SMA20'] = data['Close'].rolling(window=20).mean()
        data['SMA50'] = data['Close'].rolling(window=50).mean()

        # Get latest values
        current_price = data['Close'].iloc[-1]
        sma20 = data['SMA20'].iloc[-1]
        sma50 = data['SMA50'].iloc[-1]

        # Generate suggestion
        if sma20 > sma50:
            trend = "BULLISH"
            suggestion = "📈 Consider buying. Price is above moving averages."
        elif sma20 < sma50:
            trend = "BEARISH"
            suggestion = "📉 Consider selling. Price is below moving averages."
        else:
            trend = "NEUTRAL"
            suggestion = "➡️ Market is sideways. Wait for a clear trend."

        deepseek_analysis = analyze_with_deepseek("Custom Data", data)

        return {
            'trend': trend,
            'suggestion': suggestion,
            'current_price': current_price,
            'sma20': sma20,
            'sma50': sma50,
            'deepseek_analysis': deepseek_analysis
        }
    except Exception as e:
        st.error(f"⚠️ Error generating suggestions: {str(e)}")
        return None