import warnings
warnings.filterwarnings('ignore')
import pandas as pd
import numpy as np
import yfinance as yf

url = 'https://raw.githubusercontent.com/datasets/s-and-p-500-companies/main/data/constituents.csv'
sp500 = pd.read_csv(url)
print(sp500.shape)
print(sp500.head(3))

tickers = ['AAPL','MSFT','GOOGL','AMZN','TSLA']
prices = yf.download(tickers, period='1y', auto_adjust=True, progress=False)
prices = prices['Close'].reset_index()
prices.columns.name = None
print(prices.shape)
print(prices.head(3))

tickers = ['AAPL','MSFT','GOOGL','AMZN','TSLA']
ohlcv = yf.download(tickers, period='1y', auto_adjust=True, progress=False)
ohlcv = ohlcv.stack(future_stack=True).rename_axis(['Date','Ticker']).reset_index()
ohlcv.columns.name = None
print(ohlcv.shape)
print(ohlcv.head(3))

tsla_df = ohlcv[ohlcv['Ticker'] == 'TSLA'].copy()
tsla_df['daily_return'] = tsla_df['Close'].pct_change() * 100
print(tsla_df[['Date','Close','daily_return']].head(7))

aapl_returns = ohlcv[ohlcv['Ticker'] == 'AAPL'].copy()
msft_returns = ohlcv[ohlcv['Ticker'] == 'MSFT'].copy()
aapl_returns['cumulative_return'] = (1 + aapl_returns['Close'].pct_change()).cumprod() - 1
msft_returns['cumulative_return'] = (1 + msft_returns['Close'].pct_change()).cumprod() - 1
print(aapl_returns[['Date','cumulative_return']].tail(3))
print(msft_returns[['Date','cumulative_return']].tail(3))

close_pivot = ohlcv.pivot(index='Date', columns='Ticker', values='Close')
print(close_pivot.shape)
print(close_pivot.head(3))

fundamentals_tickers = ['AAPL','MSFT','GOOGL','AMZN','TSLA','NVDA','META','JPM','JNJ','XOM','WMT','V']
rows = []
for tk in fundamentals_tickers:
    info = yf.Ticker(tk).info
    rows.append({
        'ticker':       tk,
        'sector':       info.get('sector', 'Unknown'),
        'market_cap':   info.get('marketCap'),
        'pe_ratio':     info.get('trailingPE'),
        'eps':          info.get('trailingEps'),
        'profit_margin':info.get('profitMargins'),
        'debt_equity':  info.get('debtToEquity')
    })
fund_df = pd.DataFrame(rows)
print(fund_df.shape)
print(fund_df.head(3))

sector_stats = fund_df.groupby('sector').agg({'market_cap':'mean','pe_ratio':'mean','profit_margin':'mean'}).round(2)
print(sector_stats)

np.random.seed(42)
print('Random seed set to 42 for reproducibility')

portfolio_tickers = ['AAPL','MSFT','GOOGL','AMZN','TSLA','NVDA','META','NFLX','JPM','JNJ']
sector_map = {'AAPL':'Tech','MSFT':'Tech','GOOGL':'Tech','AMZN':'Consumer',
              'TSLA':'Auto','NVDA':'Tech','META':'Tech','NFLX':'Media',
              'JPM':'Finance','JNJ':'Health'}
prices = yf.download(portfolio_tickers, period='1y', auto_adjust=True, progress=False)['Close']
rows = []
for tk in portfolio_tickers:
    buy = round(float(prices[tk].iloc[0]), 2)
    cur = round(float(prices[tk].iloc[-1]), 2)
    shares = int(np.random.randint(5, 100))
    rows.append({'ticker': tk, 'shares': shares, 'buy_price': buy, 'cur_price': cur, 'sector': sector_map[tk]})
portfolio_df = pd.DataFrame(rows)
portfolio_df['gain_pct'] = np.round((portfolio_df['cur_price'] - portfolio_df['buy_price']) / portfolio_df['buy_price'] * 100, 2)
print(portfolio_df.shape)
print(portfolio_df.head(3))

sector_summary = portfolio_df.groupby('sector').agg({'gain_pct':'mean','shares':'sum'})
print(sector_summary)

close_pivot['AAPL_return'] = close_pivot['AAPL'].pct_change()
close_pivot['AAPL_volatility'] = close_pivot['AAPL_return'].rolling(window=21).std() * np.sqrt(252)
close_pivot['AAPL_cum'] = (1 + close_pivot['AAPL_return']).cumprod()
cum_max = close_pivot['AAPL_cum'].cummax()
drawdown = close_pivot['AAPL_cum'] / cum_max - 1
max_drawdown = drawdown.min()
print(f"Annualized volatility: {close_pivot['AAPL_volatility'].iloc[-1]:.4f}")
print(f"Maximum drawdown: {max_drawdown:.2%}")

aapl_data = yf.download('AAPL', period='1y', auto_adjust=True, progress=False)[['Close','Volume']].reset_index()
aapl_data.columns = ['date','close','volume']
aapl_data['sma20'] = aapl_data['close'].rolling(20).mean().round(2)
aapl_data['sma50'] = aapl_data['close'].rolling(50).mean().round(2)
aapl_data['signal'] = np.where(aapl_data['sma20'] > aapl_data['sma50'], 1, -1)
print(aapl_data.tail(3))

nan_count = ohlcv.isna().sum().sum()
print(f'Total missing values in OHLCV data: {nan_count}')
ohlcv_clean = ohlcv.dropna()
print(f'Shape after dropping NaNs: {ohlcv_clean.shape}')

try:
    data = yf.download('ZZZZ_NOT_A_TICKER', period='1y', auto_adjust=True, progress=False)
    print('Data shape:', data.shape)
except Exception as e:
    print('Download failed:', e)

aapl_filtered = ohlcv[ohlcv['Ticker']=='AAPL'][['Date','Close']].reset_index(drop=True)
print(aapl_filtered.head(3))

# Calculate 7-day rolling average closing price for TSLA
tsla_close = ohlcv[ohlcv['Ticker']=='TSLA'].copy()
tsla_close['rolling_avg'] = tsla_close['Close'].rolling(7).mean().round(2)
print(tsla_close[['Date', 'Close', 'rolling_avg']].tail(7))

tech_syms = sp500[sp500['GICS Sector']=='Information Technology']['Symbol'].tolist()[:5]
tech_prices = yf.download(tech_syms, period='1y', auto_adjust=True, progress=False)['Close'].reset_index()
returns = tech_prices[tech_syms].pct_change().mean() * 100
summary = pd.DataFrame({'ticker': tech_syms, 'avg_daily_return_pct': returns.round(3).values})
print(summary)

summary.to_csv('tech_returns_summary.csv', index=False)
print('Results saved to tech_returns_summary.csv')