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

# BEGINNER EXAMPLE 1: Download multi-ticker OHLCV stock data in long format
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))

# BEGINNER EXAMPLE 2: Get closing prices in wide format
tickers = ['AAPL','MSFT','GOOGL','AMZN','TSLA']
df = yf.download(tickers, period='1y', auto_adjust=True, progress=False)
df = df['Close'].reset_index()
df.columns.name = None
print(df.shape)
print(df.head(3))

# BEGINNER EXAMPLE 3: Loading the S&P 500 companies master list
url = 'https://raw.githubusercontent.com/datasets/s-and-p-500-companies/main/data/constituents.csv'
sp500_companies = pd.read_csv(url)
print(sp500_companies.shape)
print(sp500_companies.head(3))

# INTERMEDIATE EXAMPLE 1: Compute daily percentage returns for SPY ETF
data = yf.download('SPY', period='2y', auto_adjust=True, progress=False)
spy = data[['Close', 'Volume']].reset_index()
spy.columns = ['date','price','volume']
spy['daily_return'] = (spy['price'].pct_change() * 100).round(4)
spy = spy.dropna().reset_index(drop=True)
print(spy.shape)
print(spy.head(3))

# INTERMEDIATE EXAMPLE 2: Pivoting multi-ticker OHLCV data to wide format for close prices
close_wide = ohlcv.pivot(index='Date', columns='Ticker', values='Close')
print(close_wide.shape)
print(close_wide.head(3))

# INTERMEDIATE EXAMPLE 3: Select and compare a single ticker from long format
aapl = ohlcv[ohlcv['Ticker'] == 'AAPL']
print(aapl.head(3))

# ADVANCED EXAMPLE 1: Compute moving averages and generate trading signals
data = yf.download('AAPL', period='1y', auto_adjust=True, progress=False)
df = data[['Close','Volume']].reset_index()
df.columns = ['date','close','volume']
df['sma20'] = df['close'].rolling(20).mean().round(2)
df['sma50'] = df['close'].rolling(50).mean().round(2)
df['signal'] = np.where(df['sma20'] > df['sma50'], 1, -1)
print(df.tail(3))

# ADVANCED EXAMPLE 2: Build a portfolio from 10 stocks and calculate percent gain
np.random.seed(42)  # For reproducibility
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'}
data = yf.download(tickers, period='1y', auto_adjust=True, progress=False)['Close']
rows = []
for tk in tickers:
    buy = round(float(data[tk].iloc[0]), 2)
    cur = round(float(data[tk].iloc[-1]), 2)
    rows.append({'ticker': tk, 'shares': int(np.random.randint(5, 100)),
                 'buy_price': buy, 'cur_price': cur, 'sector': sector_map[tk]})
df_port = pd.DataFrame(rows)
df_port['gain_pct'] = np.round((df_port['cur_price'] - df_port['buy_price']) / df_port['buy_price'] * 100, 2)
print(df_port.head(3))

# ADVANCED EXAMPLE 3: Fetch real financial fundamentals for leading stocks
tickers = ['AAPL','MSFT','GOOGL','AMZN','TSLA','NVDA','META','JPM','JNJ','XOM','WMT','V']
rows = []
for tk in 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')
    })
df_fund = pd.DataFrame(rows)
print(df_fund.head(3))

# ERROR HANDLING 1: What happens if a ticker is removed from S&P 500 list?
missing = sp500_companies[sp500_companies['Symbol'] == 'TWTR']
if missing.empty:
    print('TWTR is not in the current S&P 500 list.')
else:
    print(missing)

# ERROR HANDLING 2: Handling missing values when merging datasets
x = ohlcv.merge(sp500_companies, left_on='Ticker', right_on='Symbol', how='left')
n_missing = x['Security'].isna().sum()
print(f'Missing company matches: {n_missing}')

# ERROR HANDLING 3: Check for NaN in fundamentals and fill as needed
n_na = df_fund['debt_equity'].isna().sum()
print(f'{n_na} companies have missing debt-to-equity ratios.')
df_fund['debt_equity'] = df_fund['debt_equity'].fillna(-1)

# BEST PRACTICES: Always sort portfolios by percent gain before display
df_port_sorted = df_port.sort_values('gain_pct', ascending=False).reset_index(drop=True)
print(df_port_sorted.head(5))

# BEST PRACTICES: Always reset seeds if using simulated numbers
np.random.seed(42)
example_shares = np.random.randint(5, 100, size=5)
print("Random share example (should be reproducible):", example_shares)

# END-TO-END CASE: Analyze AAPL performance vs sector peers over one year
apple = ohlcv[ohlcv['Ticker'] == 'AAPL'].copy()
techs = ['AAPL', 'MSFT', 'GOOGL']
tech_df = ohlcv[ohlcv['Ticker'].isin(techs)]
apple['return'] = apple['Close'].pct_change() * 100
peers = tech_df.pivot(index='Date', columns='Ticker', values='Close')
peers_ret = peers.pct_change() * 100
avg_peer = peers_ret[['MSFT', 'GOOGL']].mean(axis=1)
import matplotlib.pyplot as plt
plt.figure(figsize=(10,4))
plt.plot(apple['Date'], apple['return'], label='AAPL daily return', alpha=0.6)
plt.plot(apple['Date'], avg_peer.values, label='MSFT/GOOGL mean', alpha=0.6)
plt.title('AAPL vs Tech Peer Daily Returns (1yr)')
plt.ylabel('% daily return')
plt.xlabel('Date')
plt.legend()
plt.tight_layout()
plt.show()

# BONUS: Export your end-to-end analysis as a CSV file for reporting
export_df = pd.DataFrame({'date': apple['Date'], 'aapl_return': apple['return'], 'peer_avg_return': avg_peer.values})
export_df.to_csv('aapl_vs_peers_returns.csv', index=False)
print('Exported CSV shape:', export_df.shape)