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

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))

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))

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))

aapl = ohlcv[ohlcv['Ticker'] == 'AAPL'].copy()
print(aapl.isna().sum())
aapl = aapl.dropna()
print('Remaining rows after dropna:', len(aapl))

price_df = df.copy()
price_df['AAPL_ret'] = price_df['AAPL'].pct_change() * 100
print(price_df[['Date','AAPL','AAPL_ret']].head())
nan_count = price_df['AAPL_ret'].isna().sum()
print('Missing daily returns:', nan_count)

meta = sp500[['Symbol','GICS Sector']].rename(columns={'Symbol':'Ticker','GICS Sector':'Sector'})
aug_ohlcv = ohlcv.merge(meta, how='left', on='Ticker')
print(aug_ohlcv[['Date','Ticker','Close','Sector']].head(3))
print('Rows with missing sector:', aug_ohlcv['Sector'].isna().sum())

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'}
np.random.seed(42)
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))

big_tickers = ['AAPL','MSFT','GOOGL','AMZN','TSLA','NVDA','META','JPM','JNJ','XOM','WMT','V']
rows = []
for tk in big_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)
n_missing = fund_df.isnull().sum()
fund_df['debt_equity'] = fund_df['debt_equity'].fillna(-1)
print(n_missing)
print(fund_df.head(3))

wide = ohlcv.pivot(index='Date', columns='Ticker', values='Close')
print(wide.head(3))
print('NaN count per ticker:')
print(wide.isnull().sum())

if 'Close' not in ohlcv.columns:
    print('Error: Close column missing from dataset!')
else:
    print('Close column present - safe to proceed.')

before = wide.shape[0]
wide_clean = wide.dropna(how='any')
after = wide_clean.shape[0]
print(f'Removed {before - after} rows with missing data.')

# Save your cleaned OHLCV data for future modeling or sharing
save_path = 'cleaned_ohlcv.csv'
aug_ohlcv.to_csv(save_path, index=False)
print(f'File saved: {save_path}')

# Pivot long OHLCV data to wide format by close price
returns_wide = ohlcv.pivot(index='Date', columns='Ticker', values='Close')
# Compute daily percent returns for every ticker
returns = returns_wide.pct_change() * 100
# Drop first row (NaNs from pct_change), then all rows with any missing values
returns = returns.dropna().reset_index()
print(returns.head(3))
print(f'Final shape for portfolio modeling: {returns.shape}')