fetch_stock_data.py

import yfinance as yf
import pandas as pd
from datetime import datetime, timedelta

# The 5 tickers the dashboard covers. Add/remove here only - nothing else
# downstream (Silver, Gold, the ML model) needs to change, since everything
# is keyed off the SERIES_COLNAME (asset_symbol), not a hardcoded list.
TICKERS = ["AAPL", "MSFT", "GOOGL", "AMZN", "NVDA"]


def download_stock_data():
    end_date = datetime(2026, 8, 14)
    start_date = end_date - timedelta(days=365)

    print(f"Downloading {len(TICKERS)} tickers from {start_date:%Y-%m-%d} to {end_date:%Y-%m-%d}...")

    frames = []
    for ticker in TICKERS:
        df = yf.download(ticker, start=start_date.strftime("%Y-%m-%d"), end=end_date.strftime("%Y-%m-%d"))
        if df.empty:
            print(f"  {ticker}: no data returned, skipping")
            continue

        df = df.reset_index()
        df["ticker"] = ticker
        df = df[["ticker", "Date", "Open", "High", "Low", "Close", "Volume"]]
        df.columns = ["ticker", "trade_date", "open_price", "high_price", "low_price", "close_price", "volume"]
        frames.append(df)
        print(f"  {ticker}: {len(df)} rows")

    if not frames:
        print("No data retrieved. Verify network connectivity.")
        return

    combined = pd.concat(frames, ignore_index=True)
    price_columns = ["open_price", "high_price", "low_price", "close_price"]
    combined[price_columns] = combined[price_columns].round(4)

    output_filename = "equities_prices.csv"
    combined.to_csv(output_filename, index=False)
    print(f"Success! {len(combined)} rows across {len(frames)} tickers saved to {output_filename}")


if __name__ == "__main__":
    download_stock_data()