guardrailed-llm-agent — Step 2: Getting the Data Right (snippet 1)

step_2_getting_the_data_right_1.py

import yfinance as yf
import pandas as pd, numpy as np

# auto_adjust=True ensures prices are split- and dividend-adjusted.
# AAPL split 7-for-1 in 2014 and 4-for-1 in 2020. Without adjustment,
# those days show fake -86% and -75% returns that corrupt every feature.
df = yf.download(SYMBOL, start=START, auto_adjust=True, progress=False)

if isinstance(df.columns, pd.MultiIndex):
    df = df.droplevel(-1, axis=1)   # flatten multi-level columns
df.index = pd.to_datetime(df.index)