Closed yingh2013 closed 2 years ago
it can run if I use None as input parameter for factor_returns. then I found that benchmark1 has short history than returns history. so, here is what I did:
mask = returns.index.intersection(benchmark.index) returns1 = returns[mask] benchmark1 = benchmark[mask]
plot_rolling_returns(returns1, factor_returns=benchmark1, live_start_date=LIVE_DATE, logy=False, cone_std=2, legend_loc='best', volatility_match=False, cone_function=forecast_cone_bootstrap, ax=axes[0])
Problem Description
https://github.com/stefan-jansen/machine-learning-for-trading/blob/main/18_convolutional_neural_nets/08_backtesting_with_zipline.ipynb
plot_rolling_returns: Passing list-likes to .loc or [] with any missing labels is no longer supported.
Please provide a minimal, self-contained, and reproducible example:
Please provide the full traceback:
Please provide any additional information below:
Versions