Oleg Polakow

It's quite simple. Given you want to build a machine learning model that predicts market movements (which is tough, but who knows). The question is what exactly do you want...

Use [IndicatorFactory.from_apply_func](https://polakowo.io/vectorbt/docs/indicators/factory.html#vectorbt.indicators.factory.IndicatorFactory.from_apply_func). I will update the indicator docs soon to provide more examples. Edit: If you want to contribute it, add it to `vectorbt.indicators.contrib` and make a PR.

hyperopt takes a function, a space of hyperparameters, and slowly searches for the best parameters in that space. It has the advantage of having different optimization algorithms such as Bayesian....

There are notebooks that show how to optimize per time frame, asset, and other dimensions. Then you can go further and reduce the space based on your optimization function. Each...

Yes, on a basic walk-forward optimization, in a few days.

What exactly is not implemented, and how is portfolio optimization not similar? Please be more specific.

Grouping data by day and selecting the latest available price would do the trick: ```python from datetime import datetime sr = pd.Series([1, 2, 3, 4, 5, 6], index=pd.to_datetime([ datetime(2021, 1,...

To make it vectorized you need to build a separate column per each hour on the last day. ```python import pandas as pd from datetime import datetime sr = pd.Series([1,...

p1 and p2 are two different parameters. The difference between both functions is that in from_custom_func you’re receiving a list of values per each parameter and you’re responsible for concatenating...

That's because indicator is passing all input arrays as 2-d numpy arrays rather than pandas series/dataframes, and pandas_ta requires them to be of pandas type. This will work: ```python def...