Dorien

I suppose there are no default settings. That makes sense, but I'm just trying to quickly bulk add TIs for a machine learning project. Would I need to delve up...

Interesting! I had also tried with data from cryptocompare. ```python # !pip install cryptocompare import cryptocompare coin = 'ETH' market = 'USD' hist = cryptocompare.get_historical_price_day(coin) df = pd.DataFrame.from_dict(hist) # time...

Looks like we should all invest immediately lol. The short timeframe may indeed reflect periods of near zero negative volatility. I'll have a look at which time frame sortino is...

I'm looking at the denominator of the sortino ratio, which I think should be using: ` downside_sum_of_squares = (downside[downside < 0] ** 2).sum()` not ` downside_sum_of_squares = (downside[downside > 0]...

Oh just noticed the sign is not the issue as it's preceded by: `downside = adjusted_benchmark_rate - returns` I'll look into the definition that you implemented.

Running into the same issue with Colab. I believe changing `from scipy.misc import factorial` to `from scipy.special import factorial` should do it. Thanks for this library Uri!

It would be nice to have a few lines describing the input format.

I actually see that there is a script to generate the data. Nevertheless, it would be great to see the spoken letters pickle. The generation script seems to be a...

I understand. I was mostly interesting in understanding the structure of the pickle file. On 25 July 2017 at 11:52, Martin Andrews wrote: > I'll add some links to a...

After studying the code for a bit, it seems to be a bit different then I remember from the meetup. I remember something about an SVM to correct errors afterwards,...