mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-27 18:57:55 +00:00
Mark Aron Szulyovszky
b5ddee8dce
* feat(HPO): added `run_hpo` script * fix(Linter): ran * feat(HPO): removed any reference to sweep (superseeded by optuna) * fix(HPO): optimize for sharpe * fix(Config): removed glassnode data, save trials from hpo * feat(Labelling): added three-balanced method works again * fix(BetSizing): set the correct class labels * fix(HPO): powerset should return what's expected, added two new normalization methods * fix(Linter): ran * fix(DataLoader): sort the dataframe when fetching data * fix(Config): only take z-score of other assets
61 lines
2.1 KiB
Python
61 lines
2.1 KiB
Python
from ..types import EventLabeller, EventsDataFrame, ReturnSeries
|
|
import pandas as pd
|
|
from .utils import create_forward_returns
|
|
from typing import Callable
|
|
|
|
|
|
class FixedTimeHorionThreeClassImbalancedEventLabeller(EventLabeller):
|
|
|
|
time_horizon: int
|
|
|
|
def __init__(self, time_horizon: int):
|
|
self.time_horizon = time_horizon
|
|
|
|
def label_events(
|
|
self, event_start_times: pd.DatetimeIndex, returns: ReturnSeries
|
|
) -> EventsDataFrame:
|
|
|
|
forward_returns = create_forward_returns(returns, self.time_horizon)
|
|
cutoff_point = returns.index[-self.time_horizon]
|
|
event_start_times = event_start_times[event_start_times < cutoff_point]
|
|
event_candidates = forward_returns[event_start_times]
|
|
|
|
def get_bins_threeway(x):
|
|
bins = pd.qcut(event_candidates, 4, retbins=True, duplicates="drop")[1]
|
|
|
|
if len(bins) != 5:
|
|
# if we don't have enough data for the quantiles, we'll need to add hard-coded values
|
|
lower_bound = bins[0]
|
|
upper_bound = bins[-1]
|
|
bins = [lower_bound] + [-0.02, 0.0, 0.02] + [upper_bound]
|
|
return bins
|
|
|
|
bins = get_bins_threeway(event_candidates)
|
|
|
|
def map_class_threeway(current_value):
|
|
lower_threshold = bins[1]
|
|
upper_threshold = bins[3]
|
|
if current_value <= lower_threshold:
|
|
return -1
|
|
elif current_value > lower_threshold and current_value < upper_threshold:
|
|
return 0
|
|
else:
|
|
return 1
|
|
|
|
labels = event_candidates.map(map_class_threeway)
|
|
events = pd.DataFrame(
|
|
{
|
|
"start": event_start_times,
|
|
"end": event_start_times + pd.Timedelta(minutes=self.time_horizon * 5),
|
|
"label": labels,
|
|
"returns": forward_returns[event_start_times],
|
|
}
|
|
)
|
|
return events
|
|
|
|
def get_labels(self) -> list[int]:
|
|
return [-1, 0, 1]
|
|
|
|
def get_discretize_function(self) -> Callable:
|
|
return discretize_threeway_threshold(0.02)
|