mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 03:08:01 +00:00
Mark Aron Szulyovszky
9d47ee942d
* feat(Project): use 5 minute data, running training in parallel, sped up cusum filter by 10x with numba * fix(WalkForward): inference mini-batch parallelization * fix(WalkForward): don't use the parallel version of any of the functions * feat(CI): download the data required * fix(Project): 5min_crypto folder added * fix(Evaluate): make sure we have numerical stability in returns * feat(Models): use SKLearn models directly to enable composability * feat(Inference): batched inference now working, added forecasting_horizon * fix(Inference): works again * fix(Inference) * chore(Models): remove unused Ensemble model * fix(Labeller): don't just forward shift returns, also take the sum of the data happened until then * Update test.yml
59 lines
2.6 KiB
Python
59 lines
2.6 KiB
Python
import pandas as pd
|
|
from models.base import Model
|
|
from training.types import ModelOverTime, TransformationsOverTime
|
|
from utils.helpers import get_first_valid_return_index
|
|
from tqdm import tqdm
|
|
from typing import Optional
|
|
from data_loader.types import ForwardReturnSeries, XDataFrame, ySeries
|
|
import ray
|
|
from utils.parallel import parallel_compute_with_bar
|
|
from copy import deepcopy
|
|
|
|
def walk_forward_train(
|
|
model: Model,
|
|
X: XDataFrame,
|
|
y: ySeries,
|
|
forward_returns: ForwardReturnSeries,
|
|
expanding_window: bool,
|
|
window_size: int,
|
|
retrain_every: int,
|
|
from_index: Optional[pd.Timestamp],
|
|
transformations_over_time: TransformationsOverTime,
|
|
) -> ModelOverTime:
|
|
models_over_time = pd.Series(index=y.index).rename(model.name)
|
|
|
|
first_nonzero_return = max(get_first_valid_return_index(forward_returns), get_first_valid_return_index(X.iloc[:,0]), get_first_valid_return_index(y))
|
|
train_from = first_nonzero_return + window_size + 1 if from_index is None else X.index.to_list().index(from_index)
|
|
train_till = len(y)
|
|
|
|
if model.only_column is not None:
|
|
X = X[[column for column in X.columns if model.only_column in column]]
|
|
|
|
if model.data_transformation == 'original':
|
|
transformations_over_time = []
|
|
|
|
models = parallel_compute_with_bar([train_on_window.remote(index, first_nonzero_return, window_size, X, y, model, expanding_window, transformations_over_time) for index in tqdm(range(train_from, train_till, retrain_every))])
|
|
for index, current_model in models:
|
|
models_over_time[X.index[index]] = current_model
|
|
|
|
return models_over_time
|
|
|
|
@ray.remote
|
|
def train_on_window(index: int, first_nonzero_return: int, window_size: int, X: XDataFrame, y: ySeries, model: Model, expanding_window: bool, transformations_over_time: TransformationsOverTime) -> tuple[int, Model]:
|
|
train_window_start = X.index[first_nonzero_return] if expanding_window else X.index[index - window_size - 1]
|
|
|
|
train_window_end = X.index[index - 1]
|
|
current_transformations = [transformation_over_time[index] for transformation_over_time in transformations_over_time]
|
|
X_slice = X[train_window_start:train_window_end]
|
|
|
|
for transformation in current_transformations:
|
|
X_slice = transformation.transform(X_slice)
|
|
|
|
X_slice = X_slice.to_numpy()
|
|
y_slice = y[train_window_start:train_window_end].to_numpy()
|
|
|
|
current_model = deepcopy(model)
|
|
|
|
current_model.fit(X_slice, y_slice)
|
|
return index, model
|