gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-13 02:48:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore(Linter): reformatted code with black (#211)

Browse Source 
* chore(Linter): reformatted code with black

* Create black.yaml
This commit is contained in:
Mark Aron Szulyovszky
2022-02-17 19:22:17 +01:00
committed by GitHub
parent f3fee4a4e1
commit 8dd2d88740
101 changed files with 2595 additions and 2319 deletions
Download Patch File Download Diff File Expand all files Collapse all files
training/walk_forward/train_parallel.py
+61 -21
View File
@@ -9,46 +9,86 @@ 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:
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)
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':
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 = 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]
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]
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()