mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-01 05:07:47 +00:00
Mark Aron Szulyovszky
3eb3ea94e3
* refactor(Training): added InferenceResult & TrainedModel types * refactor(Pipeline): introduced TrainingOutcome, BetSizingWithMetaOutcome, etc. * fix(Pipeline): getting it to compile * refactor(WalkForward): separate preprocessing step * feat(Pipeline): separate out transformations processing step * refactor(Pipeline): use the Directional model terminology, put bet_sizing into pipeline instead of hiding it in a step * refactor(WalkForward): moved functions to separate folder * fix(WalkForward): use sparse array to store models, process transformations in parallel (lot faster) * fix(Tests): and evaluation * fix(Tests): for realz * fix(Inference): preloading everything now, renamed primary models to directional models * fix(BetSizing): was running transformations on the wrong data, oops * fix(BetSizing): concatenated on the wrong axis accidentally * fix(Reporting): able to use the new Stats type * fix(BetSizing): renamed int column names * fix(Portfolio): name the column properly * fix(Reporting): rename the correct Series, lol * fix(Inference): walk_forwad_inference() can deal with models not being aligned with the starting index * fix(WalkForward): accidentally using the wrong index * fix(WalkForward): use the correct indicies to fetch last model/transformations * fix(CI): changed the name of the results
93 lines
2.3 KiB
Python
93 lines
2.3 KiB
Python
import numpy as np
|
|
import pandas as pd
|
|
from training.walk_forward import walk_forward_train, walk_forward_inference
|
|
from models.base import Model
|
|
|
|
no_of_rows = 100
|
|
|
|
def __generate_incremental_test_data(no_of_rows) -> tuple[pd.DataFrame, pd.Series]:
|
|
''' Test data, where X[n][any_column] == y[n]+1
|
|
'''
|
|
|
|
no_columns = 6
|
|
X = [[row] * no_columns for row in range(no_of_rows)]
|
|
assert X[1][0] == 1
|
|
assert X[2][0] == 2
|
|
assert X[3][0] == 3
|
|
assert X[4][0] == 4
|
|
X = pd.DataFrame(X)
|
|
|
|
y = [row+1 for row in range(no_of_rows)]
|
|
assert y[1] == 2
|
|
assert y[2] == 3
|
|
assert y[3] == 4
|
|
y = pd.Series(y)
|
|
|
|
return X, y
|
|
|
|
|
|
|
|
class IncrementingStubModel(Model):
|
|
'''
|
|
A deteministic model that can predict the future with 100% accuracy
|
|
It verifies that the X[n][any_column]+1 == y[n]
|
|
'''
|
|
|
|
data_transformation = "original"
|
|
only_column = None
|
|
predict_window_size = 'single_timestamp'
|
|
|
|
|
|
def __init__(self, window_length) -> None:
|
|
super().__init__()
|
|
self.window_length = window_length
|
|
|
|
def fit(self, X, y):
|
|
assert len(X) == self.window_length
|
|
for i in range(len(X)):
|
|
assert X[i][0] + 1 == y[i]
|
|
|
|
def predict(self, X):
|
|
return (X[0][0] + 1, np.array([]))
|
|
|
|
def clone(self):
|
|
return self
|
|
|
|
def initialize_network(self, input_dim: int, output_dim: int):
|
|
pass
|
|
|
|
def test_walk_forward_train_test():
|
|
X, y = __generate_incremental_test_data(no_of_rows)
|
|
|
|
window_length = 10
|
|
retrain_every = 10
|
|
|
|
model = IncrementingStubModel(window_length = window_length)
|
|
|
|
model_over_time = walk_forward_train(
|
|
model=model,
|
|
X=X,
|
|
y=y,
|
|
forward_returns=y,
|
|
expanding_window=False,
|
|
window_size=window_length,
|
|
retrain_every=retrain_every,
|
|
from_index=None,
|
|
transformations_over_time=[],
|
|
)
|
|
predictions, _ = walk_forward_inference(
|
|
model_name='test',
|
|
model_over_time=model_over_time,
|
|
transformations_over_time=[],
|
|
X=X,
|
|
expanding_window=False,
|
|
window_size=window_length,
|
|
retrain_every=retrain_every,
|
|
from_index=None,
|
|
)
|
|
|
|
# verify if predictions are the same as y
|
|
for i in range(window_length+2, no_of_rows):
|
|
assert predictions[i] == y[i]
|
|
|