mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-04 14:47:49 +00:00
Mark Aron Szulyovszky
1cd0119589
* fix(FeatureExtractor): apply log to transform some series to normality * feat(DataLoader): add ability of not returning returns when they're not needed (exogenous data), applied log to certain features * feat(FeatureExtractors): added standard scaling for exogenous data * feat(FeatureSelection): scale data with the passed in scaler before doing feature-selection * fix(Config): sweep config * feat(Models): output probability, store it * feat(Core): added caching to select_features() and load_data() * fix(Dependencies): added diskcache * fix(Training): error when creating results DF * feat(Models): added xgboost, fixed tests * refactor(Cache): moved hashing to a separate function, created wrapper functions to separate business logic and caching * fix(Tests): new syntax * fix(Model): XGboost can't handle -1 class, so we'll use the deprecated label_encoder fornow * fix(Model): XGBoost config * feat(Cache): add run_clear_cache script * fix(Pipeline) accidentally re-instatiating all_predictions for each asset
97 lines
2.4 KiB
Python
97 lines
2.4 KiB
Python
|
|
import numpy as np
|
|
import pandas as pd
|
|
from training.walk_forward import walk_forward_train_test
|
|
from models.base import Model
|
|
from utils.evaluate import evaluate_predictions
|
|
|
|
no_of_rows = 100
|
|
|
|
def __generate_even_odd_test_data(no_of_rows) -> tuple[pd.DataFrame, pd.Series]:
|
|
''' Test data, where X[n][any_column] == 1 if n is even, else 0
|
|
'''
|
|
|
|
no_columns = 6
|
|
X = [[-1 if row % 2 == 0 else 1] * no_columns for row in range(no_of_rows)]
|
|
assert X[0][0] == -1
|
|
assert X[1][0] == 1
|
|
assert X[2][0] == -1
|
|
assert X[3][0] == 1
|
|
X = pd.DataFrame(X)
|
|
|
|
y = [-1 if (row+1) % 2 == 0 else 1 for row in range(no_of_rows)]
|
|
assert y[0] == 1
|
|
assert y[1] == -1
|
|
assert y[2] == 1
|
|
assert y[3] == -1
|
|
|
|
y = pd.Series(y)
|
|
|
|
return X, y
|
|
|
|
class EvenOddStubModel(Model):
|
|
'''
|
|
A deteministic model that can predict the future with 100% accuracy
|
|
It verifies that the X[n][any_column] == 1 if n is even,
|
|
'''
|
|
|
|
data_scaling = "unscaled"
|
|
only_column = None
|
|
|
|
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 y[i] == -1 if X[i][0] == 1 else 1
|
|
|
|
def predict(self, X):
|
|
return (-1 if X[0][0] == 1 else 1, np.array([]))
|
|
|
|
def clone(self):
|
|
return self
|
|
|
|
|
|
def test_evaluation():
|
|
X, y = __generate_even_odd_test_data(no_of_rows)
|
|
|
|
window_length = 10
|
|
|
|
model = EvenOddStubModel(window_length = window_length)
|
|
scaler = None
|
|
|
|
models, predictions, probs = walk_forward_train_test(
|
|
model_name='test',
|
|
model=model,
|
|
X=X,
|
|
y=y,
|
|
target_returns=y,
|
|
expanding_window=False,
|
|
window_size=window_length,
|
|
retrain_every=10,
|
|
scaler=scaler
|
|
)
|
|
|
|
# verify if predictions are the same as y
|
|
for i in range(window_length+2, no_of_rows):
|
|
assert predictions[i] == y[i]
|
|
|
|
fake_target_returns = y * 0.1
|
|
processed_predictions_to_match_returns = predictions * 0.1
|
|
|
|
result = evaluate_predictions(
|
|
model_name='test',
|
|
target_returns=fake_target_returns,
|
|
y_pred=processed_predictions_to_match_returns,
|
|
y_true=y,
|
|
method='classification',
|
|
no_of_classes='two'
|
|
)
|
|
|
|
assert result['accuracy'] == 100.0
|
|
|
|
|
|
|