mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 11:17:47 +00:00
Mark Aron Szulyovszky
cc70d3f907
* feat(Selection): added prototype feature selection python script * feat(Utils): added some helpers for the future from Advances in Financial ML book * feat(Selection): added RFECV * feat(Selection): added configurable feature selection step into pipeline * feat(Config): added level_1 & level_2 default config, PCA before feature selection process starts * feat(Selection): added backup feature selector models if current one can't output feature importance, removed unnecessary array for level-2 models * fix(Training): deal with zero first value coming out of static models * feat(Sweep): added feature selection sweep * fix(Sweep): config problem * fix(Sweep): config * chore(Utils): removed unnecessary purged k-fold crossval class * feat(Config): added dimensionality_reduction as a separate flag * fix(Sweep): config updated * fix(Sweep): sweep name * chore(Config): updated level_2 config to the best performing configuation
67 lines
2.5 KiB
Python
67 lines
2.5 KiB
Python
import pandas as pd
|
|
from typing import Literal
|
|
from training.walk_forward import walk_forward_train_test
|
|
from sklearn.preprocessing import MinMaxScaler, Normalizer, StandardScaler
|
|
from utils.evaluate import evaluate_predictions
|
|
from models.base import Model
|
|
|
|
def __get_scaler(type: Literal['normalize', 'minmax', 'standardize', 'none']):
|
|
if type == 'normalize':
|
|
return Normalizer()
|
|
elif type == 'minmax':
|
|
return MinMaxScaler(feature_range= (-1, 1))
|
|
elif type == 'standardize':
|
|
return StandardScaler()
|
|
else:
|
|
return None
|
|
|
|
def run_single_asset_trainig(
|
|
ticker_to_predict: str,
|
|
original_X: pd.DataFrame,
|
|
X: pd.DataFrame,
|
|
y: pd.Series,
|
|
target_returns: pd.Series,
|
|
models: list[tuple[str, Model]],
|
|
method: Literal['regression', 'classification'],
|
|
expanding_window: bool,
|
|
sliding_window_size: int,
|
|
retrain_every: int,
|
|
scaler: Literal['normalize', 'minmax', 'standardize', 'none'],
|
|
no_of_classes: Literal['two', 'three-balanced', 'three-imbalanced'],
|
|
level: int
|
|
) -> tuple[pd.DataFrame, pd.DataFrame]:
|
|
|
|
|
|
scaler = __get_scaler(scaler)
|
|
|
|
results = pd.DataFrame()
|
|
predictions = pd.DataFrame()
|
|
|
|
for model_name, model in models:
|
|
model_over_time, preds = walk_forward_train_test(
|
|
model_name=model_name,
|
|
model = model,
|
|
X = X if model.feature_selection == 'on' else original_X,
|
|
y = y,
|
|
target_returns = target_returns,
|
|
expanding_window = expanding_window,
|
|
window_size = sliding_window_size,
|
|
retrain_every = retrain_every,
|
|
scaler = scaler
|
|
)
|
|
assert len(preds) == len(y)
|
|
result = evaluate_predictions(
|
|
model_name = model_name,
|
|
target_returns = target_returns,
|
|
y_pred = preds,
|
|
y_true = y,
|
|
method = method,
|
|
no_of_classes=no_of_classes
|
|
)
|
|
column_name = ticker_to_predict + "_" + model_name + "_lvl" + str(level)
|
|
results[column_name] = result
|
|
# column names for model outputs should be different, so we can differentiate between original data and model predictions later, where necessary
|
|
predictions["model_" + column_name] = preds
|
|
|
|
|
|
return results, predictions |