gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-15 20:08:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(WalkForward): major bug where we passed in "window of windows of data" is resolved, refactored walk_forward_train_test() and load_data()

Browse Source
This commit is contained in:
Mark Aron Szulyovszky
2021-12-14 21:07:03 +01:00
parent d047b7417e
commit 1ef314c034
7 changed files with 131 additions and 302 deletions
Download Patch File Download Diff File Expand all files Collapse all files
model_walk_forward.py
+38 -86
View File
@@ -3,7 +3,7 @@ from typing import Literal
from sklearnex import patch_sklearn
patch_sklearn()
from load_data import create_target_cum_forward_returns, load_files, create_target_classes
from load_data import create_target_cum_forward_returns, load_data, create_target_classes
from sktime.forecasting.model_selection import temporal_train_test_split
from utils.evaluate import evaluate_predictions_regression, evaluate_predictions_classification
@@ -21,79 +21,42 @@ from sklearn.ensemble import AdaBoostRegressor, RandomForestRegressor, ExtraTree
from sklearn.metrics import r2_score, mean_absolute_error, confusion_matrix, classification_report, accuracy_score
from sklearn.preprocessing import MinMaxScaler
from utils.sliding_window import sliding_window_and_flatten
def walk_forward_train_test(
model_name: str,
create_model,
X: pd.DataFrame,
y: pd.Series,
window_size: int,
retrain_every: int
):
print("Training: ", model_name)
predictions = [None] * (len(y)-1)
models = [None] * len(predictions)
train_from = window_size+1
train_till = len(y)-2
iterations_since_retrain = 0
for i in range(train_from, train_till):
# if i % 20 == 0: print('Fold: ', i)
iterations_since_retrain += 1
window_start = i - window_size
window_end = i
X_train_slice = X[window_start:window_end]
y_train_slice = y[window_start:window_end]
if iterations_since_retrain >= retrain_every or models[i-1] is None:
model = create_model()
model.fit(X_train_slice, y_train_slice)
iterations_since_retrain = 0
else:
model = models[i-1]
models[window_end] = model
predictions[window_end+1] = model.predict(X[window_end+1].reshape(1, -1)).item()
return models, predictions
from utils.walk_forward import walk_forward_train_test
regression_models = [
('LR', lambda: LinearRegression(n_jobs=-1)),
('BayesianRidge', lambda: BayesianRidge()),
('KNN', lambda: KNeighborsRegressor(n_neighbors=15)),
('MLP', lambda: MLPRegressor(hidden_layer_sizes=(100,20), max_iter=1000)),
('AB', lambda: AdaBoostRegressor()),
('LR', LinearRegression(n_jobs=-1)),
('BayesianRidge', BayesianRidge()),
('KNN', KNeighborsRegressor(n_neighbors=15)),
# ('MLP', MLPRegressor(hidden_layer_sizes=(100,20), max_iter=1000)),
('AB', AdaBoostRegressor()),
# ('RF', lambda: RandomForestRegressor(n_jobs=-1)),
('SVR', lambda: SVR(kernel='rbf', C=1e3, gamma=0.1))
('SVR', SVR(kernel='rbf', C=1e3, gamma=0.1))
]
classification_models = [
('LR', lambda: LogisticRegression(n_jobs=-1)),
('LDA', lambda: LinearDiscriminantAnalysis()),
('KNN', lambda: KNeighborsClassifier()),
('CART', lambda: DecisionTreeClassifier()),
('NB', lambda: GaussianNB()),
('AB', lambda: AdaBoostClassifier()),
('RF', lambda: RandomForestClassifier(n_jobs=-1))
('LR', LogisticRegression(n_jobs=-1)),
('LDA', LinearDiscriminantAnalysis()),
('KNN', KNeighborsClassifier()),
('CART', DecisionTreeClassifier()),
('NB', GaussianNB()),
('AB', AdaBoostClassifier()),
('RF', RandomForestClassifier(n_jobs=-1))
]
def run_whole_pipeline(
ticker_to_predict: str,
models,
method: Literal['regression', 'classification'],
sliding_window_size: int,
retrain_every: int,
):
ticker_to_predict: str,
models,
method: Literal['regression', 'classification'],
sliding_window_size: int,
retrain_every: int,
scaling: bool,
):
print('Predicting: ', ticker_to_predict)
data = load_files(path='data/',
own_asset=ticker_to_predict,
own_asset_lags=[1,2,3,4,5,6,8,10,15],
X, y = load_data(path='data/',
target_asset=ticker_to_predict,
target_asset_lags=[1,2,3,4,5,6,8,10,15],
load_other_assets=False,
other_asset_lags=[],
log_returns=True,
@@ -101,34 +64,21 @@ def run_whole_pipeline(
own_technical_features='level2',
other_technical_features='none',
exogenous_features='none',
index_column='int'
index_column='int',
method=method,
)
target_col = 'target'
returns_col = ticker_to_predict + '_returns'
if method == 'regression':
data = create_target_cum_forward_returns(data, returns_col, 1)
elif method == 'classification':
data = create_target_classes(data, returns_col, 1, 'two')
X = data.drop(columns=[target_col])
y = data[target_col]
if scaling:
# TODO: should move scaling to an expanding window compomenent
feature_scaler = MinMaxScaler(feature_range= (-1, 1))
X = pd.DataFrame(feature_scaler.fit_transform(X), columns=X.columns, index=X.index)
# TODO: should scale y as well probably
# TODO: should move scaling to an expanding window compomenent
feature_scaler = MinMaxScaler(feature_range= (-1, 1))
X = feature_scaler.fit_transform(X)
# TODO: should scale y as well probably
X = sliding_window_and_flatten(X, sliding_window_size)
y = y[sliding_window_size-1:]
for model_name, create_model in models:
for model_name, model in models:
model_over_time, preds = walk_forward_train_test(
model_name=model_name,
create_model = create_model,
model = model,
X = X,
y = y,
window_size = sliding_window_size,
@@ -146,12 +96,14 @@ run_whole_pipeline(
models = regression_models,
method = 'regression',
sliding_window_size = 120,
retrain_every = 50
retrain_every = 50,
scaling=False
)
run_whole_pipeline(
ticker_to_predict = ticker_to_predict,
models = classification_models,
method = 'classification',
sliding_window_size = 120,
retrain_every = 50
retrain_every = 50,
scaling=False
)