Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

speed up tests by loading sample once #341

Merged
merged 1 commit into from
Nov 29, 2023
Merged

speed up tests by loading sample once #341

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 30 additions & 8 deletions tests/test_distns.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,8 @@

import numpy as np
import pytest
from sklearn.datasets import fetch_california_housing, load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeRegressor

from ngboost import NGBClassifier, NGBRegressor, NGBSurvival
Expand Down Expand Up @@ -29,6 +31,26 @@
Tuple4Array = Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]
Tuple5Array = Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray, np.ndarray]

# pylint: disable=redefined-outer-name
@pytest.fixture(scope="module")
def regression_data():
data = fetch_california_housing()
X, y = data["data"][:1000], data["target"][:1000]
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.2, random_state=42
)
return X_train, X_test, y_train, y_test


@pytest.fixture(scope="module")
def classification_data():
data = load_breast_cancer()
X, y = data["data"][:1000], data["target"][:1000]
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.2, random_state=42
)
return X_train, X_test, y_train, y_test


@pytest.mark.slow
@pytest.mark.parametrize(
Expand All @@ -42,8 +64,8 @@
DecisionTreeRegressor(criterion="friedman_mse", max_depth=5),
],
)
def test_dists_runs_on_examples_logscore(dist: Distn, learner, california_housing_data):
X_train, X_test, y_train, y_test = california_housing_data
def test_dists_runs_on_examples_logscore(dist: Distn, learner, regression_data):
X_train, X_test, y_train, y_test = regression_data
# TODO: test early stopping features
ngb = NGBRegressor(Dist=dist, Score=LogScore, Base=learner, verbose=False)
ngb.fit(X_train, y_train)
Expand All @@ -61,8 +83,8 @@ def test_dists_runs_on_examples_logscore(dist: Distn, learner, california_housin
DecisionTreeRegressor(criterion="friedman_mse", max_depth=5),
],
)
def test_dists_runs_on_examples_crpscore(dist: Distn, learner, california_housing_data):
X_train, X_test, y_train, y_test = california_housing_data
def test_dists_runs_on_examples_crpscore(dist: Distn, learner, regression_data):
X_train, X_test, y_train, y_test = regression_data
# TODO: test early stopping features
ngb = NGBRegressor(Dist=dist, Score=CRPScore, Base=learner, verbose=False)
ngb.fit(X_train, y_train)
Expand Down Expand Up @@ -106,8 +128,8 @@ def test_survival_runs_on_examples(
DecisionTreeRegressor(criterion="friedman_mse", max_depth=3),
],
)
def test_bernoulli(learner, breast_cancer_data: Tuple4Array):
X_cls_train, X_cls_test, Y_cls_train, Y_cls_test = breast_cancer_data
def test_bernoulli(learner, classification_data: Tuple4Array):
X_cls_train, X_cls_test, Y_cls_train, Y_cls_test = classification_data
# test early stopping features
# test other args, n_trees, LR, minibatching- args as fixture
ngb = NGBClassifier(Dist=Bernoulli, Score=LogScore, Base=learner, verbose=False)
Expand All @@ -127,8 +149,8 @@ def test_bernoulli(learner, breast_cancer_data: Tuple4Array):
DecisionTreeRegressor(criterion="friedman_mse", max_depth=3),
],
)
def test_categorical(k: int, learner, breast_cancer_data: Tuple4Array):
X_train, X_test, y_train, _ = breast_cancer_data
def test_categorical(k: int, learner, classification_data: Tuple4Array):
X_train, X_test, y_train, _ = classification_data
dist = k_categorical(k)
y_train = np.random.randint(0, k, (len(y_train)))
# test early stopping features
Expand Down
Loading