def test_classification(breast_cancer_data):
from sklearn.metrics import roc_auc_score, log_loss
x_train, x_test, y_train, y_test = breast_cancer_data
ngb = NGBClassifier(Dist=Bernoulli, verbose=False)
ngb.fit(x_train, y_train)
preds = ngb.predict(x_test)
score = roc_auc_score(y_test, preds)
# loose score requirement so it isn't failing all the time
assert score >= 0.85
preds = ngb.predict_proba(x_test)
score = log_loss(y_test, preds)
assert score <= 0.30
score = ngb.score(x_test, y_test)
assert score <= 0.30
dist = ngb.pred_dist(x_test)
assert isinstance(dist, Bernoulli)
score = roc_auc_score(y_test, preds[:, 1])
assert score >= 0.85
def test_classification():
from sklearn.datasets import load_breast_cancer
from sklearn.metrics import roc_auc_score, log_loss
data, target = load_breast_cancer(True)
x_train, x_test, y_train, y_test = train_test_split(data,
target,
test_size=0.2,
random_state=42)
ngb = NGBClassifier(Dist=Bernoulli, verbose=False)
ngb.fit(x_train, y_train)
preds = ngb.predict(x_test)
score = roc_auc_score(y_test, preds)
assert score >= 0.95
preds = ngb.predict_proba(x_test)
score = log_loss(y_test, preds)
assert score <= 0.20
score = ngb.score(x_test, y_test)
assert score <= 0.20
dist = ngb.pred_dist(x_test)
assert isinstance(dist, Bernoulli)
score = roc_auc_score(y_test, preds[:, 1])
assert score >= 0.95
def test_bernoulli(learner, breast_cancer_data: Tuple4Array):
X_cls_train, X_cls_test, Y_cls_train, Y_cls_test = breast_cancer_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)
ngb.fit(X_cls_train, Y_cls_train)
y_pred = ngb.predict(X_cls_test)
y_prob = ngb.predict_proba(X_cls_test)
y_dist = ngb.pred_dist(X_cls_test)
def test_categorical(k: int, learner, breast_cancer_data: Tuple4Array):
X_train, X_test, y_train, _ = breast_cancer_data
dist = k_categorical(k)
y_train = np.random.randint(0, k, (len(y_train)))
# test early stopping features
ngb = NGBClassifier(Dist=dist, Score=LogScore, Base=learner, verbose=False)
ngb.fit(X_train, y_train)
y_pred = ngb.predict(X_test)
y_prob = ngb.predict_proba(X_test)
y_dist = ngb.pred_dist(X_test)
def test_bernoulli(self, learners, cls_data): X_cls_train, X_cls_test, Y_cls_train, Y_cls_test = cls_data for Learner in learners: # test early stopping features # test other args, n_trees, LR, minibatching- args as fixture ngb = NGBClassifier(Dist=Bernoulli, Score=LogScore, Base=Learner, verbose=False) ngb.fit(X_cls_train, Y_cls_train) y_pred = ngb.predict(X_cls_test) y_prob = ngb.predict_proba(X_cls_test) y_dist = ngb.pred_dist(X_cls_test)
def test_categorical(self, learners, cls_data): X_cls_train, X_cls_test, Y_cls_train, Y_cls_test = cls_data for K in [2,4,7]: Dist = k_categorical(K) Y_cls_train = np.random.randint(0,K,(len(Y_cls_train))) for Learner in learners: # test early stopping features ngb = NGBClassifier(Dist=Dist, Score=LogScore, Base=Learner, verbose=False) ngb.fit(X_cls_train, Y_cls_train) y_pred = ngb.predict(X_cls_test) y_prob = ngb.predict_proba(X_cls_test) y_dist = ngb.pred_dist(X_cls_test)
import numpy as np
from ngboost import NGBClassifier
from ngboost.distns import Bernoulli
from ngboost.learners import default_tree_learner
from ngboost.scores import MLE
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score
if __name__ == "__main__":
np.random.seed(12345)
X, Y = load_breast_cancer(True)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)
ngb = NGBClassifier(Base=default_tree_learner,
Dist=Bernoulli,
Score=MLE,
verbose=True,
natural_gradient=True)
ngb.fit(X_train, Y_train)
preds = ngb.pred_dist(X_test)
print("ROC:", roc_auc_score(Y_test, preds.prob))
