def test_cls(self):
np.random.seed(1)
n_samples = 10000
test_size = 0.2
n_est = 100
max_depth = 7
lr = 0.1
X, y = make_hastie_11_2(n_samples)
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=test_size)
model_palo = PaloBoost(distribution="bernoulli",
n_estimators=n_est,
learning_rate=lr,
max_depth=max_depth)
model_sklr = GradientBoostingClassifier(
n_estimators=n_est,
learning_rate=lr,
max_depth=max_depth)
model_palo.fit(X_train, y_train)
y_hat = model_palo.predict_proba(X_test)[:,1]
auc_palo = roc_auc_score(y_test, y_hat)
model_sklr.fit(X_train, y_train)
y_hat = model_sklr.predict_proba(X_test)[:,1]
auc_sklr = roc_auc_score(y_test, y_hat)
self.assertTrue(auc_palo > auc_sklr)
def fit(self, X, y):
np.random.seed(self.random_state)
n, m = X.shape
idx = np.arange(n)
self.estimators = []
if (self.distribution == "bernoulli"
and (np.sum(y) < 3 or np.sum(y) > n - 3)):
logging.error(("the target (y) needs to have "
"at least one examples on each class"))
return None
i = 0
while i < self.n_paloboost:
mask = np.full(n, True)
if self.block_size is not None:
n_block = int(n / self.block_size) + 1
mask_block = (np.random.rand(n_block) < self.subsample0)
mask = np.repeat(mask_block, self.block_size)[:n]
else:
mask = (np.random.rand(n) < self.subsample0)
X_i, y_i = X[mask, :], y[mask]
X_j, y_j = X[~mask, :], y[~mask]
if (self.distribution == "bernoulli"
and (np.unique(y_i).shape[0] == 1
or np.unique(y_j).shape[0] == 1)):
continue
est = PaloBoost(distribution=self.distribution,
learning_rate=self.learning_rate,
max_depth=self.max_depth,
n_estimators=self.n_estimators,
subsample=self.subsample1,
subsample_splts=self.subsample2,
random_state=i * self.n_estimators)
est.fit(X_i, y_i)
self.estimators.append(est)
if self.feature_importances_ is None:
self.feature_importances_ = est.feature_importances_
else:
self.feature_importances_ += est.feature_importances_
if (self.distribution == "bernoulli" and self.calibrate):
z_j = est.predict_proba(X_j)[:, 1]
clb = IsotonicRegression(y_min=0,
y_max=1,
out_of_bounds="clip")
clb.fit(z_j, y_j)
self.calibrators.append(clb)
i += 1
self.feature_importances_ /= self.n_paloboost