def test_xgboost_classification(self):
"""Test that sklearn models can learn on simple classification datasets."""
np.random.seed(123)
dataset = sklearn.datasets.load_digits(n_class=2)
X, y = dataset.data, dataset.target
frac_train = .7
n_samples = len(X)
n_train = int(frac_train * n_samples)
X_train, y_train = X[:n_train], y[:n_train]
X_test, y_test = X[n_train:], y[n_train:]
train_dataset = dc.data.NumpyDataset(X_train, y_train)
test_dataset = dc.data.NumpyDataset(X_test, y_test)
classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score)
esr = {'early_stopping_rounds': 50}
xgb_model = xgboost.XGBClassifier(n_estimators=50, seed=123)
model = dc.models.XGBoostModel(xgb_model, verbose=False, **esr)
# Fit trained model
model.fit(train_dataset)
model.save()
# Eval model on test
scores = model.evaluate(test_dataset, [classification_metric])
assert scores[classification_metric.name] > .9
def model_builder(model_dir_xgb):
xgboost_model = xgboost.XGBClassifier(
max_depth=max_depth,
learning_rate=learning_rate,
n_estimators=n_estimators,
gamma=gamma,
min_child_weight=min_child_weight,
max_delta_step=max_delta_step,
subsample=subsample,
colsample_bytree=colsample_bytree,
colsample_bylevel=colsample_bylevel,
reg_alpha=reg_alpha,
reg_lambda=reg_lambda,
scale_pos_weight=scale_pos_weight,
base_score=base_score,
seed=seed)
return deepchem.models.xgboost_models.XGBoostModel(
xgboost_model, model_dir_xgb, **esr)