def test_same_predictions_classification(seed, min_samples_leaf, n_samples,
max_leaf_nodes):
# Same as test_same_predictions_regression but for classification
rng = np.random.RandomState(seed=seed)
n_samples = n_samples
max_iter = 1
max_bins = 256
X, y = make_classification(n_samples=n_samples,
n_classes=2,
n_features=5,
n_informative=5,
n_redundant=0,
random_state=0)
if n_samples > 255:
# bin data and convert it to float32 so that the estimator doesn't
# treat it as pre-binned
X = BinMapper(max_bins=max_bins).fit_transform(X).astype(np.float32)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=rng)
est_pygbm = GradientBoostingClassifier(loss='binary_crossentropy',
max_iter=max_iter,
max_bins=max_bins,
learning_rate=1,
n_iter_no_change=None,
min_samples_leaf=min_samples_leaf,
max_leaf_nodes=max_leaf_nodes)
est_lightgbm = get_lightgbm_estimator(est_pygbm)
est_lightgbm.fit(X_train, y_train)
est_pygbm.fit(X_train, y_train)
# We need X to be treated an numerical data, not pre-binned data.
X_train, X_test = X_train.astype(np.float32), X_test.astype(np.float32)
pred_lightgbm = est_lightgbm.predict(X_train)
pred_pygbm = est_pygbm.predict(X_train)
assert np.mean(pred_pygbm == pred_lightgbm) > .89
acc_lgbm = accuracy_score(y_train, pred_lightgbm)
acc_pygbm = accuracy_score(y_train, pred_pygbm)
np.testing.assert_almost_equal(acc_lgbm, acc_pygbm)
if max_leaf_nodes < 10 and n_samples >= 1000:
pred_lightgbm = est_lightgbm.predict(X_test)
pred_pygbm = est_pygbm.predict(X_test)
assert np.mean(pred_pygbm == pred_lightgbm) > .89
acc_lgbm = accuracy_score(y_test, pred_lightgbm)
acc_pygbm = accuracy_score(y_test, pred_pygbm)
np.testing.assert_almost_equal(acc_lgbm, acc_pygbm, decimal=2)
def test_same_predictions_classification(seed, min_samples_leaf, n_samples,
max_leaf_nodes):
# Same as test_same_predictions_regression but for classification
rng = np.random.RandomState(seed=seed)
n_samples = n_samples
max_iter = 1
max_bins = 256
X, y = make_classification(n_samples=n_samples,
n_classes=2,
n_features=5,
n_informative=5,
n_redundant=0,
random_state=0)
if n_samples > 255:
X = BinMapper(max_bins=max_bins).fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=rng)
est_pygbm = GradientBoostingClassifier(loss='binary_crossentropy',
max_iter=max_iter,
max_bins=max_bins,
learning_rate=1,
validation_split=None,
scoring=None,
min_samples_leaf=min_samples_leaf,
max_leaf_nodes=max_leaf_nodes)
est_lightgbm = get_lightgbm_estimator(est_pygbm)
est_lightgbm.fit(X_train, y_train)
est_pygbm.fit(X_train, y_train)
pred_lightgbm = est_lightgbm.predict(X_train)
pred_pygbm = est_pygbm.predict(X_train)
assert np.mean(pred_pygbm == pred_lightgbm) > .89
acc_lgbm = accuracy_score(y_train, pred_lightgbm)
acc_pygbm = accuracy_score(y_train, pred_pygbm)
np.testing.assert_almost_equal(acc_lgbm, acc_pygbm)
if max_leaf_nodes < 10 and n_samples >= 1000:
pred_lightgbm = est_lightgbm.predict(X_test)
pred_pygbm = est_pygbm.predict(X_test)
assert np.mean(pred_pygbm == pred_lightgbm) > .89
acc_lgbm = accuracy_score(y_test, pred_lightgbm)
acc_pygbm = accuracy_score(y_test, pred_pygbm)
np.testing.assert_almost_equal(acc_lgbm, acc_pygbm, decimal=2)
n_samples, n_features = data_train.shape
print(f"Training set with {n_samples} records with {n_features} features.")
print("JIT compiling code for the pygbm model...")
tic = time()
pygbm_model = GradientBoostingClassifier(learning_rate=lr,
max_iter=1,
max_bins=max_bins,
max_leaf_nodes=n_leaf_nodes,
random_state=0,
scoring=None,
verbose=0,
validation_split=None)
pygbm_model.fit(data_train[:100], target_train[:100])
pygbm_model.predict(data_train[:100]) # prediction code is also jitted
toc = time()
print(f"done in {toc - tic:.3f}s")
print("Fitting a pygbm model...")
tic = time()
pygbm_model = GradientBoostingClassifier(loss='binary_crossentropy',
learning_rate=lr,
max_iter=n_trees,
max_bins=max_bins,
max_leaf_nodes=n_leaf_nodes,
random_state=0,
scoring=None,
verbose=1,
validation_split=None)
pygbm_model.fit(data_train, target_train)
def test_same_predictions_multiclass_classification(seed, min_samples_leaf,
n_samples, max_leaf_nodes):
# Same as test_same_predictions_regression but for classification
rng = np.random.RandomState(seed=seed)
n_samples = n_samples
max_iter = 1
max_bins = 256
lr = 1
X, y = make_classification(n_samples=n_samples,
n_classes=3,
n_features=5,
n_informative=5,
n_redundant=0,
n_clusters_per_class=1,
random_state=0)
if n_samples > 255:
X = BinMapper(max_bins=max_bins).fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=rng)
est_pygbm = GradientBoostingClassifier(loss='categorical_crossentropy',
max_iter=max_iter,
max_bins=max_bins,
learning_rate=lr,
validation_split=None,
scoring=None,
min_samples_leaf=min_samples_leaf,
max_leaf_nodes=max_leaf_nodes)
est_lightgbm = get_lightgbm_estimator(est_pygbm)
est_lightgbm.fit(X_train, y_train)
est_pygbm.fit(X_train, y_train)
pred_lightgbm = est_lightgbm.predict(X_train)
pred_pygbm = est_pygbm.predict(X_train)
assert np.mean(pred_pygbm == pred_lightgbm) > .89
proba_lightgbm = est_lightgbm.predict_proba(X_train)
proba_pygbm = est_pygbm.predict_proba(X_train)
# assert more than 75% of the predicted probabilities are the same up to
# the second decimal
assert np.mean(np.abs(proba_lightgbm - proba_pygbm) < 1e-2) > .75
acc_lgbm = accuracy_score(y_train, pred_lightgbm)
acc_pygbm = accuracy_score(y_train, pred_pygbm)
np.testing.assert_almost_equal(acc_lgbm, acc_pygbm, decimal=2)
if max_leaf_nodes < 10 and n_samples >= 1000:
pred_lightgbm = est_lightgbm.predict(X_test)
pred_pygbm = est_pygbm.predict(X_test)
assert np.mean(pred_pygbm == pred_lightgbm) > .89
proba_lightgbm = est_lightgbm.predict_proba(X_train)
proba_pygbm = est_pygbm.predict_proba(X_train)
# assert more than 75% of the predicted probabilities are the same up
# to the second decimal
assert np.mean(np.abs(proba_lightgbm - proba_pygbm) < 1e-2) > .75
acc_lgbm = accuracy_score(y_test, pred_lightgbm)
acc_pygbm = accuracy_score(y_test, pred_pygbm)
np.testing.assert_almost_equal(acc_lgbm, acc_pygbm, decimal=2)