def testLocalClassifierFromToParquet(self):
n_rows = 1000
n_columns = 10
rs = np.random.RandomState(0)
X = rs.rand(n_rows, n_columns)
y = rs.rand(n_rows)
df = pd.DataFrame(X, columns=[f'c{i}' for i in range(n_columns)])
df['id'] = [f'i{i}' for i in range(n_rows)]
booster = xgboost.train({}, xgboost.DMatrix(X, y), num_boost_round=2)
with tempfile.TemporaryDirectory() as d:
m_name = os.path.join(d, 'c.model')
result_dir = os.path.join(d, 'result')
os.mkdir(result_dir)
data_dir = os.path.join(d, 'data')
os.mkdir(data_dir)
booster.save_model(m_name)
df.iloc[:500].to_parquet(os.path.join(d, 'data', 'data1.parquet'))
df.iloc[500:].to_parquet(os.path.join(d, 'data', 'data2.parquet'))
df = md.read_parquet(data_dir).set_index('id')
model = XGBClassifier()
model.load_model(m_name)
result = model.predict(df, run=False)
r = md.DataFrame(result).to_parquet(result_dir)
# tiles to ensure no iterative tiling exists
g = r.build_graph(tiled=True)
self.assertTrue(all(isinstance(n.op, Fuse) for n in g))
self.assertEqual(len(g), 2)
r.execute()
ret = md.read_parquet(result_dir).to_pandas().iloc[:, 0].to_numpy()
model2 = xgboost.XGBClassifier()
model2.load_model(m_name)
expected = model2.predict(X)
expected = np.stack([1 - expected, expected]).argmax(axis=0)
np.testing.assert_array_equal(ret, expected)
def testDistributedXGBClassifier(self):
service_ep = 'http://127.0.0.1:' + self.web_port
timeout = 120 if 'CI' in os.environ else -1
with new_session(service_ep) as sess:
run_kwargs = {'timeout': timeout}
X, y = self.X, self.y
y = (y * 10).astype(mt.int32)
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X,
y,
eval_set=[(X, y)],
session=sess,
run_kwargs=run_kwargs)
prediction = classifier.predict(X,
session=sess,
run_kwargs=run_kwargs)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
history = classifier.evals_result()
self.assertIsInstance(prediction, mt.Tensor)
self.assertIsInstance(history, dict)
self.assertEqual(list(history)[0], 'validation_0')
self.assertEqual(list(history['validation_0'])[0], 'merror')
self.assertEqual(len(history['validation_0']), 1)
self.assertEqual(len(history['validation_0']['merror']), 2)
def test_local_classifier(setup):
y = (y_raw * 10).astype(mt.int32)
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X_raw, y, eval_set=[(X_raw, y)])
prediction = classifier.predict(X_raw)
assert prediction.ndim == 1
assert prediction.shape[0] == len(X_raw)
history = classifier.evals_result()
assert isinstance(prediction, mt.Tensor)
assert isinstance(history, dict)
assert list(history)[0] == 'validation_0'
# default metrics may differ, see https://github.com/dmlc/xgboost/pull/6183
eval_metric = list(history['validation_0'])[0]
assert eval_metric in ('merror', 'mlogloss')
assert len(history['validation_0']) == 1
assert len(history['validation_0'][eval_metric]) == 2
prob = classifier.predict_proba(X_raw)
assert prob.shape == X_raw.shape
# test dataframe
X_df = X_df_raw
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X_df, y)
prediction = classifier.predict(X_df)
assert prediction.ndim == 1
assert prediction.shape[0] == len(X_raw)
# test weight
weights = [
mt.random.rand(X_raw.shape[0]),
md.Series(mt.random.rand(X_raw.shape[0])),
md.DataFrame(mt.random.rand(X_raw.shape[0]))
]
y_df = md.DataFrame(y)
for weight in weights:
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X_raw, y_df, sample_weights=weight)
prediction = classifier.predict(X_raw)
assert prediction.ndim == 1
assert prediction.shape[0] == len(X_raw)
# should raise error if weight.ndim > 1
with pytest.raises(ValueError):
XGBClassifier(verbosity=1,
n_estimators=2).fit(X_raw,
y_df,
sample_weights=mt.random.rand(1, 1))
# test binary classifier
new_y = (y > 0.5).astype(mt.int32)
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X_raw, new_y)
prediction = classifier.predict(X_raw)
assert prediction.ndim == 1
assert prediction.shape[0] == len(X_raw)
# test predict data with unknown shape
X2 = X_raw[X_raw[:, 0] > 0.1].astype(mt.int32)
prediction = classifier.predict(X2)
assert prediction.ndim == 1
# test train with unknown shape
cond = X_raw[:, 0] > 0
X3 = X_raw[cond]
y3 = y[cond]
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X3, y3)
prediction = classifier.predict(X_raw)
assert prediction.ndim == 1
assert prediction.shape[0] == len(X_raw)
classifier = XGBClassifier(verbosity=1, n_estimators=2)
with pytest.raises(TypeError):
classifier.fit(X_raw, y, wrong_param=1)
classifier.fit(X_raw, y)
with pytest.raises(TypeError):
classifier.predict(X_raw, wrong_param=1)
def testLocalClassifier(self):
X, y = self.X, self.y
y = (y * 10).astype(mt.int32)
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X, y, eval_set=[(X, y)])
prediction = classifier.predict(X)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
history = classifier.evals_result()
self.assertIsInstance(prediction, mt.Tensor)
self.assertIsInstance(history, dict)
self.assertEqual(list(history)[0], 'validation_0')
# default metrics may differ, see https://github.com/dmlc/xgboost/pull/6183
eval_metric = list(history['validation_0'])[0]
self.assertIn(eval_metric, ('merror', 'mlogloss'))
self.assertEqual(len(history['validation_0']), 1)
self.assertEqual(len(history['validation_0'][eval_metric]), 2)
prob = classifier.predict_proba(X)
self.assertEqual(prob.shape, X.shape)
# test dataframe
X_df = self.X_df
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X_df, y)
prediction = classifier.predict(X_df)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
# test weight
weights = [
mt.random.rand(X.shape[0]),
md.Series(mt.random.rand(X.shape[0])),
md.DataFrame(mt.random.rand(X.shape[0]))
]
y_df = md.DataFrame(self.y)
for weight in weights:
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X, y_df, sample_weights=weight)
prediction = classifier.predict(X)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
# should raise error if weight.ndim > 1
with self.assertRaises(ValueError):
XGBClassifier(verbosity=1,
n_estimators=2).fit(X,
y_df,
sample_weights=mt.random.rand(
1, 1))
# test binary classifier
new_y = (self.y > 0.5).astype(mt.int32)
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X, new_y)
prediction = classifier.predict(X)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
# test predict data with unknown shape
X2 = X[X[:, 0] > 0.1].astype(mt.int32)
prediction = classifier.predict(X2)
self.assertEqual(prediction.ndim, 1)
# test train with unknown shape
cond = X[:, 0] > 0
X3 = X[cond]
y3 = y[cond]
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X3, y3)
prediction = classifier.predict(X)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
classifier = XGBClassifier(verbosity=1, n_estimators=2)
with self.assertRaises(TypeError):
classifier.fit(X, y, wrong_param=1)
classifier.fit(X, y)
with self.assertRaises(TypeError):
classifier.predict(X, wrong_param=1)
def testLocalClassifier(self):
X, y = self.X, self.y
y = (y * 10).astype(mt.int32)
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X, y, eval_set=[(X, y)])
prediction = classifier.predict(X)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
history = classifier.evals_result()
self.assertIsInstance(prediction, mt.Tensor)
self.assertIsInstance(history, dict)
self.assertEqual(list(history)[0], 'validation_0')
self.assertEqual(list(history['validation_0'])[0], 'merror')
self.assertEqual(len(history['validation_0']), 1)
self.assertEqual(len(history['validation_0']['merror']), 2)
prob = classifier.predict_proba(X)
self.assertEqual(prob.shape, X.shape)
# test dataframe
X_df = self.X_df
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X_df, y)
prediction = classifier.predict(X_df)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
# test weight
weights = [mt.random.rand(X.shape[0]), md.Series(mt.random.rand(X.shape[0])),
md.DataFrame(mt.random.rand(X.shape[0]))]
y_df = md.DataFrame(self.y)
for weight in weights:
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X, y_df, sample_weights=weight)
prediction = classifier.predict(X)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
# should raise error if weight.ndim > 1
with self.assertRaises(ValueError):
XGBClassifier(verbosity=1, n_estimators=2).fit(
X, y_df, sample_weights=mt.random.rand(1, 1))
# test binary classifier
new_y = (self.y > 0.5).astype(mt.int32)
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X, new_y)
prediction = classifier.predict(X)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
classifier = XGBClassifier(verbosity=1, n_estimators=2)
with self.assertRaises(TypeError):
classifier.fit(X, y, wrong_param=1)
classifier.fit(X, y)
with self.assertRaises(TypeError):
classifier.predict(X, wrong_param=1)
def testDistributedXGBClassifier(self):
service_ep = 'http://127.0.0.1:' + self.web_port
timeout = 120 if 'CI' in os.environ else -1
with new_session(service_ep) as sess:
run_kwargs = {'timeout': timeout}
X, y = self.X, self.y
y = (y * 10).astype(mt.int32)
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X,
y,
eval_set=[(X, y)],
session=sess,
run_kwargs=run_kwargs)
prediction = classifier.predict(X,
session=sess,
run_kwargs=run_kwargs)
self.assertEqual(prediction.ndim, 1)
self.assertEqual(prediction.shape[0], len(self.X))
history = classifier.evals_result()
self.assertIsInstance(prediction, mt.Tensor)
self.assertIsInstance(history, dict)
self.assertEqual(list(history)[0], 'validation_0')
# default metrics may differ, see https://github.com/dmlc/xgboost/pull/6183
eval_metric = list(history['validation_0'])[0]
self.assertIn(eval_metric, ('merror', 'mlogloss'))
self.assertEqual(len(history['validation_0']), 1)
self.assertEqual(len(history['validation_0'][eval_metric]), 2)
X = md.DataFrame(np.random.rand(100, 20), chunk_size=20)
y = md.DataFrame(np.random.randint(0, 2, (100, 1)), chunk_size=20)
classifier = XGBClassifier(verbosity=1, n_estimators=2)
classifier.fit(X, y, session=sess, run_kwargs=run_kwargs)
prediction = classifier.predict(X,
session=sess,
run_kwargs=run_kwargs)
self.assertIsInstance(prediction, md.Series)
self.assertEqual(prediction.shape[0], len(X))