def test_to_json_multiclass(self, titanic_vd):
titanic = titanic_vd.copy()
titanic.fillna()
path = "verticapy_test_xgbr.json"
X = ["survived", "age", "fare"]
y = "pclass"
model = XGBoostClassifier(
"verticapy_xgb_multiclass_classifier_test", max_ntree=10, max_depth=5
)
model.drop()
model.fit(titanic, X, y)
X_test = titanic[X].to_numpy()
y_test_vertica = model.to_python(return_proba=True)(X_test).argsort()
if os.path.exists(path):
os.remove(path)
model.to_json(path)
model_python = xgb.XGBClassifier()
model_python.load_model(path)
y_test_python = model_python.predict_proba(X_test).argsort()
result = (y_test_vertica - y_test_python) ** 2
result = result.sum() / len(result)
assert result == 0.0
y_test_vertica = model.to_python()(X_test)
y_test_python = model_python.predict(X_test)
result = (y_test_vertica - y_test_python) ** 2
result = result.sum() / len(result)
assert result == 0.0
model.drop()
os.remove(path)
def test_contour(self, titanic_vd):
model_test = XGBoostClassifier("model_contour",)
model_test.drop()
model_test.fit(
titanic_vd, ["age", "fare"], "survived",
)
result = model_test.contour()
assert len(result.get_default_bbox_extra_artists()) in (38, 40, 43)
model_test.drop()
def test_to_sql(self, model, titanic_vd):
model_test = XGBoostClassifier("xgb_sql_test", cursor=model.cursor)
model_test.drop()
model_test.fit(titanic_vd, ["age", "fare", "sex"], "survived")
model.cursor.execute(
"SELECT PREDICT_XGB_CLASSIFIER(* USING PARAMETERS model_name = 'xgb_sql_test', match_by_pos=True, class=1, type='probability')::float, {}::float FROM (SELECT 30.0 AS age, 45.0 AS fare, 'male' AS sex) x"
.format(model_test.to_sql()))
prediction = model.cursor.fetchone()
assert prediction[0] == pytest.approx(prediction[1])
model_test.drop()
def test_model_from_vDF(self, base, xgbc_data_vd):
base.cursor.execute("DROP MODEL IF EXISTS xgbc_from_vDF")
model_test = XGBoostClassifier("xgbc_from_vDF", cursor=base.cursor)
model_test.fit(
xgbc_data_vd,
["Gender", '"owned cars"', "cost", "income"],
"TransPortation",
)
base.cursor.execute(
"SELECT model_name FROM models WHERE model_name = 'xgbc_from_vDF'")
assert base.cursor.fetchone()[0] == "xgbc_from_vDF"
model_test.drop()
def test_contour(self, base, titanic_vd):
model_test = XGBoostClassifier("model_contour", cursor=base.cursor)
model_test.drop()
model_test.fit(
titanic_vd,
[
"age",
"fare",
],
"survived",
)
result = model_test.contour()
assert len(result.get_default_bbox_extra_artists()) == 38
model_test.drop()
def test_to_python(self, model, titanic_vd):
model_test = XGBoostClassifier("rfc_python_test", cursor=model.cursor)
model_test.drop()
model_test.fit(titanic_vd, ["age", "fare", "sex"], "embarked")
model_test.cursor.execute(
"SELECT PREDICT_XGB_CLASSIFIER(30.0, 45.0, 'male' USING PARAMETERS model_name = 'rfc_python_test', match_by_pos=True)"
)
prediction = model_test.cursor.fetchone()[0]
assert prediction == model_test.to_python(return_str=False)(
[[30.0, 45.0, 'male']])[0]
model_test.cursor.execute(
"SELECT PREDICT_XGB_CLASSIFIER(30.0, 145.0, 'female' USING PARAMETERS model_name = 'rfc_python_test', match_by_pos=True)"
)
prediction = model_test.cursor.fetchone()[0]
assert prediction == model_test.to_python(return_str=False)(
[[30.0, 145.0, 'female']])[0]
def test_drop(self):
current_cursor().execute("DROP MODEL IF EXISTS xgbc_model_test_drop")
model_test = XGBoostClassifier("xgbc_model_test_drop",)
model_test.fit(
"public.xgbc_data",
["Gender", '"owned cars"', "cost", "income"],
"TransPortation",
)
current_cursor().execute(
"SELECT model_name FROM models WHERE model_name = 'xgbc_model_test_drop'"
)
assert current_cursor().fetchone()[0] == "xgbc_model_test_drop"
model_test.drop()
current_cursor().execute(
"SELECT model_name FROM models WHERE model_name = 'xgbc_model_test_drop'"
)
assert current_cursor().fetchone() is None