def test_submit_xgb_train_task(self):
model_params = {
"booster": "gbtree",
"eta": 0.4,
"num_class": 3,
"objective": "multi:softprob"
}
train_params = {"num_boost_round": 10}
feature_columns_code = """
xgboost_extended.feature_column.numeric_column(
"sepal_length", shape=[1]),
xgboost_extended.feature_column.numeric_column(
"sepal_width", shape=[1]),
xgboost_extended.feature_column.numeric_column(
"petal_length", shape=[1]),
xgboost_extended.feature_column.numeric_column(
"petal_width", shape=[1])
"""
train(testing.get_datasource(),
"XGBoost",
"SELECT * FROM alifin_jtest_dev.sqlflow_iris_train",
"select * from alifin_jtest_dev.sqlflow_iris_train",
model_params,
"e2etest_xgb_classify_model",
None,
train_params=train_params,
feature_columns=eval("[%s]" % feature_columns_code),
feature_metas=iris_feature_metas,
label_meta=iris_label_meta,
feature_column_names=iris_feature_column_names,
feature_columns_code=feature_columns_code)
def test_submit_pai_random_forest_train_task(self):
train(testing.get_datasource(),
"RandomForests",
"SELECT * FROM alifin_jtest_dev.sqlflow_iris_train",
"", {
"tree_num": 3,
},
"e2e_test_random_forest",
"",
feature_column_names=iris_feature_column_names,
label_meta=iris_label_meta)
def test_submit_pai_kmeans_train_task(self):
train(
testing.get_datasource(),
"KMeans",
"SELECT * FROM alifin_jtest_dev.sqlflow_iris_train",
"", {
"excluded_columns": "class",
"idx_table_name": "alifin_jtest_dev.e2e_test_kmeans_output_idx"
},
"e2e_test_kmeans",
"",
feature_column_names=[*iris_feature_column_names, "class"])
def test_submit_pai_random_forest_train_task(self):
original_sql = """SELECT * FROM alifin_jtest_dev.sqlflow_iris_train
TO TRAIN RandomForests
WITH model.tree_num=3
LABEL class
INTO e2e_test_random_forest;"""
train(testing.get_datasource(), original_sql,
"SELECT * FROM alifin_jtest_dev.sqlflow_iris_train", "",
"RandomForests", "", feature_column_map, label_column,
{"tree_num": 3}, {
"feature_column_names":
iris_feature_column_names,
"label_meta":
json.loads(label_column.get_field_desc()[0].to_json())
}, "e2e_test_random_forest_wuyi", None)
def test_submit_pai_kmeans_train_task(self):
original_sql = """SELECT * FROM alifin_jtest_dev.sqlflow_iris_train
TO TRAIN KMeans
WITH model.excluded_columns="class",
model.idx_table_name="alifin_jtest_dev.e2e_test_kmeans_output_idx"
INTO e2e_test_kmeans;"""
train(
testing.get_datasource(), original_sql,
"SELECT * FROM alifin_jtest_dev.sqlflow_iris_train", "", "KMeans",
"", feature_column_map, None, {
"excluded_columns": "class",
"idx_table_name": "alifin_jtest_dev.e2e_test_kmeans_output_idx"
}, {"feature_column_names": iris_feature_column_names},
"e2e_test_kmeans", None)
def test_submit_pai_train_task(self):
model_params = dict()
model_params["hidden_units"] = [10, 20]
model_params["n_classes"] = 3
original_sql = """
SELECT * FROM alifin_jtest_dev.sqlflow_test_iris_train
TO TRAIN DNNClassifier
WITH model.n_classes = 3, model.hidden_units = [10, 20]
LABEL class
INTO e2etest_pai_dnn;"""
train(testing.get_datasource(), original_sql,
"SELECT * FROM alifin_jtest_dev.sqlflow_iris_train", "",
"DNNClassifier", "", feature_column_map, label_column,
model_params, {}, "e2etest_pai_dnn", None)
def test_submit_pai_train_task(self):
model_params = dict()
model_params["hidden_units"] = [10, 20]
model_params["n_classes"] = 3
# feature_columns_code will be used to save the training information
# together with the saved model.
feature_columns_code = """{"feature_columns": [
tf.feature_column.numeric_column("sepal_length", shape=[1]),
tf.feature_column.numeric_column("sepal_width", shape=[1]),
tf.feature_column.numeric_column("petal_length", shape=[1]),
tf.feature_column.numeric_column("petal_width", shape=[1]),
]}"""
feature_columns = eval(feature_columns_code)
train(testing.get_datasource(),
"DNNClassifier",
"SELECT * FROM alifin_jtest_dev.sqlflow_iris_train",
"",
model_params,
"e2etest_pai_dnn",
None,
feature_columns=feature_columns,
feature_column_names=iris_feature_column_names,
feature_column_names_map=iris_feature_column_names_map,
feature_metas=iris_feature_metas,
label_meta=iris_label_meta,
validation_metrics="Accuracy".split(","),
batch_size=1,
epoch=1,
validation_steps=1,
verbose=0,
max_steps=None,
validation_start_delay_secs=0,
validation_throttle_secs=0,
save_checkpoints_steps=100,
log_every_n_iter=10,
load_pretrained_model=False,
is_pai=True,
feature_columns_code=feature_columns_code,
model_repo_image="",
original_sql='''
SELECT * FROM alifin_jtest_dev.sqlflow_test_iris_train
TO TRAIN DNNClassifier
WITH model.n_classes = 3, model.hidden_units = [10, 20]
LABEL class
INTO e2etest_pai_dnn;''')
def test_submit_xgb_train_task(self):
original_sql = """SELECT * FROM iris.train
TO TRAIN xgboost.gbtree
WITH objective="multi:softprob", num_class=3, eta=0.4, booster="gbtree"
validatioin.select="select * from alifin_jtest_dev.sqlflow_iris_test"
LABEL class
INTO e2etest_xgb_classify_model;"""
model_params = {
"eta": 0.4,
"num_class": 3,
"objective": "multi:softprob"
}
train_params = {"num_boost_round": 10}
train(testing.get_datasource(), original_sql,
"SELECT * FROM alifin_jtest_dev.sqlflow_iris_train",
"SELECT * FROM alifin_jtest_dev.sqlflow_iris_test",
"xgboost.gbtree", "", feature_column_map, label_column,
model_params, train_params, "e2etest_xgb_classify_model", None)