if __name__ == "__main__":
train(datasource=datasource,
estimator_string="sqlflow_models.DNNRegressor",
select=select,
validation_select=validation_select,
feature_columns=feature_columns,
feature_column_names=feature_column_names,
feature_metas=feature_metas,
label_meta=label_meta,
model_params={"hidden_units": [10, 20]},
validation_metrics=["CategoricalAccuracy"],
save="myregmodel_keras",
batch_size=1,
epoch=3,
verbose=0)
pred(datasource=datasource,
estimator_string="sqlflow_models.DNNRegressor",
select=validation_select,
result_table="housing.predict",
feature_columns=feature_columns,
feature_column_names=feature_column_names,
feature_column_names_map=feature_column_names_map,
train_label_name=label_meta["feature_name"],
result_col_name=label_meta["feature_name"],
feature_metas=feature_metas,
model_params={"hidden_units": [10, 20]},
save="myregmodel_keras",
batch_size=1)
shutil.rmtree("myregmodel_keras")
feature_columns=feature_columns,
feature_column_names=feature_column_names,
feature_metas=feature_metas,
label_meta=label_meta,
model_params={
"n_classes": 2,
"hidden_units": [10, 20]
},
save="mymodel_binary",
batch_size=1,
epoch=3,
verbose=1)
pred(datasource=datasource,
estimator_string="DNNClassifier",
select=select,
result_table="iris.predict",
feature_columns=feature_columns,
feature_column_names=feature_column_names,
feature_column_names_map=feature_column_names_map,
train_label_name=label_meta["feature_name"],
result_col_name=label_meta["feature_name"],
feature_metas=feature_metas,
model_params={
"n_classes": 3,
"hidden_units": [10, 20]
},
save="mymodel",
batch_size=1)
shutil.rmtree("mymodel")
shutil.rmtree("mymodel_binary")