def predict(datasource, select, data_table, result_table, label_column,
oss_model_path):
"""PAI TensorFlow prediction wrapper
This function do some preparation for the local prediction, say,
download the model from OSS, extract metadata and so on.
Args:
datasource: the datasource from which to get data
select: data selection SQL statement
data_table: tmp table which holds the data from select
result_table: table to save prediction result
label_column: prediction label column
oss_model_path: the model path on OSS
"""
try:
tf.enable_eager_execution()
except: # noqa: E722
pass
(estimator, feature_column_names, feature_column_names_map, feature_metas,
label_meta, model_params,
feature_columns_code) = oss.load_metas(oss_model_path,
"tensorflow_model_desc")
feature_columns = eval(feature_columns_code)
# NOTE(typhoonzero): No need to eval model_params["optimizer"] and
# model_params["loss"] because predicting do not need these parameters.
is_estimator = is_tf_estimator(import_model(estimator))
# Keras single node is using h5 format to save the model, no need to deal
# with export model format. Keras distributed mode will use estimator, so
# this is also needed.
if is_estimator:
oss.load_file(oss_model_path, "exported_path")
# NOTE(typhoonzero): directory "model_save" is hardcoded in
# codegen/tensorflow/codegen.go
oss.load_dir("%s/model_save" % oss_model_path)
else:
oss.load_file(oss_model_path, "model_save")
_predict(datasource=datasource,
estimator_string=estimator,
select=select,
result_table=result_table,
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_column,
feature_metas=feature_metas,
model_params=model_params,
save="model_save",
batch_size=1,
pai_table=data_table)
def evaluate(datasource,
estimator_string,
select,
result_table,
feature_columns,
feature_column_names,
feature_metas={},
label_meta={},
model_params={},
validation_metrics=["Accuracy"],
save="",
batch_size=1,
validation_steps=None,
verbose=0,
hdfs_namenode_addr="",
hive_location="",
hdfs_user="",
hdfs_pass=""):
estimator_cls = import_model(estimator_string)
is_estimator = is_tf_estimator(estimator_cls)
set_log_level(verbose, is_estimator)
eval_dataset = get_dataset_fn(select,
datasource,
feature_column_names,
feature_metas,
label_meta,
is_pai=False,
pai_table="",
batch_size=batch_size)
model_params.update(feature_columns)
if is_estimator:
model_params["model_dir"] = save
estimator = estimator_cls(**model_params)
result_metrics = estimator_evaluate(estimator, eval_dataset,
validation_metrics)
else:
keras_model = init_model_with_feature_column(estimator_cls,
model_params)
keras_model_pkg = sys.modules[estimator_cls.__module__]
result_metrics = keras_evaluate(keras_model, eval_dataset, save,
keras_model_pkg, validation_metrics)
# write result metrics to a table
conn = connect_with_data_source(datasource)
driver = conn.driver
if result_table:
metric_name_list = ["loss"] + validation_metrics
write_result_metrics(result_metrics,
metric_name_list,
result_table,
driver,
conn,
hdfs_namenode_addr=hdfs_namenode_addr,
hive_location=hive_location,
hdfs_user=hdfs_user,
hdfs_pass=hdfs_pass)
def evaluate(datasource, select, data_table, result_table, oss_model_path,
metrics):
"""PAI Tensorflow evaluate wrapper
This function do some preparation for the local evaluation, say,
download the model from OSS, extract metadata and so on.
Args:
datasource: the datasource from which to get data
select: data selection SQL statement
data_table: tmp table which holds the data from select
result_table: table to save prediction result
oss_model_path: the model path on OSS
metrics: metrics to evaluate
"""
(estimator, feature_column_names, feature_column_names_map, feature_metas,
label_meta, model_params,
feature_columns_code) = oss.load_metas(oss_model_path,
"tensorflow_model_desc")
feature_columns = eval(feature_columns_code)
# NOTE(typhoonzero): No need to eval model_params["optimizer"] and
# model_params["loss"] because predicting do not need these parameters.
is_estimator = is_tf_estimator(import_model(estimator))
# Keras single node is using h5 format to save the model, no need to deal
# with export model format. Keras distributed mode will use estimator, so
# this is also needed.
if is_estimator:
oss.load_file(oss_model_path, "exported_path")
# NOTE(typhoonzero): directory "model_save" is hardcoded in
# codegen/tensorflow/codegen.go
oss.load_dir("%s/model_save" % oss_model_path)
else:
oss.load_file(oss_model_path, "model_save")
_evaluate(datasource=datasource,
estimator_string=estimator,
select=select,
result_table=result_table,
feature_columns=feature_columns,
feature_column_names=feature_column_names,
feature_metas=feature_metas,
label_meta=label_meta,
model_params=model_params,
validation_metrics=metrics,
save="model_save",
batch_size=1,
validation_steps=None,
verbose=0,
is_pai=True,
pai_table=data_table)
def _explain(datasource,
estimator_string,
select,
feature_columns,
feature_column_names,
feature_metas={},
label_meta={},
model_params={},
save="",
pai_table="",
plot_type='bar',
result_table="",
oss_dest=None,
oss_ak=None,
oss_sk=None,
oss_endpoint=None,
oss_bucket_name=None):
estimator_cls = import_model(estimator_string)
FLAGS = tf.app.flags.FLAGS
model_params["model_dir"] = FLAGS.checkpointDir
model_params.update(feature_columns)
def _input_fn():
dataset = input_fn("",
datasource,
feature_column_names,
feature_metas,
label_meta,
is_pai=True,
pai_table=pai_table)
return dataset.batch(1).cache()
estimator = init_model_with_feature_column(estimator_cls, model_params)
driver = "pai_maxcompute"
conn = None
if estimator_cls in (tf.estimator.BoostedTreesClassifier,
tf.estimator.BoostedTreesRegressor):
explain_boosted_trees(datasource, estimator, _input_fn, plot_type,
result_table, feature_column_names, driver, conn,
"", "", "", "", oss_dest, oss_ak, oss_sk,
oss_endpoint, oss_bucket_name)
else:
shap_dataset = pd.DataFrame(columns=feature_column_names)
for i, (features, label) in enumerate(_input_fn()):
shap_dataset.loc[i] = [
item.numpy()[0][0] for item in features.values()
]
explain_dnns(datasource, estimator, shap_dataset, plot_type,
result_table, feature_column_names, driver, conn, "", "",
"", "", oss_dest, oss_ak, oss_sk, oss_endpoint,
oss_bucket_name)
def _evaluate(datasource,
estimator_string,
select,
result_table,
feature_columns,
feature_column_names,
feature_metas={},
label_meta={},
model_params={},
validation_metrics=["Accuracy"],
save="",
batch_size=1,
validation_steps=None,
verbose=0,
pai_table=""):
estimator_cls = import_model(estimator_string)
is_estimator = is_tf_estimator(estimator_cls)
set_log_level(verbose, is_estimator)
eval_dataset = get_dataset_fn(select,
datasource,
feature_column_names,
feature_metas,
label_meta,
is_pai=True,
pai_table=pai_table,
batch_size=batch_size)
model_params.update(feature_columns)
if is_estimator:
FLAGS = tf.app.flags.FLAGS
model_params["model_dir"] = FLAGS.checkpointDir
estimator = estimator_cls(**model_params)
result_metrics = estimator_evaluate(estimator, eval_dataset,
validation_metrics)
else:
keras_model = init_model_with_feature_column(estimator, model_params)
keras_model_pkg = sys.modules[estimator_cls.__module__]
result_metrics = keras_evaluate(keras_model, eval_dataset, save,
keras_model_pkg, validation_metrics)
if result_table:
metric_name_list = ["loss"] + validation_metrics
write_result_metrics(result_metrics,
metric_name_list,
result_table,
"pai_maxcompute",
None,
hdfs_namenode_addr="",
hive_location="",
hdfs_user="",
hdfs_pass="")
def explain(datasource,
estimator_string,
select,
feature_columns,
feature_column_names,
feature_metas={},
label_meta={},
model_params={},
save="",
pai_table="",
plot_type='bar',
result_table="",
hdfs_namenode_addr="",
hive_location="",
hdfs_user="",
hdfs_pass="",
oss_dest=None,
oss_ak=None,
oss_sk=None,
oss_endpoint=None,
oss_bucket_name=None):
estimator_cls = import_model(estimator_string)
model_params['model_dir'] = save
model_params.update(feature_columns)
def _input_fn():
dataset = input_fn(select, datasource, feature_column_names,
feature_metas, label_meta)
return dataset.batch(1).cache()
estimator = init_model_with_feature_column(estimator_cls, model_params)
conn = connect_with_data_source(datasource)
if estimator_cls in (tf.estimator.BoostedTreesClassifier,
tf.estimator.BoostedTreesRegressor):
explain_boosted_trees(datasource, estimator, _input_fn, plot_type,
result_table, feature_column_names, conn.driver,
conn, hdfs_namenode_addr, hive_location,
hdfs_user, hdfs_pass, oss_dest, oss_ak, oss_sk,
oss_endpoint, oss_bucket_name)
else:
shap_dataset = pd.DataFrame(columns=feature_column_names)
for i, (features, label) in enumerate(_input_fn()):
shap_dataset.loc[i] = [
item.numpy()[0][0] for item in features.values()
]
explain_dnns(datasource, estimator, shap_dataset, plot_type,
result_table, feature_column_names, conn.driver, conn,
hdfs_namenode_addr, hive_location, hdfs_user, hdfs_pass,
oss_dest, oss_ak, oss_sk, oss_endpoint, oss_bucket_name)
def pred(datasource,
estimator_string,
select,
result_table,
feature_columns,
feature_column_names,
feature_column_names_map,
train_label_name,
result_col_name,
feature_metas={},
model_params={},
save="",
batch_size=1,
hdfs_namenode_addr="",
hive_location="",
hdfs_user="",
hdfs_pass=""):
estimator = import_model(estimator_string)
model_params.update(feature_columns)
is_estimator = is_tf_estimator(estimator)
conn = db.connect_with_data_source(datasource)
driver = conn.driver
predict_generator = db.db_generator(conn, select)
selected_cols = db.selected_cols(conn, select)
if not is_estimator:
if not issubclass(estimator, tf.keras.Model):
# functional model need field_metas parameter
model_params["field_metas"] = feature_metas
print("Start predicting using keras model...")
keras_predict(estimator, model_params, save, result_table,
feature_column_names, feature_metas, train_label_name,
result_col_name, driver, conn, predict_generator,
selected_cols, hdfs_namenode_addr, hive_location,
hdfs_user, hdfs_pass)
else:
model_params['model_dir'] = save
print("Start predicting using estimator model...")
estimator_predict(estimator, model_params, save, result_table,
feature_column_names, feature_column_names_map,
feature_columns, feature_metas, train_label_name,
result_col_name, driver, conn, predict_generator,
selected_cols, hdfs_namenode_addr, hive_location,
hdfs_user, hdfs_pass)
print("Done predicting. Predict table : %s" % result_table)
def explain(datasource, select, data_table, result_table, label_column,
oss_model_path):
try:
tf.enable_eager_execution()
except Exception as e:
sys.stderr.write("warning: failed to enable_eager_execution: %s" % e)
pass
(estimator, feature_column_names, feature_column_names_map, feature_metas,
label_meta, model_params,
feature_columns_code) = oss.load_metas(oss_model_path,
"tensorflow_model_desc")
feature_columns = eval(feature_columns_code)
# NOTE(typhoonzero): No need to eval model_params["optimizer"] and
# model_params["loss"] because predicting do not need these parameters.
is_estimator = is_tf_estimator(import_model(estimator))
# Keras single node is using h5 format to save the model, no need to deal
# with export model format. Keras distributed mode will use estimator, so
# this is also needed.
if is_estimator:
oss.load_file(oss_model_path, "exported_path")
# NOTE(typhoonzero): directory "model_save" is hardcoded in
# codegen/tensorflow/codegen.go
oss.load_dir("%s/model_save" % oss_model_path)
else:
oss.load_file(oss_model_path, "model_save")
# (TODO: lhw) use oss to store result image
_explain(datasource=datasource,
estimator_string=estimator,
select=select,
feature_columns=feature_columns,
feature_column_names=feature_column_names,
feature_metas=feature_metas,
label_meta=label_meta,
model_params=model_params,
save="model_save",
result_table=result_table,
pai_table=data_table,
oss_dest=None,
oss_ak=None,
oss_sk=None,
oss_endpoint=None,
oss_bucket_name=None)
def train(datasource,
estimator_string,
select,
validation_select,
feature_columns,
feature_column_names,
feature_metas={},
label_meta={},
model_params={},
validation_metrics=["Accuracy"],
save="",
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,
pai_table="",
pai_val_table="",
feature_columns_code="",
model_repo_image="",
original_sql="",
feature_column_names_map=None):
model_meta = collect_model_metadata(original_sql, select,
validation_select, estimator_string,
model_params, feature_columns_code,
feature_metas, label_meta, None,
model_repo_image)
estimator = import_model(estimator_string)
is_estimator = is_tf_estimator(estimator)
if verbose < 1: # always use verbose == 1 when using PAI to get more logs
verbose = 1
set_log_level(verbose, is_estimator)
model_params.update(feature_columns)
FLAGS = define_tf_flags()
set_oss_environs(FLAGS)
num_workers = len(FLAGS.worker_hosts.split(","))
worker_id = FLAGS.task_index
train_dataset_fn = get_dataset_fn(select,
datasource,
feature_column_names,
feature_metas,
label_meta,
is_pai,
pai_table,
batch_size,
epochs=epoch,
shuffle_size=1000,
num_workers=num_workers,
worker_id=worker_id)
val_dataset_fn = None
if validation_select:
val_dataset_fn = get_dataset_fn(validation_select, datasource,
feature_column_names, feature_metas,
label_meta, is_pai, pai_val_table,
batch_size)
if not is_estimator:
if isinstance(estimator, types.FunctionType):
# functional model need field_metas parameter
model_params["field_metas"] = feature_metas
keras_train_and_save(estimator, model_params, save, FLAGS,
train_dataset_fn, val_dataset_fn, label_meta,
epoch, verbose, validation_metrics,
validation_steps, load_pretrained_model,
model_meta)
else:
estimator_train_and_save(estimator, model_params, save, FLAGS,
train_dataset_fn, val_dataset_fn,
log_every_n_iter, max_steps,
validation_start_delay_secs,
validation_throttle_secs,
save_checkpoints_steps, validation_metrics,
load_pretrained_model, model_meta)
# save model to OSS
if num_workers == 1 or worker_id == 0:
oss_model_dir = FLAGS.sqlflow_oss_modeldir
oss.save_oss_model(oss_model_dir, estimator_string, is_estimator,
feature_column_names, feature_column_names_map,
feature_metas, label_meta, model_params,
feature_columns_code, num_workers)
print("Model saved to oss: %s" % oss_model_dir)
print("Done training")
def train(datasource,
estimator_string,
select,
validation_select,
feature_columns,
feature_column_names,
feature_metas={},
label_meta={},
model_params={},
validation_metrics=["Accuracy"],
save="",
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=False,
pai_table="",
pai_val_table="",
feature_columns_code="",
model_repo_image="",
original_sql=""):
model_meta = collect_model_metadata(original_sql, select,
validation_select, estimator_string,
model_params, feature_columns_code,
feature_metas, label_meta, None,
model_repo_image)
estimator = import_model(estimator_string)
is_estimator = is_tf_estimator(estimator)
set_log_level(verbose, is_estimator)
model_params.update(feature_columns)
train_dataset_fn = get_dataset_fn(select,
datasource,
feature_column_names,
feature_metas,
label_meta,
is_pai,
pai_table,
batch_size,
epochs=epoch,
shuffle_size=1000)
val_dataset_fn = None
if validation_select:
val_dataset_fn = get_dataset_fn(validation_select, datasource,
feature_column_names, feature_metas,
label_meta, is_pai, pai_val_table,
batch_size)
if not is_estimator: # keras
if isinstance(estimator, types.FunctionType):
# functional model need field_metas parameter
model_params["field_metas"] = feature_metas
keras_train_and_save(estimator, model_params, save, is_pai,
train_dataset_fn, val_dataset_fn, label_meta,
epoch, verbose, validation_metrics,
validation_steps, load_pretrained_model,
model_meta)
else:
estimator_train_and_save(
estimator, model_params, save, train_dataset_fn, val_dataset_fn,
log_every_n_iter, max_steps, validation_start_delay_secs,
validation_throttle_secs, save_checkpoints_steps,
validation_metrics, load_pretrained_model, model_meta)
# remove cache files
any(map(os.remove, glob.glob('cache_train.*')))
any(map(os.remove, glob.glob('cache_validation.*')))
print("Done training")
def _predict(datasource,
estimator_string,
select,
result_table,
feature_columns,
feature_column_names,
feature_column_names_map,
train_label_name,
result_col_name,
feature_metas={},
model_params={},
save="",
batch_size=1,
pai_table=""):
estimator = import_model(estimator_string)
model_params.update(feature_columns)
is_estimator = is_tf_estimator(estimator)
conn = None
driver = "pai_maxcompute"
pai_table_parts = pai_table.split(".")
formatted_pai_table = "odps://%s/tables/%s" % (pai_table_parts[0],
pai_table_parts[1])
selected_cols = db.pai_selected_cols(formatted_pai_table)
predict_generator = db.pai_maxcompute_db_generator(formatted_pai_table)
if not is_estimator:
if not issubclass(estimator, tf.keras.Model):
# functional model need field_metas parameter
model_params["field_metas"] = feature_metas
print("Start predicting using keras model...")
keras_predict(estimator,
model_params,
save,
result_table,
feature_column_names,
feature_metas,
train_label_name,
result_col_name,
driver,
conn,
predict_generator,
selected_cols,
hdfs_namenode_addr="",
hive_location="",
hdfs_user="",
hdfs_pass="")
else:
model_params['model_dir'] = save
print("Start predicting using estimator model...")
estimator_predict(estimator,
model_params,
save,
result_table,
feature_column_names,
feature_column_names_map,
feature_columns,
feature_metas,
train_label_name,
result_col_name,
driver,
conn,
predict_generator,
selected_cols,
hdfs_namenode_addr="",
hive_location="",
hdfs_user="",
hdfs_pass="")
print("Done predicting. Predict table : %s" % result_table)