def test_generator(self):
driver = os.environ.get('SQLFLOW_TEST_DB')
if driver == "mysql":
database = "iris"
user = os.environ.get('SQLFLOW_TEST_DB_MYSQL_USER') or "root"
password = os.environ.get('SQLFLOW_TEST_DB_MYSQL_PASSWD') or "root"
conn = connect(driver, database, user=user, password=password, host="127.0.0.1", port="3306")
# prepare test data
execute(driver, conn, self.drop_statement)
execute(driver, conn, self.create_statement)
execute(driver, conn, self.insert_statement)
column_name_to_type = {"features": {
"feature_name": "features",
"delimiter": "",
"dtype": "float32",
"is_sparse": False,
"shape": []
}}
gen = db_generator(driver, conn, "SELECT * FROM test_table_float_fea",
["features"], "label", column_name_to_type)
idx = 0
for d in gen():
if idx == 0:
self.assertEqual(d, ((1.0,), [0]))
elif idx == 1:
self.assertEqual(d, ((2.0,), [1]))
idx += 1
self.assertEqual(idx, 2)
def xgb_shap_dataset(datasource, select, feature_column_names, label_spec,
feature_specs, is_pai, pai_explain_table):
label_column_name = label_spec["feature_name"]
if is_pai:
pai_table_parts = pai_explain_table.split(".")
formated_pai_table = "odps://%s/tables/%s" % (pai_table_parts[0],
pai_table_parts[1])
stream = db.pai_maxcompute_db_generator(formated_pai_table,
feature_column_names,
label_column_name,
feature_specs)
else:
conn = db.connect_with_data_source(datasource)
stream = db.db_generator(conn.driver, conn, select,
feature_column_names, label_spec,
feature_specs)
xs = pd.DataFrame(columns=feature_column_names)
i = 0
for row in stream():
xs.loc[i] = [item[0] for item in row[0]]
i += 1
# NOTE(typhoonzero): set dtype to the feature's actual type, or the dtype
# may be "object". Use below code to reproduce:
# import pandas as pd
# feature_column_names=["a", "b"]
# xs = pd.DataFrame(columns=feature_column_names)
# for i in range(10):
# xs.loc[i] = [int(j) for j in range(2)]
# print(xs.dtypes)
for fname in feature_column_names:
dtype = feature_specs[fname]["dtype"]
xs[fname] = xs[fname].astype(dtype)
return xs
def input_fn(select, conn, feature_column_names, feature_metas, label_meta):
feature_types = []
shapes = []
for name in feature_column_names:
# NOTE: vector columns like 23,21,3,2,0,0 should use shape None
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
shapes.append((None, None, None))
else:
feature_types.append(get_dtype(feature_metas[name]["dtype"]))
shapes.append(feature_metas[name]["shape"])
gen = db_generator(conn.driver, conn, select, feature_column_names,
label_meta["feature_name"], feature_metas)
# Clustering model do not have label
if label_meta["feature_name"] == "":
dataset = tf.data.Dataset.from_generator(gen, (tuple(feature_types), ),
(tuple(shapes), ))
ds_mapper = functools.partial(
parse_sparse_feature_predict,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
else:
dataset = tf.data.Dataset.from_generator(
gen, (tuple(feature_types), eval("tf.%s" % label_meta["dtype"])),
(tuple(shapes), label_meta["shape"]))
ds_mapper = functools.partial(
parse_sparse_feature,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
return dataset.map(ds_mapper)
def test_generate_fetch_size(self):
driver = os.environ.get('SQLFLOW_TEST_DB')
if driver == "mysql":
database = "iris"
user = os.environ.get('SQLFLOW_TEST_DB_MYSQL_USER') or "root"
password = os.environ.get('SQLFLOW_TEST_DB_MYSQL_PASSWD') or "root"
conn = connect(driver,
database,
user=user,
password=password,
host="127.0.0.1",
port="3306")
column_name_to_type = {
"sepal_length": {
"feature_name": "sepal_length",
"delimiter": "",
"dtype": "float32",
"is_sparse": False,
"shape": []
}
}
gen = db_generator(driver,
conn,
'SELECT * FROM iris.train limit 10',
["sepal_length"],
"class",
column_name_to_type,
fetch_size=4)
self.assertEqual(len([g for g in gen()]), 10)
def eval_input_fn(batch_size, cache=False):
feature_types = []
for name in feature_column_names:
# NOTE: vector columns like 23,21,3,2,0,0 should use shape None
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
else:
feature_types.append(
get_dtype(feature_metas[name]["dtype"]))
gen = db_generator(conn.driver, conn, select, feature_column_names,
label_meta["feature_name"], feature_metas)
dataset = tf.data.Dataset.from_generator(
gen,
(tuple(feature_types), eval("tf.%s" % label_meta["dtype"])))
ds_mapper = functools.partial(
parse_sparse_feature,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
dataset = dataset.map(ds_mapper).batch(batch_size)
if cache:
dataset = dataset.cache(
"cache/predict" if TF_VERSION_2 else "")
return dataset
def eval_input_fn(batch_size, cache=False):
feature_types = []
for name in feature_column_names:
# NOTE: vector columns like 23,21,3,2,0,0 should use shape None
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
else:
feature_types.append(get_dtype(feature_metas[name]["dtype"]))
if is_pai:
pai_table_parts = pai_table.split(".")
formatted_pai_table = "odps://%s/tables/%s" % (pai_table_parts[0],
pai_table_parts[1])
gen = db.pai_maxcompute_db_generator(formatted_pai_table,
feature_column_names, None,
feature_metas)
else:
gen = db.db_generator(conn.driver, conn, select,
feature_column_names, None, feature_metas)
dataset = tf.data.Dataset.from_generator(gen, (tuple(feature_types), ))
ds_mapper = functools.partial(
parse_sparse_feature_predict,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
dataset = dataset.map(ds_mapper).batch(batch_size)
if cache:
dataset = dataset.cache()
return dataset
def test_generate_fetch_size(self):
driver = os.environ.get('SQLFLOW_TEST_DB')
if driver == "mysql":
user, password, host, port, database = testing_mysql_cfg()
conn = connect(driver,
database,
user=user,
password=password,
host=host,
port=port)
column_name_to_type = {
"sepal_length": {
"feature_name": "sepal_length",
"delimiter": "",
"dtype": "float32",
"is_sparse": False,
"shape": []
}
}
label_spec = {
"feature_name": "label",
"shape": [],
"delimiter": ""
}
gen = db_generator(driver,
conn,
'SELECT * FROM iris.train limit 10',
["sepal_length"],
label_spec,
column_name_to_type,
fetch_size=4)
self.assertEqual(len([g for g in gen()]), 10)
def estimator_predict(estimator, model_params, save, result_table,
feature_column_names, feature_metas, label_meta,
datasource, select, hdfs_namenode_addr, hive_location,
hdfs_user, hdfs_pass, is_pai, pai_table):
classifier = estimator(**model_params)
conn = connect_with_data_source(datasource)
def fast_input_fn(generator):
feature_types = []
for name in feature_column_names:
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
else:
feature_types.append(get_dtype(feature_metas[name]["dtype"]))
def _inner_input_fn():
if is_pai:
dataset = pai_maxcompute_input_fn(pai_table, datasource,
feature_column_names,
feature_metas, label_meta)
else:
dataset = tf.data.Dataset.from_generator(
generator,
(tuple(feature_types), eval(
"tf.%s" % label_meta["dtype"])))
ds_mapper = functools.partial(
parse_sparse_feature,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
dataset = dataset.map(ds_mapper)
dataset = dataset.batch(1).cache()
iterator = dataset.make_one_shot_iterator()
features = iterator.get_next()
return features
return _inner_input_fn
column_names = feature_column_names[:]
column_names.append(label_meta["feature_name"])
fast_predictor = FastPredict(classifier, fast_input_fn)
with buffered_db_writer(conn.driver, conn, result_table, column_names, 100,
hdfs_namenode_addr, hive_location, hdfs_user,
hdfs_pass) as w:
for features in db_generator(conn.driver, conn, select,
feature_column_names,
label_meta["feature_name"],
feature_metas)():
result = fast_predictor.predict(features)
row = []
for idx, _ in enumerate(feature_column_names):
val = features[0][idx][0]
row.append(str(val))
if "class_ids" in list(result)[0]:
row.append(str(list(result)[0]["class_ids"][0]))
else:
# regression predictions
row.append(str(list(result)[0]["predictions"][0]))
w.write(row)
def xgb_dataset(conn, fn, dataset_sql, feature_column_name, label_name, feature_spec):
gen = db_generator(conn.driver, conn, dataset_sql, feature_column_name, label_name, feature_spec)
with open(fn, 'w') as f:
for item in gen():
features, label = item
row_data = [str(label[0])] + ["%d:%f" % (i, v) for i, v in enumerate(features)]
f.write("\t".join(row_data) + "\n")
# TODO(yancey1989): generate group and weight text file if necessary
return xgb.DMatrix(fn)
def input_fn(select,
datasource,
feature_column_names,
feature_metas,
label_meta,
is_pai=False,
pai_table="",
num_workers=1,
worker_id=0):
feature_types = []
shapes = []
for name in feature_column_names:
# NOTE: vector columns like 23,21,3,2,0,0 should use shape None
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
shapes.append((None, None, None))
else:
feature_types.append(get_dtype(feature_metas[name]["dtype"]))
shapes.append(feature_metas[name]["shape"])
if is_pai:
pai_table = "odps://{}/tables/{}".format(*pai_table.split("."))
return pai_dataset(pai_table,
feature_column_names,
label_meta,
feature_metas,
slice_id=worker_id,
slice_count=num_workers)
selected_cols = db.pai_selected_cols(pai_table)
else:
conn = db.connect_with_data_source(datasource)
gen = db.db_generator(conn.driver, conn, select, feature_column_names,
label_meta, feature_metas)
selected_cols = db.selected_cols(conn.driver, conn, select)
gen = tf_generator(gen, selected_cols, feature_column_names, feature_metas)
# Clustering model do not have label
if not label_meta or label_meta["feature_name"] == "":
dataset = tf.data.Dataset.from_generator(gen, (tuple(feature_types), ),
(tuple(shapes), ))
ds_mapper = functools.partial(
parse_sparse_feature_predict,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
else:
dataset = tf.data.Dataset.from_generator(
gen, (tuple(feature_types), eval("tf.%s" % label_meta["dtype"])),
(tuple(shapes), label_meta["shape"]))
ds_mapper = functools.partial(
parse_sparse_feature,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
return dataset.map(ds_mapper)
def xgb_shap_dataset(datasource, select, feature_column_names, label_name,
feature_specs):
conn = connect_with_data_source(datasource)
stream = db_generator(conn.driver, conn, select, feature_column_names,
label_name, feature_specs)
xs = pd.DataFrame(columns=feature_column_names)
ys = pd.DataFrame(columns=[label_name])
i = 0
for row in stream():
xs.loc[i] = [item[0] for item in row[0]]
ys.loc[i] = row[1]
i += 1
return xs
def xgb_dataset(datasource,
fn,
dataset_sql,
feature_specs,
feature_column_names,
label_spec,
is_pai=False,
pai_table="",
pai_single_file=False,
cache=False,
batch_size=None,
epoch=1,
rank=0,
nworkers=1):
if is_pai:
for dmatrix in pai_dataset(
fn,
feature_specs,
feature_column_names,
label_spec,
"odps://{}/tables/{}".format(*pai_table.split(".")),
pai_single_file,
cache,
rank,
nworkers,
batch_size=batch_size):
yield dmatrix
return
conn = db.connect_with_data_source(datasource)
gen = db.db_generator(conn.driver, conn, dataset_sql, feature_column_names,
label_spec, feature_specs)()
selected_cols = db.selected_cols(conn.driver, conn, dataset_sql)
for i in range(epoch):
step = 0
# the filename per batch is [filename]_[step]
step_file_name = "%s_%d" % (fn, step)
written_rows = dump_dmatrix(step_file_name, gen, feature_column_names,
feature_specs, label_spec, selected_cols)
while written_rows > 0:
yield load_dmatrix('{0}#{0}.cache'.format(step_file_name)
if cache else step_file_name)
os.remove(step_file_name)
step += 1
step_file_name = "%s_%d" % (fn, step)
written_rows = dump_dmatrix(step_file_name, gen,
feature_column_names, feature_specs,
label_spec, selected_cols)
def input_fn(select,
datasource,
feature_column_names,
feature_metas,
label_meta,
is_pai=False,
pai_table=""):
feature_types = []
shapes = []
for name in feature_column_names:
# NOTE: vector columns like 23,21,3,2,0,0 should use shape None
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
shapes.append((None, None, None))
else:
feature_types.append(get_dtype(feature_metas[name]["dtype"]))
shapes.append(feature_metas[name]["shape"])
if is_pai:
pai_table_parts = pai_table.split(".")
formated_pai_table = "odps://%s/tables/%s" % (pai_table_parts[0],
pai_table_parts[1])
gen = pai_maxcompute_db_generator(formated_pai_table,
feature_column_names,
label_meta["feature_name"],
feature_metas)
else:
conn = connect_with_data_source(datasource)
gen = db_generator(conn.driver, conn, select, feature_column_names,
label_meta, feature_metas)
# Clustering model do not have label
if label_meta["feature_name"] == "":
dataset = tf.data.Dataset.from_generator(gen, (tuple(feature_types), ),
(tuple(shapes), ))
ds_mapper = functools.partial(
parse_sparse_feature_predict,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
else:
dataset = tf.data.Dataset.from_generator(
gen, (tuple(feature_types), eval("tf.%s" % label_meta["dtype"])),
(tuple(shapes), label_meta["shape"]))
ds_mapper = functools.partial(
parse_sparse_feature,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
return dataset.map(ds_mapper)
def test_generator(self):
driver = os.environ.get('SQLFLOW_TEST_DB')
if driver == "mysql":
database = "iris"
user, password, host, port, database = testing_mysql_cfg()
conn = connect(driver,
database,
user=user,
password=password,
host=host,
port=int(port))
# prepare test data
execute(driver, conn, self.drop_statement)
execute(driver, conn, self.create_statement)
execute(driver, conn, self.insert_statement)
column_name_to_type = {
"features": {
"feature_name": "features",
"delimiter": "",
"dtype": "float32",
"is_sparse": False,
"shape": []
}
}
label_spec = {
"feature_name": "label",
"shape": [],
"delimiter": ""
}
gen = db_generator(driver, conn,
"SELECT * FROM test_table_float_fea",
["features"], label_spec, column_name_to_type)
idx = 0
for row, label in gen():
features = read_features_from_row(row, ["features"],
["features"],
column_name_to_type)
d = (features, label)
if idx == 0:
self.assertEqual(d, (((1.0, ), ), 0))
elif idx == 1:
self.assertEqual(d, (((2.0, ), ), 1))
idx += 1
self.assertEqual(idx, 2)
def input_fn(datasetStr):
feature_types = []
for name in feature_column_names:
# NOTE: vector columns like 23,21,3,2,0,0 should use shape None
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
else:
feature_types.append(get_dtype(feature_metas[name]["dtype"]))
gen = db_generator(conn.driver, conn, datasetStr, feature_column_names,
label_meta["feature_name"], feature_metas)
dataset = tf.data.Dataset.from_generator(
gen, (tuple(feature_types), eval("tf.%s" % label_meta["dtype"])))
ds_mapper = functools.partial(
parse_sparse_feature,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
return dataset.map(ds_mapper)
def xgb_dataset(datasource,
fn,
dataset_sql,
feature_specs,
feature_column_names,
label_spec,
is_pai=False,
pai_table="",
pai_single_file=False):
if is_pai:
pai_dataset(fn, feature_specs, feature_column_names, label_spec,
"odps://{}/tables/{}".format(*pai_table.split(".")),
pai_single_file)
else:
conn = db.connect_with_data_source(datasource)
gen = db.db_generator(conn.driver, conn, dataset_sql,
feature_column_names, label_spec, feature_specs)
dump_dmatrix(fn, gen, label_spec)
return xgb.DMatrix(fn)
def xgb_shap_dataset(datasource, select, feature_column_names, label_spec,
feature_specs, is_pai, pai_explain_table):
label_column_name = label_spec["feature_name"]
if is_pai:
pai_table_parts = pai_explain_table.split(".")
formated_pai_table = "odps://%s/tables/%s" % (pai_table_parts[0],
pai_table_parts[1])
stream = pai_maxcompute_db_generator(formated_pai_table,
feature_column_names,
label_column_name, feature_specs)
else:
conn = connect_with_data_source(datasource)
stream = db_generator(conn.driver, conn, select, feature_column_names,
label_spec, feature_specs)
xs = pd.DataFrame(columns=feature_column_names)
i = 0
for row in stream():
xs.loc[i] = [item[0] for item in row[0]]
i += 1
return xs
def xgb_dataset(datasource,
fn,
dataset_sql,
feature_metas,
feature_column_names,
label_meta,
is_pai=False,
pai_table=""):
if is_pai:
pai_table_parts = pai_table.split(".")
formated_pai_table = "odps://%s/tables/%s" % (pai_table_parts[0],
pai_table_parts[1])
if label_meta:
label_column_name = label_meta['feature_name']
else:
label_column_name = None
gen = pai_maxcompute_db_generator(formated_pai_table,
feature_column_names,
label_column_name, feature_metas)
else:
conn = connect_with_data_source(datasource)
gen = db_generator(conn.driver, conn, dataset_sql,
feature_column_names, label_meta, feature_metas)
with open(fn, 'w') as f:
for item in gen():
if label_meta is None:
row_data = ["%d:%f" % (i, v[0]) for i, v in enumerate(item[0])]
else:
features, label = item
row_data = [str(label)] + [
"%d:%f" % (i, v[0]) for i, v in enumerate(features)
]
f.write("\t".join(row_data) + "\n")
# TODO(yancey1989): generate group and weight text file if necessary
return xgb.DMatrix(fn)
def xgb_dataset(datasource,
fn,
dataset_sql,
feature_specs,
feature_column_names,
label_spec,
is_pai=False,
pai_table="",
pai_single_file=False,
cache=False,
batch_size=None,
epoch=1,
rank=0,
nworkers=1,
transform_fn=None,
feature_column_code="",
raw_data_dir=None):
if raw_data_dir:
# raw_data_dir is needed when predicting. Because we
# should write the raw data from the source db into
# the dest db, instead of the transformed data after
# `transform_fn(features)` . If raw_data_dir is not
# None, the raw data from the source db would be written
# into another file.
if os.path.exists(raw_data_dir):
shutil.rmtree(raw_data_dir, ignore_errors=True)
os.mkdir(raw_data_dir)
if is_pai:
for dmatrix in pai_dataset(
fn,
feature_specs,
feature_column_names,
label_spec,
"odps://{}/tables/{}".format(*pai_table.split(".")),
pai_single_file,
cache,
rank,
nworkers,
batch_size=batch_size,
feature_column_code=feature_column_code,
raw_data_dir=raw_data_dir):
yield dmatrix
return
conn = db.connect_with_data_source(datasource)
gen = db.db_generator(conn.driver, conn, dataset_sql, feature_column_names,
label_spec, feature_specs)()
selected_cols = db.selected_cols(conn.driver, conn, dataset_sql)
for _ in six.moves.range(epoch):
step = 0
# the filename per batch is [filename]_[step]
step_file_name = "%s_%d" % (fn, step)
written_rows = dump_dmatrix(step_file_name,
gen,
feature_column_names,
feature_specs,
label_spec,
selected_cols,
transform_fn=transform_fn,
raw_data_dir=raw_data_dir)
while written_rows > 0:
yield load_dmatrix('{0}#{0}.cache'.format(step_file_name)
if cache else step_file_name)
os.remove(step_file_name)
step += 1
step_file_name = "%s_%d" % (fn, step)
written_rows = dump_dmatrix(step_file_name,
gen,
feature_column_names,
feature_specs,
label_spec,
selected_cols,
transform_fn=transform_fn,
raw_data_dir=raw_data_dir)
def pred(is_keras_model,
datasource,
estimator,
select,
result_table,
feature_columns,
feature_column_names,
feature_metas={},
label_meta={},
model_params={},
save="",
batch_size=1,
hdfs_namenode_addr="",
hive_location="",
hdfs_user="",
hdfs_pass=""):
conn = connect_with_data_source(datasource)
model_params.update(feature_columns)
if not is_keras_model:
model_params['model_dir'] = save
classifier = estimator(**model_params)
else:
if not issubclass(estimator, tf.keras.Model):
# functional model need field_metas parameter
model_params["field_metas"] = feature_metas
classifier = estimator(**model_params)
classifier_pkg = sys.modules[estimator.__module__]
if is_keras_model:
def eval_input_fn(batch_size, cache=False):
feature_types = []
for name in feature_column_names:
# NOTE: vector columns like 23,21,3,2,0,0 should use shape None
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
else:
feature_types.append(
get_dtype(feature_metas[name]["dtype"]))
gen = db_generator(conn.driver, conn, select, feature_column_names,
label_meta["feature_name"], feature_metas)
dataset = tf.data.Dataset.from_generator(
gen,
(tuple(feature_types), eval("tf.%s" % label_meta["dtype"])))
ds_mapper = functools.partial(
parse_sparse_feature,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
dataset = dataset.map(ds_mapper).batch(batch_size)
if cache:
dataset = dataset.cache()
return dataset
# NOTE: always use batch_size=1 when predicting to get the pairs of features and predict results
# to insert into result table.
pred_dataset = eval_input_fn(1)
one_batch = pred_dataset.__iter__().next()
# NOTE: must run predict one batch to initialize parameters
# see: https://www.tensorflow.org/alpha/guide/keras/saving_and_serializing#saving_subclassed_models
classifier.predict_on_batch(one_batch[0])
classifier.load_weights(save)
del pred_dataset
pred_dataset = eval_input_fn(1, cache=True).make_one_shot_iterator()
buff_rows = []
column_names = feature_column_names[:]
column_names.append(label_meta["feature_name"])
with buffered_db_writer(conn.driver, conn, result_table, column_names,
100, hdfs_namenode_addr, hive_location,
hdfs_user, hdfs_pass) as w:
while True:
try:
features = pred_dataset.get_next()
except tf.errors.OutOfRangeError:
break
result = classifier.predict_on_batch(features[0])
result = classifier_pkg.prepare_prediction_column(result[0])
row = []
for idx, name in enumerate(feature_column_names):
val = features[0][name].numpy()[0]
row.append(str(val))
row.append(str(result))
w.write(row)
del pred_dataset
else:
def fast_input_fn(generator):
feature_types = []
for name in feature_column_names:
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
else:
feature_types.append(
get_dtype(feature_metas[name]["dtype"]))
def _inner_input_fn():
dataset = tf.data.Dataset.from_generator(
generator,
(tuple(feature_types), eval(
"tf.%s" % label_meta["dtype"])))
ds_mapper = functools.partial(
parse_sparse_feature,
feature_column_names=feature_column_names,
feature_metas=feature_metas)
dataset = dataset.map(ds_mapper).batch(1).cache()
iterator = dataset.make_one_shot_iterator()
features = iterator.get_next()
return features
return _inner_input_fn
column_names = feature_column_names[:]
column_names.append(label_meta["feature_name"])
pred_gen = db_generator(conn.driver, conn, select,
feature_column_names,
label_meta["feature_name"], feature_metas)()
fast_predictor = FastPredict(classifier, fast_input_fn)
with buffered_db_writer(conn.driver, conn, result_table, column_names,
100, hdfs_namenode_addr, hive_location,
hdfs_user, hdfs_pass) as w:
while True:
try:
features = next(pred_gen)
except StopIteration:
break
result = fast_predictor.predict(features)
row = []
for idx, _ in enumerate(feature_column_names):
val = features[0][idx]
row.append(str(val))
if "class_ids" in list(result)[0]:
row.append(str(list(result)[0]["class_ids"][0]))
else:
# regression predictions
row.append(str(list(result)[0]["predictions"][0]))
w.write(row)
fast_predictor.close()
print("Done predicting. Predict table : %s" % result_table)
def pred(is_keras_model,
datasource,
estimator,
select,
result_table,
feature_columns,
feature_column_names,
feature_metas={},
label_meta={},
model_params={},
save="",
batch_size=1,
hdfs_namenode_addr="",
hive_location="",
hdfs_user="",
hdfs_pass="",
is_pai=False,
pai_table=""):
global FLAGS
define_tf_flags()
if not is_pai:
conn = connect_with_data_source(datasource)
model_params.update(feature_columns)
if is_keras_model:
if not issubclass(estimator, tf.keras.Model):
# functional model need field_metas parameter
model_params["field_metas"] = feature_metas
classifier = estimator(**model_params)
classifier_pkg = sys.modules[estimator.__module__]
def eval_input_fn(batch_size, cache=False):
feature_types = []
for name in feature_column_names:
# NOTE: vector columns like 23,21,3,2,0,0 should use shape None
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
else:
feature_types.append(get_dtype(feature_metas[name]["dtype"]))
gen = db_generator(conn.driver, conn, select,
feature_column_names, label_meta["feature_name"], feature_metas)
dataset = tf.data.Dataset.from_generator(gen, (tuple(feature_types), eval("tf.%s" % label_meta["dtype"])))
ds_mapper = functools.partial(parse_sparse_feature, feature_column_names=feature_column_names, feature_metas=feature_metas)
dataset = dataset.map(ds_mapper).batch(batch_size)
if cache:
dataset = dataset.cache()
return dataset
# NOTE: always use batch_size=1 when predicting to get the pairs of features and predict results
# to insert into result table.
pred_dataset = eval_input_fn(1)
one_batch = pred_dataset.__iter__().next()
# NOTE: must run predict one batch to initialize parameters
# see: https://www.tensorflow.org/alpha/guide/keras/saving_and_serializing#saving_subclassed_models
classifier.predict_on_batch(one_batch[0])
classifier.load_weights(save)
del pred_dataset
pred_dataset = eval_input_fn(1, cache=True).make_one_shot_iterator()
buff_rows = []
column_names = feature_column_names[:]
column_names.append(label_meta["feature_name"])
with buffered_db_writer(conn.driver, conn, result_table, column_names, 100, hdfs_namenode_addr, hive_location, hdfs_user, hdfs_pass) as w:
while True:
try:
features = pred_dataset.get_next()
except tf.errors.OutOfRangeError:
break
result = classifier.predict_on_batch(features[0])
result = classifier_pkg.prepare_prediction_column(result[0])
row = []
for idx, name in enumerate(feature_column_names):
val = features[0][name].numpy()[0]
row.append(str(val))
row.append(str(result))
w.write(row)
del pred_dataset
else:
if is_pai:
model_params["model_dir"] = FLAGS.checkpointDir
else:
model_params['model_dir'] = save
classifier = estimator(**model_params)
# FIXME(typhoonzero): copied from train.py
def pai_maxcompute_input_fn():
table_parts = pai_table.split(".")
if len(table_parts) == 2:
database, table_name = table_parts
elif len(table_parts) == 1:
table_name = pai_table
driver, dsn = datasource.split("://")
database = parseMaxComputeDSN(dsn)[-1]
else:
raise ValueError("error database.table format: %s" % pai_table)
tables = ["odps://%s/tables/%s" % (database, table_name)]
record_defaults = []
for name in feature_column_names:
dtype = get_dtype(feature_metas[name]["dtype"])
record_defaults.append(tf.constant(0, dtype=dtype, shape=feature_metas[name]["shape"]))
dataset = tf.data.TableRecordDataset(tables,
record_defaults=record_defaults,
selected_cols=",".join(feature_column_names))
def tensor_to_dict(*args):
num_features = len(feature_column_names)
features_dict = dict()
for idx in range(num_features):
name = feature_column_names[idx]
features_dict[name] = tf.reshape(args[idx], [-1])
return features_dict
return dataset.map(tensor_to_dict)
def fast_input_fn(generator):
feature_types = []
for name in feature_column_names:
if feature_metas[name]["is_sparse"]:
feature_types.append((tf.int64, tf.int32, tf.int64))
else:
feature_types.append(get_dtype(feature_metas[name]["dtype"]))
def _inner_input_fn():
if is_pai:
dataset = pai_maxcompute_input_fn()
else:
dataset = tf.data.Dataset.from_generator(generator, (tuple(feature_types), eval("tf.%s" % label_meta["dtype"])))
ds_mapper = functools.partial(parse_sparse_feature, feature_column_names=feature_column_names, feature_metas=feature_metas)
dataset = dataset.map(ds_mapper)
dataset = dataset.batch(1).cache()
iterator = dataset.make_one_shot_iterator()
features = iterator.get_next()
return features
return _inner_input_fn
column_names = feature_column_names[:]
column_names.append(label_meta["feature_name"])
pred_gen = db_generator(conn.driver, conn, select, feature_column_names, label_meta["feature_name"], feature_metas)()
fast_predictor = FastPredict(classifier, fast_input_fn)
with buffered_db_writer(conn.driver, conn, result_table, column_names, 100, hdfs_namenode_addr, hive_location, hdfs_user, hdfs_pass) as w:
while True:
try:
features = next(pred_gen)
except StopIteration:
break
result = fast_predictor.predict(features)
row = []
for idx, _ in enumerate(feature_column_names):
val = features[0][idx]
row.append(str(val))
if "class_ids" in list(result)[0]:
row.append(str(list(result)[0]["class_ids"][0]))
else:
# regression predictions
row.append(str(list(result)[0]["predictions"][0]))
w.write(row)
fast_predictor.close()
print("Done predicting. Predict table : %s" % result_table)
def estimator_predict(estimator, model_params, save, result_table,
feature_column_names, feature_column_names_map,
feature_columns, feature_metas, result_col_name,
datasource, select, hdfs_namenode_addr, hive_location,
hdfs_user, hdfs_pass, is_pai, pai_table):
if not is_pai:
conn = db.connect_with_data_source(datasource)
column_names = feature_column_names[:]
column_names.append(result_col_name)
if is_pai:
driver = "pai_maxcompute"
conn = None
pai_table_parts = pai_table.split(".")
formatted_pai_table = "odps://%s/tables/%s" % (pai_table_parts[0],
pai_table_parts[1])
predict_generator = db.pai_maxcompute_db_generator(
formatted_pai_table, feature_column_names, None, feature_metas)()
else:
driver = conn.driver
predict_generator = db.db_generator(conn.driver, conn, select,
feature_column_names, None,
feature_metas)()
# load from the exported model
with open("exported_path", "r") as fn:
export_path = fn.read()
if tf_is_version2():
imported = tf.saved_model.load(export_path)
else:
imported = tf.saved_model.load_v2(export_path)
def add_to_example(example, x, i):
feature_name = feature_column_names[i]
dtype_str = feature_metas[feature_name]["dtype"]
if feature_metas[feature_name]["delimiter"] != "":
if feature_metas[feature_name]["is_sparse"]:
# NOTE(typhoonzero): sparse feature will get (indices,values,shape) here, use indices only
values = x[0][i][0].flatten()
else:
values = x[0][i].flatten()
if dtype_str == "float32" or dtype_str == "float64":
example.features.feature[feature_name].float_list.value.extend(
list(values))
elif dtype_str == "int32" or dtype_str == "int64":
example.features.feature[feature_name].int64_list.value.extend(
list(values))
else:
if "feature_columns" in feature_columns:
idx = feature_column_names.index(feature_name)
fc = feature_columns["feature_columns"][idx]
else:
# DNNLinearCombinedXXX have dnn_feature_columns and linear_feature_columns param.
idx = -1
try:
idx = feature_column_names_map[
"dnn_feature_columns"].index(feature_name)
fc = feature_columns["dnn_feature_columns"][idx]
except:
try:
idx = feature_column_names_map[
"linear_feature_columns"].index(feature_name)
fc = feature_columns["linear_feature_columns"][idx]
except:
pass
if idx == -1:
raise ValueError(
"can not found feature %s in all feature columns")
if dtype_str == "float32" or dtype_str == "float64":
# need to pass a tuple(float, )
example.features.feature[feature_name].float_list.value.extend(
(float(x[0][i][0]), ))
elif dtype_str == "int32" or dtype_str == "int64":
numeric_type = type(tf.feature_column.numeric_column("tmp"))
if type(fc) == numeric_type:
example.features.feature[
feature_name].float_list.value.extend(
(float(x[0][i][0]), ))
else:
example.features.feature[
feature_name].int64_list.value.extend(
(int(x[0][i][0]), ))
elif dtype_str == "string":
example.features.feature[feature_name].bytes_list.value.extend(
x[0][i])
def predict(x):
example = tf.train.Example()
for i in range(len(feature_column_names)):
add_to_example(example, x, i)
return imported.signatures["predict"](
examples=tf.constant([example.SerializeToString()]))
with db.buffered_db_writer(driver, conn, result_table, column_names, 100,
hdfs_namenode_addr, hive_location, hdfs_user,
hdfs_pass) as w:
for features in predict_generator:
result = predict(features)
row = []
for idx, _ in enumerate(feature_column_names):
per_feature = features[0][idx]
if isinstance(per_feature, tuple) or isinstance(
per_feature, list):
# is sparse feature: tuple (indices, values, shape) or scalar
val = per_feature[0]
elif isinstance(per_feature, np.ndarray):
val = per_feature
# val = features[0][idx][0]
row.append(str(val))
if "class_ids" in result:
row.append(str(result["class_ids"].numpy()[0][0]))
else:
# regression predictions
row.append(str(result["predictions"].numpy()[0][0]))
w.write(row)
def estimator_predict(estimator, model_params, save, result_table,
feature_column_names, feature_metas, result_col_name,
datasource, select, hdfs_namenode_addr, hive_location,
hdfs_user, hdfs_pass, is_pai, pai_table):
if not is_pai:
conn = connect_with_data_source(datasource)
column_names = feature_column_names[:]
column_names.append(result_col_name)
if is_pai:
driver = "pai_maxcompute"
conn = None
pai_table_parts = pai_table.split(".")
formated_pai_table = "odps://%s/tables/%s" % (pai_table_parts[0],
pai_table_parts[1])
predict_generator = pai_maxcompute_db_generator(
formated_pai_table, feature_column_names, None, feature_metas)()
else:
driver = conn.driver
predict_generator = db_generator(conn.driver, conn, select,
feature_column_names, None,
feature_metas)()
# load from the exported model
if save.startswith("oss://"):
with open("exported_path", "r") as fn:
export_path = fn.read()
parts = save.split("?")
export_path_oss = parts[0] + export_path
if TF_VERSION_2:
imported = tf.saved_model.load(export_path_oss)
else:
imported = tf.saved_model.load_v2(export_path_oss)
else:
with open("exported_path", "r") as fn:
export_path = fn.read()
if TF_VERSION_2:
imported = tf.saved_model.load(export_path)
else:
imported = tf.saved_model.load_v2(export_path)
def add_to_example(example, x, i):
feature_name = feature_column_names[i]
dtype_str = feature_metas[feature_name]["dtype"]
if feature_metas[feature_name]["delimiter"] != "":
if feature_metas[feature_name]["is_sparse"]:
# NOTE(typhoonzero): sparse feature will get (indices,values,shape) here, use indices only
values = x[0][i][0].flatten()
else:
values = x[0][i].flatten()
if dtype_str == "float32" or dtype_str == "float64":
example.features.feature[feature_name].float_list.value.extend(
list(values))
elif dtype_str == "int32" or dtype_str == "int64":
example.features.feature[feature_name].int64_list.value.extend(
list(values))
else:
if dtype_str == "float32" or dtype_str == "float64":
# need to pass a tuple(float, )
example.features.feature[feature_name].float_list.value.extend(
(float(x[0][i][0]), ))
elif dtype_str == "int32" or dtype_str == "int64":
# FIXME(typhoonzero): figure out why int64 features need to convert to float
example.features.feature[feature_name].float_list.value.extend(
(float(x[0][i][0]), ))
elif dtype_str == "string":
example.features.feature[feature_name].bytes_list.value.extend(
x[0][i])
def predict(x):
example = tf.train.Example()
for i in range(len(feature_column_names)):
add_to_example(example, x, i)
return imported.signatures["predict"](
examples=tf.constant([example.SerializeToString()]))
with buffered_db_writer(driver, conn, result_table, column_names, 100,
hdfs_namenode_addr, hive_location, hdfs_user,
hdfs_pass) as w:
for features in predict_generator:
result = predict(features)
row = []
for idx, _ in enumerate(feature_column_names):
per_feature = features[0][idx]
if isinstance(per_feature, tuple) or isinstance(
per_feature, list):
# is sparse feature: tuple (indices, values, shape) or scalar
val = per_feature[0]
elif isinstance(per_feature, np.ndarray):
val = per_feature
# val = features[0][idx][0]
row.append(str(val))
if "class_ids" in result:
row.append(str(result["class_ids"].numpy()[0][0]))
else:
# regression predictions
row.append(str(result["predictions"].numpy()[0][0]))
w.write(row)
def xgb_shap_dataset(datasource,
select,
feature_column_names,
label_spec,
feature_specs,
is_pai,
pai_explain_table,
transform_fn=None,
feature_column_code=""):
label_column_name = label_spec["feature_name"]
if is_pai:
pai_table_parts = pai_explain_table.split(".")
formatted_pai_table = "odps://%s/tables/%s" % (pai_table_parts[0],
pai_table_parts[1])
stream = db.pai_maxcompute_db_generator(formatted_pai_table,
feature_column_names,
label_column_name,
feature_specs)
selected_cols = db.pai_selected_cols(formatted_pai_table)
else:
conn = db.connect_with_data_source(datasource)
stream = db.db_generator(conn.driver, conn, select,
feature_column_names, label_spec,
feature_specs)
selected_cols = db.selected_cols(conn.driver, conn, select)
if transform_fn:
column_names = transform_fn.get_column_names()
else:
column_names = feature_column_names
# NOTE(sneaxiy): pandas.DataFrame does not support Tensor whose rank is larger than 2.
# But `INDICATOR` would generate one hot vector for each element, and pandas.DataFrame
# would not accept `INDICATOR` results as its input. In a word, we do not support
# `TO EXPLAIN` when using `INDICATOR`.
xs = pd.DataFrame(columns=column_names)
dtypes = []
i = 0
for row, label in stream():
features = db.read_features_from_row(row, selected_cols,
feature_column_names,
feature_specs)
if transform_fn:
features = transform_fn(features)
# TODO(sneaxiy): support sparse features in `TO EXPLAIN`
features = [item[0] for item in features]
xs.loc[i] = features
if i == 0:
for f in features:
if isinstance(f, np.ndarray):
if f.dtype == np.float32 or f.dtype == np.float64:
dtypes.append('float32')
elif f.dtype == np.int32 or f.dtype == np.int64:
dtypes.append('int64')
else:
raise ValueError('Not supported data type {}'.format(
f.dtype))
elif isinstance(f, (np.float32, np.float64, float)):
dtypes.append('float32')
elif isinstance(f, (np.int32, np.int64, six.integer_types)):
dtypes.append('int64')
else:
raise ValueError('Not supported data type {}'.format(
type(f)))
i += 1
# NOTE(typhoonzero): set dtype to the feature's actual type, or the dtype
# may be "object". Use below code to reproduce:
# import pandas as pd
# feature_column_names=["a", "b"]
# xs = pd.DataFrame(columns=feature_column_names)
# for i in range(10):
# xs.loc[i] = [int(j) for j in range(2)]
# print(xs.dtypes)
for dtype, name in zip(dtypes, column_names):
xs[name] = xs[name].astype(dtype)
return xs
