def pai_download_table_data_worker(dname, feature_metas, feature_column_names,
label_meta, pai_table, slice_id,
slice_count, feature_column_code,
raw_data_dir):
import runtime.xgboost as xgboost_extended
feature_column_transformers = eval('[{}]'.format(feature_column_code))
transform_fn = xgboost_extended.feature_column.ComposedColumnTransformer(
feature_column_names, *feature_column_transformers)
label_column_name = label_meta['feature_name'] if label_meta else None
gen = db.pai_maxcompute_db_generator(pai_table,
label_column_name,
slice_id=slice_id,
slice_count=slice_count)()
selected_cols = db.pai_selected_cols(pai_table)
filename = "{}/{}.txt".format(dname, slice_id)
dump_dmatrix(filename,
gen,
feature_column_names,
feature_metas,
label_meta,
selected_cols,
transform_fn=transform_fn,
raw_data_dir=raw_data_dir)
def xgb_shap_dataset(datasource,
select,
feature_column_names,
label_meta,
feature_metas,
is_pai,
pai_explain_table,
transform_fn=None,
feature_column_code=""):
label_column_name = label_meta["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,
label_column_name)
selected_cols = db.pai_selected_cols(formatted_pai_table)
else:
conn = db.connect_with_data_source(datasource)
stream = db.db_generator(conn, select, label_meta)
selected_cols = db.selected_cols(conn, select)
if transform_fn:
feature_names = transform_fn.get_feature_column_names()
else:
feature_names = feature_column_names
xs = None
dtypes = []
sizes = []
offsets = []
i = 0
for row, label in stream():
features = db.read_features_from_row(row, selected_cols,
feature_column_names,
feature_metas)
if transform_fn:
features = transform_fn(features)
flatten_features = []
for j, feature in enumerate(features):
if len(feature) == 3: # convert sparse to dense
col_indices, values, dense_shape = feature
size = int(np.prod(dense_shape))
row_indices = np.zeros(shape=[col_indices.size])
sparse_matrix = scipy.sparse.csr_matrix(
(values, (row_indices, col_indices)), shape=[1, size])
values = sparse_matrix.toarray()
else:
values = feature[0]
if isinstance(values, np.ndarray):
flatten_features.extend(values.flatten().tolist())
if i == 0:
sizes.append(values.size)
dtypes.append(infer_dtype(values))
else:
flatten_features.append(values)
if i == 0:
sizes.append(1)
dtypes.append(infer_dtype(values))
# Create the column name according to the feature number
# of each column.
#
# If the column "c" contains only 1 feature, the result
# column name would be "c" too.
#
# If the column "c" contains 3 features,
# the result column name would be "c-0", "c-1" and "c-2"
if i == 0:
offsets = np.cumsum([0] + sizes)
column_names = []
for j in six.moves.range(len(offsets) - 1):
start = offsets[j]
end = offsets[j + 1]
if end - start == 1:
column_names.append(feature_names[j])
else:
for k in six.moves.range(start, end):
column_names.append('{}-{}'.format(
feature_names[j], k))
xs = pd.DataFrame(columns=column_names)
xs.loc[i] = flatten_features
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)
columns = xs.columns
for i, dtype in enumerate(dtypes):
for j in six.moves.range(offsets[i], offsets[i + 1]):
xs[columns[j]] = xs[columns[j]].astype(dtype)
return xs
def 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, 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)
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])
selected_cols = db.pai_selected_cols(formatted_pai_table)
predict_generator = db.pai_maxcompute_db_generator(
formatted_pai_table)()
else:
driver = conn.driver
# bypass all selected cols to the prediction result table
selected_cols = db.selected_cols(conn, select)
predict_generator = db.db_generator(conn, select)()
write_cols = selected_cols[:]
try:
train_label_index = selected_cols.index(train_label_name)
except ValueError:
train_label_index = -1
if train_label_index != -1:
del write_cols[train_label_index]
write_cols.append(result_col_name)
# 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, write_cols, 100,
hdfs_namenode_addr, hive_location, hdfs_user,
hdfs_pass) as w:
for row, _ in predict_generator:
features = db.read_features_from_row(row, selected_cols,
feature_column_names,
feature_metas)
result = predict((features, ))
if train_label_index != -1 and len(row) > train_label_index:
del row[train_label_index]
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 keras_predict(estimator, model_params, save, result_table, is_pai,
pai_table, feature_column_names, feature_metas,
train_label_name, result_col_name, datasource, select,
hdfs_namenode_addr, hive_location, hdfs_user, hdfs_pass):
classifier = init_model_with_feature_column(estimator, model_params)
classifier_pkg = sys.modules[estimator.__module__]
conn = None
if is_pai:
driver = "pai_maxcompute"
else:
conn = db.connect_with_data_source(datasource)
driver = conn.driver
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)
selected_cols = feature_column_names
else:
gen = db.db_generator(conn, select)
selected_cols = db.selected_cols(conn, select)
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"]))
tf_gen = tf_generator(gen, selected_cols, feature_column_names,
feature_metas)
dataset = tf.data.Dataset.from_generator(tf_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
# 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 = next(iter(pred_dataset))
# 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)
classifier.load_weights(save)
pred_dataset = eval_input_fn(1, cache=True).make_one_shot_iterator()
column_names = selected_cols[:]
train_label_index = selected_cols.index(train_label_name)
if train_label_index != -1:
del column_names[train_label_index]
column_names.append(result_col_name)
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 pred_dataset:
result = classifier.predict_on_batch(features)
# FIXME(typhoonzero): determine the predict result is classification by
# adding the prediction result together to see if it is close to 1.0.
if len(result[0]) == 1: # regression result
result = result[0][0]
else:
sum = 0
for i in result[0]:
sum += i
if np.isclose(sum, 1.0): # classification result
result = result[0].argmax(axis=-1)
else:
result = result[0] # multiple regression result
row = []
for idx, name in enumerate(feature_column_names):
val = features[name].numpy()[0][0]
row.append(str(val))
if isinstance(result, np.ndarray):
if len(result) > 1:
# NOTE(typhoonzero): if the output dimension > 1, format output tensor
# using a comma separated string. Only available for keras models.
row.append(",".join([str(i) for i in result]))
else:
row.append(str(result[0]))
else:
row.append(str(result))
w.write(row)
del pred_dataset
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)