def predict(self, data, batch_size=32, feature_cols=None, profile=False):
"""
Using this PyTorch model to make predictions on the data.
:param data: An instance of SparkXShards or a Spark DataFrame
:param batch_size: The number of samples per batch for each worker. Default is 32.
:param profile: Boolean. Whether to return time stats for the training procedure.
Default is False.
:param feature_cols: feature column names if data is a Spark DataFrame.
:return: A SparkXShards that contains the predictions with key "prediction" in each shard
"""
from bigdl.orca.data import SparkXShards
param = dict(batch_size=batch_size, profile=profile)
from pyspark.sql import DataFrame
if isinstance(data, DataFrame):
xshards, _ = dataframe_to_xshards(data,
validation_data=None,
feature_cols=feature_cols,
label_cols=None,
mode="predict")
pred_shards = self._predict_spark_xshards(xshards, param)
result = convert_predict_xshards_to_dataframe(data, pred_shards)
elif isinstance(data, SparkXShards):
if data._get_class_name() == 'pandas.core.frame.DataFrame':
data = process_xshards_of_pandas_dataframe(data, feature_cols)
pred_shards = self._predict_spark_xshards(data, param)
result = update_predict_xshards(data, pred_shards)
else:
raise ValueError(
"Only xshards or Spark DataFrame is supported for predict")
return result
def predict(self,
data,
batch_size=None,
verbose=1,
steps=None,
callbacks=None,
data_config=None,
feature_cols=None):
"""
Predict the input data
:param data: predict input data. It can be XShards or Spark DataFrame.
If data is XShards, each partition can be a Pandas DataFrame or a dictionary of
{'x': feature}, where feature is a numpy array or a tuple of numpy arrays.
:param batch_size: Batch size used for inference. Default: None.
:param verbose: Prints output of one model if true.
:param steps: Total number of steps (batches of samples) before declaring the prediction
round finished. Ignored with the default value of None.
:param callbacks: List of Keras compatible callbacks to apply during prediction.
:param data_config: An optional dictionary that can be passed to data creator function.
:param feature_cols: Feature column name(s) of data. Only used when data is a Spark
DataFrame or an XShards of Pandas DataFrame. Default: None.
:return:
"""
logger.info("Starting predict step.")
params = dict(
verbose=verbose,
batch_size=batch_size,
steps=steps,
callbacks=callbacks,
data_config=data_config,
)
from bigdl.orca.data import SparkXShards
from pyspark.sql import DataFrame
if isinstance(data, DataFrame):
xshards, _ = dataframe_to_xshards(data,
validation_data=None,
feature_cols=feature_cols,
label_cols=None,
mode="predict",
accept_str_col=True)
pred_shards = self._predict_spark_xshards(xshards, params)
result = convert_predict_xshards_to_dataframe(data, pred_shards)
elif isinstance(data, SparkXShards):
if data._get_class_name() == 'pandas.core.frame.DataFrame':
data = process_xshards_of_pandas_dataframe(data, feature_cols)
pred_shards = self._predict_spark_xshards(data, params)
result = update_predict_xshards(data, pred_shards)
else:
raise ValueError(
"Only xshards or Spark DataFrame is supported for predict")
return result
def predict(self, data, feature_cols=None, batch_size=4):
"""
Predict input data
:param batch_size: Int. Set batch Size, default is 4.
:param data: data to be predicted. XShards, Spark DataFrame, numpy array and list of numpy
arrays are supported. If data is XShards, each partition is a dictionary of {'x':
feature}, where feature(label) is a numpy array or a list of numpy arrays.
:param feature_cols: Feature column name(s) of data. Only used when data is a Spark
DataFrame. Default: None.
:return: predicted result.
If the input data is XShards, the predict result is a XShards, each partition
of the XShards is a dictionary of {'prediction': result}, where the result is a
numpy array or a list of numpy arrays.
If the input data is numpy arrays or list of numpy arrays, the predict result is
a numpy array or a list of numpy arrays.
"""
sc = init_nncontext()
model_bytes_broadcast = sc.broadcast(self.model_bytes)
weight_bytes_broadcast = sc.broadcast(self.weight_bytes)
def partition_inference(partition):
model_bytes = model_bytes_broadcast.value
weight_bytes = weight_bytes_broadcast.value
partition = list(partition)
data_num = len(partition)
ie = IECore()
config = {'CPU_THREADS_NUM': str(self.core_num)}
ie.set_config(config, 'CPU')
net = ie.read_network(model=model_bytes,
weights=weight_bytes,
init_from_buffer=True)
net.batch_size = batch_size
local_model = ie.load_network(network=net,
device_name="CPU",
num_requests=data_num)
inputs = list(iter(local_model.requests[0].input_blobs))
outputs = list(iter(local_model.requests[0].output_blobs))
assert len(
outputs) != 0, "The number of model outputs should not be 0."
def add_elem(d):
d_len = len(d)
if d_len < batch_size:
rep_time = [1] * (d_len - 1)
rep_time.append(batch_size - d_len + 1)
return np.repeat(d, rep_time, axis=0), d_len
else:
return d, d_len
results = []
for idx, batch_data in enumerate(partition):
infer_request = local_model.requests[idx]
input_dict = dict()
elem_num = 0
if isinstance(batch_data, list):
for i, input in enumerate(inputs):
input_dict[input], elem_num = add_elem(batch_data[i])
else:
input_dict[inputs[0]], elem_num = add_elem(batch_data)
infer_request.infer(input_dict)
if len(outputs) == 1:
results.append(infer_request.output_blobs[
outputs[0]].buffer[:elem_num])
else:
results.append(
list(
map(
lambda output: infer_request.output_blobs[
output].buffer[:elem_num], outputs)))
return results
def predict_transform(dict_data, batch_size):
assert isinstance(dict_data, dict), "each shard should be an dict"
assert "x" in dict_data, "key x should in each shard"
feature_data = dict_data["x"]
if isinstance(feature_data, np.ndarray):
assert feature_data.shape[0] <= batch_size, \
"The batch size of input data (the second dim) should be less than the model " \
"batch size, otherwise some inputs will be ignored."
elif isinstance(feature_data, list):
for elem in feature_data:
assert isinstance(elem, np.ndarray), "Each element in the x list should be " \
"a ndarray, but get " + \
elem.__class__.__name__
assert elem.shape[0] <= batch_size, "The batch size of each input data (the " \
"second dim) should be less than the " \
"model batch size, otherwise some inputs " \
"will be ignored."
else:
raise ValueError(
"x in each shard should be a ndarray or a list of ndarray."
)
return feature_data
if isinstance(data, DataFrame):
from bigdl.orca.learn.utils import dataframe_to_xshards, convert_predict_rdd_to_dataframe
xshards, _ = dataframe_to_xshards(data,
validation_data=None,
feature_cols=feature_cols,
label_cols=None,
mode="predict")
transformed_data = xshards.transform_shard(predict_transform,
batch_size)
result_rdd = transformed_data.rdd.mapPartitions(
lambda iter: partition_inference(iter))
return convert_predict_rdd_to_dataframe(
data, result_rdd.flatMap(lambda data: data))
elif isinstance(data, SparkXShards):
transformed_data = data.transform_shard(predict_transform,
batch_size)
result_rdd = transformed_data.rdd.mapPartitions(
lambda iter: partition_inference(iter))
def update_result_shard(data):
shard, y = data
shard["prediction"] = y
return shard
return SparkXShards(
data.rdd.zip(result_rdd).map(update_result_shard))
elif isinstance(data, (np.ndarray, list)):
if isinstance(data, np.ndarray):
split_num = math.ceil(len(data) / batch_size)
arrays = np.array_split(data, split_num)
num_slices = min(split_num, self.node_num)
data_rdd = sc.parallelize(arrays, numSlices=num_slices)
elif isinstance(data, list):
flattened = nest.flatten(data)
data_length = len(flattened[0])
data_to_be_rdd = []
split_num = math.ceil(flattened[0].shape[0] / batch_size)
num_slices = min(split_num, self.node_num)
for i in range(split_num):
data_to_be_rdd.append([])
for x in flattened:
assert isinstance(x, np.ndarray), "the data in the data list should be " \
"ndarrays, but get " + \
x.__class__.__name__
assert len(x) == data_length, \
"the ndarrays in data must all have the same size in first dimension" \
", got first ndarray of size {} and another {}".format(data_length, len(x))
x_parts = np.array_split(x, split_num)
for idx, x_part in enumerate(x_parts):
data_to_be_rdd[idx].append(x_part)
data_to_be_rdd = [
nest.pack_sequence_as(data, shard)
for shard in data_to_be_rdd
]
data_rdd = sc.parallelize(data_to_be_rdd, numSlices=num_slices)
print("Partition number: ", data_rdd.getNumPartitions())
result_rdd = data_rdd.mapPartitions(
lambda iter: partition_inference(iter))
result_arr_list = result_rdd.collect()
result_arr = None
if isinstance(result_arr_list[0], list):
result_arr = [
np.concatenate([r[i] for r in result_arr_list], axis=0)
for i in range(len(result_arr_list[0]))
]
elif isinstance(result_arr_list[0], np.ndarray):
result_arr = np.concatenate(result_arr_list, axis=0)
return result_arr
else:
raise ValueError(
"Only XShards, Spark DataFrame, a numpy array and a list of numpy arr"
"ays are supported as input data, but get " +
data.__class__.__name__)
def predict(self,
data,
batch_size=None,
verbose=1,
steps=None,
callbacks=None,
data_config=None,
feature_cols=None):
"""
Predict the input data
:param data: predict input data. It can be XShards or Spark DataFrame.
If data is XShards, each partition can be a Pandas DataFrame or a dictionary of
{'x': feature}, where feature is a numpy array or a tuple of numpy arrays.
:param batch_size: Batch size used for inference. Default: None.
:param verbose: Prints output of one model if true.
:param steps: Total number of steps (batches of samples) before declaring the prediction
round finished. Ignored with the default value of None.
:param callbacks: List of Keras compatible callbacks to apply during prediction.
:param data_config: An optional dictionary that can be passed to data creator function.
:param feature_cols: Feature column name(s) of data. Only used when data is a Spark
DataFrame or an XShards of Pandas DataFrame. Default: None.
:return:
"""
logger.info("Starting predict step.")
sc = OrcaContext.get_spark_context()
if self.model_weights:
weights = sc.broadcast(self.model_weights)
else:
weights = None
init_params = dict(model_creator=self.model_creator,
compile_args_creator=self.compile_args_creator,
config=self.config,
verbose=self.verbose,
size=self.num_workers,
model_weights=weights,
mode="predict",
cluster_info=None)
params = dict(verbose=verbose,
batch_size=batch_size,
steps=steps,
callbacks=callbacks,
data_config=data_config)
if isinstance(data, DataFrame):
data = data.repartition(self.num_workers)
xshards, _ = dataframe_to_xshards(data,
validation_data=None,
feature_cols=feature_cols,
label_cols=None,
mode="predict",
accept_str_col=True)
def transform_func(iter, init_param, param):
partition_data = list(iter)
# res = combine_in_partition(partition_data)
param["data_creator"] = make_data_creator(partition_data)
return SparkRunner(**init_param).predict(**param)
pred_shards = SparkXShards(xshards.rdd.repartition(self.num_workers) \
.mapPartitions(
lambda iter: transform_func(iter, init_params, params)))
result = convert_predict_xshards_to_dataframe(data, pred_shards)
else:
raise ValueError(
"Only xshards or Spark DataFrame is supported for predict")
return result