sagemaker.core.serializers.base

sagemaker.core.serializers.base#

Implements base methods for serializing data for an inference endpoint.

Classes

`BaseSerializer`()	Abstract base class for creation of new serializers.
`CSVSerializer`([content_type])	Serialize data of various formats to a CSV-formatted string.
`DataSerializer`([content_type])	Serialize data in any file by extracting raw bytes from the file.
`IdentitySerializer`([content_type])	Serialize data by returning data without modification.
`JSONLinesSerializer`([content_type])	Serialize data to a JSON Lines formatted string.
`JSONSerializer`([content_type])	Serialize data to a JSON formatted string.
`LibSVMSerializer`([content_type])	Serialize data of various formats to a LibSVM-formatted string.
`NumpySerializer`([dtype, content_type])	Serialize data to a buffer using the .npy format.
`RecordSerializer`([content_type])	Serialize a NumPy array for an inference request.
`SimpleBaseSerializer`([content_type])	Abstract base class for creation of new serializers.
`SparseMatrixSerializer`([content_type])	Serialize a sparse matrix to a buffer using the .npz format.
`StringSerializer`([content_type])	Encode the string to utf-8 bytes.
`TorchTensorSerializer`([content_type])	Serialize torch.Tensor to a buffer by converting tensor to numpy and call NumpySerializer.

class sagemaker.core.serializers.base.BaseSerializer[source]#

Bases: ABC

Abstract base class for creation of new serializers.

Provides a skeleton for customization requiring the overriding of the method serialize and the class attribute CONTENT_TYPE.

abstract property CONTENT_TYPE#: The MIME type of the data sent to the inference endpoint.

abstract serialize(data)[source]#

Serialize data into the media type specified by CONTENT_TYPE.

Parameters:: data (object) – Data to be serialized.
Returns:: Serialized data used for a request.
Return type:: object

class sagemaker.core.serializers.base.CSVSerializer(content_type='text/csv')[source]#

Bases: SimpleBaseSerializer

Serialize data of various formats to a CSV-formatted string.

serialize(data)[source]#

Serialize data of various formats to a CSV-formatted string.

Parameters:: data (object) – Data to be serialized. Can be a NumPy array, list, file, Pandas DataFrame, or buffer.
Returns:: The data serialized as a CSV-formatted string.
Return type:: str

class sagemaker.core.serializers.base.DataSerializer(content_type='file-path/raw-bytes')[source]#

Bases: SimpleBaseSerializer

Serialize data in any file by extracting raw bytes from the file.

serialize(data)[source]#

Serialize file data to a raw bytes.

Parameters:: data (object) – Data to be serialized. The data can be a string representing file-path or the raw bytes from a file.
Returns:: The data serialized as raw-bytes from the input.
Return type:: raw-bytes

class sagemaker.core.serializers.base.IdentitySerializer(content_type='application/octet-stream')[source]#

Bases: SimpleBaseSerializer

Serialize data by returning data without modification.

This serializer may be useful if, for example, you’re sending raw bytes such as from an image file’s .read() method.

serialize(data)[source]#

Return data without modification.

Parameters:: data (object) – Data to be serialized.
Returns:: The unmodified data.
Return type:: object

class sagemaker.core.serializers.base.JSONLinesSerializer(content_type='application/jsonlines')[source]#

Bases: SimpleBaseSerializer

Serialize data to a JSON Lines formatted string.

serialize(data)[source]#

Serialize data of various formats to a JSON Lines formatted string.

Parameters:

data (object) – Data to be serialized. The data can be a string, iterable of JSON serializable objects, or a file-like object.

Returns:

The data serialized as a string containing newline-separated: JSON values.

Return type:

str

class sagemaker.core.serializers.base.JSONSerializer(content_type='application/json')[source]#

Bases: SimpleBaseSerializer

Serialize data to a JSON formatted string.

serialize(data)[source]#

Serialize data of various formats to a JSON formatted string.

Parameters:: data (object) – Data to be serialized.
Returns:: The data serialized as a JSON string.
Return type:: str

class sagemaker.core.serializers.base.LibSVMSerializer(content_type='text/libsvm')[source]#

Bases: SimpleBaseSerializer

Serialize data of various formats to a LibSVM-formatted string.

The data must already be in LIBSVM file format: <label> <index1>:<value1> <index2>:<value2> …

It is suitable for sparse datasets since it does not store zero-valued features.

serialize(data)[source]#

Serialize data of various formats to a LibSVM-formatted string.

Parameters:: data (object) – Data to be serialized. Can be a string or a file-like object.
Returns:: The data serialized as a LibSVM-formatted string.
Return type:: str
Raises:: ValueError – If unable to handle input format

class sagemaker.core.serializers.base.NumpySerializer(dtype=None, content_type='application/x-npy')[source]#

Bases: SimpleBaseSerializer

Serialize data to a buffer using the .npy format.

serialize(data)[source]#

Serialize data to a buffer using the .npy format.

Parameters:: data (object) – Data to be serialized. Can be a NumPy array, list, file, or buffer.
Returns:: A buffer containing data serialzied in the .npy format.
Return type:: io.BytesIO

class sagemaker.core.serializers.base.RecordSerializer(content_type='application/x-recordio-protobuf')[source]#

Bases: SimpleBaseSerializer

Serialize a NumPy array for an inference request.

serialize(data)[source]#

Serialize a NumPy array into a buffer containing RecordIO records.

Parameters:: data (numpy.ndarray) – The data to serialize.
Returns:: A buffer containing the data serialized as records.
Return type:: io.BytesIO

class sagemaker.core.serializers.base.SimpleBaseSerializer(content_type='application/json')[source]#

Bases: BaseSerializer

Abstract base class for creation of new serializers.

This class extends the API of :class:~`sagemaker.serializers.BaseSerializer` with more user-friendly options for setting the Content-Type header, in situations where it can be provided at init and freely updated.

property CONTENT_TYPE#: The data MIME type set in the Content-Type header on prediction endpoint requests.

class sagemaker.core.serializers.base.SparseMatrixSerializer(content_type='application/x-npz')[source]#

Bases: SimpleBaseSerializer

Serialize a sparse matrix to a buffer using the .npz format.

serialize(data)[source]#

Serialize a sparse matrix to a buffer using the .npz format.

Sparse matrices can be in the csc, csr, bsr, dia or coo formats.

Parameters:: data (scipy.sparse.spmatrix) – The sparse matrix to serialize.
Returns:: A buffer containing the serialized sparse matrix.
Return type:: io.BytesIO

class sagemaker.core.serializers.base.StringSerializer(content_type='text/plain')[source]#

Bases: SimpleBaseSerializer

Encode the string to utf-8 bytes.

serialize(data)[source]#

Encode the string to utf-8 bytes.

Parameters:: data (object) – Data to be serialized.
Returns:: The data serialized as raw-bytes from the input.
Return type:: raw-bytes

class sagemaker.core.serializers.base.TorchTensorSerializer(content_type='tensor/pt')[source]#

Bases: SimpleBaseSerializer

Serialize torch.Tensor to a buffer by converting tensor to numpy and call NumpySerializer.

Parameters:: data (object) – Data to be serialized. The data must be of torch.Tensor type.
Returns:: The data serialized as raw-bytes from the input.
Return type:: raw-bytes

serialize(data)[source]#

Serialize torch.Tensor to a buffer.

Parameters:: data (object) – Data to be serialized. The data must be of torch.Tensor type.
Returns:: The data serialized as raw-bytes from the input.
Return type:: raw-bytes

sagemaker.core.serializers.base

Contents

sagemaker.core.serializers.base#