1. Advisor
  2. petastorm
  3. functions
  4. petastorm.codecs.ScalarCodec
View all petastorm analysis

How to use the petastorm.codecs.ScalarCodec function in petastorm

To help you get started, we’ve selected a few petastorm examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github uber / petastorm / petastorm / unischema.py View on Github external
if types.is_int8(field_type):
        np_type = np.int8
        codec = ScalarCodec(ByteType())
    elif types.is_int16(field_type):
        np_type = np.int16
        codec = ScalarCodec(ShortType())
    elif types.is_int32(field_type):
        np_type = np.int32
        codec = ScalarCodec(IntegerType())
    elif types.is_int64(field_type):
        np_type = np.int64
        codec = ScalarCodec(LongType())
    elif types.is_string(field_type):
        np_type = np.unicode_
        codec = ScalarCodec(StringType())
    elif types.is_boolean(field_type):
        np_type = np.bool_
        codec = ScalarCodec(BooleanType())
    elif types.is_float32(field_type):
        np_type = np.float32
        codec = ScalarCodec(FloatType())
    elif types.is_float64(field_type):
        np_type = np.float64
        codec = ScalarCodec(DoubleType())
    elif types.is_decimal(field_type):
        np_type = Decimal
        codec = ScalarCodec(DecimalType(field_type.precision, field_type.scale))
    elif types.is_binary(field_type):
        codec = ScalarCodec(StringType())
        np_type = np.string_
    elif types.is_fixed_size_binary(field_type):
github uber / petastorm / petastorm / unischema.py View on Github external
codec = ScalarCodec(LongType())
    elif types.is_string(field_type):
        np_type = np.unicode_
        codec = ScalarCodec(StringType())
    elif types.is_boolean(field_type):
        np_type = np.bool_
        codec = ScalarCodec(BooleanType())
    elif types.is_float32(field_type):
        np_type = np.float32
        codec = ScalarCodec(FloatType())
    elif types.is_float64(field_type):
        np_type = np.float64
        codec = ScalarCodec(DoubleType())
    elif types.is_decimal(field_type):
        np_type = Decimal
        codec = ScalarCodec(DecimalType(field_type.precision, field_type.scale))
    elif types.is_binary(field_type):
        codec = ScalarCodec(StringType())
        np_type = np.string_
    elif types.is_fixed_size_binary(field_type):
        codec = ScalarCodec(StringType())
        np_type = np.string_
    elif types.is_date(field_type):
        np_type = np.datetime64
        codec = ScalarCodec(DateType())
    elif types.is_timestamp(field_type):
        np_type = np.datetime64
        codec = ScalarCodec(TimestampType())
    elif types.is_list(field_type):
        _, np_type = _numpy_and_codec_from_arrow_type(field_type.value_type)
        codec = None
    else:
github uber / petastorm / petastorm / unischema.py View on Github external
codec = ScalarCodec(DoubleType())
    elif types.is_decimal(field_type):
        np_type = Decimal
        codec = ScalarCodec(DecimalType(field_type.precision, field_type.scale))
    elif types.is_binary(field_type):
        codec = ScalarCodec(StringType())
        np_type = np.string_
    elif types.is_fixed_size_binary(field_type):
        codec = ScalarCodec(StringType())
        np_type = np.string_
    elif types.is_date(field_type):
        np_type = np.datetime64
        codec = ScalarCodec(DateType())
    elif types.is_timestamp(field_type):
        np_type = np.datetime64
        codec = ScalarCodec(TimestampType())
    elif types.is_list(field_type):
        _, np_type = _numpy_and_codec_from_arrow_type(field_type.value_type)
        codec = None
    else:
        raise ValueError('Cannot auto-create unischema due to unsupported column type {}'.format(field_type))
    return codec, np_type
github uber / petastorm / petastorm / unischema.py View on Github external
def _numpy_and_codec_from_arrow_type(field_type):
    from pyarrow import types

    if types.is_int8(field_type):
        np_type = np.int8
        codec = ScalarCodec(ByteType())
    elif types.is_int16(field_type):
        np_type = np.int16
        codec = ScalarCodec(ShortType())
    elif types.is_int32(field_type):
        np_type = np.int32
        codec = ScalarCodec(IntegerType())
    elif types.is_int64(field_type):
        np_type = np.int64
        codec = ScalarCodec(LongType())
    elif types.is_string(field_type):
        np_type = np.unicode_
        codec = ScalarCodec(StringType())
    elif types.is_boolean(field_type):
        np_type = np.bool_
        codec = ScalarCodec(BooleanType())
    elif types.is_float32(field_type):
        np_type = np.float32
        codec = ScalarCodec(FloatType())
    elif types.is_float64(field_type):
        np_type = np.float64
        codec = ScalarCodec(DoubleType())
    elif types.is_decimal(field_type):
github uber / petastorm / petastorm / unischema.py View on Github external
codec = ScalarCodec(FloatType())
    elif types.is_float64(field_type):
        np_type = np.float64
        codec = ScalarCodec(DoubleType())
    elif types.is_decimal(field_type):
        np_type = Decimal
        codec = ScalarCodec(DecimalType(field_type.precision, field_type.scale))
    elif types.is_binary(field_type):
        codec = ScalarCodec(StringType())
        np_type = np.string_
    elif types.is_fixed_size_binary(field_type):
        codec = ScalarCodec(StringType())
        np_type = np.string_
    elif types.is_date(field_type):
        np_type = np.datetime64
        codec = ScalarCodec(DateType())
    elif types.is_timestamp(field_type):
        np_type = np.datetime64
        codec = ScalarCodec(TimestampType())
    elif types.is_list(field_type):
        _, np_type = _numpy_and_codec_from_arrow_type(field_type.value_type)
        codec = None
    else:
        raise ValueError('Cannot auto-create unischema due to unsupported column type {}'.format(field_type))
    return codec, np_type
github uber / petastorm / petastorm / unischema.py View on Github external
def _numpy_and_codec_from_arrow_type(field_type):
    from pyarrow import types

    if types.is_int8(field_type):
        np_type = np.int8
        codec = ScalarCodec(ByteType())
    elif types.is_int16(field_type):
        np_type = np.int16
        codec = ScalarCodec(ShortType())
    elif types.is_int32(field_type):
        np_type = np.int32
        codec = ScalarCodec(IntegerType())
    elif types.is_int64(field_type):
        np_type = np.int64
        codec = ScalarCodec(LongType())
    elif types.is_string(field_type):
        np_type = np.unicode_
        codec = ScalarCodec(StringType())
    elif types.is_boolean(field_type):
        np_type = np.bool_
        codec = ScalarCodec(BooleanType())
    elif types.is_float32(field_type):
        np_type = np.float32
        codec = ScalarCodec(FloatType())
    elif types.is_float64(field_type):
        np_type = np.float64
        codec = ScalarCodec(DoubleType())
    elif types.is_decimal(field_type):
        np_type = Decimal
        codec = ScalarCodec(DecimalType(field_type.precision, field_type.scale))
    elif types.is_binary(field_type):
github uber / petastorm / petastorm / unischema.py View on Github external
codec = ScalarCodec(ShortType())
    elif types.is_int32(field_type):
        np_type = np.int32
        codec = ScalarCodec(IntegerType())
    elif types.is_int64(field_type):
        np_type = np.int64
        codec = ScalarCodec(LongType())
    elif types.is_string(field_type):
        np_type = np.unicode_
        codec = ScalarCodec(StringType())
    elif types.is_boolean(field_type):
        np_type = np.bool_
        codec = ScalarCodec(BooleanType())
    elif types.is_float32(field_type):
        np_type = np.float32
        codec = ScalarCodec(FloatType())
    elif types.is_float64(field_type):
        np_type = np.float64
        codec = ScalarCodec(DoubleType())
    elif types.is_decimal(field_type):
        np_type = Decimal
        codec = ScalarCodec(DecimalType(field_type.precision, field_type.scale))
    elif types.is_binary(field_type):
        codec = ScalarCodec(StringType())
        np_type = np.string_
    elif types.is_fixed_size_binary(field_type):
        codec = ScalarCodec(StringType())
        np_type = np.string_
    elif types.is_date(field_type):
        np_type = np.datetime64
        codec = ScalarCodec(DateType())
    elif types.is_timestamp(field_type):

petastorm

Petastorm is a library enabling the use of Parquet storage from Tensorflow, Pytorch, and other Python-based ML training frameworks.

GitHub
Apache-2.0
Latest version published 2 years ago

Package Health Score

55 / 100
Full package analysis

Popular petastorm functions

Similar packages