Python pyarrow.int16方法代码示例

# 需要导入模块: import pyarrow [as 别名]
# 或者: from pyarrow import int16 [as 别名]
def _get_numeric_byte_size_test_cases():
  result = []
  for array_type, sizeof in [
      (pa.int8(), 1),
      (pa.uint8(), 1),
      (pa.int16(), 2),
      (pa.uint16(), 2),
      (pa.int32(), 4),
      (pa.uint32(), 4),
      (pa.int64(), 8),
      (pa.uint64(), 8),
      (pa.float32(), 4),
      (pa.float64(), 8),
  ]:
    result.append(
        dict(
            testcase_name=str(array_type),
            array=pa.array(range(9), type=array_type),
            slice_offset=2,
            slice_length=3,
            expected_size=(_all_false_null_bitmap_size(2) + sizeof * 9),
            expected_sliced_size=(_all_false_null_bitmap_size(1) + sizeof * 3)))
  return result 

# 需要导入模块: import pyarrow [as 别名]
# 或者: from pyarrow import int16 [as 别名]
def test_iterate_over_int16_chunk():
    random.seed(datetime.datetime.now())
    column_meta = [
            {"logicalType": "FIXED", "precision": "5", "scale": "0"},
            {"logicalType": "FIXED", "precision": "5", "scale": "0"}
    ]

    def int16_generator():
        return random.randint(-32768, 32767)

    iterate_over_test_chunk([pyarrow.int16(), pyarrow.int16()],
                            column_meta, int16_generator) 

# 需要导入模块: import pyarrow [as 别名]
# 或者: from pyarrow import int16 [as 别名]
def get_pyarrow_types():
    return {
        'bool': PA_BOOL,
        'float32': PA_FLOAT32,
        'float64': PA_FLOAT64,
        'int8': PA_INT8,
        'int16': PA_INT16,
        'int32': PA_INT32,
        'int64': PA_INT64,
        'string': PA_STRING,
        'timestamp': PA_TIMESTAMP,
        'base64': PA_BINARY
    }

# pylint: disable=too-many-branches,too-many-statements 

# 需要导入模块: import pyarrow [as 别名]
# 或者: from pyarrow import int16 [as 别名]
def setUp(self):
        self.sa_meta = sa.MetaData()
        self.data = [
            [17.124, 1.12, 3.14, 13.37],
            [1, 2, 3, 4],
            [1, 2, 3, 4],
            [1, 2, 3, 4],
            [True, None, False, True],
            ['string 1', 'string 2', None, 'string 3'],
            [datetime(2007, 7, 13, 1, 23, 34, 123456),
             None,
             datetime(2006, 1, 13, 12, 34, 56, 432539),
             datetime(2010, 8, 13, 5, 46, 57, 437699), ],
            ["Test Text", "Some#More#Test#  Text", "!@#$%%^&*&", None],
        ]
        self.table = sa.Table(
            'unit_test_table',
            self.sa_meta,
            sa.Column('real_col', sa.REAL),
            sa.Column('bigint_col', sa.BIGINT),
            sa.Column('int_col', sa.INTEGER),
            sa.Column('smallint_col', sa.SMALLINT),
            sa.Column('bool_col', sa.BOOLEAN),
            sa.Column('str_col', sa.VARCHAR),
            sa.Column('timestamp_col', sa.TIMESTAMP),
            sa.Column('plaintext_col', sa.TEXT),
        )

        self.expected_datatypes = [
            pa.float32(),
            pa.int64(),
            pa.int32(),
            pa.int16(),
            pa.bool_(),
            pa.string(),
            pa.timestamp('ns'),
            pa.string(),
        ] 

# 需要导入模块: import pyarrow [as 别名]
# 或者: from pyarrow import int16 [as 别名]
def test_arrow_schema_convertion():
    fields = [
        pa.field('string', pa.string()),
        pa.field('int8', pa.int8()),
        pa.field('int16', pa.int16()),
        pa.field('int32', pa.int32()),
        pa.field('int64', pa.int64()),
        pa.field('float', pa.float32()),
        pa.field('double', pa.float64()),
        pa.field('bool', pa.bool_(), False),
        pa.field('fixed_size_binary', pa.binary(10)),
        pa.field('variable_size_binary', pa.binary()),
        pa.field('decimal', pa.decimal128(3, 4)),
        pa.field('timestamp_s', pa.timestamp('s')),
        pa.field('timestamp_ns', pa.timestamp('ns')),
        pa.field('date_32', pa.date32()),
        pa.field('date_64', pa.date64())
    ]
    arrow_schema = pa.schema(fields)

    mock_dataset = _mock_parquet_dataset([], arrow_schema)

    unischema = Unischema.from_arrow_schema(mock_dataset)
    for name in arrow_schema.names:
        assert getattr(unischema, name).name == name
        assert getattr(unischema, name).codec is None

        if name == 'bool':
            assert not getattr(unischema, name).nullable
        else:
            assert getattr(unischema, name).nullable

    # Test schema preserve fields order
    field_name_list = [f.name for f in fields]
    assert list(unischema.fields.keys()) == field_name_list 

# 需要导入模块: import pyarrow [as 别名]
# 或者: from pyarrow import int16 [as 别名]
def to_arrow_type(dt):
    """ Convert Spark data type to pyarrow type
    """
    from distutils.version import LooseVersion
    import pyarrow as pa
    if type(dt) == BooleanType:
        arrow_type = pa.bool_()
    elif type(dt) == ByteType:
        arrow_type = pa.int8()
    elif type(dt) == ShortType:
        arrow_type = pa.int16()
    elif type(dt) == IntegerType:
        arrow_type = pa.int32()
    elif type(dt) == LongType:
        arrow_type = pa.int64()
    elif type(dt) == FloatType:
        arrow_type = pa.float32()
    elif type(dt) == DoubleType:
        arrow_type = pa.float64()
    elif type(dt) == DecimalType:
        arrow_type = pa.decimal128(dt.precision, dt.scale)
    elif type(dt) == StringType:
        arrow_type = pa.string()
    elif type(dt) == BinaryType:
        # TODO: remove version check once minimum pyarrow version is 0.10.0
        if LooseVersion(pa.__version__) < LooseVersion("0.10.0"):
            raise TypeError("Unsupported type in conversion to Arrow: " + str(dt) +
                            "\nPlease install pyarrow >= 0.10.0 for BinaryType support.")
        arrow_type = pa.binary()
    elif type(dt) == DateType:
        arrow_type = pa.date32()
    elif type(dt) == TimestampType:
        # Timestamps should be in UTC, JVM Arrow timestamps require a timezone to be read
        arrow_type = pa.timestamp('us', tz='UTC')
    elif type(dt) == ArrayType:
        if type(dt.elementType) == TimestampType:
            raise TypeError("Unsupported type in conversion to Arrow: " + str(dt))
        arrow_type = pa.list_(to_arrow_type(dt.elementType))
    else:
        raise TypeError("Unsupported type in conversion to Arrow: " + str(dt))
    return arrow_type 

# 需要导入模块: import pyarrow [as 别名]
# 或者: from pyarrow import int16 [as 别名]
def test_load_table_creates(self, con):

        data = pd.DataFrame(
            {
                "boolean_": [True, False],
                "smallint_cast": np.array([0, 1], dtype=np.int8),
                "smallint_": np.array([0, 1], dtype=np.int16),
                "int_": np.array([0, 1], dtype=np.int32),
                "bigint_": np.array([0, 1], dtype=np.int64),
                "float_": np.array([0, 1], dtype=np.float32),
                "double_": np.array([0, 1], dtype=np.float64),
                "varchar_": ["a", "b"],
                "text_": ['a', 'b'],
                "time_": [datetime.time(0, 11, 59), datetime.time(13)],
                "timestamp_": [pd.Timestamp("2016"), pd.Timestamp("2017")],
                "date_": [
                    datetime.date(2016, 1, 1),
                    datetime.date(2017, 1, 1),
                ],
            },
            columns=[
                'boolean_',
                'smallint_',
                'int_',
                'bigint_',
                'float_',
                'double_',
                'varchar_',
                'text_',
                'time_',
                'timestamp_',
                'date_',
            ],
        )

        con.execute("drop table if exists test_load_table_creates;")
        con.load_table("test_load_table_creates", data, create=True)
        con.execute("drop table if exists test_load_table_creates;") 

# 需要导入模块: import pyarrow [as 别名]
# 或者: from pyarrow import int16 [as 别名]
def _get_numba_typ_from_pa_typ(pa_typ):
    import pyarrow as pa
    _typ_map = {
        # boolean
        pa.bool_(): types.bool_,
        # signed int types
        pa.int8(): types.int8,
        pa.int16(): types.int16,
        pa.int32(): types.int32,
        pa.int64(): types.int64,
        # unsigned int types
        pa.uint8(): types.uint8,
        pa.uint16(): types.uint16,
        pa.uint32(): types.uint32,
        pa.uint64(): types.uint64,
        # float types (TODO: float16?)
        pa.float32(): types.float32,
        pa.float64(): types.float64,
        # String
        pa.string(): string_type,
        # date
        pa.date32(): types.NPDatetime('ns'),
        pa.date64(): types.NPDatetime('ns'),
        # time (TODO: time32, time64, ...)
        pa.timestamp('ns'): types.NPDatetime('ns'),
        pa.timestamp('us'): types.NPDatetime('ns'),
        pa.timestamp('ms'): types.NPDatetime('ns'),
        pa.timestamp('s'): types.NPDatetime('ns'),
    }
    if pa_typ not in _typ_map:
        raise ValueError("Arrow data type {} not supported yet".format(pa_typ))
    return _typ_map[pa_typ] 

# 需要导入模块: import pyarrow [as 别名]
# 或者: from pyarrow import int16 [as 别名]
def _dtype_to_arrow_type(dtype: np.dtype) -> pyarrow.DataType:
    if dtype == np.int8:
        return pyarrow.int8()
    elif dtype == np.int16:
        return pyarrow.int16()
    elif dtype == np.int32:
        return pyarrow.int32()
    elif dtype == np.int64:
        return pyarrow.int64()
    elif dtype == np.uint8:
        return pyarrow.uint8()
    elif dtype == np.uint16:
        return pyarrow.uint16()
    elif dtype == np.uint32:
        return pyarrow.uint32()
    elif dtype == np.uint64:
        return pyarrow.uint64()
    elif dtype == np.float16:
        return pyarrow.float16()
    elif dtype == np.float32:
        return pyarrow.float32()
    elif dtype == np.float64:
        return pyarrow.float64()
    elif dtype.kind == "M":
        # [2019-09-17] Pandas only allows "ns" unit -- as in, datetime64[ns]
        # https://github.com/pandas-dev/pandas/issues/7307#issuecomment-224180563
        assert dtype.str.endswith("[ns]")
        return pyarrow.timestamp(unit="ns", tz=None)
    elif dtype == np.object_:
        return pyarrow.string()
    else:
        raise RuntimeError("Unhandled dtype %r" % dtype)