Python pyarrow.int32函数代码示例

def test_type_comparisons():
    val = pa.int32()
    assert val == pa.int32()
    assert val == 'int32'

    with pytest.raises(TypeError):
        val == 5

def test_schema():
    fields = [
        pa.field('foo', pa.int32()),
        pa.field('bar', pa.string()),
        pa.field('baz', pa.list_(pa.int8()))
    ]
    sch = pa.schema(fields)

    assert sch.names == ['foo', 'bar', 'baz']
    assert sch.types == [pa.int32(), pa.string(), pa.list_(pa.int8())]

    assert len(sch) == 3
    assert sch[0].name == 'foo'
    assert sch[0].type == fields[0].type
    assert sch.field_by_name('foo').name == 'foo'
    assert sch.field_by_name('foo').type == fields[0].type

    assert repr(sch) == """\
foo: int32
bar: string
baz: list<item: int8>
  child 0, item: int8"""

    with pytest.raises(TypeError):
        pa.schema([None])

def test_table_unsafe_casting():
    data = [
        pa.array(range(5), type=pa.int64()),
        pa.array([-10, -5, 0, 5, 10], type=pa.int32()),
        pa.array([1.1, 2.2, 3.3, 4.4, 5.5], type=pa.float64()),
        pa.array(['ab', 'bc', 'cd', 'de', 'ef'], type=pa.string())
    ]
    table = pa.Table.from_arrays(data, names=tuple('abcd'))

    expected_data = [
        pa.array(range(5), type=pa.int32()),
        pa.array([-10, -5, 0, 5, 10], type=pa.int16()),
        pa.array([1, 2, 3, 4, 5], type=pa.int64()),
        pa.array(['ab', 'bc', 'cd', 'de', 'ef'], type=pa.string())
    ]
    expected_table = pa.Table.from_arrays(expected_data, names=tuple('abcd'))

    target_schema = pa.schema([
        pa.field('a', pa.int32()),
        pa.field('b', pa.int16()),
        pa.field('c', pa.int64()),
        pa.field('d', pa.string())
    ])

    with pytest.raises(pa.ArrowInvalid,
                       match='Floating point value truncated'):
        table.cast(target_schema)

    casted_table = table.cast(target_schema, safe=False)
    assert casted_table.equals(expected_table)

def test_orcfile_empty():
    from pyarrow import orc
    f = orc.ORCFile(path_for_orc_example('TestOrcFile.emptyFile'))
    table = f.read()
    assert table.num_rows == 0
    schema = table.schema
    expected_schema = pa.schema([
        ('boolean1', pa.bool_()),
        ('byte1', pa.int8()),
        ('short1', pa.int16()),
        ('int1', pa.int32()),
        ('long1', pa.int64()),
        ('float1', pa.float32()),
        ('double1', pa.float64()),
        ('bytes1', pa.binary()),
        ('string1', pa.string()),
        ('middle', pa.struct([
            ('list', pa.list_(pa.struct([
                ('int1', pa.int32()),
                ('string1', pa.string()),
                ]))),
            ])),
        ('list', pa.list_(pa.struct([
            ('int1', pa.int32()),
            ('string1', pa.string()),
            ]))),
        ('map', pa.list_(pa.struct([
            ('key', pa.string()),
            ('value', pa.struct([
                ('int1', pa.int32()),
                ('string1', pa.string()),
                ])),
            ]))),
        ])
    assert schema == expected_schema

def test_is_union():
    for mode in [pa.lib.UnionMode_SPARSE, pa.lib.UnionMode_DENSE]:
        assert types.is_union(pa.union([pa.field('a', pa.int32()),
                                        pa.field('b', pa.int8()),
                                        pa.field('c', pa.string())],
                                       mode=mode))
    assert not types.is_union(pa.list_(pa.int32()))

def test_cast_from_null():
    in_data = [None] * 3
    in_type = pa.null()
    out_types = [
        pa.null(),
        pa.uint8(),
        pa.float16(),
        pa.utf8(),
        pa.binary(),
        pa.binary(10),
        pa.list_(pa.int16()),
        pa.decimal128(19, 4),
        pa.timestamp('us'),
        pa.timestamp('us', tz='UTC'),
        pa.timestamp('us', tz='Europe/Paris'),
        pa.struct([pa.field('a', pa.int32()),
                   pa.field('b', pa.list_(pa.int8())),
                   pa.field('c', pa.string())]),
        ]
    for out_type in out_types:
        _check_cast_case((in_data, in_type, in_data, out_type))

    out_types = [
        pa.dictionary(pa.int32(), pa.string()),
        pa.union([pa.field('a', pa.binary(10)),
                  pa.field('b', pa.string())], mode=pa.lib.UnionMode_DENSE),
        pa.union([pa.field('a', pa.binary(10)),
                  pa.field('b', pa.string())], mode=pa.lib.UnionMode_SPARSE),
        ]
    in_arr = pa.array(in_data, type=pa.null())
    for out_type in out_types:
        with pytest.raises(NotImplementedError):
            in_arr.cast(out_type)

def test_table_safe_casting():
    data = [
        pa.array(range(5), type=pa.int64()),
        pa.array([-10, -5, 0, 5, 10], type=pa.int32()),
        pa.array([1.0, 2.0, 3.0, 4.0, 5.0], type=pa.float64()),
        pa.array(['ab', 'bc', 'cd', 'de', 'ef'], type=pa.string())
    ]
    table = pa.Table.from_arrays(data, names=tuple('abcd'))

    expected_data = [
        pa.array(range(5), type=pa.int32()),
        pa.array([-10, -5, 0, 5, 10], type=pa.int16()),
        pa.array([1, 2, 3, 4, 5], type=pa.int64()),
        pa.array(['ab', 'bc', 'cd', 'de', 'ef'], type=pa.string())
    ]
    expected_table = pa.Table.from_arrays(expected_data, names=tuple('abcd'))

    target_schema = pa.schema([
        pa.field('a', pa.int32()),
        pa.field('b', pa.int16()),
        pa.field('c', pa.int64()),
        pa.field('d', pa.string())
    ])
    casted_table = table.cast(target_schema)

    assert casted_table.equals(expected_table)

def test_field_add_remove_metadata():
    import collections

    f0 = pa.field('foo', pa.int32())

    assert f0.metadata is None

    metadata = {b'foo': b'bar', b'pandas': b'badger'}
    metadata2 = collections.OrderedDict([
        (b'a', b'alpha'),
        (b'b', b'beta')
    ])

    f1 = f0.add_metadata(metadata)
    assert f1.metadata == metadata

    f2 = f0.add_metadata(metadata2)
    assert f2.metadata == metadata2

    with pytest.raises(TypeError):
        f0.add_metadata([1, 2, 3])

    f3 = f1.remove_metadata()
    assert f3.metadata is None

    # idempotent
    f4 = f3.remove_metadata()
    assert f4.metadata is None

    f5 = pa.field('foo', pa.int32(), True, metadata)
    f6 = f0.add_metadata(metadata)
    assert f5.equals(f6)

def test_array_eq_raises():
    # ARROW-2150: we are raising when comparing arrays until we define the
    # behavior to either be elementwise comparisons or data equality
    arr1 = pa.array([1, 2, 3], type=pa.int32())
    arr2 = pa.array([1, 2, 3], type=pa.int32())

    with pytest.raises(NotImplementedError):
        arr1 == arr2

def test_fields_hashable():
    in_dict = {}
    fields = [pa.field('a', pa.int64()),
              pa.field('a', pa.int32()),
              pa.field('b', pa.int32())]
    for i, field in enumerate(fields):
        in_dict[field] = i
    assert len(in_dict) == len(fields)
    for i, field in enumerate(fields):
        assert in_dict[field] == i

def test_floating_point_truncate_safe():
    safe_cases = [
        (np.array([1.0, 2.0, 3.0], dtype='float32'), 'float32',
         np.array([1, 2, 3], dtype='i4'), pa.int32()),
        (np.array([1.0, 2.0, 3.0], dtype='float64'), 'float64',
         np.array([1, 2, 3], dtype='i4'), pa.int32()),
        (np.array([-10.0, 20.0, -30.0], dtype='float64'), 'float64',
         np.array([-10, 20, -30], dtype='i4'), pa.int32()),
    ]
    for case in safe_cases:
        _check_cast_case(case, safe=True)

def test_is_nested_or_struct():
    struct_ex = pa.struct([pa.field('a', pa.int32()),
                           pa.field('b', pa.int8()),
                           pa.field('c', pa.string())])

    assert types.is_struct(struct_ex)
    assert not types.is_struct(pa.list_(pa.int32()))

    assert types.is_nested(struct_ex)
    assert types.is_nested(pa.list_(pa.int32()))
    assert not types.is_nested(pa.int32())

def test_struct_type():
    fields = [pa.field('a', pa.int64()),
              pa.field('a', pa.int32()),
              pa.field('b', pa.int32())]
    ty = pa.struct(fields)

    assert len(ty) == ty.num_children == 3
    assert list(ty) == fields

    for a, b in zip(ty, fields):
        a == b

def test_convert_options():
    cls = ConvertOptions
    opts = cls()

    assert opts.check_utf8 is True
    opts.check_utf8 = False
    assert opts.check_utf8 is False

    assert opts.strings_can_be_null is False
    opts.strings_can_be_null = True
    assert opts.strings_can_be_null is True

    assert opts.column_types == {}
    # Pass column_types as mapping
    opts.column_types = {'b': pa.int16(), 'c': pa.float32()}
    assert opts.column_types == {'b': pa.int16(), 'c': pa.float32()}
    opts.column_types = {'v': 'int16', 'w': 'null'}
    assert opts.column_types == {'v': pa.int16(), 'w': pa.null()}
    # Pass column_types as schema
    schema = pa.schema([('a', pa.int32()), ('b', pa.string())])
    opts.column_types = schema
    assert opts.column_types == {'a': pa.int32(), 'b': pa.string()}
    # Pass column_types as sequence
    opts.column_types = [('x', pa.binary())]
    assert opts.column_types == {'x': pa.binary()}

    with pytest.raises(TypeError, match='DataType expected'):
        opts.column_types = {'a': None}
    with pytest.raises(TypeError):
        opts.column_types = 0

    assert isinstance(opts.null_values, list)
    assert '' in opts.null_values
    assert 'N/A' in opts.null_values
    opts.null_values = ['xxx', 'yyy']
    assert opts.null_values == ['xxx', 'yyy']

    assert isinstance(opts.true_values, list)
    opts.true_values = ['xxx', 'yyy']
    assert opts.true_values == ['xxx', 'yyy']

    assert isinstance(opts.false_values, list)
    opts.false_values = ['xxx', 'yyy']
    assert opts.false_values == ['xxx', 'yyy']

    opts = cls(check_utf8=False, column_types={'a': pa.null()},
               null_values=['N', 'nn'], true_values=['T', 'tt'],
               false_values=['F', 'ff'], strings_can_be_null=True)
    assert opts.check_utf8 is False
    assert opts.column_types == {'a': pa.null()}
    assert opts.null_values == ['N', 'nn']
    assert opts.false_values == ['F', 'ff']
    assert opts.true_values == ['T', 'tt']
    assert opts.strings_can_be_null is True

def test_dictionary_type():
    ty0 = pa.dictionary(pa.int32(), pa.array(['a', 'b', 'c']))
    assert ty0.index_type == pa.int32()
    assert isinstance(ty0.dictionary, pa.Array)
    assert ty0.dictionary.to_pylist() == ['a', 'b', 'c']
    assert ty0.ordered is False

    ty1 = pa.dictionary(pa.int8(), pa.array([1.0, 2.0]), ordered=True)
    assert ty1.index_type == pa.int8()
    assert isinstance(ty0.dictionary, pa.Array)
    assert ty1.dictionary.to_pylist() == [1.0, 2.0]
    assert ty1.ordered is True