Python pyarrow.null函数代码示例

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_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_custom_nulls(self):
        # Infer nulls with custom values
        opts = ConvertOptions(null_values=['Xxx', 'Zzz'])
        rows = b"a,b,c,d\nZzz,Xxx,1,2\nXxx,#N/A,,Zzz\n"
        table = self.read_bytes(rows, convert_options=opts)
        schema = pa.schema([('a', pa.null()),
                            ('b', pa.string()),
                            ('c', pa.string()),
                            ('d', pa.int64())])
        assert table.schema == schema
        assert table.to_pydict() == {
            'a': [None, None],
            'b': [u"Xxx", u"#N/A"],
            'c': [u"1", u""],
            'd': [2, None],
            }

        opts = ConvertOptions(null_values=[])
        rows = b"a,b\n#N/A,\n"
        table = self.read_bytes(rows, convert_options=opts)
        schema = pa.schema([('a', pa.string()),
                            ('b', pa.string())])
        assert table.schema == schema
        assert table.to_pydict() == {
            'a': [u"#N/A"],
            'b': [u""],
            }

def test_empty_cast():
    types = [
        pa.null(),
        pa.bool_(),
        pa.int8(),
        pa.int16(),
        pa.int32(),
        pa.int64(),
        pa.uint8(),
        pa.uint16(),
        pa.uint32(),
        pa.uint64(),
        pa.float16(),
        pa.float32(),
        pa.float64(),
        pa.date32(),
        pa.date64(),
        pa.binary(),
        pa.binary(length=4),
        pa.string(),
    ]

    for (t1, t2) in itertools.product(types, types):
        try:
            # ARROW-4766: Ensure that supported types conversion don't segfault
            # on empty arrays of common types
            pa.array([], type=t1).cast(t2)
        except pa.lib.ArrowNotImplementedError:
            continue

def test_type_to_pandas_dtype():
    M8_ns = np.dtype('datetime64[ns]')
    cases = [
        (pa.null(), np.float64),
        (pa.bool_(), np.bool_),
        (pa.int8(), np.int8),
        (pa.int16(), np.int16),
        (pa.int32(), np.int32),
        (pa.int64(), np.int64),
        (pa.uint8(), np.uint8),
        (pa.uint16(), np.uint16),
        (pa.uint32(), np.uint32),
        (pa.uint64(), np.uint64),
        (pa.float16(), np.float16),
        (pa.float32(), np.float32),
        (pa.float64(), np.float64),
        (pa.date32(), M8_ns),
        (pa.date64(), M8_ns),
        (pa.timestamp('ms'), M8_ns),
        (pa.binary(), np.object_),
        (pa.binary(12), np.object_),
        (pa.string(), np.object_),
        (pa.list_(pa.int8()), np.object_),
    ]
    for arrow_type, numpy_type in cases:
        assert arrow_type.to_pandas_dtype() == numpy_type

def field(jvm_field):
    """
    Construct a Field from a org.apache.arrow.vector.types.pojo.Field
    instance.

    Parameters
    ----------
    jvm_field: org.apache.arrow.vector.types.pojo.Field

    Returns
    -------
    pyarrow.Field
    """
    name = jvm_field.getName()
    jvm_type = jvm_field.getType()

    typ = None
    if not jvm_type.isComplex():
        type_str = jvm_type.getTypeID().toString()
        if type_str == 'Null':
            typ = pa.null()
        elif type_str == 'Int':
            typ = _from_jvm_int_type(jvm_type)
        elif type_str == 'FloatingPoint':
            typ = _from_jvm_float_type(jvm_type)
        elif type_str == 'Utf8':
            typ = pa.string()
        elif type_str == 'Binary':
            typ = pa.binary()
        elif type_str == 'FixedSizeBinary':
            typ = pa.binary(jvm_type.getByteWidth())
        elif type_str == 'Bool':
            typ = pa.bool_()
        elif type_str == 'Time':
            typ = _from_jvm_time_type(jvm_type)
        elif type_str == 'Timestamp':
            typ = _from_jvm_timestamp_type(jvm_type)
        elif type_str == 'Date':
            typ = _from_jvm_date_type(jvm_type)
        elif type_str == 'Decimal':
            typ = pa.decimal128(jvm_type.getPrecision(), jvm_type.getScale())
        else:
            raise NotImplementedError(
                "Unsupported JVM type: {}".format(type_str))
    else:
        # TODO: The following JVM types are not implemented:
        #       Struct, List, FixedSizeList, Union, Dictionary
        raise NotImplementedError(
            "JVM field conversion only implemented for primitive types.")

    nullable = jvm_field.isNullable()
    if jvm_field.getMetadata().isEmpty():
        metadata = None
    else:
        metadata = dict(jvm_field.getMetadata())
    return pa.field(name, typ, nullable, metadata)

    def test_nested_lists_all_none(self):
        data = np.array([[None, None], None], dtype=object)

        arr = pa.array(data)
        expected = pa.array(list(data))
        assert arr.equals(expected)
        assert arr.type == pa.list_(pa.null())

        data2 = np.array([None, None, [None, None],
                          np.array([None, None], dtype=object)],
                         dtype=object)
        arr = pa.array(data2)
        expected = pa.array([None, None, [None, None], [None, None]])
        assert arr.equals(expected)

 def test_simple_nulls(self):
     # Infer various kinds of data, with nulls
     rows = (b'{"a": 1, "b": 2, "c": null, "d": null, "e": null}\n'
             b'{"a": null, "b": -5, "c": "foo", "d": null, "e": true}\n'
             b'{"a": 4.5, "b": null, "c": "nan", "d": null,"e": false}\n')
     table = self.read_bytes(rows)
     schema = pa.schema([('a', pa.float64()),
                         ('b', pa.int64()),
                         ('c', pa.string()),
                         ('d', pa.null()),
                         ('e', pa.bool_())])
     assert table.schema == schema
     assert table.to_pydict() == {
         'a': [1.0, None, 4.5],
         'b': [2, -5, None],
         'c': [None, u"foo", u"nan"],
         'd': [None, None, None],
         'e': [None, True, False],
         }

 def test_simple_nulls(self):
     # Infer various kinds of data, with nulls
     rows = (b"a,b,c,d,e\n"
             b"1,2,,,3\n"
             b"nan,-5,foo,,nan\n"
             b"4.5,#N/A,nan,,\xff\n")
     table = self.read_bytes(rows)
     schema = pa.schema([('a', pa.float64()),
                         ('b', pa.int64()),
                         ('c', pa.string()),
                         ('d', pa.null()),
                         ('e', pa.binary())])
     assert table.schema == schema
     assert table.to_pydict() == {
         'a': [1.0, None, 4.5],
         'b': [2, -5, None],
         'c': [u"", u"foo", u"nan"],
         'd': [None, None, None],
         'e': [b"3", b"nan", b"\xff"],
         }

def test_types_hashable():
    types = [
        pa.null(),
        pa.int32(),
        pa.time32('s'),
        pa.time64('us'),
        pa.date32(),
        pa.timestamp('us'),
        pa.string(),
        pa.binary(),
        pa.binary(10),
        pa.list_(pa.int32()),
        pa.struct([pa.field('a', pa.int32()),
                   pa.field('b', pa.int8()),
                   pa.field('c', pa.string())])
    ]

    in_dict = {}
    for i, type_ in enumerate(types):
        assert hash(type_) == hash(type_)
        in_dict[type_] = i
        assert in_dict[type_] == i

def get_many_types():
    # returning them from a function is required because of pa.dictionary
    # type holds a pyarrow array and test_array.py::test_toal_bytes_allocated
    # checks that the default memory pool has zero allocated bytes
    return (
        pa.null(),
        pa.bool_(),
        pa.int32(),
        pa.time32('s'),
        pa.time64('us'),
        pa.date32(),
        pa.timestamp('us'),
        pa.timestamp('us', tz='UTC'),
        pa.timestamp('us', tz='Europe/Paris'),
        pa.float16(),
        pa.float32(),
        pa.float64(),
        pa.decimal128(19, 4),
        pa.string(),
        pa.binary(),
        pa.binary(10),
        pa.list_(pa.int32()),
        pa.struct([pa.field('a', pa.int32()),
                   pa.field('b', pa.int8()),
                   pa.field('c', pa.string())]),
        pa.struct([pa.field('a', pa.int32(), nullable=False),
                   pa.field('b', pa.int8(), nullable=False),
                   pa.field('c', 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),
        pa.union([pa.field('a', pa.binary(10), nullable=False),
                  pa.field('b', pa.string())], mode=pa.lib.UnionMode_SPARSE),
        pa.dictionary(pa.int32(), pa.string())
    )

    else:
        return schema_cls(fields)


# In the following, we use the JSON serialization of the Field objects in Java.
# This ensures that we neither rely on the exact mechanics on how to construct
# them using Java code as well as enables us to define them as parameters
# without to invoke the JVM.
#
# The specifications were created using:
#
#   om = jpype.JClass('com.fasterxml.jackson.databind.ObjectMapper')()
#   field = …  # Code to instantiate the field
#   jvm_spec = om.writeValueAsString(field)
@pytest.mark.parametrize('pa_type,jvm_spec', [
    (pa.null(), '{"name":"null"}'),
    (pa.bool_(), '{"name":"bool"}'),
    (pa.int8(), '{"name":"int","bitWidth":8,"isSigned":true}'),
    (pa.int16(), '{"name":"int","bitWidth":16,"isSigned":true}'),
    (pa.int32(), '{"name":"int","bitWidth":32,"isSigned":true}'),
    (pa.int64(), '{"name":"int","bitWidth":64,"isSigned":true}'),
    (pa.uint8(), '{"name":"int","bitWidth":8,"isSigned":false}'),
    (pa.uint16(), '{"name":"int","bitWidth":16,"isSigned":false}'),
    (pa.uint32(), '{"name":"int","bitWidth":32,"isSigned":false}'),
    (pa.uint64(), '{"name":"int","bitWidth":64,"isSigned":false}'),
    (pa.float16(), '{"name":"floatingpoint","precision":"HALF"}'),
    (pa.float32(), '{"name":"floatingpoint","precision":"SINGLE"}'),
    (pa.float64(), '{"name":"floatingpoint","precision":"DOUBLE"}'),
    (pa.time32('s'), '{"name":"time","unit":"SECOND","bitWidth":32}'),
    (pa.time32('ms'), '{"name":"time","unit":"MILLISECOND","bitWidth":32}'),
    (pa.time64('us'), '{"name":"time","unit":"MICROSECOND","bitWidth":64}'),

 def test_all_none(self):
     arr = pyarrow.from_pylist([None, None])
     assert len(arr) == 2
     assert arr.null_count == 2
     assert arr.type == pyarrow.null()
     assert arr.to_pylist() == [None, None]

 def test_empty_list(self):
     arr = pyarrow.from_pylist([])
     assert len(arr) == 0
     assert arr.null_count == 0
     assert arr.type == pyarrow.null()
     assert arr.to_pylist() == []

def test_empty_range():
    arr = pa.array(range(0))
    assert len(arr) == 0
    assert arr.null_count == 0
    assert arr.type == pa.null()
    assert arr.to_pylist() == []