Python pyarrow.int64函数代码示例

def test_sequence_nesting_levels():
    data = [1, 2, None]
    arr = pa.array(data)
    assert arr.type == pa.int64()
    assert arr.to_pylist() == data

    data = [[1], [2], None]
    arr = pa.array(data)
    assert arr.type == pa.list_(pa.int64())
    assert arr.to_pylist() == data

    data = [[1], [2, 3, 4], [None]]
    arr = pa.array(data)
    assert arr.type == pa.list_(pa.int64())
    assert arr.to_pylist() == data

    data = [None, [[None, 1]], [[2, 3, 4], None], [None]]
    arr = pa.array(data)
    assert arr.type == pa.list_(pa.list_(pa.int64()))
    assert arr.to_pylist() == data

    exceptions = (pa.ArrowInvalid, pa.ArrowTypeError)

    # Mixed nesting levels are rejected
    with pytest.raises(exceptions):
        pa.array([1, 2, [1]])

    with pytest.raises(exceptions):
        pa.array([1, 2, []])

    with pytest.raises(exceptions):
        pa.array([[1], [2], [None, [1]]])

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_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_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

    # Construct from list of tuples
    ty = pa.struct([('a', pa.int64()),
                    ('a', pa.int32()),
                    ('b', pa.int32())])
    assert list(ty) == fields
    for a, b in zip(ty, fields):
        a == b

    # Construct from mapping
    fields = [pa.field('a', pa.int64()),
              pa.field('b', pa.int32())]
    ty = pa.struct(OrderedDict([('a', pa.int64()),
                                ('b', pa.int32())]))
    assert list(ty) == fields
    for a, b in zip(ty, fields):
        a == b

def dataframe_with_arrays(include_index=False):
    """
    Dataframe with numpy arrays columns of every possible primtive type.

    Returns
    -------
    df: pandas.DataFrame
    schema: pyarrow.Schema
        Arrow schema definition that is in line with the constructed df.
    """
    dtypes = [('i1', pa.int8()), ('i2', pa.int16()),
              ('i4', pa.int32()), ('i8', pa.int64()),
              ('u1', pa.uint8()), ('u2', pa.uint16()),
              ('u4', pa.uint32()), ('u8', pa.uint64()),
              ('f4', pa.float32()), ('f8', pa.float64())]

    arrays = OrderedDict()
    fields = []
    for dtype, arrow_dtype in dtypes:
        fields.append(pa.field(dtype, pa.list_(arrow_dtype)))
        arrays[dtype] = [
            np.arange(10, dtype=dtype),
            np.arange(5, dtype=dtype),
            None,
            np.arange(1, dtype=dtype)
        ]

    fields.append(pa.field('str', pa.list_(pa.string())))
    arrays['str'] = [
        np.array([u"1", u"ä"], dtype="object"),
        None,
        np.array([u"1"], dtype="object"),
        np.array([u"1", u"2", u"3"], dtype="object")
    ]

    fields.append(pa.field('datetime64', pa.list_(pa.timestamp('ms'))))
    arrays['datetime64'] = [
        np.array(['2007-07-13T01:23:34.123456789',
                  None,
                  '2010-08-13T05:46:57.437699912'],
                 dtype='datetime64[ms]'),
        None,
        None,
        np.array(['2007-07-13T02',
                  None,
                  '2010-08-13T05:46:57.437699912'],
                 dtype='datetime64[ms]'),
    ]

    if include_index:
        fields.append(pa.field('__index_level_0__', pa.int64()))
    df = pd.DataFrame(arrays)
    schema = pa.schema(fields)

    return df, schema

def test_struct_type():
    fields = [
        # Duplicate field name on purpose
        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
    assert ty[0].name == 'a'
    assert ty[2].type == pa.int32()
    with pytest.raises(IndexError):
        assert ty[3]

    assert ty['b'] == ty[2]

    # Duplicate
    with pytest.warns(UserWarning):
        with pytest.raises(KeyError):
            ty['a']

    # Not found
    with pytest.raises(KeyError):
        ty['c']

    # Neither integer nor string
    with pytest.raises(TypeError):
        ty[None]

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

    # Construct from list of tuples
    ty = pa.struct([('a', pa.int64()),
                    ('a', pa.int32()),
                    ('b', pa.int32())])
    assert list(ty) == fields
    for a, b in zip(ty, fields):
        a == b

    # Construct from mapping
    fields = [pa.field('a', pa.int64()),
              pa.field('b', pa.int32())]
    ty = pa.struct(OrderedDict([('a', pa.int64()),
                                ('b', pa.int32())]))
    assert list(ty) == fields
    for a, b in zip(ty, fields):
        a == b

    # Invalid args
    with pytest.raises(TypeError):
        pa.struct([('a', None)])

def test_fields_hashable():
    in_dict = {}
    fields = [pa.field('a', pa.int32()),
              pa.field('a', pa.int64()),
              pa.field('a', pa.int64(), nullable=False),
              pa.field('b', pa.int32()),
              pa.field('b', pa.int32(), nullable=False)]
    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 dataframe_with_lists(include_index=False):
    """
    Dataframe with list columns of every possible primtive type.

    Returns
    -------
    df: pandas.DataFrame
    schema: pyarrow.Schema
        Arrow schema definition that is in line with the constructed df.
    """
    arrays = OrderedDict()
    fields = []

    fields.append(pa.field('int64', pa.list_(pa.int64())))
    arrays['int64'] = [
        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
        [0, 1, 2, 3, 4],
        None,
        [],
        np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9] * 2,
                 dtype=np.int64)[::2]
    ]
    fields.append(pa.field('double', pa.list_(pa.float64())))
    arrays['double'] = [
        [0., 1., 2., 3., 4., 5., 6., 7., 8., 9.],
        [0., 1., 2., 3., 4.],
        None,
        [],
        np.array([0., 1., 2., 3., 4., 5., 6., 7., 8., 9.] * 2)[::2],
    ]
    fields.append(pa.field('bytes_list', pa.list_(pa.binary())))
    arrays['bytes_list'] = [
        [b"1", b"f"],
        None,
        [b"1"],
        [b"1", b"2", b"3"],
        [],
    ]
    fields.append(pa.field('str_list', pa.list_(pa.string())))
    arrays['str_list'] = [
        [u"1", u"ä"],
        None,
        [u"1"],
        [u"1", u"2", u"3"],
        [],
    ]

    if include_index:
        fields.append(pa.field('__index_level_0__', pa.int64()))
    df = pd.DataFrame(arrays)
    schema = pa.schema(fields)

    return df, schema

def test_table_from_arrays_preserves_column_metadata():
    # Added to test https://issues.apache.org/jira/browse/ARROW-3866
    arr0 = pa.array([1, 2])
    arr1 = pa.array([3, 4])
    field0 = pa.field('field1', pa.int64(), metadata=dict(a="A", b="B"))
    field1 = pa.field('field2', pa.int64(), nullable=False)
    columns = [
        pa.column(field0, arr0),
        pa.column(field1, arr1)
    ]
    table = pa.Table.from_arrays(columns)
    assert b"a" in table.column(0).field.metadata
    assert table.column(1).field.nullable is False

 def test_simple_ints(self):
     # Infer integer columns
     rows = b"a,b,c\n1,2,3\n4,5,6\n"
     table = self.read_bytes(rows)
     schema = pa.schema([('a', pa.int64()),
                         ('b', pa.int64()),
                         ('c', pa.int64())])
     assert table.schema == schema
     assert table.to_pydict() == {
         'a': [1, 4],
         'b': [2, 5],
         'c': [3, 6],
         }

def test_list_array_flatten():
    typ2 = pa.list_(
        pa.list_(
            pa.int64()
        )
    )
    arr2 = pa.array([
        None,
        [
            [1, None, 2],
            None,
            [3, 4]
        ],
        [],
        [
            [],
            [5, 6],
            None
        ],
        [
            [7, 8]
        ]
    ])
    assert arr2.type.equals(typ2)

    typ1 = pa.list_(pa.int64())
    arr1 = pa.array([
        [1, None, 2],
        None,
        [3, 4],
        [],
        [5, 6],
        None,
        [7, 8]
    ])
    assert arr1.type.equals(typ1)

    typ0 = pa.int64()
    arr0 = pa.array([
        1, None, 2,
        3, 4,
        5, 6,
        7, 8
    ])
    assert arr0.type.equals(typ0)

    assert arr2.flatten().equals(arr1)
    assert arr1.flatten().equals(arr0)
    assert arr2.flatten().flatten().equals(arr0)

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_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 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_list_of_int(self):
     data = [[1, 2, 3], [], None, [1, 2]]
     arr = pyarrow.from_pylist(data)
     assert len(arr) == 4
     assert arr.null_count == 1
     assert arr.type == pyarrow.list_(pyarrow.int64())
     assert arr.to_pylist() == data