def test_double(self):
data = [1.5, 1, None, 2.5, None, None]
arr = pyarrow.from_pylist(data)
assert len(arr) == 6
assert arr.null_count == 3
assert arr.type == pyarrow.double()
assert arr.to_pylist() == data
def test_double(self):
data = [1.5, 1, None, 2.5, None, None]
arr = pyarrow.from_pylist(data)
assert len(arr) == 6
assert arr.null_count == 3
assert arr.type == pyarrow.double()
assert arr.to_pylist() == data
def test_float_nulls(self):
num_values = 100
null_mask = np.random.randint(0, 10, size=num_values) < 3
dtypes = [('f4', A.float_()), ('f8', A.double())]
names = ['f4', 'f8']
expected_cols = []
arrays = []
fields = []
for name, arrow_dtype in dtypes:
values = np.random.randn(num_values).astype(name)
arr = A.from_pandas_series(values, null_mask)
arrays.append(arr)
fields.append(A.Field.from_py(name, arrow_dtype))
values[null_mask] = np.nan
expected_cols.append(values)
ex_frame = pd.DataFrame(dict(zip(names, expected_cols)),
columns=names)
table = A.Table.from_arrays(arrays, names)
assert table.schema.equals(A.Schema.from_fields(fields))
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def test_float_nulls(self):
num_values = 100
null_mask = np.random.randint(0, 10, size=num_values) < 3
dtypes = [('f4', A.float_()), ('f8', A.double())]
names = ['f4', 'f8']
expected_cols = []
arrays = []
fields = []
for name, arrow_dtype in dtypes:
values = np.random.randn(num_values).astype(name)
arr = A.from_pandas_series(values, null_mask)
arrays.append(arr)
fields.append(A.Field.from_py(name, arrow_dtype))
values[null_mask] = np.nan
expected_cols.append(values)
ex_frame = pd.DataFrame(dict(zip(names, expected_cols)),
columns=names)
table = A.Table.from_arrays(names, arrays)
assert table.schema.equals(A.Schema.from_fields(fields))
result = table.to_pandas()
tm.assert_frame_equal(result, ex_frame)
def dataframe_with_arrays():
"""
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.float_()), ('f8', pa.double())]
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]'),
]
df = pd.DataFrame(arrays)
schema = pa.Schema.from_fields(fields)
return df, schema
def test_float_no_nulls(self):
data = {}
fields = []
dtypes = [('f4', A.float_()), ('f8', A.double())]
num_values = 100
for numpy_dtype, arrow_dtype in dtypes:
values = np.random.randn(num_values)
data[numpy_dtype] = values.astype(numpy_dtype)
fields.append(A.Field.from_py(numpy_dtype, arrow_dtype))
df = pd.DataFrame(data)
schema = A.Schema.from_fields(fields)
self._check_pandas_roundtrip(df, expected_schema=schema)
def test_float_no_nulls(self):
data = {}
fields = []
dtypes = [('f4', A.float_()), ('f8', A.double())]
num_values = 100
for numpy_dtype, arrow_dtype in dtypes:
values = np.random.randn(num_values)
data[numpy_dtype] = values.astype(numpy_dtype)
fields.append(A.Field.from_py(numpy_dtype, arrow_dtype))
df = pd.DataFrame(data)
schema = A.Schema.from_fields(fields)
self._check_pandas_roundtrip(df, expected_schema=schema)
def normalize_arrow_dtype(dtype): # noqa: C901
if dtype in ['bool']:
return pa.bool_()
if dtype in ['int8_t', 'int8', 'byte']:
return pa.int8()
if dtype in ['uint8_t', 'uint8', 'char']:
return pa.uint8()
if dtype in ['int16_t', 'int16', 'short']:
return pa.int16()
if dtype in ['uint16_t', 'uint16']:
return pa.uint16()
if dtype in ['int32_t', 'int32', 'int']:
return pa.int32()
if dtype in ['uint32_t', 'uint32']:
return pa.uint32()
if dtype in ['int64_t', 'int64', 'long']:
return pa.int64()
if dtype in ['uint64_t', 'uint64']:
return pa.uint64()
if dtype in ['half']:
return pa.float16()
if dtype in ['float', 'float32']:
return pa.float32()
if dtype in ['double', 'float64']:
return pa.float64()
if dtype in ['string', 'std::string', 'std::__1::string', 'str']:
return pa.large_string()
if dtype in ['large_list<item: int32>']:
return pa.large_list(pa.int32())
if dtype in ['large_list<item: uint32>']:
return pa.large_list(pa.uint32())
if dtype in ['large_list<item: int64>']:
return pa.large_list(pa.int64())
if dtype in ['large_list<item: uint64>']:
return pa.large_list(pa.uint64())
if dtype in ['large_list<item: float>']:
return pa.large_list(pa.float())
if dtype in ['large_list<item: double>']:
return pa.large_list(pa.double())
if dtype in ['null', 'NULL', 'None', None]:
return pa.null()
raise ValueError('Unsupported data type: %s' % dtype)
def dataframe_with_lists():
"""
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,
[0]
]
fields.append(pa.field('double', pa.list_(pa.double())))
arrays['double'] = [
[0., 1., 2., 3., 4., 5., 6., 7., 8., 9.],
[0., 1., 2., 3., 4.],
None,
[0.]
]
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"]
]
df = pd.DataFrame(arrays)
schema = pa.Schema.from_fields(fields)
return df, schema
