def test_read_year_month_nano_interval(tmpdir):
"""ARROW-15783: Verify to_pandas works for interval types.
Interval types require static structures to be enabled. This test verifies
that they are when no other library functions are invoked.
"""
mdn_interval_type = pa.month_day_nano_interval()
schema = pa.schema([pa.field('nums', mdn_interval_type)])
path = tmpdir.join('file.arrow').strpath
with pa.OSFile(path, 'wb') as sink:
with pa.ipc.new_file(sink, schema) as writer:
interval_array = pa.array([(1, 2, 3)], type=mdn_interval_type)
batch = pa.record_batch([interval_array], schema)
writer.write(batch)
invoke_script('read_record_batch.py', path)
def test_is_temporal_date_time_timestamp():
date_types = [pa.date32(), pa.date64()]
time_types = [pa.time32('s'), pa.time64('ns')]
timestamp_types = [pa.timestamp('ms')]
duration_types = [pa.duration('ms')]
interval_types = [pa.month_day_nano_interval()]
for case in (date_types + time_types + timestamp_types + duration_types +
interval_types):
assert types.is_temporal(case)
for case in date_types:
assert types.is_date(case)
assert not types.is_time(case)
assert not types.is_timestamp(case)
assert not types.is_duration(case)
assert not types.is_interval(case)
for case in time_types:
assert types.is_time(case)
assert not types.is_date(case)
assert not types.is_timestamp(case)
assert not types.is_duration(case)
assert not types.is_interval(case)
for case in timestamp_types:
assert types.is_timestamp(case)
assert not types.is_date(case)
assert not types.is_time(case)
assert not types.is_duration(case)
assert not types.is_interval(case)
for case in duration_types:
assert types.is_duration(case)
assert not types.is_date(case)
assert not types.is_time(case)
assert not types.is_timestamp(case)
assert not types.is_interval(case)
for case in interval_types:
assert types.is_interval(case)
assert not types.is_date(case)
assert not types.is_time(case)
assert not types.is_timestamp(case)
assert not types.is_temporal(pa.int32())
def test_type_for_alias():
cases = [
('i1', pa.int8()),
('int8', pa.int8()),
('i2', pa.int16()),
('int16', pa.int16()),
('i4', pa.int32()),
('int32', pa.int32()),
('i8', pa.int64()),
('int64', pa.int64()),
('u1', pa.uint8()),
('uint8', pa.uint8()),
('u2', pa.uint16()),
('uint16', pa.uint16()),
('u4', pa.uint32()),
('uint32', pa.uint32()),
('u8', pa.uint64()),
('uint64', pa.uint64()),
('f4', pa.float32()),
('float32', pa.float32()),
('f8', pa.float64()),
('float64', pa.float64()),
('date32', pa.date32()),
('date64', pa.date64()),
('string', pa.string()),
('str', pa.string()),
('binary', pa.binary()),
('time32[s]', pa.time32('s')),
('time32[ms]', pa.time32('ms')),
('time64[us]', pa.time64('us')),
('time64[ns]', pa.time64('ns')),
('timestamp[s]', pa.timestamp('s')),
('timestamp[ms]', pa.timestamp('ms')),
('timestamp[us]', pa.timestamp('us')),
('timestamp[ns]', pa.timestamp('ns')),
('duration[s]', pa.duration('s')),
('duration[ms]', pa.duration('ms')),
('duration[us]', pa.duration('us')),
('duration[ns]', pa.duration('ns')),
('month_day_nano_interval', pa.month_day_nano_interval()),
]
for val, expected in cases:
assert pa.type_for_alias(val) == expected
pa.time64('us'),
pa.time64('ns')])
if tzst and zoneinfo:
timezones = st.one_of(st.none(), tzst.timezones(), st.timezones())
elif tzst:
timezones = st.one_of(st.none(), tzst.timezones())
elif zoneinfo:
timezones = st.one_of(st.none(), st.timezones())
else:
timezones = st.none()
timestamp_types = st.builds(pa.timestamp,
unit=st.sampled_from(['s', 'ms', 'us', 'ns']),
tz=timezones)
duration_types = st.builds(pa.duration,
st.sampled_from(['s', 'ms', 'us', 'ns']))
interval_types = st.just(pa.month_day_nano_interval())
temporal_types = st.one_of(date_types, time_types, timestamp_types,
duration_types, interval_types)
primitive_types = st.one_of(null_type, bool_type, numeric_types,
temporal_types, binary_like_types)
metadata = st.dictionaries(st.text(), st.text())
@st.composite
def fields(draw, type_strategy=primitive_types):
name = draw(custom_text)
typ = draw(type_strategy)
if pa.types.is_null(typ):
nullable = True
scale=st.integers(min_value=1, max_value=76))
numeric_types = st.one_of(integer_types, floating_types, decimal128_type,
decimal256_type)
date_types = st.sampled_from([pa.date32(), pa.date64()])
time_types = st.sampled_from(
[pa.time32('s'),
pa.time32('ms'),
pa.time64('us'),
pa.time64('ns')])
timestamp_types = st.builds(pa.timestamp,
unit=st.sampled_from(['s', 'ms', 'us', 'ns']),
tz=tzst.timezones())
duration_types = st.builds(pa.duration,
st.sampled_from(['s', 'ms', 'us', 'ns']))
interval_types = st.sampled_from(pa.month_day_nano_interval())
temporal_types = st.one_of(date_types, time_types, timestamp_types,
duration_types, interval_types)
primitive_types = st.one_of(null_type, bool_type, numeric_types,
temporal_types, binary_like_types)
metadata = st.dictionaries(st.text(), st.text())
@st.composite
def fields(draw, type_strategy=primitive_types):
name = draw(custom_text)
typ = draw(type_strategy)
if pa.types.is_null(typ):
nullable = True