def test_na_value_for_dtype():
for dtype in [np.dtype('M8[ns]'), np.dtype('m8[ns]'),
DatetimeTZDtype('datetime64[ns, US/Eastern]')]:
assert na_value_for_dtype(dtype) is NaT
for dtype in ['u1', 'u2', 'u4', 'u8',
'i1', 'i2', 'i4', 'i8']:
assert na_value_for_dtype(np.dtype(dtype)) == 0
for dtype in ['bool']:
assert na_value_for_dtype(np.dtype(dtype)) is False
for dtype in ['f2', 'f4', 'f8']:
assert np.isnan(na_value_for_dtype(np.dtype(dtype)))
for dtype in ['O']:
assert np.isnan(na_value_for_dtype(np.dtype(dtype)))
def _maybe_add_join_keys(self, result, left_indexer, right_indexer):
left_has_missing = None
right_has_missing = None
keys = zip(self.join_names, self.left_on, self.right_on)
for i, (name, lname, rname) in enumerate(keys):
if not _should_fill(lname, rname):
continue
take_left, take_right = None, None
if name in result:
if left_indexer is not None and right_indexer is not None:
if name in self.left:
if left_has_missing is None:
left_has_missing = any(left_indexer == -1)
if left_has_missing:
take_right = self.right_join_keys[i]
if not com.is_dtype_equal(result[name].dtype,
self.left[name].dtype):
take_left = self.left[name]._values
elif name in self.right:
if right_has_missing is None:
right_has_missing = any(right_indexer == -1)
if right_has_missing:
take_left = self.left_join_keys[i]
if not com.is_dtype_equal(result[name].dtype,
self.right[name].dtype):
take_right = self.right[name]._values
elif left_indexer is not None \
and isinstance(self.left_join_keys[i], np.ndarray):
take_left = self.left_join_keys[i]
take_right = self.right_join_keys[i]
if take_left is not None or take_right is not None:
if take_left is None:
lvals = result[name]._values
else:
lfill = na_value_for_dtype(take_left.dtype)
lvals = algos.take_1d(take_left, left_indexer,
fill_value=lfill)
if take_right is None:
rvals = result[name]._values
else:
rfill = na_value_for_dtype(take_right.dtype)
rvals = algos.take_1d(take_right, right_indexer,
fill_value=rfill)
# if we have an all missing left_indexer
# make sure to just use the right values
mask = left_indexer == -1
if mask.all():
key_col = rvals
else:
key_col = Index(lvals).where(~mask, rvals)
if name in result:
result[name] = key_col
else:
result.insert(i, name or 'key_%d' % i, key_col)
