def test_integers(self):
arr = np.array([1, 2, 3, np.int64(4), np.int32(5)], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'integer')
arr = np.array([1, 2, 3, np.int64(4), np.int32(5), 'foo'], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'mixed')
arr = np.array([1, 2, 3, 4, 5], dtype='i4')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'integer')
def test_integers(self):
arr = np.array([1, 2, 3, np.int64(4), np.int32(5)], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'integer')
arr = np.array([1, 2, 3, np.int64(4), np.int32(5), 'foo'],
dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'mixed-integer')
arr = np.array([1, 2, 3, 4, 5], dtype='i4')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'integer')
def test_bools(self):
arr = np.array([True, False, True, True, True], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'boolean')
arr = np.array([np.bool_(True), np.bool_(False)], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'boolean')
arr = np.array([True, False, True, 'foo'], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'mixed')
arr = np.array([True, False, True], dtype=bool)
result = lib.infer_dtype(arr)
self.assertEqual(result, 'boolean')
def test_bools(self):
arr = np.array([True, False, True, True, True], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'boolean')
arr = np.array([np.bool_(True), np.bool_(False)], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'boolean')
arr = np.array([True, False, True, 'foo'], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'mixed')
arr = np.array([True, False, True], dtype=bool)
result = lib.infer_dtype(arr)
self.assertEqual(result, 'boolean')
def _convert_index(index):
inferred_type = lib.infer_dtype(index)
# Let's assume the index is homogeneous
values = np.asarray(index)
if inferred_type == 'datetime64':
converted = values.view('i8')
return converted, 'datetime64', _tables().Int64Col()
elif isinstance(values[0], datetime):
converted = np.array([(time.mktime(v.timetuple()) +
v.microsecond / 1E6) for v in values],
dtype=np.float64)
return converted, 'datetime', _tables().Time64Col()
elif isinstance(values[0], date):
converted = np.array([time.mktime(v.timetuple()) for v in values],
dtype=np.int32)
return converted, 'date', _tables().Time32Col()
elif isinstance(values[0], basestring):
converted = np.array(list(values), dtype=np.str_)
itemsize = converted.dtype.itemsize
return converted, 'string', _tables().StringCol(itemsize)
elif com.is_integer(values[0]):
# take a guess for now, hope the values fit
atom = _tables().Int64Col()
return np.asarray(values, dtype=np.int64), 'integer', atom
elif com.is_float(values[0]):
atom = _tables().Float64Col()
return np.asarray(values, dtype=np.float64), 'float', atom
else: # pragma: no cover
atom = _tables().ObjectAtom()
return np.asarray(values, dtype='O'), 'object', atom
def test_floats(self):
arr = np.array([1., 2., 3., np.float64(4), np.float32(5)], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'floating')
arr = np.array([1, 2, 3, np.float64(4), np.float32(5), 'foo'],
dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'mixed-integer')
arr = np.array([1, 2, 3, 4, 5], dtype='f4')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'floating')
arr = np.array([1, 2, 3, 4, 5], dtype='f8')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'floating')
def test_floats(self):
arr = np.array([1., 2., 3., np.float64(4), np.float32(5)], dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'floating')
arr = np.array([1, 2, 3, np.float64(4),
np.float32(5), 'foo'],
dtype='O')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'mixed')
arr = np.array([1, 2, 3, 4, 5], dtype='f4')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'floating')
arr = np.array([1, 2, 3, 4, 5], dtype='f8')
result = lib.infer_dtype(arr)
self.assertEqual(result, 'floating')
def _convert_index(index):
if isinstance(index, DatetimeIndex):
converted = np.asarray(index, dtype='i8')
return converted, 'datetime64', _tables().Int64Col()
elif isinstance(index, (Int64Index, PeriodIndex)):
atom = _tables().Int64Col()
return np.asarray(index, dtype=np.int64), 'integer', atom
inferred_type = lib.infer_dtype(index)
values = np.asarray(index)
if inferred_type == 'datetime64':
converted = values.view('i8')
return converted, 'datetime64', _tables().Int64Col()
elif inferred_type == 'datetime':
converted = np.array([(time.mktime(v.timetuple()) +
v.microsecond / 1E6) for v in values],
dtype=np.float64)
return converted, 'datetime', _tables().Time64Col()
elif inferred_type == 'date':
converted = np.array([time.mktime(v.timetuple()) for v in values],
dtype=np.int32)
return converted, 'date', _tables().Time32Col()
elif inferred_type =='string':
try:
converted = np.array(list(values), dtype=np.str_)
itemsize = converted.dtype.itemsize
return converted, 'string', _tables().StringCol(itemsize)
except UnicodeError: # Write an all unicode index as object array
atom = _tables().ObjectAtom()
return np.asarray(values, dtype='O'), 'object', atom
elif inferred_type == 'integer':
# take a guess for now, hope the values fit
atom = _tables().Int64Col()
return np.asarray(values, dtype=np.int64), 'integer', atom
elif inferred_type == 'floating':
atom = _tables().Float64Col()
return np.asarray(values, dtype=np.float64), 'float', atom
else: # pragma: no cover
atom = _tables().ObjectAtom()
return np.asarray(values, dtype='O'), 'object', atom
def test_length_zero(self):
result = lib.infer_dtype(np.array([], dtype='i4'))
self.assertEqual(result, 'empty')
result = lib.infer_dtype(np.array([], dtype='O'))
self.assertEqual(result, 'empty')
def test_length_zero(self):
result = lib.infer_dtype(np.array([], dtype='i4'))
self.assertEqual(result, 'empty')
result = lib.infer_dtype(np.array([], dtype='O'))
self.assertEqual(result, 'empty')
