def sdc_reindex_series_impl(arr, index, name, by_index):
# no reindexing is needed if indexes are equal
if range_indexes == True: # noqa
equal_indexes = numpy_like.array_equal(index, by_index)
elif int64_indexes == True: # noqa
equal_indexes = numpy_like.array_equal(index, by_index)
else:
equal_indexes = False
if (index is by_index or equal_indexes):
return pandas.Series(data=arr, index=by_index, name=name)
if data_is_str_arr == True: # noqa
_res_data = [''] * len(by_index)
res_data_nan_mask = numpy.zeros(len(by_index), dtype=types.bool_)
else:
_res_data = numpy.empty(len(by_index), dtype=data_dtype)
# build a dict of self.index values to their positions:
map_index_to_position = Dict.empty(key_type=index_dtype,
value_type=types.int32)
for i, value in enumerate(index):
if value in map_index_to_position:
raise ValueError("cannot reindex from a duplicate axis")
else:
map_index_to_position[value] = i
index_mismatch = 0
for i in numba.prange(len(by_index)):
val = by_index[i]
if val in map_index_to_position:
pos_in_self = map_index_to_position[val]
_res_data[i] = arr[pos_in_self]
if data_is_str_arr == True: # noqa
res_data_nan_mask[i] = isna(arr, i)
else:
index_mismatch += 1
if index_mismatch:
msg = "Unalignable boolean Series provided as indexer " + \
"(index of the boolean Series and of the indexed object do not match)."
raise IndexingError(msg)
if data_is_str_arr == True: # noqa
res_data = create_str_arr_from_list(_res_data)
str_arr_set_na_by_mask(res_data, res_data_nan_mask)
else:
res_data = _res_data
return pandas.Series(data=res_data, index=by_index, name=name)
def sdc_join_range_indexes_impl(left, right):
if (left is right or numpy_like.array_equal(left, right)):
joined = left.values
lidx = numpy.arange(len(joined))
ridx = lidx
return joined, lidx, ridx
else:
return sdc_join_series_indexes(left.values, right.values)
def pd_indexes_join_array_indexes_impl(left, right):
_left = left.values if convert_left == True else left # noqa
_right = right.values if convert_right == True else right # noqa
if (_left is _right or numpy_like.array_equal(_left, _right)):
if index_dtypes_match == False: # noqa
joined_index = numpy_like.astype(_left, res_index_dtype)
else:
joined_index = _left
return joined_index, None, None
return _sdc_internal_join(_left, _right)
def _series_comp_binop_common_impl(self, other, fill_value=None):
left_index, right_index = self.index, other.index
if not (left_index is right_index
or numpy_like.array_equal(left_index, right_index)):
raise ValueError(
"Can only compare identically-labeled Series objects")
_left, _right = pandas.Series(self._data), pandas.Series(
other._data)
partial_res = _left.comp_binop(_right, fill_value=fill_value)
if index_dtypes_match == False: # noqa
result_index = numpy_like.astype(left_index,
numba_index_common_dtype)
else:
result_index = left_index.values if left_index_is_range == True else left_index # noqa
return pandas.Series(partial_res._data, result_index)
def _series_comp_binop_common_impl(self,
other,
level=None,
fill_value=None,
axis=0):
numpy_like.fillna(self._data, inplace=True, value=fill_value)
numpy_like.fillna(other._data, inplace=True, value=fill_value)
left_index, right_index = self.index, other.index
if (left_index is right_index
or numpy_like.array_equal(left_index, right_index)):
if index_dtypes_match == False: # noqa
new_index = numpy_like.astype(
left_index, numba_index_common_dtype)
else:
new_index = left_index.values if left_index_is_range == True else left_index # noqa
return pandas.Series(self._data < other._data, new_index)
else:
raise ValueError(
"Can only compare identically-labeled Series objects")
def _series_binop_common_impl(self,
other,
level=None,
fill_value=None,
axis=0):
left_index, right_index = self.index, other.index
numpy_like.fillna(self._data, inplace=True, value=fill_value)
numpy_like.fillna(other._data, inplace=True, value=fill_value)
if check_index_equal == True: # noqa
equal_indexes = numpy_like.array_equal(
left_index, right_index)
else:
equal_indexes = False
if (left_index is right_index or equal_indexes):
result_data = numpy.empty(len(self._data),
dtype=numpy.float64)
result_data[:] = self._data + other._data
if index_dtypes_match == False: # noqa
result_index = numpy_like.astype(
left_index, numba_index_common_dtype)
else:
result_index = left_index.values if left_index_is_range == True else left_index # noqa
return pandas.Series(result_data, index=result_index)
# TODO: replace below with core join(how='outer', return_indexers=True) when implemented
joined_index, left_indexer, right_indexer = sdc_join_series_indexes(
left_index, right_index)
result_size = len(joined_index)
left_values = numpy.empty(result_size, dtype=numpy.float64)
right_values = numpy.empty(result_size, dtype=numpy.float64)
_fill_value = numpy.nan if fill_value_is_none == True else fill_value # noqa
for i in range(result_size):
left_pos, right_pos = left_indexer[i], right_indexer[i]
left_values[i] = self._data[
left_pos] if left_pos != -1 else _fill_value
right_values[i] = other._data[
right_pos] if right_pos != -1 else _fill_value
result_data = left_values + right_values
return pandas.Series(result_data, joined_index)
def sdc_binop_impl(self, other, fill_value=None):
# check if indexes are equal and series don't have to be aligned
left_index, right_index = self.index, other.index
if (left_index is right_index
or numpy_like.array_equal(left_index, right_index)):
_left = pandas.Series(self._data)
_right = pandas.Series(other._data)
partial_res = _left.binop(_right, fill_value=fill_value)
if index_dtypes_match == False: # noqa
result_index = numpy_like.astype(
left_index, numba_index_common_dtype)
else:
result_index = left_index.values if left_index_is_range == True else left_index # noqa
return pandas.Series(partial_res._data, index=result_index)
_fill_value = numpy.nan if fill_value_is_none == True else fill_value # noqa
# TODO: replace below with core join(how='outer', return_indexers=True) when implemented
joined_index, left_indexer, right_indexer = sdc_join_series_indexes(
left_index, right_index)
result_size = len(joined_index)
result_data = numpy.empty(result_size, dtype=numpy.float64)
for i in numba.prange(result_size):
left_pos, right_pos = left_indexer[i], right_indexer[i]
left_nan = (left_pos == -1
or numpy.isnan(self._data[left_pos]))
right_nan = (right_pos == -1
or numpy.isnan(other._data[right_pos]))
_left = _fill_value if left_nan else self._data[left_pos]
_right = _fill_value if right_nan else other._data[
right_pos]
result_data[i] = numpy.nan if (
left_nan and right_nan) else _left + _right
return pandas.Series(result_data, index=joined_index)
def _series_lt_common_impl(self, other, fill_value=None):
left_index, right_index = self.index, other.index
if index_api_supported == True: # noqa
if not (left_index is right_index or left_index.equals(right_index)):
raise ValueError("Can only compare identically-labeled Series objects")
else:
if not (left_index is right_index or numpy_like.array_equal(left_index, right_index)):
raise ValueError("Can only compare identically-labeled Series objects")
res_size = len(left_index)
if fill_value_is_none == True: # noqa
res_data = self._data < other._data
else:
res_data = numpy.empty(res_size, dtype=types.bool_)
for i in numba.prange(res_size):
left_nan = isna(self._data, i)
right_nan = isna(other._data, i)
_left = fill_value if left_nan else self._data[i]
_right = fill_value if right_nan else other._data[i]
res_data[i] = False if (left_nan and right_nan) else _left < _right
res_index = sdc_unify_index_types(left_index, right_index)
return pandas.Series(res_data, index=res_index)
def sdc_func(index1, index2):
return array_equal(index1, index2)
def sdc_numeric_indexes_equals_impl(left, right):
left = left.values if convert_A == True else left # noqa
right = right.values if convert_B == True else right # noqa
return numpy_like.array_equal(left, right)
