def _get_matches_list(matches: csr_matrix) -> pd.DataFrame:
"""Returns a list of all the indices of matches"""
r, c = matches.nonzero()
matches_list = pd.DataFrame({'master_side': r.astype(np.int64),
'dupe_side': c.astype(np.int64),
'similarity': matches.data})
return matches_list
def make_non_zero_information(
self, weight_csr_matrix: csr_matrix) -> List[ROW_COL_VAL]:
"""Construct Tuple of matrix value. Return value is array of ROW_COL_VAL namedtuple.
:param weight_csr_matrix:
:return:
"""
assert isinstance(weight_csr_matrix, (csr_matrix, ndarray))
row_col_index_array = weight_csr_matrix.nonzero()
row_indexes = row_col_index_array[0]
column_indexes = row_col_index_array[1]
assert len(row_indexes) == len(column_indexes)
value_index_items = [None] * len(
row_indexes) # type: List[ROW_COL_VAL]
for i in range(0, len(row_indexes)):
value_index_items[i] = ROW_COL_VAL(
row_indexes[i], column_indexes[i],
self.__get_value_index(row_indexes[i], column_indexes[i],
weight_csr_matrix))
return value_index_items
def make_non_zero_information(weight_csr_matrix:csr_matrix):
"""Construct Tuple of matrix value. Return value is array of ROW_COL_VAL namedtuple.
:param weight_csr_matrix:
:return:
"""
assert isinstance(weight_csr_matrix, csr_matrix)
row_col_index_array = weight_csr_matrix.nonzero()
row_indexes = row_col_index_array[0]
column_indexes = row_col_index_array[1]
assert len(row_indexes) == len(column_indexes)
value_index_items = [
ROW_COL_VAL(
row_indexes[i],
column_indexes[i],
__get_value_index(row_indexes[i], column_indexes[i], weight_csr_matrix)
)
for i
in range(0, len(row_indexes))]
return value_index_items
