def transform_regression_label(self, data_inst):
edge = self.split_points[-1] + 1
split_points_bin = self.split_points + [edge]
bin_labels = data_inst.mapValues(
lambda v: BaseBinning.get_bin_num(v.label, split_points_bin))
binned_y = [v for k, v in bin_labels.collect()]
return binned_y
def convert(instances):
if is_sparse:
all_data = instances.features.get_all_data()
indice = []
sparse_value = []
data_shape = instances.features.get_shape()
for col_idx, col_value in all_data:
if col_idx in transform_cols_idx:
if col_value in abnormal_list:
indice.append(col_idx)
sparse_value.append(col_value)
continue
# Maybe it is because missing value add in sparse value, but
col_name = bin_inner_param.header[col_idx]
split_points = split_points_dict[col_name]
bin_num = BaseBinning.get_bin_num(col_value, split_points)
indice.append(col_idx)
col_results = bin_res.all_cols_results.get(col_name)
woe_value = col_results.woe_array[bin_num]
sparse_value.append(woe_value)
else:
indice.append(col_idx)
sparse_value.append(col_value)
sparse_vector = SparseVector(indice, sparse_value, data_shape)
instances.features = sparse_vector
else:
features = instances.features
assert isinstance(features, np.ndarray)
transform_cols_idx_set = set(transform_cols_idx)
for col_idx, col_value in enumerate(features):
if col_idx in transform_cols_idx_set:
if col_value in abnormal_list:
features[col_idx] = col_value
continue
col_name = bin_inner_param.header[col_idx]
split_points = split_points_dict[col_name]
bin_num = BaseBinning.get_bin_num(col_value, split_points)
col_results = bin_res.all_cols_results.get(col_name)
woe_value = col_results.woe_array[bin_num]
features[col_idx] = woe_value
instances.features = features
return instances