def host_optimal_binning(self, data_instances, host_idx,
encrypted_bin_info, result_counts,
category_names):
optimal_binning_params = encrypted_bin_info['optimal_params']
host_model_params = copy.deepcopy(self.model_param)
host_model_params.bin_num = optimal_binning_params.get('bin_num')
host_model_params.optimal_binning_param.metric_method = optimal_binning_params.get(
'metric_method')
host_model_params.optimal_binning_param.mixture = optimal_binning_params.get(
'mixture')
host_model_params.optimal_binning_param.max_bin_pct = optimal_binning_params.get(
'max_bin_pct')
host_model_params.optimal_binning_param.min_bin_pct = optimal_binning_params.get(
'min_bin_pct')
event_total, non_event_total = self.get_histogram(data_instances)
result_counts = dict(result_counts.collect())
optimal_binning_cols = {
x: y
for x, y in result_counts.items() if x not in category_names
}
host_binning_obj = OptimalBinning(
params=host_model_params,
abnormal_list=self.binning_obj.abnormal_list)
host_binning_obj.event_total = event_total
host_binning_obj.non_event_total = non_event_total
host_binning_obj = self.optimal_binning_sync(host_binning_obj,
optimal_binning_cols,
data_instances.count(),
data_instances.partitions,
host_idx)
return host_binning_obj
def optimal_binning_sync(self, result_counts, sample_count, partitions, host_idx, host_model_params):
host_binning_obj = OptimalBinning(params=host_model_params, abnormal_list=self.binning_obj.abnormal_list)
host_binning_obj.event_total = self.binning_obj.event_total
host_binning_obj.non_event_total = self.binning_obj.non_event_total
LOGGER.debug("Start host party optimal binning train")
bucket_table = host_binning_obj.bin_sum_to_bucket_list(result_counts, partitions)
host_binning_obj.fit_buckets(bucket_table, sample_count)
encoded_split_points = host_binning_obj.bin_results.all_split_points
self.transfer_variable.bucket_idx.remote(encoded_split_points,
role=consts.HOST,
idx=host_idx)
return host_binning_obj