def _make_string_stats_proto(string_stats,
total_num_values
):
"""Convert the partial string statistics into StringStatistics proto."""
result = statistics_pb2.StringStatistics()
if total_num_values > 0:
result.avg_length = string_stats.total_bytes_length / total_num_values
return result
def _make_feature_stats_proto(common_stats, feature_name, q_combiner,
num_values_histogram_buckets, is_categorical,
has_weights):
"""Convert the partial common stats into a FeatureNameStatistics proto.
Args:
common_stats: The partial common stats associated with a feature.
feature_name: The name of the feature.
q_combiner: The quantiles combiner used to construct the quantiles
histogram for the number of values in the feature.
num_values_histogram_buckets: Number of buckets in the quantiles
histogram for the number of values per feature.
is_categorical: A boolean indicating whether the feature is categorical.
has_weights: A boolean indicating whether a weight feature is specified.
Returns:
A statistics_pb2.FeatureNameStatistics proto.
"""
common_stats_proto = statistics_pb2.CommonStatistics()
common_stats_proto.num_non_missing = common_stats.num_non_missing
common_stats_proto.num_missing = common_stats.num_missing
common_stats_proto.tot_num_values = common_stats.total_num_values
if common_stats.num_non_missing > 0:
common_stats_proto.min_num_values = common_stats.min_num_values
common_stats_proto.max_num_values = common_stats.max_num_values
common_stats_proto.avg_num_values = (common_stats.total_num_values /
common_stats.num_non_missing)
# Add num_values_histogram to the common stats proto.
num_values_quantiles = q_combiner.extract_output(
common_stats.num_values_summary)
histogram = quantiles_util.generate_quantiles_histogram(
num_values_quantiles, common_stats.min_num_values,
common_stats.max_num_values, common_stats.num_non_missing,
num_values_histogram_buckets)
common_stats_proto.num_values_histogram.CopyFrom(histogram)
# Add weighted common stats to the proto.
if has_weights:
weighted_common_stats_proto = statistics_pb2.WeightedCommonStatistics(
num_non_missing=common_stats.weighted_num_non_missing,
num_missing=common_stats.weighted_num_missing,
tot_num_values=common_stats.weighted_total_num_values)
if common_stats.weighted_num_non_missing > 0:
weighted_common_stats_proto.avg_num_values = (
common_stats.weighted_total_num_values /
common_stats.weighted_num_non_missing)
common_stats_proto.weighted_common_stats.CopyFrom(
weighted_common_stats_proto)
# Create a new FeatureNameStatistics proto.
result = statistics_pb2.FeatureNameStatistics()
result.name = feature_name
# Set the feature type.
# If we have a categorical feature, we preserve the type to be the original
# INT type. Currently we don't set the type if we cannot infer it, which
# happens when all the values are missing. We need to add an UNKNOWN type
# to the stats proto to handle this case.
if is_categorical:
result.type = statistics_pb2.FeatureNameStatistics.INT
elif common_stats.type is None:
# If a feature is completely missing, we assume the type to be STRING.
result.type = statistics_pb2.FeatureNameStatistics.STRING
else:
result.type = common_stats.type
# Copy the common stats into appropriate numeric/string stats.
# If the type is not set, we currently wrap the common stats
# within numeric stats.
if (result.type == statistics_pb2.FeatureNameStatistics.STRING
or is_categorical):
# Add the common stats into string stats.
string_stats_proto = statistics_pb2.StringStatistics()
string_stats_proto.common_stats.CopyFrom(common_stats_proto)
result.string_stats.CopyFrom(string_stats_proto)
else:
# Add the common stats into numeric stats.
numeric_stats_proto = statistics_pb2.NumericStatistics()
numeric_stats_proto.common_stats.CopyFrom(common_stats_proto)
result.num_stats.CopyFrom(numeric_stats_proto)
return result