def _make_numeric_stats_proto(
numeric_stats,
total_num_values,
quantiles_combiner,
num_histogram_buckets,
num_quantiles_histogram_buckets,
has_weights
):
"""Convert the partial numeric statistics into NumericStatistics proto."""
result = statistics_pb2.NumericStatistics()
if numeric_stats.num_nan > 0:
total_num_values -= numeric_stats.num_nan
# Set the stats in the proto only if we have at least one value for the
# feature.
if total_num_values == 0:
return result
mean = numeric_stats.sum / total_num_values
variance = max(
0, (numeric_stats.sum_of_squares / total_num_values) -
mean * mean)
result.mean = float(mean)
result.std_dev = math.sqrt(variance)
result.num_zeros = numeric_stats.num_zeros
result.min = float(numeric_stats.min)
result.max = float(numeric_stats.max)
# Extract the quantiles from the summary.
quantiles = quantiles_combiner.extract_output(
numeric_stats.quantiles_summary)
# Find the median from the quantiles and update the numeric stats proto.
result.median = float(quantiles_util.find_median(quantiles))
# Construct the equi-width histogram from the quantiles and add it to the
# numeric stats proto.
std_histogram = quantiles_util.generate_equi_width_histogram(
quantiles, numeric_stats.min, numeric_stats.max,
total_num_values, num_histogram_buckets)
std_histogram.num_nan = numeric_stats.num_nan
new_std_histogram = result.histograms.add()
new_std_histogram.CopyFrom(std_histogram)
# Construct the quantiles histogram from the quantiles and add it to the
# numeric stats proto.
q_histogram = quantiles_util.generate_quantiles_histogram(
quantiles, numeric_stats.min, numeric_stats.max,
total_num_values, num_quantiles_histogram_buckets)
q_histogram.num_nan = numeric_stats.num_nan
new_q_histogram = result.histograms.add()
new_q_histogram.CopyFrom(q_histogram)
# Add weighted numeric stats to the proto.
if has_weights:
weighted_numeric_stats_proto = statistics_pb2.WeightedNumericStatistics()
if numeric_stats.weighted_total_num_values == 0:
weighted_mean = 0
weighted_variance = 0
else:
weighted_mean = (numeric_stats.weighted_sum /
numeric_stats.weighted_total_num_values)
weighted_variance = max(0, (numeric_stats.weighted_sum_of_squares /
numeric_stats.weighted_total_num_values)
- weighted_mean**2)
weighted_numeric_stats_proto.mean = weighted_mean
weighted_numeric_stats_proto.std_dev = math.sqrt(weighted_variance)
# Extract the weighted quantiles from the summary.
weighted_quantiles = quantiles_combiner.extract_output(
numeric_stats.weighted_quantiles_summary)
# Find the weighted median from the quantiles and update the proto.
weighted_numeric_stats_proto.median = float(
quantiles_util.find_median(weighted_quantiles))
# Construct the weighted equi-width histogram from the quantiles and
# add it to the numeric stats proto.
weighted_std_histogram = quantiles_util.generate_equi_width_histogram(
weighted_quantiles, numeric_stats.min, numeric_stats.max,
numeric_stats.weighted_total_num_values, num_histogram_buckets)
weighted_std_histogram.num_nan = numeric_stats.num_nan
weighted_numeric_stats_proto.histograms.extend([weighted_std_histogram])
# Construct the weighted quantiles histogram from the quantiles and
# add it to the numeric stats proto.
weighted_q_histogram = quantiles_util.generate_quantiles_histogram(
weighted_quantiles, numeric_stats.min, numeric_stats.max,
numeric_stats.weighted_total_num_values,
num_quantiles_histogram_buckets)
weighted_q_histogram.num_nan = numeric_stats.num_nan
weighted_numeric_stats_proto.histograms.extend([weighted_q_histogram])
result.weighted_numeric_stats.CopyFrom(
weighted_numeric_stats_proto)
return result
def _make_numeric_stats_proto(
numeric_stats: _PartialNumericStats,
total_num_values: int,
num_histogram_buckets: int,
num_quantiles_histogram_buckets: int,
has_weights: bool
) -> statistics_pb2.NumericStatistics:
"""Convert the partial numeric statistics into NumericStatistics proto."""
result = statistics_pb2.NumericStatistics()
if numeric_stats.num_nan > 0:
total_num_values -= numeric_stats.num_nan
if total_num_values == 0:
# If we only have nan values, we only set num_nan.
if numeric_stats.num_nan > 0:
result.histograms.add(type=statistics_pb2.Histogram.STANDARD).num_nan = (
numeric_stats.num_nan)
result.histograms.add(type=statistics_pb2.Histogram.QUANTILES).num_nan = (
numeric_stats.num_nan)
return result
mean = numeric_stats.sum / total_num_values
variance = max(
0, (numeric_stats.sum_of_squares / total_num_values) -
mean * mean)
result.mean = float(mean)
result.std_dev = math.sqrt(variance)
result.num_zeros = numeric_stats.num_zeros
result.min = float(numeric_stats.min)
result.max = float(numeric_stats.max)
# Extract the quantiles from the summary.
assert numeric_stats.quantiles_summary is not None
quantiles = (
numeric_stats.quantiles_summary.GetQuantiles(
max(num_quantiles_histogram_buckets,
_NUM_QUANTILES_FACTOR_FOR_STD_HISTOGRAM *
num_histogram_buckets)).flatten().to_pylist())
# Find the median from the quantiles and update the numeric stats proto.
result.median = float(quantiles_util.find_median(quantiles))
# Construct the equi-width histogram from the quantiles and add it to the
# numeric stats proto.
std_histogram = quantiles_util.generate_equi_width_histogram(
quantiles, numeric_stats.finite_min, numeric_stats.finite_max,
total_num_values, num_histogram_buckets)
std_histogram.num_nan = numeric_stats.num_nan
new_std_histogram = result.histograms.add()
new_std_histogram.CopyFrom(std_histogram)
# Construct the quantiles histogram from the quantiles and add it to the
# numeric stats proto.
q_histogram = quantiles_util.generate_quantiles_histogram(
quantiles, total_num_values, num_quantiles_histogram_buckets)
q_histogram.num_nan = numeric_stats.num_nan
new_q_histogram = result.histograms.add()
new_q_histogram.CopyFrom(q_histogram)
# Add weighted numeric stats to the proto.
if has_weights:
weighted_numeric_stats_proto = statistics_pb2.WeightedNumericStatistics()
if numeric_stats.weighted_total_num_values == 0:
weighted_mean = 0
weighted_variance = 0
else:
weighted_mean = (numeric_stats.weighted_sum /
numeric_stats.weighted_total_num_values)
weighted_variance = max(0, (numeric_stats.weighted_sum_of_squares /
numeric_stats.weighted_total_num_values)
- weighted_mean**2)
weighted_numeric_stats_proto.mean = weighted_mean
weighted_numeric_stats_proto.std_dev = math.sqrt(weighted_variance)
# Extract the weighted quantiles from the summary.
assert numeric_stats.weighted_quantiles_summary is not None
weighted_quantiles = (
numeric_stats.weighted_quantiles_summary.GetQuantiles(
max(num_quantiles_histogram_buckets,
_NUM_QUANTILES_FACTOR_FOR_STD_HISTOGRAM *
num_histogram_buckets)).flatten().to_pylist())
# Find the weighted median from the quantiles and update the proto.
weighted_numeric_stats_proto.median = float(
quantiles_util.find_median(weighted_quantiles))
# Construct the weighted equi-width histogram from the quantiles and
# add it to the numeric stats proto.
weighted_std_histogram = quantiles_util.generate_equi_width_histogram(
weighted_quantiles, numeric_stats.finite_min, numeric_stats.finite_max,
numeric_stats.weighted_total_num_values, num_histogram_buckets)
weighted_std_histogram.num_nan = numeric_stats.num_nan
weighted_numeric_stats_proto.histograms.extend([weighted_std_histogram])
# Construct the weighted quantiles histogram from the quantiles and
# add it to the numeric stats proto.
weighted_q_histogram = quantiles_util.generate_quantiles_histogram(
weighted_quantiles, numeric_stats.weighted_total_num_values,
num_quantiles_histogram_buckets)
weighted_q_histogram.num_nan = numeric_stats.num_nan
weighted_numeric_stats_proto.histograms.extend([weighted_q_histogram])
result.weighted_numeric_stats.CopyFrom(
weighted_numeric_stats_proto)
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
def _make_common_stats_proto(
common_stats: _PartialCommonStats,
parent_common_stats: Optional[_PartialCommonStats],
make_quantiles_sketch_fn: Callable[[], sketches.QuantilesSketch],
num_values_histogram_buckets: int,
has_weights: bool
) -> statistics_pb2.CommonStatistics:
"""Convert the partial common stats into a CommonStatistics proto."""
result = statistics_pb2.CommonStatistics()
parent_presence_and_valency = None
if parent_common_stats is not None:
parent_presence_and_valency = (
_PresenceAndValencyStats(make_quantiles_sketch_fn)
if parent_common_stats.presence_and_valency_stats is None else
parent_common_stats.presence_and_valency_stats[-1])
presence_and_valency_stats = common_stats.presence_and_valency_stats
# the CommonStatistics already contains the presence and valency
# for a 1-nested feature.
if (presence_and_valency_stats is not None and
len(presence_and_valency_stats) > 1):
result.presence_and_valency_stats.extend(
_make_presence_and_valency_stats_protos(
parent_presence_and_valency,
common_stats.presence_and_valency_stats))
if has_weights:
result.weighted_presence_and_valency_stats.extend(
_make_weighted_presence_and_valency_stats_protos(
parent_presence_and_valency,
common_stats.presence_and_valency_stats))
top_level_presence_and_valency = (
_PresenceAndValencyStats(make_quantiles_sketch_fn)
if common_stats.presence_and_valency_stats is None else
common_stats.presence_and_valency_stats[0])
result.num_non_missing = top_level_presence_and_valency.num_non_missing
if parent_presence_and_valency is not None:
result.num_missing = (
parent_presence_and_valency.total_num_values -
top_level_presence_and_valency.num_non_missing)
result.tot_num_values = top_level_presence_and_valency.total_num_values
# TODO(b/79685042): Need to decide on what is the expected values for
# statistics like min_num_values, max_num_values, avg_num_values, when
# all the values for the feature are missing.
if top_level_presence_and_valency.num_non_missing > 0:
result.min_num_values = top_level_presence_and_valency.min_num_values
result.max_num_values = top_level_presence_and_valency.max_num_values
result.avg_num_values = (
top_level_presence_and_valency.total_num_values /
top_level_presence_and_valency.num_non_missing)
if top_level_presence_and_valency.num_values_summary is not None:
# Add num_values_histogram to the common stats proto.
num_values_quantiles = (
top_level_presence_and_valency.num_values_summary.GetQuantiles(
num_values_histogram_buckets).flatten().to_pylist())
histogram = quantiles_util.generate_quantiles_histogram(
num_values_quantiles, top_level_presence_and_valency.num_non_missing,
num_values_histogram_buckets)
result.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=top_level_presence_and_valency.weighted_num_non_missing,
tot_num_values=top_level_presence_and_valency.weighted_total_num_values)
if parent_presence_and_valency is not None:
weighted_common_stats_proto.num_missing = (
parent_presence_and_valency.weighted_total_num_values -
top_level_presence_and_valency.weighted_num_non_missing)
if top_level_presence_and_valency.weighted_num_non_missing > 0:
weighted_common_stats_proto.avg_num_values = (
top_level_presence_and_valency.weighted_total_num_values /
top_level_presence_and_valency.weighted_num_non_missing)
result.weighted_common_stats.CopyFrom(
weighted_common_stats_proto)
return result