def from_protobuf(
cls: "NLPMetrics",
message: NLPMetricsMessage,
):
nlp_met = NLPMetrics()
nlp_met.wer = NumberTracker.from_protobuf(message.wer)
nlp_met.wil = NumberTracker.from_protobuf(message.wil)
nlp_met.mer = NumberTracker.from_protobuf(message.mer)
return nlp_met
def test_merge():
x = NumberTracker()
for v in [10, 11, 13]:
x.track(v)
merged = x.merge(x)
assert merged.ints.count == 6
assert merged.floats.count == 0
assert merged.histogram.get_n() == 6
assert merged.histogram.get_max_value() == 13.0
assert merged.histogram.get_min_value() == 10.0
msg = merged.to_protobuf()
NumberTracker.from_protobuf(msg)
def test_merge():
x = NumberTracker()
for v in [10, 11, 13]:
x.track(v)
merged = x.merge(x)
assert merged.ints.count == 6
assert merged.floats.count == 0
assert merged.histogram.get_n() == 6
assert merged.histogram.get_max_value() == 13.0
assert merged.histogram.get_min_value() == 10.0
expected_freq = [
(10, 2, 2, 2),
(11, 2, 2, 2),
(13, 2, 2, 2),
]
compare_frequent_items(expected_freq, merged.frequent_numbers.get_frequent_items())
msg = merged.to_protobuf()
NumberTracker.from_protobuf(msg)
def test_protobuf_roundtrip():
x0 = NumberTracker()
for v in [10, 11, 13]:
x0.track(v)
msg = x0.to_protobuf()
roundtrip = NumberTracker.from_protobuf(msg)
assert x0.ints.count == roundtrip.ints.count
assert x0.floats.count == roundtrip.floats.count
assert x0.histogram.get_n() == roundtrip.histogram.get_n()
assert x0.histogram.get_min_value() == roundtrip.histogram.get_min_value()
assert x0.histogram.get_max_value() == roundtrip.histogram.get_max_value()
def from_protobuf(message):
"""
Load from a protobuf message
Returns
-------
column_profile : ColumnProfile
"""
return ColumnProfile(
message.name,
counters=CountersTracker.from_protobuf(message.counters),
schema_tracker=SchemaTracker.from_protobuf(message.schema),
number_tracker=NumberTracker.from_protobuf(message.numbers),
string_tracker=StringTracker.from_protobuf(message.strings),
frequent_items=FrequentItemsSketch.from_protobuf(
message.frequent_items),
cardinality_tracker=HllSketch.from_protobuf(
message.cardinality_tracker),
)
def from_protobuf(
cls,
message: ScoreMatrixMessage,
):
if message.ByteSize() == 0:
return None
labels = message.labels
num_labels = len(labels)
matrix = np.array(
[NumberTracker.from_protobuf(score)
for score in message.scores]).reshape(
(num_labels, num_labels)) if num_labels > 0 else None
cm_instance = ConfusionMatrix(
labels=labels,
prediction_field=message.prediction_field,
target_field=message.target_field,
score_field=message.score_field)
cm_instance.confusion_matrix = matrix
return cm_instance