def __init__(
self,
name: str,
number_tracker: NumberTracker = None,
string_tracker: StringTracker = None,
schema_tracker: SchemaTracker = None,
counters: CountersTracker = None,
frequent_items: FrequentItemsSketch = None,
cardinality_tracker: HllSketch = None,
):
# Handle default values
if counters is None:
counters = CountersTracker()
if number_tracker is None:
number_tracker = NumberTracker()
if string_tracker is None:
string_tracker = StringTracker()
if schema_tracker is None:
schema_tracker = SchemaTracker()
if frequent_items is None:
frequent_items = FrequentItemsSketch()
if cardinality_tracker is None:
cardinality_tracker = HllSketch()
# Assign values
self.column_name = name
self.number_tracker = number_tracker
self.string_tracker = string_tracker
self.schema_tracker = schema_tracker
self.counters = counters
self.frequent_items = frequent_items
self.cardinality_tracker = cardinality_tracker
def test_fallback_fallbacks_to_number_counter():
col = ColumnProfile("test")
vals = ["a", "b", 1.0, 2.0]
for v in vals:
col.track(v)
col.cardinality_tracker = HllSketch()
summary = col.to_summary()
assert summary.unique_count.estimate == summary.number_summary.unique_count.estimate
def test_fallback_number_counter():
col = ColumnProfile("test")
vals = [1, 1.0, 2, 3, 4, 5, 6, 6.0, "text"]
for v in vals:
col.track(v)
col.cardinality_tracker = HllSketch()
summary = col.to_summary()
assert summary.unique_count.estimate == summary.number_summary.unique_count.estimate
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),
)