def hasUniqueness(self, columns, assertion):
"""
Creates a constraint that asserts on uniqueness in a single or combined set of key columns.
@param columns Key columns
@param assertion Function that receives a double input parameter and returns a boolean.
Refers to the fraction of unique values
@param hint A hint to provide additional context why a constraint could have failed
"""
if (not isinstance(columns, list)):
# Single column is provided
columns = [columns]
function = jc.scala_function1(self.spark.sparkContext._gateway,
assertion)
jvmConstraint = self.jvmCheck.hasUniqueness(
jc.iterable_to_scala_seq(self._jvm, columns), function)
return Check(self.spark, self.level, self.description, jvmConstraint)
def jvmAnalyzer(self):
return self.jvmdeequAnalyzers.UniqueValueRatio(
jc.iterable_to_scala_seq(self._jvm, self.columns),
getattr(self.jvmdeequAnalyzers.UniqueValueRatio,
"apply$default$2")())
def jvmAnalyzer(self):
return self.jvmdeequAnalyzers.MutualInformation(
jc.iterable_to_scala_seq(self._jvm, self.columns),
getattr(self.jvmdeequAnalyzers.MutualInformation,
"apply$default$2")())
def jvmAnalyzer(self):
return self.jvmdeequAnalyzers.Distinctness(
jc.iterable_to_scala_seq(self._jvm, self.columns),
getattr(self.jvmdeequAnalyzers.DataType, "apply$default$2")())
def jvmAnalyzer(self):
return self.jvmdeequAnalyzers.CountDistinct(
jc.iterable_to_scala_seq(self._jvm, self.column))