def __init__()

in pydeequ/profiles.py [0:0]

• 32 lines of code
• 3 McCabe index (conditional complexity)

    def __init__(self, spark_session: SparkSession, column, java_column_profile):
        super().__init__(spark_session, column, java_column_profile)
        # TODO: self.numRecords = java_column_profile.numRecords()
        self._kll = (
            BucketDistribution(spark_session, java_column_profile.kll().get())
            if get_or_else_none(java_column_profile.kll())
            else None
        )
        self._mean = get_or_else_none(java_column_profile.mean())
        self._maximum = get_or_else_none(java_column_profile.maximum())
        self._minimum = get_or_else_none(java_column_profile.minimum())
        self._sum = get_or_else_none(java_column_profile.sum())
        self._stdDev = get_or_else_none(java_column_profile.stdDev())
        self._approxPercentiles = (
            java_list_to_python_list(str(get_or_else_none(java_column_profile.approxPercentiles())), float)
            if get_or_else_none(java_column_profile.approxPercentiles())
            else []
        )
        self.all = {
            "completeness": self.completeness,
            "approximateNumDistinctValues": self.approximateNumDistinctValues,
            "dataType": self.dataType,
            "isDataTypeInferred": self.isDataTypeInferred,
            "typeCounts": self.typeCounts,
            "histogram": self.histogram,
            "kll": str(self._kll),
            "mean": self._mean,
            "maximum": self._maximum,
            "minimum": self._minimum,
            "sum": self._sum,
            "stdDev": self._stdDev,
            "approxPercentiles": self._approxPercentiles,
        }