def __init__()

in pydeequ/profiles.py [0:0]

• 22 lines of code
• 4 McCabe index (conditional complexity)

    def __init__(self, spark_session: SparkSession, column, java_column_profile):
        if not isinstance(spark_session, SparkSession):
            raise TypeError(f"Expected SparkSession object for spark_session, not {type(spark_session)}")
        self._spark_session = spark_session
        self._sc = spark_session.sparkContext
        self._jvm = spark_session._jvm
        self._java_column_profile = java_column_profile
        self._column = column
        self._completeness = java_column_profile.completeness()
        self._approximateNumDistinctValues = java_column_profile.approximateNumDistinctValues()
        self._dataType = java_column_profile.dataType()
        self._typeCounts = scala_map_to_dict(self._jvm, java_column_profile.typeCounts())
        self._isDataTypeInferred = java_column_profile.isDataTypeInferred() == "true"
        if get_or_else_none(self._java_column_profile.histogram()):
            self._histogram = [
                DistributionValue(k, v.absolute(), v.ratio())
                for k, v in scala_map_to_java_map(
                    self._jvm, self._java_column_profile.histogram().get().values()
                ).items()
            ]
        else:
            self._histogram = None