Function columnar_update has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def columnar_update(self, data: PreprocessedColumn) -> OperationResult:
        vectors = data.list.tensors if data.list.tensors else []
        vectors = vectors + (data.pandas.tensors.tolist() if data.pandas.tensors else [])

        if not vectors:

• Read up
  Read up

Function whylogs_pandas_segmented_profiler has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

def whylogs_pandas_segmented_profiler(
    pdf_iterator: Iterable[pd.DataFrame], schema: Optional[DatasetSchema] = None
) -> Iterable[pd.DataFrame]:
    if schema is None or not schema.segments:
        raise ValueError(

• Read up
  Read up

Function _process_flush_message has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def _process_flush_message(self, message: FlushMessage) -> None:
        for dataset_timestamp, container in self._cache.items():
            self._logger.debug(f"Generating result set for dataset timestamp {dataset_timestamp}")

            result_set = container.to_result_set()

• Read up
  Read up

Method doTrack has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

  private void doTrack(HashMap<String, ?> row) {
    boolean dirty = this.schema.resolve(row);
    if (dirty) {
      Set<String> schemaColumnNames = this.schema.getColNames();
      Set<String> newColumnNames = new HashSet<>();

• Read up
  Read up

Function _generate_segment_tags_metadata has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

def _generate_segment_tags_metadata(
    segment: Segment, partition: SegmentationPartition
) -> Tuple[Dict[str, str], List[SegmentTag], Dict[str, str]]:
    segment_metadata: Optional[Dict[str, str]] = None
    segment_tags: Optional[List[SegmentTag]] = None

• Read up
  Read up

Function __init__ has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def __init__(self, schedule: Schedule, fn: Callable[[], Any], timer_class: Type[Any] = Timer) -> None:
        self._logger = logging.getLogger(f"{type(self).__name__}_{id(self)}")
        self._fn = fn
        self._schedule = schedule
        self._running = True

• Read up
  Read up

Function merge has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def merge(self, other: "EmbeddingMetric") -> "EmbeddingMetric":
        if self.references.value.shape != other.references.value.shape:
            if other.references.value.shape == (1, 1):
                # TODO: handle merging with other.serialize_references==False better
                # The (1, 1) shape indicates the other metric was created without a reference matrix.

• Read up
  Read up

Function calculate has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def calculate(
        self, target_column_view: ColumnProfileView, reference_column_view: ColumnProfileView, with_thresholds=False
    ) -> Optional[DriftAlgorithmScore]:
        """Calculates drift score for a given column.

• Read up
  Read up

Function _convert_to_int_if_bool has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

def _convert_to_int_if_bool(data: pd.core.frame.DataFrame, *columns: str) -> pd.core.frame.DataFrame:
    for col in columns:
        if all(isinstance(x, bool) for x in data[col]):
            data[col] = data[col].apply(lambda x: 1 if x else 0)
    return data

• Read up
  Read up

Function _write_segmented_result_set has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def _write_segmented_result_set(self, file: SegmentedResultSet, **kwargs: Any) -> Tuple[bool, str]:
        views = file.get_writables()
        if not views:
            logger.warning("Attempt to write a result set with no writables, nothing written!")
            return True, ""

• Read up
  Read up

Function get has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def get(name: str, writable: Optional[_Writable] = None, **kwargs) -> Union[Writer, WriterWrapper]:
        if name == "local":
            from whylogs.api.writer.local import LocalWriter

            writer = LocalWriter(**kwargs)  # type: ignore

• Read up
  Read up

Function __post_init__ has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def __post_init__(self):
        if self.column_name and self.column_type:
            logger.warning(f"ResolverSpec: column {self.column_name} also specified type, name takes precedence")
        if not (self.column_name or self.column_type):
            raise ValueError("ResolverSpec: resolver specification must supply name or type")

• Read up
  Read up

Function get_cardinality_estimate has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

def get_cardinality_estimate(column_profile: ColumnProfileView) -> CardinalityEstimate:
    cardinality = column_profile.get_metric("cardinality")
    counts = column_profile.get_metric("counts")
    est_value: Optional[float] = None
    est_ratio: Optional[float] = None

• Read up
  Read up

Function resolve has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def resolve(
        self,
        *,
        pandas: Optional[pd.DataFrame] = None,
        row: Optional[Mapping[str, Any]] = None,

• Read up
  Read up

Function _do_match has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def _do_match(cls, dtype_or_type: Any, maybe_type: Optional[Any]) -> bool:
        # Pandas Categorical is Strings
        if CategoricalDtype is not None and isinstance(dtype_or_type, CategoricalDtype):
            return True

• Read up
  Read up

Function _write has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def _write(
        self, path: Optional[str] = None, filename: Optional[str] = None, **kwargs: Any
    ) -> Tuple[bool, Union[str, List[str]]]:
        file_to_write = kwargs.get("file")
        if file_to_write is None:

• Read up
  Read up

Function to_summary_dict has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def to_summary_dict(self, cfg: Optional[SummaryConfig] = None) -> Dict[str, Any]:
        cfg = cfg or SummaryConfig()
        summary = {}
        for sub_name, metrics in self.submetrics.items():
            for namespace, metric in metrics.items():

• Read up
  Read up

Function to_protobuf has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def to_protobuf(
        self,
    ) -> ModelProfileMessage:
        model_type = ModelType.UNKNOWN
        if not self.model_type:

• Read up
  Read up

Function merge_submetrics has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def merge_submetrics(self: MULTI_METRIC, other: MULTI_METRIC) -> Dict[str, Dict[str, Metric]]:
        if self.namespace != other.namespace:
            raise ValueError(f"Attempt to merge MultiMetrics {self.namespace} and {other.namespace}")

        submetric_names = set(self.submetrics.keys())

• Read up
  Read up

Avoid too many return statements within this method.

Open

      return (T) result;