def __init__(self, input_col: str, partition_key: str, output_col: str,
vocab_df: DataFrame):
super().__init__()
ExplainBuilder.build(self,
inputCol=input_col,
partitionKey=partition_key,
outputCol=output_col)
self._vocab_df = vocab_df
def __init__(self, input_col: str, partition_key: str, output_col: str,
reset_per_partition: bool):
super().__init__()
ExplainBuilder.build(self,
inputCol=input_col,
partitionKey=partition_key,
outputCol=output_col,
resetPerPartition=reset_per_partition)
def __init__(self, partition_key: Optional[str],
indexed_col_names_arr: List[str], complementset_factor: int):
super().__init__()
# we assume here that all indices of the columns are continuous within their partition_key
ExplainBuilder.build(self,
partitionKey=partition_key,
indexedColNamesArr=indexed_col_names_arr,
complementsetFactor=complementset_factor)
def __init__(self,
input_col: str,
partition_key: Optional[str],
output_col: str,
use_pandas: bool = True):
super().__init__()
ExplainBuilder.build(self,
inputCol=input_col,
partitionKey=partition_key,
outputCol=output_col)
self._use_pandas = use_pandas
def __init__(self,
input_col: str,
partition_key: Optional[str],
output_col: str,
per_group_stats: Union[DataFrame, Dict[str, float]],
use_pandas: bool = True):
super().__init__()
ExplainBuilder.build(self,
inputCol=input_col,
partitionKey=partition_key,
outputCol=output_col)
self._per_group_stats = per_group_stats
self._use_pandas = use_pandas
def __init__(self):
super().__init__()
ExplainBuilder.build(self, inputCol='input', partitionKey=1)
self.setSecondPartitionKey(2)
self.setOutputCol('output')