Frequent Pattern
FPGrowth
@Plugin(type = SparkCompute.PLUGIN_TYPE)
@Name("FPGrowth")
@Description("A transformation stage that leverages the Apache Spark ML FPGrowth "
+ "algorithm to detect frequent patterns.")
public class FPGrowth extends MiningCompute {
...
}
Parameters
| Items Field | The name of the field in the into schema that contains the items. |
| Minimal Support | Minimal support level of the frequent pattern. Value must be in range [0.0, 1.0]. Any pattern that appears more than (minSupport * data size) times will be output in the frequent itemsets. Default is 0.3. |
| Minimal Confidence | Minimal confidence for generating Association Rule. minConfidence will not affect the mining for frequent itemsets, but will affect the association rules generation. Default is 0.8. |