VCFSchemaInferrer

Value Members

1. final def !=(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

3. final def ==(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

4. val VCF_HEADER_COUNT_KEY: String

   

5. val VCF_HEADER_DESCRIPTION_KEY: String

   

6. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

7. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

8. final def eq(arg0: AnyRef): Boolean

   

   Definition Classes

   AnyRef

9. def equals(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

10. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

11. final def getClass(): Class[_]

    

    Definition Classes

    AnyRef → Any

12. def getInfoFieldStruct(headerLine: VCFInfoHeaderLine): StructField

    

13. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

14. def headerLinesFromSchema(schema: StructType): Seq[VCFHeaderLine]

    

    Returns the VCF header lines that correspond to a variant schema.

    Returns the VCF header lines that correspond to a variant schema. Each flattened info field (those fields whose names start with "INFO_") will be converted to an info header line, and fields from the "genotype" struct will be converted to format header lines.

    If the count type is available in the schema metadata (which is always the case if the original schema was generated by inferSchema), that will be the returned count type. If not, we provide a best guess count type according to the following schema possibilities: - If it's a boolean field, return count = 0, as is the convention for flags - If it's a non-array field, return count = 1 - If it's an array field, return count = UNBOUNDED

    schema

    The schema of the variant DataFrame

    returns

    VCF header lines that can be inferred from the input schema

15. def inferGenotypeSchema(includeSampleIds: Boolean, formatHeaders: Seq[VCFFormatHeaderLine]): StructType

    

16. def inferSchema(includeSampleIds: Boolean, flattenInfoFields: Boolean, header: VCFHeader): StructType

    

17. def inferSchema(includeSampleIds: Boolean, flattenInfoFields: Boolean, infoHeaders: Seq[VCFInfoHeaderLine], formatHeaders: Seq[VCFFormatHeaderLine]): StructType

    
    includeSampleIds

    If true, a sampleId column will be added to the genotype fields

    flattenInfoFields

    If true, each INFO field will be promoted to a column. If false, they will instead be stored in a string -> string map

    returns

    A StructType describing the schema

18. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

19. final def ne(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

20. final def notify(): Unit

    

    Definition Classes

    AnyRef

21. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

22. final def synchronized[T0](arg0: ⇒ T0): T0

    

    Definition Classes

    AnyRef

23. def toString(): String

    

    Definition Classes

    AnyRef → Any

24. def typesForHeader(line: VCFCompoundHeaderLine): Seq[DataType]

    

25. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

26. final def wait(arg0: Long, arg1: Int): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

27. final def wait(arg0: Long): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )