class Sampling extends AnyRef
Routines for creating and managing frequency sampled minimizer orderings.
- Alphabetic
- By Inheritance
- Sampling
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
- new Sampling()(implicit spark: SparkSession)
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native() @IntrinsicCandidate()
- def countFeatures(reads: Dataset[NTSeq], table: MinTable, partitions: Int): SampledFrequencies
-
def
createSampledTable(input: Dataset[InputFragment], template: MinTable, sampledFraction: Double, persistLocation: Option[String] = None): MinTable
Create a MinTable based on sampling reads for minimizer frequencies.
Create a MinTable based on sampling reads for minimizer frequencies.
- input
Input data (already sampled)
- template
Template table, containing minimizers to sort according to frequencies in the sample
- sampledFraction
Fraction of input data that was sampled. Note: the input data is assumed to already be sampled, but we need this value again for data adjustments.
- persistLocation
Location to optionally write the new table to for later reuse count
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native() @IntrinsicCandidate()
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native() @IntrinsicCandidate()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
def
motifCounts(reads: Dataset[NTSeq], table: MinTable, partitions: Int): Dataset[(Int, Long)]
Count motifs (m-length minimizers) in a set of reads.
Count motifs (m-length minimizers) in a set of reads.
- reads
Data to count motifs in
- table
Template table with a motif set
- returns
a DataFrame with (motif, count) pairs
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native() @IntrinsicCandidate()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native() @IntrinsicCandidate()
- def readMotifList(location: String): Dataset[Int]
-
def
readMotifList(location: String, k: Int, m: Int): Dataset[Int]
Read a saved minimizer ordering/motif list
Read a saved minimizer ordering/motif list
- location
Location to read from. If the location is a directory, it will be scanned for files called minimizers_{k}_{m} for various values of m and k and the most optimal file will be used. If it is a file, the file will be read as is.
- k
k-mer width
- m
minimizer length
- def readMotifWidth(location: String): Int
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
- def writeFrequencies(f: SampledFrequencies, location: String): Unit
Deprecated Value Members
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] ) @Deprecated
- Deprecated