Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/1814#discussion_r15908504
--- Diff: mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala ---
@@ -177,18 +115,72 @@ private object IDF {
private def isEmpty: Boolean = m == 0L
/** Returns the current IDF vector. */
- def idf(): BDV[Double] = {
+ def idf(): Vector = {
if (isEmpty) {
throw new IllegalStateException("Haven't seen any document yet.")
}
val n = df.length
- val inv = BDV.zeros[Double](n)
+ val inv = new Array[Double](n)
var j = 0
while (j < n) {
inv(j) = math.log((m + 1.0)/ (df(j) + 1.0))
j += 1
}
- inv
+ Vectors.dense(inv)
}
}
}
+
+/**
+ * :: Experimental ::
+ * Represents an IDF model that can transform term frequency vectors.
+ */
+@Experimental
+class IDFModel private[mllib] (val idf: Vector) extends Serializable {
+
+ /**
+ * Transforms term frequency (TF) vectors to TF-IDF vectors.
+ * @param dataset an RDD of term frequency vectors
+ * @return an RDD of TF-IDF vectors
+ */
+ def transform(dataset: RDD[Vector]): RDD[Vector] = {
+ val bcIdf = dataset.context.broadcast(idf)
+ dataset.mapPartitions { iter =>
+ val thisIdf = bcIdf.value
+ iter.map { v =>
+ val n = v.size
+ v match {
+ case sv: SparseVector =>
+ val nnz = sv.indices.size
+ val newValues = new Array[Double](nnz)
+ var k = 0
+ while (k < nnz) {
+ newValues(k) = sv.values(k) * thisIdf(sv.indices(k))
+ k += 1
+ }
+ Vectors.sparse(n, sv.indices, newValues)
+ case dv: DenseVector =>
+ val newValues = new Array[Double](n)
+ var j = 0
+ while (j < n) {
+ newValues(j) = dv.values(j) * thisIdf(j)
+ j += 1
+ }
+ Vectors.dense(newValues)
+ case other =>
+ throw new UnsupportedOperationException(
--- End diff --
The following exception is used for unsupported vector in appendBias and
StandardScaler, maybe we could have a global definition of this in util.
case v => throw new IllegalArgumentException("Do not support vector
type " + v.getClass)
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
