Github user WeichenXu123 commented on a diff in the pull request:
https://github.com/apache/spark/pull/21119#discussion_r184346287
--- Diff: python/pyspark/ml/clustering.py ---
@@ -1156,6 +1156,201 @@ def getKeepLastCheckpoint(self):
return self.getOrDefault(self.keepLastCheckpoint)
+class _PowerIterationClusteringParams(JavaParams, HasMaxIter,
HasPredictionCol):
+ """
+ Params for :py:attr:`PowerIterationClustering`.
+ .. versionadded:: 2.4.0
+ """
+
+ k = Param(Params._dummy(), "k",
+ "The number of clusters to create. Must be > 1.",
+ typeConverter=TypeConverters.toInt)
+ initMode = Param(Params._dummy(), "initMode",
+ "The initialization algorithm. This can be either " +
+ "'random' to use a random vector as vertex
properties, or 'degree' to use " +
+ "a normalized sum of similarities with other
vertices. Supported options: " +
+ "'random' and 'degree'.",
+ typeConverter=TypeConverters.toString)
+ idCol = Param(Params._dummy(), "idCol",
+ "Name of the input column for vertex IDs.",
+ typeConverter=TypeConverters.toString)
+ neighborsCol = Param(Params._dummy(), "neighborsCol",
+ "Name of the input column for neighbors in the
adjacency list " +
+ "representation.",
+ typeConverter=TypeConverters.toString)
+ similaritiesCol = Param(Params._dummy(), "similaritiesCol",
+ "Name of the input column for non-negative
weights (similarities) " +
+ "of edges between the vertex in `idCol` and
each neighbor in " +
+ "`neighborsCol`",
+ typeConverter=TypeConverters.toString)
+
+ @since("2.4.0")
+ def getK(self):
+ """
+ Gets the value of `k`
+ """
+ return self.getOrDefault(self.k)
+
+ @since("2.4.0")
+ def getInitMode(self):
+ """
+ Gets the value of `initMode`
+ """
+ return self.getOrDefault(self.initMode)
+
+ @since("2.4.0")
+ def getIdCol(self):
+ """
+ Gets the value of `idCol`
+ """
+ return self.getOrDefault(self.idCol)
+
+ @since("2.4.0")
+ def getNeighborsCol(self):
+ """
+ Gets the value of `neighborsCol`
+ """
+ return self.getOrDefault(self.neighborsCol)
+
+ @since("2.4.0")
+ def getSimilaritiesCol(self):
+ """
+ Gets the value of `similaritiesCol`
+ """
+ return self.getOrDefault(self.binary)
+
+
+@inherit_doc
+class PowerIterationClustering(JavaTransformer,
_PowerIterationClusteringParams, JavaMLReadable,
+ JavaMLWritable):
+ """
+ Model produced by [[PowerIterationClustering]].
+ >>> from pyspark.sql.types import ArrayType, DoubleType, LongType,
StructField, StructType
+ >>> import math
+ >>> def genCircle(r, n):
+ ... points = []
+ ... for i in range(0, n):
+ ... theta = 2.0 * math.pi * i / n
+ ... points.append((r * math.cos(theta), r * math.sin(theta)))
+ ... return points
+ >>> def sim(x, y):
+ ... dist = (x[0] - y[0]) * (x[0] - y[0]) + (x[1] - y[1]) * (x[1] -
y[1])
+ ... return math.exp(-dist / 2.0)
+ >>> r1 = 1.0
+ >>> n1 = 10
+ >>> r2 = 4.0
+ >>> n2 = 40
+ >>> n = n1 + n2
+ >>> points = genCircle(r1, n1) + genCircle(r2, n2)
+ >>> similarities = []
+ >>> for i in range (1, n):
+ ... neighbor = []
+ ... weight = []
+ ... for j in range (i):
+ ... neighbor.append((long)(j))
+ ... weight.append(sim(points[i], points[j]))
+ ... similarities.append([(long)(i), neighbor, weight])
--- End diff --
The doctest code looks like too long, maybe more proper to put it in
examples.
Could you replace the data generation code here by using a simple hardcoded
dataset ?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
