Github user zhangjiajin commented on a diff in the pull request:
https://github.com/apache/spark/pull/7258#discussion_r34118782
--- Diff: mllib/src/main/scala/org/apache/spark/mllib/fpm/Prefixspan.scala
---
@@ -0,0 +1,183 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.mllib.fpm
+
+import org.apache.spark.rdd.RDD
+
+/**
+ *
+ * A parallel PrefixSpan algorithm to mine sequential pattern.
+ * The PrefixSpan algorithm is described in
+ * [[http://web.engr.illinois.edu/~hanj/pdf/span01.pdf]].
+ *
+ * @param sequences original sequences data
+ * @param minSupport the minimal support level of the sequential pattern,
any pattern appears
+ * more than minSupport times will be output
+ * @param maxPatternLength the maximal length of the sequential pattern,
any pattern appears
+ * less than maxPatternLength will be output
+ *
+ * @see [[https://en.wikipedia.org/wiki/Sequential_Pattern_Mining
Sequential Pattern Mining
+ * (Wikipedia)]]
+ */
+class Prefixspan(
+ val sequences: RDD[Array[Int]],
+ val minSupport: Int = 2,
--- End diff --
Changed these input parameters to private var s, and add getters and
setters.
But I have a question, why don't we use the public input parameters ?
The following code, the class A is smaller than class B, Why is class B
code style better ?
class A (var x: Int = 12) {
def f() = {
println(x)
}
}
class B (private var x: Int) {
def this() = this(12)
def setX(x: Int): this.type = {
this.x=x
this
}
def f() = {
println(x)
}
}
val a = new A()
a.f()
a.x = 15
a.f()
val b = new B()
b.f()
b.setX(15)
b.f()
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
