You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by jk...@apache.org on 2015/05/31 20:51:56 UTC
spark git commit: [SPARK-7949] [MLLIB] [DOC] update document with
some missing save/load
Repository: spark
Updated Branches:
refs/heads/master e1067d0ad -> 067470030
[SPARK-7949] [MLLIB] [DOC] update document with some missing save/load
add save load for examples:
KMeansModel
PowerIterationClusteringModel
Word2VecModel
IsotonicRegressionModel
Author: Yuhao Yang <hh...@gmail.com>
Closes #6498 from hhbyyh/docSaveLoad and squashes the following commits:
7f9f06d [Yuhao Yang] add missing imports
c604cad [Yuhao Yang] Merge remote-tracking branch 'upstream/master' into docSaveLoad
1dd77cc [Yuhao Yang] update document with some missing save/load
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/06747003
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/06747003
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/06747003
Branch: refs/heads/master
Commit: 0674700303da3e4737d73f5fabd2a925ec712f63
Parents: e1067d0
Author: Yuhao Yang <hh...@gmail.com>
Authored: Sun May 31 11:51:49 2015 -0700
Committer: Joseph K. Bradley <jo...@databricks.com>
Committed: Sun May 31 11:51:49 2015 -0700
----------------------------------------------------------------------
docs/mllib-clustering.md | 28 ++++++++++++++++++++++++----
docs/mllib-feature-extraction.md | 6 +++++-
docs/mllib-isotonic-regression.md | 10 +++++++++-
3 files changed, 38 insertions(+), 6 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/06747003/docs/mllib-clustering.md
----------------------------------------------------------------------
diff --git a/docs/mllib-clustering.md b/docs/mllib-clustering.md
index f41ca70..dac22f7 100644
--- a/docs/mllib-clustering.md
+++ b/docs/mllib-clustering.md
@@ -47,7 +47,7 @@ Set Sum of Squared Error (WSSSE). You can reduce this error measure by increasin
optimal *k* is usually one where there is an "elbow" in the WSSSE graph.
{% highlight scala %}
-import org.apache.spark.mllib.clustering.KMeans
+import org.apache.spark.mllib.clustering.{KMeans, KMeansModel}
import org.apache.spark.mllib.linalg.Vectors
// Load and parse the data
@@ -62,6 +62,10 @@ val clusters = KMeans.train(parsedData, numClusters, numIterations)
// Evaluate clustering by computing Within Set Sum of Squared Errors
val WSSSE = clusters.computeCost(parsedData)
println("Within Set Sum of Squared Errors = " + WSSSE)
+
+// Save and load model
+clusters.save(sc, "myModelPath")
+val sameModel = KMeansModel.load(sc, "myModelPath")
{% endhighlight %}
</div>
@@ -110,6 +114,10 @@ public class KMeansExample {
// Evaluate clustering by computing Within Set Sum of Squared Errors
double WSSSE = clusters.computeCost(parsedData.rdd());
System.out.println("Within Set Sum of Squared Errors = " + WSSSE);
+
+ // Save and load model
+ clusters.save(sc.sc(), "myModelPath");
+ KMeansModel sameModel = KMeansModel.load(sc.sc(), "myModelPath");
}
}
{% endhighlight %}
@@ -124,7 +132,7 @@ Within Set Sum of Squared Error (WSSSE). You can reduce this error measure by in
fact the optimal *k* is usually one where there is an "elbow" in the WSSSE graph.
{% highlight python %}
-from pyspark.mllib.clustering import KMeans
+from pyspark.mllib.clustering import KMeans, KMeansModel
from numpy import array
from math import sqrt
@@ -143,6 +151,10 @@ def error(point):
WSSSE = parsedData.map(lambda point: error(point)).reduce(lambda x, y: x + y)
print("Within Set Sum of Squared Error = " + str(WSSSE))
+
+# Save and load model
+clusters.save(sc, "myModelPath")
+sameModel = KMeansModel.load(sc, "myModelPath")
{% endhighlight %}
</div>
@@ -312,12 +324,12 @@ Calling `PowerIterationClustering.run` returns a
which contains the computed clustering assignments.
{% highlight scala %}
-import org.apache.spark.mllib.clustering.PowerIterationClustering
+import org.apache.spark.mllib.clustering.{PowerIterationClustering, PowerIterationClusteringModel}
import org.apache.spark.mllib.linalg.Vectors
val similarities: RDD[(Long, Long, Double)] = ...
-val pic = new PowerIteartionClustering()
+val pic = new PowerIterationClustering()
.setK(3)
.setMaxIterations(20)
val model = pic.run(similarities)
@@ -325,6 +337,10 @@ val model = pic.run(similarities)
model.assignments.foreach { a =>
println(s"${a.id} -> ${a.cluster}")
}
+
+// Save and load model
+model.save(sc, "myModelPath")
+val sameModel = PowerIterationClusteringModel.load(sc, "myModelPath")
{% endhighlight %}
A full example that produces the experiment described in the PIC paper can be found under
@@ -360,6 +376,10 @@ PowerIterationClusteringModel model = pic.run(similarities);
for (PowerIterationClustering.Assignment a: model.assignments().toJavaRDD().collect()) {
System.out.println(a.id() + " -> " + a.cluster());
}
+
+// Save and load model
+model.save(sc.sc(), "myModelPath");
+PowerIterationClusteringModel sameModel = PowerIterationClusteringModel.load(sc.sc(), "myModelPath");
{% endhighlight %}
</div>
http://git-wip-us.apache.org/repos/asf/spark/blob/06747003/docs/mllib-feature-extraction.md
----------------------------------------------------------------------
diff --git a/docs/mllib-feature-extraction.md b/docs/mllib-feature-extraction.md
index 1f6ad8b..4fe470a 100644
--- a/docs/mllib-feature-extraction.md
+++ b/docs/mllib-feature-extraction.md
@@ -188,7 +188,7 @@ Here we assume the extracted file is `text8` and in same directory as you run th
import org.apache.spark._
import org.apache.spark.rdd._
import org.apache.spark.SparkContext._
-import org.apache.spark.mllib.feature.Word2Vec
+import org.apache.spark.mllib.feature.{Word2Vec, Word2VecModel}
val input = sc.textFile("text8").map(line => line.split(" ").toSeq)
@@ -201,6 +201,10 @@ val synonyms = model.findSynonyms("china", 40)
for((synonym, cosineSimilarity) <- synonyms) {
println(s"$synonym $cosineSimilarity")
}
+
+// Save and load model
+model.save(sc, "myModelPath")
+val sameModel = Word2VecModel.load(sc, "myModelPath")
{% endhighlight %}
</div>
<div data-lang="python">
http://git-wip-us.apache.org/repos/asf/spark/blob/06747003/docs/mllib-isotonic-regression.md
----------------------------------------------------------------------
diff --git a/docs/mllib-isotonic-regression.md b/docs/mllib-isotonic-regression.md
index b521c2f..5732bc4 100644
--- a/docs/mllib-isotonic-regression.md
+++ b/docs/mllib-isotonic-regression.md
@@ -60,7 +60,7 @@ Model is created using the training set and a mean squared error is calculated f
labels and real labels in the test set.
{% highlight scala %}
-import org.apache.spark.mllib.regression.IsotonicRegression
+import org.apache.spark.mllib.regression.{IsotonicRegression, IsotonicRegressionModel}
val data = sc.textFile("data/mllib/sample_isotonic_regression_data.txt")
@@ -88,6 +88,10 @@ val predictionAndLabel = test.map { point =>
// Calculate mean squared error between predicted and real labels.
val meanSquaredError = predictionAndLabel.map{case(p, l) => math.pow((p - l), 2)}.mean()
println("Mean Squared Error = " + meanSquaredError)
+
+// Save and load model
+model.save(sc, "myModelPath")
+val sameModel = IsotonicRegressionModel.load(sc, "myModelPath")
{% endhighlight %}
</div>
@@ -150,6 +154,10 @@ Double meanSquaredError = new JavaDoubleRDD(predictionAndLabel.map(
).rdd()).mean();
System.out.println("Mean Squared Error = " + meanSquaredError);
+
+// Save and load model
+model.save(sc.sc(), "myModelPath");
+IsotonicRegressionModel sameModel = IsotonicRegressionModel.load(sc.sc(), "myModelPath");
{% endhighlight %}
</div>
</div>
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org