diff options
author | GayathriMurali <gayathri.m@intel.com> | 2016-06-24 13:25:40 +0200 |
---|---|---|
committer | Nick Pentreath <nickp@za.ibm.com> | 2016-06-24 13:25:40 +0200 |
commit | be88383e15a86d094963de5f7e8792510bc990de (patch) | |
tree | 3e4c7b8101ea1ea6a919f283e6d31b47fbee96c4 /examples/src | |
parent | 158af162eac7348464c6751c8acd48fc6c117688 (diff) | |
download | spark-be88383e15a86d094963de5f7e8792510bc990de.tar.gz spark-be88383e15a86d094963de5f7e8792510bc990de.tar.bz2 spark-be88383e15a86d094963de5f7e8792510bc990de.zip |
[SPARK-15997][DOC][ML] Update user guide for HashingTF, QuantileVectorizer and CountVectorizer
## What changes were proposed in this pull request?
Made changes to HashingTF,QuantileVectorizer and CountVectorizer
Author: GayathriMurali <gayathri.m@intel.com>
Closes #13745 from GayathriMurali/SPARK-15997.
Diffstat (limited to 'examples/src')
3 files changed, 21 insertions, 6 deletions
diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java index 16f58a852d..dd20cac621 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaQuantileDiscretizerExample.java @@ -54,7 +54,12 @@ public class JavaQuantileDiscretizerExample { }); Dataset<Row> df = spark.createDataFrame(data, schema); - + // $example off$ + // Output of QuantileDiscretizer for such small datasets can depend on the number of + // partitions. Here we force a single partition to ensure consistent results. + // Note this is not necessary for normal use cases + df = df.repartition(1); + // $example on$ QuantileDiscretizer discretizer = new QuantileDiscretizer() .setInputCol("hour") .setOutputCol("result") diff --git a/examples/src/main/python/ml/quantile_discretizer_example.py b/examples/src/main/python/ml/quantile_discretizer_example.py index 6ae7bb18f8..5444cacd95 100644 --- a/examples/src/main/python/ml/quantile_discretizer_example.py +++ b/examples/src/main/python/ml/quantile_discretizer_example.py @@ -28,11 +28,16 @@ if __name__ == "__main__": # $example on$ data = [(0, 18.0,), (1, 19.0,), (2, 8.0,), (3, 5.0,), (4, 2.2,)] - dataFrame = spark.createDataFrame(data, ["id", "hour"]) - + df = spark.createDataFrame(data, ["id", "hour"]) + # $example off$ + # Output of QuantileDiscretizer for such small datasets can depend on the number of + # partitions. Here we force a single partition to ensure consistent results. + # Note this is not necessary for normal use cases + df = df.repartition(1) + # $example on$ discretizer = QuantileDiscretizer(numBuckets=3, inputCol="hour", outputCol="result") - result = discretizer.fit(dataFrame).transform(dataFrame) + result = discretizer.fit(df).transform(df) result.show() # $example off$ diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala index 1a16515594..2f7e217b8f 100644 --- a/examples/src/main/scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/ml/QuantileDiscretizerExample.scala @@ -32,8 +32,13 @@ object QuantileDiscretizerExample { // $example on$ val data = Array((0, 18.0), (1, 19.0), (2, 8.0), (3, 5.0), (4, 2.2)) - val df = spark.createDataFrame(data).toDF("id", "hour") - + var df = spark.createDataFrame(data).toDF("id", "hour") + // $example off$ + // Output of QuantileDiscretizer for such small datasets can depend on the number of + // partitions. Here we force a single partition to ensure consistent results. + // Note this is not necessary for normal use cases + .repartition(1) + // $example on$ val discretizer = new QuantileDiscretizer() .setInputCol("hour") .setOutputCol("result") |