srowen commented on a change in pull request #26035: [SPARK-29360][PYTHON][ML]
PySpark FPGrowthModel supports getter/setter
URL: https://github.com/apache/spark/pull/26035#discussion_r331797932
##########
File path: python/pyspark/ml/fpm.py
##########
@@ -197,20 +171,22 @@ class FPGrowth(JavaEstimator, HasItemsCol,
HasPredictionCol,
| [r]| 3|
+---------+----+
only showing top 5 rows
+ ...
>>> fpm.associationRules.show(5)
- +----------+----------+----------+
- |antecedent|consequent|confidence|
- +----------+----------+----------+
- | [t, s]| [y]| 1.0|
- | [t, s]| [x]| 1.0|
- | [t, s]| [z]| 1.0|
- | [p]| [r]| 1.0|
- | [p]| [z]| 1.0|
- +----------+----------+----------+
+ +----------+----------+----------+----+
+ |antecedent|consequent|confidence|lift|
+ +----------+----------+----------+----+
+ | [t, s]| [y]| 1.0| 2.0|
+ | [t, s]| [x]| 1.0| 1.5|
+ | [t, s]| [z]| 1.0| 1.2|
+ | [p]| [r]| 1.0| 2.0|
+ | [p]| [z]| 1.0| 1.2|
+ +----------+----------+----------+----+
only showing top 5 rows
+ ...
>>> new_data = spark.createDataFrame([(["t", "s"], )], ["items"])
- >>> sorted(fpm.transform(new_data).first().prediction)
- ['x', 'y', 'z']
+ >>> sorted(fpm.transform(new_data).first().newPrediction)
+ [u'x', u'y', u'z']
Review comment:
I'm kind of curious why this changed, do you know?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
