diff options
| author | Yu ISHIKAWA <yuu.ishikawa@gmail.com> | 2016-02-25 13:29:10 -0800 |
|---|---|---|
| committer | Xiangrui Meng <meng@databricks.com> | 2016-02-25 13:29:10 -0800 |
| commit | 35316cb0b744bef9bcb390411ddc321167f953be (patch) | |
| tree | 3ed75c8c6e20cb0a5468925416f70cd86a2933c2 /python | |
| parent | 14e2700de29d06460179a94cc9816bcd37344cf7 (diff) | |
| download | spark-35316cb0b744bef9bcb390411ddc321167f953be.tar.gz spark-35316cb0b744bef9bcb390411ddc321167f953be.tar.bz2 spark-35316cb0b744bef9bcb390411ddc321167f953be.zip | |
[SPARK-13292] [ML] [PYTHON] QuantileDiscretizer should take random seed in PySpark
## What changes were proposed in this pull request?
QuantileDiscretizer in Python should also specify a random seed.
## How was this patch tested?
unit tests
Author: Yu ISHIKAWA <yuu.ishikawa@gmail.com>
Closes #11362 from yu-iskw/SPARK-13292 and squashes the following commits:
02ffa76 [Yu ISHIKAWA] [SPARK-13292][ML][PYTHON] QuantileDiscretizer should take random seed in PySpark
Diffstat (limited to 'python')
| -rw-r--r-- | python/pyspark/ml/feature.py | 14 |
1 files changed, 8 insertions, 6 deletions
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py index 464c9446f2..67bccfae7a 100644 --- a/python/pyspark/ml/feature.py +++ b/python/pyspark/ml/feature.py @@ -939,7 +939,7 @@ class PolynomialExpansion(JavaTransformer, HasInputCol, HasOutputCol): @inherit_doc -class QuantileDiscretizer(JavaEstimator, HasInputCol, HasOutputCol): +class QuantileDiscretizer(JavaEstimator, HasInputCol, HasOutputCol, HasSeed): """ .. note:: Experimental @@ -951,7 +951,9 @@ class QuantileDiscretizer(JavaEstimator, HasInputCol, HasOutputCol): >>> df = sqlContext.createDataFrame([(0.1,), (0.4,), (1.2,), (1.5,)], ["values"]) >>> qds = QuantileDiscretizer(numBuckets=2, - ... inputCol="values", outputCol="buckets") + ... inputCol="values", outputCol="buckets", seed=123) + >>> qds.getSeed() + 123 >>> bucketizer = qds.fit(df) >>> splits = bucketizer.getSplits() >>> splits[0] @@ -971,9 +973,9 @@ class QuantileDiscretizer(JavaEstimator, HasInputCol, HasOutputCol): "categories) into which data points are grouped. Must be >= 2. Default 2.") @keyword_only - def __init__(self, numBuckets=2, inputCol=None, outputCol=None): + def __init__(self, numBuckets=2, inputCol=None, outputCol=None, seed=None): """ - __init__(self, numBuckets=2, inputCol=None, outputCol=None) + __init__(self, numBuckets=2, inputCol=None, outputCol=None, seed=None) """ super(QuantileDiscretizer, self).__init__() self._java_obj = self._new_java_obj("org.apache.spark.ml.feature.QuantileDiscretizer", @@ -987,9 +989,9 @@ class QuantileDiscretizer(JavaEstimator, HasInputCol, HasOutputCol): @keyword_only @since("2.0.0") - def setParams(self, numBuckets=2, inputCol=None, outputCol=None): + def setParams(self, numBuckets=2, inputCol=None, outputCol=None, seed=None): """ - setParams(self, numBuckets=2, inputCol=None, outputCol=None) + setParams(self, numBuckets=2, inputCol=None, outputCol=None, seed=None) Set the params for the QuantileDiscretizer """ kwargs = self.setParams._input_kwargs |