diff options
Diffstat (limited to 'examples/src/main/python/ml/simple_params_example.py')
| -rw-r--r-- | examples/src/main/python/ml/simple_params_example.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/examples/src/main/python/ml/simple_params_example.py b/examples/src/main/python/ml/simple_params_example.py index 3933d59b52..a9f29dab2d 100644 --- a/examples/src/main/python/ml/simple_params_example.py +++ b/examples/src/main/python/ml/simple_params_example.py @@ -41,8 +41,8 @@ if __name__ == "__main__": # prepare training data. # We create an RDD of LabeledPoints and convert them into a DataFrame. - # Spark DataFrames can automatically infer the schema from named tuples - # and LabeledPoint implements __reduce__ to behave like a named tuple. + # A LabeledPoint is an Object with two fields named label and features + # and Spark SQL identifies these fields and creates the schema appropriately. training = sc.parallelize([ LabeledPoint(1.0, DenseVector([0.0, 1.1, 0.1])), LabeledPoint(0.0, DenseVector([2.0, 1.0, -1.0])), |