how can I convert a CoordinateMatrix to a Pyspark Dataframe?
I have tried to convert my dataframe to a rowmatrix and then to a dataframe using this
df.toRowMatrix().rows.map(lambda x: (x, )).toDF()
but it looks really weird.
| _1|
+--------------------+
|(100,[20,21,22,23...|
|(100,[40,41,42,43...|
|(100,[35,36,37,38...|
|(100,[5,6,7,8,9,1...|
Would appreciate any help, thanks!