From e158478a9fff5e63ae0336a54b3f360d0cd38921 Mon Sep 17 00:00:00 2001
From: Yanbo Liang <ybliang8@gmail.com>
Date: Tue, 28 Jun 2016 06:28:22 -0700
Subject: [SPARK-16242][MLLIB][PYSPARK] Conversion between old/new matrix
 columns in a DataFrame (Python)

## What changes were proposed in this pull request?
This PR implements python wrappers for #13888 to convert old/new matrix columns in a DataFrame.

## How was this patch tested?
Doctest in python.

Author: Yanbo Liang <ybliang8@gmail.com>

Closes #13935 from yanboliang/spark-16242.
---
 python/pyspark/mllib/util.py | 80 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 80 insertions(+)

(limited to 'python/pyspark')

diff --git a/python/pyspark/mllib/util.py b/python/pyspark/mllib/util.py
index a7e6bcc754..48867a08db 100644
--- a/python/pyspark/mllib/util.py
+++ b/python/pyspark/mllib/util.py
@@ -281,6 +281,86 @@ class MLUtils(object):
             raise TypeError("Input dataset must be a DataFrame but got {}.".format(type(dataset)))
         return callMLlibFunc("convertVectorColumnsFromML", dataset, list(cols))
 
+    @staticmethod
+    @since("2.0.0")
+    def convertMatrixColumnsToML(dataset, *cols):
+        """
+        Converts matrix columns in an input DataFrame from the
+        :py:class:`pyspark.mllib.linalg.Matrix` type to the new
+        :py:class:`pyspark.ml.linalg.Matrix` type under the `spark.ml`
+        package.
+
+        :param dataset:
+          input dataset
+        :param cols:
+          a list of matrix columns to be converted.
+          New matrix columns will be ignored. If unspecified, all old
+          matrix columns will be converted excepted nested ones.
+        :return:
+          the input dataset with old matrix columns converted to the
+          new matrix type
+
+        >>> import pyspark
+        >>> from pyspark.mllib.linalg import Matrices
+        >>> from pyspark.mllib.util import MLUtils
+        >>> df = spark.createDataFrame(
+        ...     [(0, Matrices.sparse(2, 2, [0, 2, 3], [0, 1, 1], [2, 3, 4]),
+        ...     Matrices.dense(2, 2, range(4)))], ["id", "x", "y"])
+        >>> r1 = MLUtils.convertMatrixColumnsToML(df).first()
+        >>> isinstance(r1.x, pyspark.ml.linalg.SparseMatrix)
+        True
+        >>> isinstance(r1.y, pyspark.ml.linalg.DenseMatrix)
+        True
+        >>> r2 = MLUtils.convertMatrixColumnsToML(df, "x").first()
+        >>> isinstance(r2.x, pyspark.ml.linalg.SparseMatrix)
+        True
+        >>> isinstance(r2.y, pyspark.mllib.linalg.DenseMatrix)
+        True
+        """
+        if not isinstance(dataset, DataFrame):
+            raise TypeError("Input dataset must be a DataFrame but got {}.".format(type(dataset)))
+        return callMLlibFunc("convertMatrixColumnsToML", dataset, list(cols))
+
+    @staticmethod
+    @since("2.0.0")
+    def convertMatrixColumnsFromML(dataset, *cols):
+        """
+        Converts matrix columns in an input DataFrame to the
+        :py:class:`pyspark.mllib.linalg.Matrix` type from the new
+        :py:class:`pyspark.ml.linalg.Matrix` type under the `spark.ml`
+        package.
+
+        :param dataset:
+          input dataset
+        :param cols:
+          a list of matrix columns to be converted.
+          Old matrix columns will be ignored. If unspecified, all new
+          matrix columns will be converted except nested ones.
+        :return:
+          the input dataset with new matrix columns converted to the
+          old matrix type
+
+        >>> import pyspark
+        >>> from pyspark.ml.linalg import Matrices
+        >>> from pyspark.mllib.util import MLUtils
+        >>> df = spark.createDataFrame(
+        ...     [(0, Matrices.sparse(2, 2, [0, 2, 3], [0, 1, 1], [2, 3, 4]),
+        ...     Matrices.dense(2, 2, range(4)))], ["id", "x", "y"])
+        >>> r1 = MLUtils.convertMatrixColumnsFromML(df).first()
+        >>> isinstance(r1.x, pyspark.mllib.linalg.SparseMatrix)
+        True
+        >>> isinstance(r1.y, pyspark.mllib.linalg.DenseMatrix)
+        True
+        >>> r2 = MLUtils.convertMatrixColumnsFromML(df, "x").first()
+        >>> isinstance(r2.x, pyspark.mllib.linalg.SparseMatrix)
+        True
+        >>> isinstance(r2.y, pyspark.ml.linalg.DenseMatrix)
+        True
+        """
+        if not isinstance(dataset, DataFrame):
+            raise TypeError("Input dataset must be a DataFrame but got {}.".format(type(dataset)))
+        return callMLlibFunc("convertMatrixColumnsFromML", dataset, list(cols))
+
 
 class Saveable(object):
     """
-- 
cgit v1.2.3