diff options
Diffstat (limited to 'docs')
-rw-r--r-- | docs/mllib-data-types.md | 106 |
1 files changed, 104 insertions, 2 deletions
diff --git a/docs/mllib-data-types.md b/docs/mllib-data-types.md index 3aa040046f..11033bf4f9 100644 --- a/docs/mllib-data-types.md +++ b/docs/mllib-data-types.md @@ -372,12 +372,37 @@ long m = mat.numRows(); long n = mat.numCols(); {% endhighlight %} </div> + +<div data-lang="python" markdown="1"> + +A [`RowMatrix`](api/python/pyspark.mllib.html#pyspark.mllib.linalg.distributed.RowMatrix) can be +created from an `RDD` of vectors. + +{% highlight python %} +from pyspark.mllib.linalg.distributed import RowMatrix + +# Create an RDD of vectors. +rows = sc.parallelize([[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]]) + +# Create a RowMatrix from an RDD of vectors. +mat = RowMatrix(rows) + +# Get its size. +m = mat.numRows() # 4 +n = mat.numCols() # 3 + +# Get the rows as an RDD of vectors again. +rowsRDD = mat.rows +{% endhighlight %} +</div> + </div> ### IndexedRowMatrix An `IndexedRowMatrix` is similar to a `RowMatrix` but with meaningful row indices. It is backed by -an RDD of indexed rows, so that each row is represented by its index (long-typed) and a local vector. +an RDD of indexed rows, so that each row is represented by its index (long-typed) and a local +vector. <div class="codetabs"> <div data-lang="scala" markdown="1"> @@ -431,7 +456,48 @@ long n = mat.numCols(); // Drop its row indices. RowMatrix rowMat = mat.toRowMatrix(); {% endhighlight %} -</div></div> +</div> + +<div data-lang="python" markdown="1"> + +An [`IndexedRowMatrix`](api/python/pyspark.mllib.html#pyspark.mllib.linalg.distributed.IndexedRowMatrix) +can be created from an `RDD` of `IndexedRow`s, where +[`IndexedRow`](api/python/pyspark.mllib.html#pyspark.mllib.linalg.distributed.IndexedRow) is a +wrapper over `(long, vector)`. An `IndexedRowMatrix` can be converted to a `RowMatrix` by dropping +its row indices. + +{% highlight python %} +from pyspark.mllib.linalg.distributed import IndexedRow, IndexedRowMatrix + +# Create an RDD of indexed rows. +# - This can be done explicitly with the IndexedRow class: +indexedRows = sc.parallelize([IndexedRow(0, [1, 2, 3]), + IndexedRow(1, [4, 5, 6]), + IndexedRow(2, [7, 8, 9]), + IndexedRow(3, [10, 11, 12])]) +# - or by using (long, vector) tuples: +indexedRows = sc.parallelize([(0, [1, 2, 3]), (1, [4, 5, 6]), + (2, [7, 8, 9]), (3, [10, 11, 12])]) + +# Create an IndexedRowMatrix from an RDD of IndexedRows. +mat = IndexedRowMatrix(indexedRows) + +# Get its size. +m = mat.numRows() # 4 +n = mat.numCols() # 3 + +# Get the rows as an RDD of IndexedRows. +rowsRDD = mat.rows + +# Convert to a RowMatrix by dropping the row indices. +rowMat = mat.toRowMatrix() + +# Convert to a CoordinateMatrix. +coordinateMat = mat.toCoordinateMatrix() +{% endhighlight %} +</div> + +</div> ### CoordinateMatrix @@ -495,6 +561,42 @@ long n = mat.numCols(); IndexedRowMatrix indexedRowMatrix = mat.toIndexedRowMatrix(); {% endhighlight %} </div> + +<div data-lang="python" markdown="1"> + +A [`CoordinateMatrix`](api/python/pyspark.mllib.html#pyspark.mllib.linalg.distributed.CoordinateMatrix) +can be created from an `RDD` of `MatrixEntry` entries, where +[`MatrixEntry`](api/python/pyspark.mllib.html#pyspark.mllib.linalg.distributed.MatrixEntry) is a +wrapper over `(long, long, float)`. A `CoordinateMatrix` can be converted to a `RowMatrix` by +calling `toRowMatrix`, or to an `IndexedRowMatrix` with sparse rows by calling `toIndexedRowMatrix`. + +{% highlight python %} +from pyspark.mllib.linalg.distributed import CoordinateMatrix, MatrixEntry + +# Create an RDD of coordinate entries. +# - This can be done explicitly with the MatrixEntry class: +entries = sc.parallelize([MatrixEntry(0, 0, 1.2), MatrixEntry(1, 0, 2.1), MatrixEntry(6, 1, 3.7)]) +# - or using (long, long, float) tuples: +entries = sc.parallelize([(0, 0, 1.2), (1, 0, 2.1), (2, 1, 3.7)]) + +# Create an CoordinateMatrix from an RDD of MatrixEntries. +mat = CoordinateMatrix(entries) + +# Get its size. +m = mat.numRows() # 3 +n = mat.numCols() # 2 + +# Get the entries as an RDD of MatrixEntries. +entriesRDD = mat.entries + +# Convert to a RowMatrix. +rowMat = mat.toRowMatrix() + +# Convert to an IndexedRowMatrix. +indexedRowMat = mat.toIndexedRowMatrix() +{% endhighlight %} +</div> + </div> ### BlockMatrix |