aboutsummaryrefslogtreecommitdiff
path: root/docs/mllib-data-types.md
diff options
context:
space:
mode:
authorDmitriy Sokolov <silentsokolov@gmail.com>2016-08-30 11:23:37 +0100
committerSean Owen <sowen@cloudera.com>2016-08-30 11:23:37 +0100
commitd4eee9932edf1a489d7fe9120a0f003150834df6 (patch)
tree2b05ac9cfaf1e76ca0b44e579d54ec8b3b7494f2 /docs/mllib-data-types.md
parentbefab9c1c6b59ad90f63a7d10e12b186be897f15 (diff)
downloadspark-d4eee9932edf1a489d7fe9120a0f003150834df6.tar.gz
spark-d4eee9932edf1a489d7fe9120a0f003150834df6.tar.bz2
spark-d4eee9932edf1a489d7fe9120a0f003150834df6.zip
[MINOR][DOCS] Fix minor typos in python example code
## What changes were proposed in this pull request? Fix minor typos python example code in streaming programming guide ## How was this patch tested? N/A Author: Dmitriy Sokolov <silentsokolov@gmail.com> Closes #14805 from silentsokolov/fix-typos.
Diffstat (limited to 'docs/mllib-data-types.md')
-rw-r--r--docs/mllib-data-types.md16
1 files changed, 8 insertions, 8 deletions
diff --git a/docs/mllib-data-types.md b/docs/mllib-data-types.md
index 7dd3c97a83..35cee3275e 100644
--- a/docs/mllib-data-types.md
+++ b/docs/mllib-data-types.md
@@ -104,7 +104,7 @@ dv2 = [1.0, 0.0, 3.0]
# Create a SparseVector.
sv1 = Vectors.sparse(3, [0, 2], [1.0, 3.0])
# Use a single-column SciPy csc_matrix as a sparse vector.
-sv2 = sps.csc_matrix((np.array([1.0, 3.0]), np.array([0, 2]), np.array([0, 2])), shape = (3, 1))
+sv2 = sps.csc_matrix((np.array([1.0, 3.0]), np.array([0, 2]), np.array([0, 2])), shape=(3, 1))
{% endhighlight %}
</div>
@@ -517,12 +517,12 @@ 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]),
+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]),
+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.
@@ -731,15 +731,15 @@ from pyspark.mllib.linalg import Matrices
from pyspark.mllib.linalg.distributed import BlockMatrix
# Create an RDD of sub-matrix blocks.
-blocks = sc.parallelize([((0, 0), Matrices.dense(3, 2, [1, 2, 3, 4, 5, 6])),
+blocks = sc.parallelize([((0, 0), Matrices.dense(3, 2, [1, 2, 3, 4, 5, 6])),
((1, 0), Matrices.dense(3, 2, [7, 8, 9, 10, 11, 12]))])
# Create a BlockMatrix from an RDD of sub-matrix blocks.
mat = BlockMatrix(blocks, 3, 2)
# Get its size.
-m = mat.numRows() # 6
-n = mat.numCols() # 2
+m = mat.numRows() # 6
+n = mat.numCols() # 2
# Get the blocks as an RDD of sub-matrix blocks.
blocksRDD = mat.blocks