diff options
Diffstat (limited to 'docs/mllib-clustering.md')
-rw-r--r-- | docs/mllib-clustering.md | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/docs/mllib-clustering.md b/docs/mllib-clustering.md index 429cdf8d40..c76ac010d3 100644 --- a/docs/mllib-clustering.md +++ b/docs/mllib-clustering.md @@ -51,7 +51,7 @@ import org.apache.spark.mllib.clustering.KMeans import org.apache.spark.mllib.linalg.Vectors // Load and parse the data -val data = sc.textFile("data/kmeans_data.txt") +val data = sc.textFile("data/mllib/kmeans_data.txt") val parsedData = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble))) // Cluster the data into two classes using KMeans @@ -86,7 +86,7 @@ from numpy import array from math import sqrt # Load and parse the data -data = sc.textFile("data/kmeans_data.txt") +data = sc.textFile("data/mllib/kmeans_data.txt") parsedData = data.map(lambda line: array([float(x) for x in line.split(' ')])) # Build the model (cluster the data) |