From 635888cbed0e3f4127252fb84db449f0cc9ed659 Mon Sep 17 00:00:00 2001 From: Sean Owen Date: Sun, 13 Jul 2014 19:27:43 -0700 Subject: SPARK-2363. Clean MLlib's sample data files (Just made a PR for this, mengxr was the reporter of:) MLlib has sample data under serveral folders: 1) data/mllib 2) data/ 3) mllib/data/* Per previous discussion with Matei Zaharia, we want to put them under `data/mllib` and clean outdated files. Author: Sean Owen Closes #1394 from srowen/SPARK-2363 and squashes the following commits: 54313dd [Sean Owen] Move ML example data from /mllib/data/ and /data/ into /data/mllib/ --- docs/mllib-collaborative-filtering.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'docs/mllib-collaborative-filtering.md') diff --git a/docs/mllib-collaborative-filtering.md b/docs/mllib-collaborative-filtering.md index d51002f015..5cd7173872 100644 --- a/docs/mllib-collaborative-filtering.md +++ b/docs/mllib-collaborative-filtering.md @@ -58,7 +58,7 @@ import org.apache.spark.mllib.recommendation.ALS import org.apache.spark.mllib.recommendation.Rating // Load and parse the data -val data = sc.textFile("mllib/data/als/test.data") +val data = sc.textFile("data/mllib/als/test.data") val ratings = data.map(_.split(',') match { case Array(user, item, rate) => Rating(user.toInt, item.toInt, rate.toDouble) }) @@ -112,7 +112,7 @@ from pyspark.mllib.recommendation import ALS from numpy import array # Load and parse the data -data = sc.textFile("mllib/data/als/test.data") +data = sc.textFile("data/mllib/als/test.data") ratings = data.map(lambda line: array([float(x) for x in line.split(',')])) # Build the recommendation model using Alternating Least Squares -- cgit v1.2.3