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2) data/ 3) mllib/data/* Per previous discussion with Matei Zaharia, we want to put them under `data/mllib` and clean outdated files.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 <sowen@cloudera.com> Closes apache#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/
panbingkun · Jul 14, 2014 · 635888c · 635888c
1 parent 4c8be64
commit 635888c
Show file tree

Hide file tree

Showing 18 changed files with 16 additions and 16 deletions.
diff --git a/mllib/data/als/test.data → data/mllib/als/test.data b/mllib/data/als/test.data → data/mllib/als/test.data
diff --git a/data/kmeans_data.txt → data/mllib/kmeans_data.txt b/data/kmeans_data.txt → data/mllib/kmeans_data.txt
diff --git a/mllib/data/lr-data/random.data → data/mllib/lr-data/random.data b/mllib/data/lr-data/random.data → data/mllib/lr-data/random.data
diff --git a/data/lr_data.txt → data/mllib/lr_data.txt b/data/lr_data.txt → data/mllib/lr_data.txt
diff --git a/data/pagerank_data.txt → data/mllib/pagerank_data.txt b/data/pagerank_data.txt → data/mllib/pagerank_data.txt
diff --git a/mllib/data/ridge-data/lpsa.data → data/mllib/ridge-data/lpsa.data b/mllib/data/ridge-data/lpsa.data → data/mllib/ridge-data/lpsa.data
diff --git a/mllib/data/sample_libsvm_data.txt → data/mllib/sample_libsvm_data.txt b/mllib/data/sample_libsvm_data.txt → data/mllib/sample_libsvm_data.txt
diff --git a/mllib/data/sample_naive_bayes_data.txt → data/mllib/sample_naive_bayes_data.txt b/mllib/data/sample_naive_bayes_data.txt → data/mllib/sample_naive_bayes_data.txt
diff --git a/mllib/data/sample_svm_data.txt → data/mllib/sample_svm_data.txt b/mllib/data/sample_svm_data.txt → data/mllib/sample_svm_data.txt
diff --git a/mllib/data/sample_tree_data.csv → data/mllib/sample_tree_data.csv b/mllib/data/sample_tree_data.csv → data/mllib/sample_tree_data.csv
diff --git a/docs/bagel-programming-guide.md b/docs/bagel-programming-guide.md
@@ -46,7 +46,7 @@ import org.apache.spark.bagel.Bagel._
 Next, we load a sample graph from a text file as a distributed dataset and package it into `PRVertex` objects. We also cache the distributed dataset because Bagel will use it multiple times and we'd like to avoid recomputing it.
 
 {% highlight scala %}
-val input = sc.textFile("data/pagerank_data.txt")
+val input = sc.textFile("data/mllib/pagerank_data.txt")
 
 val numVerts = input.count()
 

diff --git a/docs/mllib-basics.md b/docs/mllib-basics.md
@@ -193,7 +193,7 @@ import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.mllib.util.MLUtils
 import org.apache.spark.rdd.RDD
 
-val examples: RDD[LabeledPoint] = MLUtils.loadLibSVMFile(sc, "mllib/data/sample_libsvm_data.txt")
+val examples: RDD[LabeledPoint] = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")
 {% endhighlight %}
 </div>
 
@@ -207,7 +207,7 @@ import org.apache.spark.mllib.util.MLUtils;
 import org.apache.spark.api.java.JavaRDD;
 
 JavaRDD<LabeledPoint> examples = 
-  MLUtils.loadLibSVMFile(jsc.sc(), "mllib/data/sample_libsvm_data.txt").toJavaRDD();
+  MLUtils.loadLibSVMFile(jsc.sc(), "data/mllib/sample_libsvm_data.txt").toJavaRDD();
 {% endhighlight %}
 </div>
 
@@ -218,7 +218,7 @@ examples stored in LIBSVM format.
 {% highlight python %}
 from pyspark.mllib.util import MLUtils
 
-examples = MLUtils.loadLibSVMFile(sc, "mllib/data/sample_libsvm_data.txt")
+examples = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")
 {% endhighlight %}
 </div>
 </div>

diff --git 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)

diff --git 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

diff --git a/docs/mllib-decision-tree.md b/docs/mllib-decision-tree.md
@@ -122,7 +122,7 @@ import org.apache.spark.mllib.tree.configuration.Algo._
 import org.apache.spark.mllib.tree.impurity.Gini
 
 // Load and parse the data file
-val data = sc.textFile("mllib/data/sample_tree_data.csv")
+val data = sc.textFile("data/mllib/sample_tree_data.csv")
 val parsedData = data.map { line =>
   val parts = line.split(',').map(_.toDouble)
   LabeledPoint(parts(0), Vectors.dense(parts.tail))
@@ -161,7 +161,7 @@ import org.apache.spark.mllib.tree.configuration.Algo._
 import org.apache.spark.mllib.tree.impurity.Variance
 
 // Load and parse the data file
-val data = sc.textFile("mllib/data/sample_tree_data.csv")
+val data = sc.textFile("data/mllib/sample_tree_data.csv")
 val parsedData = data.map { line =>
   val parts = line.split(',').map(_.toDouble)
   LabeledPoint(parts(0), Vectors.dense(parts.tail))

diff --git a/docs/mllib-linear-methods.md b/docs/mllib-linear-methods.md
@@ -187,7 +187,7 @@ import org.apache.spark.mllib.linalg.Vectors
 import org.apache.spark.mllib.util.MLUtils
 
 // Load training data in LIBSVM format.
-val data = MLUtils.loadLibSVMFile(sc, "mllib/data/sample_libsvm_data.txt")
+val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")
 
 // Split data into training (60%) and test (40%).
 val splits = data.randomSplit(Array(0.6, 0.4), seed = 11L)
@@ -259,7 +259,7 @@ def parsePoint(line):
     values = [float(x) for x in line.split(' ')]
     return LabeledPoint(values[0], values[1:])
 
-data = sc.textFile("mllib/data/sample_svm_data.txt")
+data = sc.textFile("data/mllib/sample_svm_data.txt")
 parsedData = data.map(parsePoint)
 
 # Build the model
@@ -309,7 +309,7 @@ import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.mllib.linalg.Vectors
 
 // Load and parse the data
-val data = sc.textFile("mllib/data/ridge-data/lpsa.data")
+val data = sc.textFile("data/mllib/ridge-data/lpsa.data")
 val parsedData = data.map { line =>
   val parts = line.split(',')
   LabeledPoint(parts(0).toDouble, Vectors.dense(parts(1).split(' ').map(_.toDouble)))
@@ -356,7 +356,7 @@ def parsePoint(line):
     values = [float(x) for x in line.replace(',', ' ').split(' ')]
     return LabeledPoint(values[0], values[1:])
 
-data = sc.textFile("mllib/data/ridge-data/lpsa.data")
+data = sc.textFile("data/mllib/ridge-data/lpsa.data")
 parsedData = data.map(parsePoint)
 
 # Build the model

diff --git a/docs/mllib-naive-bayes.md b/docs/mllib-naive-bayes.md
@@ -40,7 +40,7 @@ import org.apache.spark.mllib.classification.NaiveBayes
 import org.apache.spark.mllib.linalg.Vectors
 import org.apache.spark.mllib.regression.LabeledPoint
 
-val data = sc.textFile("mllib/data/sample_naive_bayes_data.txt")
+val data = sc.textFile("data/mllib/sample_naive_bayes_data.txt")
 val parsedData = data.map { line =>
   val parts = line.split(',')
   LabeledPoint(parts(0).toDouble, Vectors.dense(parts(1).split(' ').map(_.toDouble)))

diff --git a/docs/mllib-optimization.md b/docs/mllib-optimization.md
@@ -214,7 +214,7 @@ import org.apache.spark.mllib.linalg.Vectors
 import org.apache.spark.mllib.util.MLUtils
 import org.apache.spark.mllib.classification.LogisticRegressionModel
 
-val data = MLUtils.loadLibSVMFile(sc, "mllib/data/sample_libsvm_data.txt")
+val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")
 val numFeatures = data.take(1)(0).features.size
 
 // Split data into training (60%) and test (40%).