modified files for 2.0.x

Author: rajdeepd

Chapter_09/2.0.x/python/org/sparksamples/plot_singular_values.py

@@ -6,7 +6,7 @@
 
 
 def main():
-    file_name = '/home/ubuntu/work/ml-resources/spark-ml/Chapter_09/scala/s.csv'
+    file_name = '/home/ubuntu/work/ml-resources/spark-ml/Chapter_09/data/s.csv'
     data = np.genfromtxt(file_name, delimiter=',')
 
     plt.plot(data)

Chapter_09/2.0.x/python/org/sparksamples/ploy_gallery.py

@@ -5,7 +5,7 @@
 from PIL import Image, ImageFilter
 import os
 
-PATH = "../../../data"
+PATH = "../../../../data"
 
 
 def main():
@@ -15,11 +15,11 @@ def main():
     im = Image.open(path)
     im.show()
 
-    tmp_path = "/tmp/aeGray.jpg"
+    tmp_path = PATH + "/aeGray.jpg"
     ae_gary = Image.open(tmp_path)
     ae_gary.show()
 
-    pc = np.loadtxt("/tmp/pc.csv", delimiter=",")
+    pc = np.loadtxt(PATH + "/pc.csv", delimiter=",")
     print(pc.shape)
     # (2500, 10)
 

Chapter_09/2.0.x/scala/src/main/scala/org/sparksamples/ImageProcessing.scala

@@ -10,18 +10,17 @@ import org.apache.spark.{SparkConf, SparkContext}
   * @author Rajdeep Dua
   */
 object ImageProcessing {
-  val PATH= "../data"
+  val PATH= "../../data"
+
   def main(args: Array[String]): Unit = {
     val spConfig = (new SparkConf).setMaster("local[1]").setAppName("SparkApp").
       set("spark.driver.allowMultipleContexts", "true")
     val sc = new SparkContext(spConfig)
     val path = PATH +  "/lfw/*"
     val rdd = sc.wholeTextFiles(path)
     val first = rdd.first
-    //println(first)
     val files = rdd.map { case (fileName, content) => fileName.replace("file:", "") }
-    //println(files.first)
-    // file:/PATH/lfw/Aaron_Eckhart/Aaron_Eckhart_0001.jpg
+
     println(files.count)
 
     val aePath = PATH + "/lfw/Aaron_Eckhart/Aaron_Eckhart_0001.jpg"
@@ -50,7 +49,7 @@ object ImageProcessing {
     val cols = pc.numCols
     val pcBreeze = new DenseMatrix(rows, cols, pc.toArray)
     println(rows, cols)
-    //csvwrite(new File("/tmp/pc.csv"), pcBreeze)
+    csvwrite(new File(PATH + "/pc.csv"), pcBreeze)
     val projected = matrix.multiply(pc)
     println(projected.numRows, projected.numCols)
     // (1055,10)
@@ -88,7 +87,7 @@ object ImageProcessing {
     val svd300 = matrix.computeSVD(300, computeU = false)
     val sMatrix = new DenseMatrix(1, 300, svd300.s.toArray)
     println(sMatrix)
-    csvwrite(new File("/home/ubuntu/work/ml-resources/spark-ml/Chapter_09/scala/s.csv"), sMatrix)
+    csvwrite(new File(PATH + "/s.csv"), sMatrix)
 
   }
   def approxEqual(array1: Array[Double], array2: Array[Double], tolerance: Double = 1e-6): Boolean = {