[mlpack-svn] r15389 - in mlpack/conf/jenkins-conf/benchmark: methods/shogun util
fastlab-svn at coffeetalk-1.cc.gatech.edu
fastlab-svn at coffeetalk-1.cc.gatech.edu
Wed Jul 3 10:24:21 EDT 2013
Author: marcus
Date: Wed Jul 3 10:24:21 2013
New Revision: 15389
Log:
Add Principal Components Analysis shogun method.
Added:
mlpack/conf/jenkins-conf/benchmark/methods/shogun/
mlpack/conf/jenkins-conf/benchmark/methods/shogun/pca.py
Modified:
mlpack/conf/jenkins-conf/benchmark/util/timer.py
Added: mlpack/conf/jenkins-conf/benchmark/methods/shogun/pca.py
==============================================================================
--- (empty file)
+++ mlpack/conf/jenkins-conf/benchmark/methods/shogun/pca.py Wed Jul 3 10:24:21 2013
@@ -0,0 +1,96 @@
+ '''
+ @file pca.py
+ @author Marcus Edel
+
+ Principal Components Analysis with shogun.
+'''
+
+import os
+import sys
+import inspect
+
+# Import the util path, this method even works if the path contains symlinks to
+# modules.
+cmd_subfolder = os.path.realpath(os.path.abspath(os.path.join(
+ os.path.split(inspect.getfile(inspect.currentframe()))[0], "../../util")))
+if cmd_subfolder not in sys.path:
+ sys.path.insert(0, cmd_subfolder)
+
+from log import *
+from timer import *
+
+import numpy as np
+from shogun.Features import RealFeatures
+from shogun.Classifier import PCA as ShogunPCA
+
+'''
+This class implements the Principal Components Analysis benchmark.
+'''
+class PCA(object):
+
+ '''
+ Create the Principal Components Analysis benchmark instance.
+
+ @param dataset - Input dataset to perform PCA on.
+ @param verbose - Display informational messages.
+ '''
+ def __init__(self, dataset, verbose=True):
+ self.verbose = verbose
+ self.dataset = dataset
+
+ '''
+ Destructor to clean up at the end.
+ '''
+ def __del__(self):
+ pass
+
+ '''
+ Use the shogun libary to implement Principal Components Analysis.
+
+ @param options - Extra options for the method.
+ @return - Elapsed time in seconds or -1 if the method was not successful.
+ '''
+ def PCAShogun(self, options):
+ totalTimer = Timer()
+ loadTimer = Timer()
+ with totalTimer:
+ # Load input dataset.
+ with loadTimer:
+ Log.Info("Loading dataset", self.verbose)
+ data = np.genfromtxt(self.dataset, delimiter=',')
+ feat = RealFeatures(data.T)
+
+ # Find out what dimension we want.
+ match = re.search('-d (\d+)', options)
+
+ if not match:
+ k = data.shape[1]
+ else:
+ k = int(match.group(1))
+ if (k > data.shape[1]):
+ Log.Fatal("New dimensionality (" + str(k) + ") cannot be greater "
+ + "than existing dimensionality (" + str(data.shape[1]) + ")!")
+ return -1
+
+ # Get the options for running PCA.
+ s = True if options.find("-s") > -1 else False
+
+ # Perform PCA.
+ prep = ShogunPCA(s)
+ prep.set_target_dim(k)
+ prep.init(feat)
+ prep.apply_to_feature_matrix(feat)
+
+ return (totalTimer.ElapsedTime() - loadTimer.ElapsedTime())
+
+ '''
+ Perform Principal Components Analysis. If the method has been successfully
+ completed return the elapsed time in seconds.
+
+ @param options - Extra options for the method.
+ @return - Elapsed time in seconds or -1 if the method was not successful.
+ '''
+ def RunMethod(self, options):
+ Log.Info("Perform PCA.", self.verbose)
+
+ return self.PCAShogun(options)
Modified: mlpack/conf/jenkins-conf/benchmark/util/timer.py
==============================================================================
--- mlpack/conf/jenkins-conf/benchmark/util/timer.py (original)
+++ mlpack/conf/jenkins-conf/benchmark/util/timer.py Wed Jul 3 10:24:21 2013
@@ -1,5 +1,5 @@
'''
- @file log.py
+ @file timer.py
@author Marcus Edel
Implementation of the timer class.
More information about the mlpack-svn
mailing list