[mlpack-svn] r15413 - mlpack/conf/jenkins-conf/benchmark/methods/matlab

[fastlab-svn at coffeetalk-1.cc.gatech.edu]

Author: marcus
Date: Thu Jul  4 09:36:25 2013
New Revision: 15413

Log:
Add matlab nbc method and nbc benchmark script.

Added:
   mlpack/conf/jenkins-conf/benchmark/methods/matlab/NBC.m
   mlpack/conf/jenkins-conf/benchmark/methods/matlab/nbc.py

Added: mlpack/conf/jenkins-conf/benchmark/methods/matlab/NBC.m
==============================================================================
--- (empty file)
+++ mlpack/conf/jenkins-conf/benchmark/methods/matlab/NBC.m	Thu Jul  4 09:36:25 2013
@@ -0,0 +1,35 @@
+% @file NBC.m
+% @author Marcus Edel
+%
+% Naive Bayes Classifier with matlab.
+
+function nbc(cmd)
+%This program trains the Naive Bayes classifier on the given labeled 
+% training set and then uses the trained classifier to classify the points
+% in the given test set. Labels are expected to be the last row of the 
+% training set.
+%
+% Required options:
+%     (-T) [string]    A file containing the test set.
+%     (-t) [string]    A file containing the training set.
+
+trainFile = regexp(cmd, '.*?-t ([^\s]+)', 'tokens', 'once');
+testFile = regexp(cmd, '.*?-T ([^\s]+)', 'tokens', 'once');
+
+% Load input dataset.
+TrainData = csvread(trainFile{:});
+TestData = csvread(testFile{:});
+
+% Use the last row of the training data as the labels.
+labels = TrainData(:,end);
+% Remove the label row.
+TrainData = TrainData(:,1:end-1);
+
+% Create and train the classifier.
+total_time = tic;
+classifier = NaiveBayes.fit(TrainData, labels);
+% Run Naive Bayes Classifier on the test dataset.
+labels = classifier.predict(TestData);
+
+disp(sprintf('[INFO ]   total_time: %fs', toc(total_time)))
+end

Added: mlpack/conf/jenkins-conf/benchmark/methods/matlab/nbc.py
==============================================================================
--- (empty file)
+++ mlpack/conf/jenkins-conf/benchmark/methods/matlab/nbc.py	Thu Jul  4 09:36:25 2013
@@ -0,0 +1,115 @@
+'''
+  @file nbc.py
+  @author Marcus Edel
+
+  Class to benchmark the matlab Naive Bayes Classifier method.
+'''
+
+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 profiler import *
+
+import shlex
+import subprocess
+import re
+import collections
+
+'''
+This class implements the Naive Bayes Classifier benchmark.
+'''
+class NBC(object):
+
+	''' 
+	Create the Naive Bayes Classifier benchmark instance.
+  
+  @param dataset - Input dataset to perform NBC on.
+  @param path - Path to the mlpack executable.
+  @param verbose - Display informational messages.
+	'''
+	def __init__(self, dataset, path="/Applications/MATLAB_R2012a.app/bin/", verbose=True): 
+		self.verbose = verbose
+		self.dataset = dataset
+		self.path = path
+
+	'''
+	Destructor to clean up at the end.
+	'''
+	def __del__(self):		
+		pass	
+		
+	'''
+  Naive Bayes Classifier. 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 NBC.", self.verbose)
+
+		inputCmd = "-t " + self.dataset[0] + " -T " + self.dataset[1] + " " + options
+		# Split the command using shell-like syntax.
+		cmd = shlex.split(self.path + "matlab -nodisplay -nosplash -r \"try, NBC('" 
+				+ inputCmd + "'), catch, exit(1), end, exit(0)\"")
+		
+		# Run command with the nessecary arguments and return its output as a byte
+		# string. We have untrusted input so we disables all shell based features.
+		try:
+			s = subprocess.check_output(cmd, stderr=subprocess.STDOUT, shell=False)		
+		except Exception:
+			Log.Fatal("Could not execute command: " + str(cmd))
+			return -1
+
+		# Return the elapsed time.
+		timer = self.parseTimer(s)
+		if not timer:
+			Log.Fatal("Can't parse the timer")
+			return -1
+		else:
+			time = self.GetTime(timer)
+			Log.Info(("total time: %fs" % time), self.verbose)
+
+			return time
+
+	'''
+	Parse the timer data form a given string.
+
+	@param data - String to parse timer data from.
+	@return - Namedtuple that contains the timer data.
+	'''
+	def parseTimer(self, data):
+		# Compile the regular expression pattern into a regular expression object to
+		# parse the timer data.
+		pattern = re.compile(r"""
+				.*?total_time: (?P<total_time>.*?)s.*?
+				""", re.VERBOSE|re.MULTILINE|re.DOTALL)
+		
+		match = pattern.match(data)
+		if not match:
+			Log.Fatal("Can't parse the data: wrong format")
+			return -1
+		else:
+			# Create a namedtuple and return the timer data.
+			timer = collections.namedtuple("timer", ["total_time"])
+			
+			return timer(float(match.group("total_time")))
+
+	'''
+	Return the elapsed time in seconds.
+
+	@param timer - Namedtuple that contains the timer data.
+	@return Elapsed time in seconds.
+	'''
+	def GetTime(self, timer):
+		time = timer.total_time
+		return time