[mlpack-svn] r15459 - mlpack/conf/jenkins-conf/benchmark/methods/weka

fastlab-svn at coffeetalk-1.cc.gatech.edu fastlab-svn at coffeetalk-1.cc.gatech.edu
Fri Jul 12 09:38:58 EDT 2013


Author: marcus
Date: Fri Jul 12 09:38:58 2013
New Revision: 15459

Log:
Add weka benchmark script for allknn, kmeans, nbc and pca.

Added:
   mlpack/conf/jenkins-conf/benchmark/methods/weka/allknn.py
   mlpack/conf/jenkins-conf/benchmark/methods/weka/kmeans.py
   mlpack/conf/jenkins-conf/benchmark/methods/weka/nbc.py
   mlpack/conf/jenkins-conf/benchmark/methods/weka/pca.py

Added: mlpack/conf/jenkins-conf/benchmark/methods/weka/allknn.py
==============================================================================
--- (empty file)
+++ mlpack/conf/jenkins-conf/benchmark/methods/weka/allknn.py	Fri Jul 12 09:38:58 2013
@@ -0,0 +1,124 @@
+'''
+  @file allknn.py
+  @author Marcus Edel
+
+  Class to benchmark the weka All K-Nearest-Neighbors 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 All K-Nearest-Neighbors benchmark.
+'''
+class ALLKNN(object):
+
+	''' 
+	Create the All K-Nearest-Neighbors benchmark instance.
+  
+  @param dataset - Input dataset to perform ALLKNN on.
+  @param path - Path to the mlpack executable.
+  @param verbose - Display informational messages.
+	'''
+	def __init__(self, dataset, path=os.environ["WEKA_CLASSPATH"], verbose = True): 
+		self.verbose = verbose
+		self.dataset = dataset
+		self.path = path
+
+	'''
+	Destructor to clean up at the end.
+	'''
+	def __del__(self):		
+		pass	
+		
+	'''
+  All K-Nearest-Neighbors. 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 ALLKNN.", self.verbose)
+
+		# If the dataset contains two files then the second file is the query file.
+		# In this case we add this to the command line.
+		if len(self.dataset) == 2:
+			inputCmd = "-r " + self.dataset[0] + " -q " + self.dataset[1] + " " + options
+		else:
+			inputCmd = "-r " + self.dataset + " " + options
+		
+		# Split the command using shell-like syntax.
+		cmd = shlex.split("java -classpath " + self.path + ":methods/weka" + 
+			" AllKnn " + inputCmd + " " + options)
+		
+		# 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"])
+			
+			if match.group("total_time").count(".") == 1:
+				return timer(float(match.group("total_time")))
+			else:
+				return timer(float(match.group("total_time").replace(",", ".")))
+
+	'''
+	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

Added: mlpack/conf/jenkins-conf/benchmark/methods/weka/kmeans.py
==============================================================================
--- (empty file)
+++ mlpack/conf/jenkins-conf/benchmark/methods/weka/kmeans.py	Fri Jul 12 09:38:58 2013
@@ -0,0 +1,117 @@
+'''
+  @file kmeans.py
+  @author Marcus Edel
+
+  Class to benchmark the weka K-Means Clustering 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 K-Means Clustering benchmark.
+'''
+class KMEANS(object):
+
+	''' 
+	Create the K-Means Clustering benchmark instance.
+  
+  @param dataset - Input dataset to perform K-Means on.
+  @param path - Path to the mlpack executable.
+  @param verbose - Display informational messages.
+	'''
+	def __init__(self, dataset, path=os.environ["WEKA_CLASSPATH"], verbose = True): 
+		self.verbose = verbose
+		self.dataset = dataset
+		self.path = path
+
+	'''
+	Destructor to clean up at the end.
+	'''
+	def __del__(self):		
+		pass	
+		
+	'''
+  K-Means Clustering benchmark instance. 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 K-Means.", self.verbose)
+		
+		# Split the command using shell-like syntax.
+		cmd = shlex.split("java -classpath " + self.path + ":methods/weka" + 
+			" KMeans -i " + self.dataset + " " + options)
+		
+		# 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"])
+			
+			if match.group("total_time").count(".") == 1:
+				return timer(float(match.group("total_time")))
+			else:
+				return timer(float(match.group("total_time").replace(",", ".")))
+
+	'''
+	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

Added: mlpack/conf/jenkins-conf/benchmark/methods/weka/nbc.py
==============================================================================
--- (empty file)
+++ mlpack/conf/jenkins-conf/benchmark/methods/weka/nbc.py	Fri Jul 12 09:38:58 2013
@@ -0,0 +1,121 @@
+'''
+  @file nbc.py
+  @author Marcus Edel
+
+  Class to benchmark the weka 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=os.environ["WEKA_CLASSPATH"], 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)
+
+		if len(self.dataset) < 2:
+			Log.Fatal("The method need two datasets.")
+			return -1
+
+		# Split the command using shell-like syntax.
+		cmd = shlex.split("java -classpath " + self.path + ":methods/weka" + 
+			" NBC -t " + self.dataset[0] + " -T " + self.dataset[1] + " " + options)
+
+		# 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"])
+			
+			if match.group("total_time").count(".") == 1:
+				return timer(float(match.group("total_time")))
+			else:
+				return timer(float(match.group("total_time").replace(",", ".")))
+
+	'''
+	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

Added: mlpack/conf/jenkins-conf/benchmark/methods/weka/pca.py
==============================================================================
--- (empty file)
+++ mlpack/conf/jenkins-conf/benchmark/methods/weka/pca.py	Fri Jul 12 09:38:58 2013
@@ -0,0 +1,120 @@
+'''
+  @file pca.py
+  @author Marcus Edel
+
+  Class to benchmark the weka Principal Components Analysis 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 Principal Components Analysis benchmark.
+'''
+class PCA(object):
+
+	''' 
+	Create the Principal Components Analysis benchmark instance.
+  
+  @param dataset - Input dataset to perform PCA on.
+  @param path - Path to the mlpack executable.
+  @param verbose - Display informational messages.
+	'''
+	def __init__(self, dataset, path=os.environ["WEKA_CLASSPATH"], verbose=True): 
+		self.verbose = verbose
+		self.dataset = dataset
+		self.path = path
+
+	'''
+	Destructor to clean up at the end.
+	'''
+	def __del__(self):		
+		pass	
+		
+	'''
+  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)
+
+		# Split the command using shell-like syntax.
+		cmd = shlex.split("java -classpath " + self.path + ":methods/weka" + 
+			" PCA -i " + self.dataset + " " + options)
+
+		# 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"""
+				.*?loading_data: (?P<loading_time>.*?)s.*?
+				.*?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", ["loading_time", "total_time"])
+
+			if match.group("loading_time").count(".") == 1:
+				return timer(float(match.group("loading_time")),
+					float(match.group("total_time")))
+			else:
+				return timer(float(match.group("loading_time").replace(",", ".")),
+						 	float(match.group("total_time").replace(",", ".")))
+
+	'''
+	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 - timer.loading_time
+		return time



More information about the mlpack-svn mailing list