ch3 perceptron

.gitignore

@@ -60,3 +60,5 @@ target/
 
 #Ipython Notebook
 .ipynb_checkpoints
+
+.*.swp

ch3/or.py

@@ -0,0 +1,26 @@
+#!/usr/bin/python
+
+import numpy as np
+import pcn_logic_eg as pcn
+
+def main():
+	#or_training = np.array( [ [0,0,0], [1,0,1], [0,1,1], [1,1,1] ])
+	or_inputs = np.array( [[0,0], [0,1], [1,0], [1,1]])
+	or_targets = np.array([[0],[1],[1],[1]])
+
+	#p = pcn.pcn(a[:,0:2], a[:,2:])
+	p = pcn.pcn(or_inputs, or_targets)
+	#p.pcntrain(a[:,0:2], a[:, 2:], 0.25, 10)
+	p.pcntrain(or_inputs, or_targets, 0.25, 10)
+	print "confusion matrix"
+	p.confmat(or_inputs, or_targets)
+
+	print "doing"
+	print "  for "
+	print or_inputs
+	inputs_bias = np.concatenate((or_inputs,-np.ones((np.shape(or_inputs)[0],1))), axis=1)
+	print "  results"
+	print p.pcnfwd(inputs_bias)
+
+
+main()

ch3/pcn.py

@@ -0,0 +1,85 @@
+# Code from Chapter 3 of Machine Learning: An Algorithmic Perspective (2nd Edition)
+# by Stephen Marsland (http://stephenmonika.net)
+
+# You are free to use, change, or redistribute the code in any way you wish for
+# non-commercial purposes, but please maintain the name of the original author.
+# This code comes with no warranty of any kind.
+
+# Stephen Marsland, 2008, 2014
+
+import numpy as np
+
+class pcn:
+	""" A basic Perceptron"""
+	
+	def __init__(self,inputs,targets):
+		""" Constructor """
+		# Set up network size
+		if np.ndim(inputs)>1:
+			self.nIn = np.shape(inputs)[1]
+		else: 
+			self.nIn = 1
+	
+		if np.ndim(targets)>1:
+			self.nOut = np.shape(targets)[1]
+		else:
+			self.nOut = 1
+
+		self.nData = np.shape(inputs)[0]
+	
+		# Initialise network
+		self.weights = np.random.rand(self.nIn+1,self.nOut)*0.1-0.05
+
+	def pcntrain(self,inputs,targets,eta,nIterations):
+		""" Train the thing """	
+		# Add the inputs that match the bias node
+		inputs = np.concatenate((inputs,-np.ones((self.nData,1))),axis=1)
+		# Training
+		change = range(self.nData)
+
+		for n in range(nIterations):
+			
+			self.activations = self.pcnfwd(inputs);
+			self.weights -= eta*np.dot(np.transpose(inputs),self.activations-targets)
+		
+			# Randomise order of inputs
+			#np.random.shuffle(change)
+			#inputs = inputs[change,:]
+			#targets = targets[change,:]
+			
+		#return self.weights
+
+	def pcnfwd(self,inputs):
+		""" Run the network forward """
+		# Compute activations
+		activations =  np.dot(inputs,self.weights)
+
+		# Threshold the activations
+		return np.where(activations>0,1,0)
+
+
+	def confmat(self,inputs,targets):
+		"""Confusion matrix"""
+
+		# Add the inputs that match the bias node
+		inputs = np.concatenate((inputs,-np.ones((self.nData,1))),axis=1)
+		
+		outputs = np.dot(inputs,self.weights)
+	
+		nClasses = np.shape(targets)[1]
+
+		if nClasses==1:
+			nClasses = 2
+			outputs = np.where(outputs>0,1,0)
+		else:
+			# 1-of-N encoding
+			outputs = np.argmax(outputs,1)
+			targets = np.argmax(targets,1)
+
+		cm = np.zeros((nClasses,nClasses))
+		for i in range(nClasses):
+			for j in range(nClasses):
+				cm[i,j] = np.sum(np.where(outputs==i,1,0)*np.where(targets==j,1,0))
+
+		print cm
+		print np.trace(cm)/np.sum(cm)

ch3/pcn_logic_eg.py

@@ -0,0 +1,86 @@
+# Code from Chapter 3 of Machine Learning: An Algorithmic Perspective (2nd Edition)
+# by Stephen Marsland (http://stephenmonika.net)
+
+# You are free to use, change, or redistribute the code in any way you wish for
+# non-commercial purposes, but please maintain the name of the original author.
+# This code comes with no warranty of any kind.
+
+# Stephen Marsland, 2008, 2014
+
+import numpy as np
+
+class pcn:
+	""" A basic Perceptron (the same pcn.py except with the weights printed
+	and it does not reorder the inputs)"""
+	
+	def __init__(self,inputs,targets):
+		""" Constructor """
+		# Set up network size
+		if np.ndim(inputs)>1:
+			self.nIn = np.shape(inputs)[1]
+		else: 
+			self.nIn = 1
+	
+		if np.ndim(targets)>1:
+			self.nOut = np.shape(targets)[1]
+		else:
+			self.nOut = 1
+
+		self.nData = np.shape(inputs)[0]
+	
+		# Initialise network
+		self.weights = np.random.rand(self.nIn+1,self.nOut)*0.1-0.05
+
+	def pcntrain(self,inputs,targets,eta,nIterations):
+		""" Train the thing """	
+		# Add the inputs that match the bias node
+		inputs = np.concatenate((inputs,-np.ones((self.nData,1))),axis=1)
+	
+		# Training
+		change = range(self.nData)
+
+		for n in range(nIterations):
+			
+			self.activations = self.pcnfwd(inputs);
+			self.weights -= eta*np.dot(np.transpose(inputs),self.activations-targets)
+			print "Iteration: ", n
+			print self.weights
+			
+			activations = self.pcnfwd(inputs)
+			print "Final outputs are:"
+			print activations
+		#return self.weights
+
+	def pcnfwd(self,inputs):
+		""" Run the network forward """
+
+		# Compute activations
+		activations =  np.dot(inputs,self.weights)
+
+		# Threshold the activations
+		return np.where(activations>0,1,0)
+
+	def confmat(self,inputs,targets):
+		"""Confusion matrix"""
+
+		# Add the inputs that match the bias node
+		inputs = np.concatenate((inputs,-np.ones((self.nData,1))),axis=1)
+		outputs = np.dot(inputs,self.weights)
+	
+		nClasses = np.shape(targets)[1]
+
+		if nClasses==1:
+			nClasses = 2
+			outputs = np.where(outputs>0,1,0)
+		else:
+			# 1-of-N encoding
+			outputs = np.argmax(outputs,1)
+			targets = np.argmax(targets,1)
+
+		cm = np.zeros((nClasses,nClasses))
+		for i in range(nClasses):
+			for j in range(nClasses):
+				cm[i,j] = np.sum(np.where(outputs==i,1,0)*np.where(targets==j,1,0))
+
+		print cm
+		print np.trace(cm)/np.sum(cm)

ch3/xor.py

@@ -0,0 +1,23 @@
+#!/usr/bin/python
+
+import numpy as np
+import pcn_logic_eg as pcn
+
+def main():
+	or_inputs = np.array( [[0,0], [0,1], [1,0], [1,1]])
+	or_targets = np.array([[0],[1],[1],[0]])
+
+	p = pcn.pcn(or_inputs, or_targets)
+	p.pcntrain(or_inputs, or_targets, 0.25, 10)
+	print "confusion matrix"
+	p.confmat(or_inputs, or_targets)
+
+	print "doing"
+	print "  for "
+	print or_inputs
+	inputs_bias = np.concatenate((or_inputs,-np.ones((np.shape(or_inputs)[0],1))), axis=1)
+	print "  results"
+	print p.pcnfwd(inputs_bias)
+
+
+main()