def train( self, trainingData, trainingLabels, validationData, validationLabels, showPlot=True, showPacmanPlot=True):
"""
Stochastic gradient descent to learn self.weights
"""
numDimensions = trainingData[0].size
# Initializes weights to zero
self.weights = np.zeros(numDimensions)
if showPlot:
# Initialize list to store loss per iteration for plotting later
trainingLossPerIteration = []
# Initial loss
trainingLoss = self.classificationLoss(trainingData, trainingLabels)
trainingLossPerIteration.append(trainingLoss)
# Check for offset term
plotDims = numDimensions-1
for datum in trainingData:
if datum[-1] != 1:
plotDims += 1
break
if showPacmanPlot and plotDims <=2:
if plotDims == 2:
pacmanDisplay = pacmanPlot.PacmanPlotClassification2D();
pacmanDisplay.plot(trainingData[:,:plotDims], trainingLabels)
else:
pacmanDisplay = pacmanPlot.PacmanPlotLogisticRegression1D();
pacmanDisplay.plot(trainingData[:,0], trainingLabels)
graphicsUtils.sleep(0.1)
# Stochastic gradient descent
for itr in xrange(self.max_iterations):
for (datum, label) in zip(trainingData, trainingLabels):
self.weights = stochasticGradientDescentUpdate(datum, label, self.weights, self.alpha, self.der_loss_dw)
if showPlot:
predictions = self.classify(validationData)
accuracyCount = [predictions[i] == validationLabels[i] for i in range(len(validationLabels))].count(True)
print "Performance on validation set for iteration= %d: (%.1f%%)" % (itr, 100.0*accuracyCount/len(validationLabels))
trainingLoss = self.classificationLoss(trainingData, trainingLabels)
trainingLossPerIteration.append(trainingLoss)
if plotDims <= 2:
if showPacmanPlot:
pacmanDisplay.setWeights(self.weights)
graphicsUtils.sleep(0.1)
else:
if plotDims == 2:
plotUtil.plotClassification2D(trainingData[:,:plotDims],trainingLabels, self.weights, 1)
else:
plotUtil.plotLogisticRegression1D(trainingData[:,:plotDims],trainingLabels, self.weights, 1)
plotUtil.plotCurve(range(len(trainingLossPerIteration)), trainingLossPerIteration, 2, "Training Loss")
if showPlot and showPacmanPlot:
graphicsUtils.end_graphics()
def train( self, trainingData, trainingLabels, validationData, validationLabels, showPlot=True, showPacmanPlot=True):
"""
Stochastic gradient descent to learn self.weights
"""
numDimensions = trainingData[0].size
# Initializes weights to zero
self.weights = np.zeros(numDimensions)
if showPlot:
# Initialize list to store loss per iteration for plotting later
trainingLossPerIteration = []
# Initial loss
trainingLoss = self.classificationLoss(trainingData, trainingLabels)
trainingLossPerIteration.append(trainingLoss)
# Check for offset term
plotDims = numDimensions-1
for datum in trainingData:
if datum[-1] != 1:
plotDims += 1
break
if showPacmanPlot and plotDims <=2:
if plotDims == 2:
pacmanDisplay = pacmanPlot.PacmanPlotClassification2D();
pacmanDisplay.plot(trainingData[:,:plotDims], trainingLabels)
else:
pacmanDisplay = pacmanPlot.PacmanPlotLogisticRegression1D();
pacmanDisplay.plot(trainingData[:,0], trainingLabels)
graphicsUtils.sleep(0.1)
# Stochastic gradient descent
for itr in xrange(self.max_iterations):
for (datum, label) in zip(trainingData, trainingLabels):
self.weights = stochasticGradientDescentUpdate(datum, label, self.weights, self.alpha, self.der_loss_dw)
if showPlot:
predictions = self.classify(validationData)
accuracyCount = [predictions[i] == validationLabels[i] for i in range(len(validationLabels))].count(True)
print "Performance on validation set for iteration= %d: (%.1f%%)" % (itr, 100.0*accuracyCount/len(validationLabels))
trainingLoss = self.classificationLoss(trainingData, trainingLabels)
trainingLossPerIteration.append(trainingLoss)
if plotDims <= 2:
if showPacmanPlot:
pacmanDisplay.setWeights(self.weights)
graphicsUtils.sleep(0.1)
else:
if plotDims == 2:
plotUtil.plotClassification2D(trainingData[:,:plotDims],trainingLabels, self.weights, 1)
else:
plotUtil.plotLogisticRegression1D(trainingData[:,:plotDims],trainingLabels, self.weights, 1)
plotUtil.plotCurve(range(len(trainingLossPerIteration)), trainingLossPerIteration, 2, "Training Loss")
if showPlot and showPacmanPlot:
graphicsUtils.end_graphics()
def trainGradient(self,
trainingData,
regressionData,
numIterations,
showPlot=True,
showPacmanPlot=True):
print 'Training with gradient ...'
if showPlot:
# Initialize list to store loss per iteration for plotting later
trainingLossPerIteration = []
if showPacmanPlot:
pacmanDisplay = pacmanPlot.PacmanPlotRegression()
pacmanDisplay.plot(trainingData, regressionData)
graphicsUtils.sleep(0.1)
# Initializes weights to zero
numDimensions = trainingData[0].size
self.weights = np.zeros(numDimensions)
# Stochastic gradient descent
for i in xrange(numIterations):
if i + 1 % 10 == 0:
print "Iteration " + str(i + 1) + " of " + str(numIterations)
for (datum, label) in zip(trainingData, regressionData):
self.weights = stochasticGradientDescentUpdate(
datum, label, self.weights, self.alpha, self.der_loss_dw)
if showPlot:
trainingLoss = self.regressionLoss(trainingData,
regressionData)
trainingLossPerIteration.append(trainingLoss)
if showPacmanPlot:
pacmanDisplay.setWeights(self.weights)
graphicsUtils.sleep(0.05)
else:
plotUtil.plotRegression(trainingData, regressionData,
self.weights, 1)
plotUtil.plotCurve(range(len(trainingLossPerIteration)),
trainingLossPerIteration, 2,
"Training Loss")
if showPlot and showPacmanPlot:
graphicsUtils.end_graphics()
def trainGradient(self, trainingData, regressionData, numIterations, showPlot=True, showPacmanPlot=True):
print 'Training with gradient ...'
if showPlot:
# Initialize list to store loss per iteration for plotting later
trainingLossPerIteration = []
if showPacmanPlot:
pacmanDisplay = pacmanPlot.PacmanPlotRegression();
pacmanDisplay.plot(trainingData, regressionData)
graphicsUtils.sleep(0.1)
# Initializes weights to zero
numDimensions = trainingData[0].size
self.weights = np.zeros(numDimensions)
# Stochastic gradient descent
for i in xrange(numIterations):
if i+1 % 10 == 0:
print "Iteration " + str(i+1) + " of "+ str(numIterations)
for (datum, label) in zip(trainingData, regressionData):
self.weights = stochasticGradientDescentUpdate(datum, label, self.weights, self.alpha, self.der_loss_dw)
if showPlot:
trainingLoss = self.regressionLoss(trainingData, regressionData)
trainingLossPerIteration.append(trainingLoss)
if showPacmanPlot:
pacmanDisplay.setWeights(self.weights)
graphicsUtils.sleep(0.05)
else:
plotUtil.plotRegression(trainingData,regressionData, self.weights, 1)
plotUtil.plotCurve(range(len(trainingLossPerIteration)), trainingLossPerIteration, 2, "Training Loss")
if showPlot and showPacmanPlot:
graphicsUtils.end_graphics()
def runRegressor(args, options):
regressor = args['regressor']
# Load data
numIter = options.iterations
if (options.data != "BerkeleyHousing"):
print "Loading simple dataset: " + options.data + " ..."
data = np.load(options.data + ".npz")
regressor.setLearningRate(0.01)
trainingData = data["data"]
trainingRegressionResult = data["regressionResults"]
validationData = data["dataVali"]
validationRegressionResult = data["regressionResultsVali"]
testingData = data["dataTest"]
testingRegressionResult = data["regressionResultsTest"]
paras = data["paras"]
else:
print "Loading Berkeley housing dataset ..."
regressor.setLearningRate(0.00000001)
data = np.load("BerkeleyHousing.npz")
# dataTest = np.load("berkeleyHousingTest.npz")
trainingData = data["data"]
trainingRegressionResult = data["regressionResults"]
validationData = []
validationRegressionResult = []
testingData = data["dataTest"]
testingRegressionResult = data["regressionResults"]
# Append 1 to all data points to allow for a bias offset (and convert to Nx2 matrix)
trainingData = np.hstack(
(trainingData[:, None], np.ones((trainingData.size, 1))))
if options.data != "BerkeleyHousing":
validationData = np.hstack(
(validationData[:, None], np.ones((validationData.size, 1))))
testingData = np.hstack(
(testingData[:, None], np.ones((testingData.size, 1))))
# Conduct training and testing
print "Training..."
if (options.method == "analytical"):
regressor.trainAnalytical(trainingData, trainingRegressionResult)
else:
regressor.trainGradient(trainingData, trainingRegressionResult,
numIter, options.Print)
if options.Print:
if options.ghosts:
pacmanDisplay = pacmanPlot.PacmanPlotRegression()
pacmanDisplay.plot(trainingData,
trainingRegressionResult,
regressor.weights,
title='Training: Linear Regression')
graphicsUtils.sleep(3)
else:
plotUtil.plotRegression(trainingData, trainingRegressionResult,
regressor.weights, 1, True, False,
'Training: Linear Regression')
if len(validationData) > 0:
print "Validating..."
if options.Print:
if options.ghosts:
pacmanDisplay = pacmanPlot.PacmanPlotRegression()
pacmanDisplay.plot(validationData,
validationRegressionResult,
regressor.weights,
title='Validating: Linear Regression')
graphicsUtils.sleep(3)
else:
plotUtil.plotRegression(validationData,
validationRegressionResult,
regressor.weights, 1, True, False,
'Validating: Linear Regression')
validationLoss = regressor.regressionLoss(validationData,
validationRegressionResult)
print "Validation loss: " + str(validationLoss)
else:
print "No validation data provided"
print "Testing..."
if options.Print:
if options.ghosts:
pacmanDisplay = pacmanPlot.PacmanPlotRegression()
pacmanDisplay.plot(testingData,
testingRegressionResult,
regressor.weights,
title='Testing: Linear Regression')
graphicsUtils.sleep(3)
else:
plotUtil.plotRegression(testingData, testingRegressionResult,
regressor.weights, 1, True, False,
'Testing: Linear Regression')
testingLoss = regressor.regressionLoss(testingData,
testingRegressionResult)
print "Testing loss: " + str(testingLoss)
if options.Print:
if options.ghosts:
# pacmanDisplay.takeControl()
graphicsUtils.end_graphics()
def finish(self):
gU.end_graphics()
def finish(self):
end_graphics()
def endGraphics():
graphicsUtils.end_graphics()
def runRegressor(args, options):
regressor = args['regressor']
# Load data
numIter = options.iterations
if(options.data!="BerkeleyHousing"):
print "Loading simple dataset: " + options.data + " ..."
data = np.load(options.data + ".npz")
regressor.setLearningRate(0.01)
trainingData = data["data"]
trainingRegressionResult = data["regressionResults"]
validationData = data["dataVali"]
validationRegressionResult = data["regressionResultsVali"]
testingData = data["dataTest"]
testingRegressionResult = data["regressionResultsTest"]
paras = data["paras"]
else:
print "Loading Berkeley housing dataset ..."
regressor.setLearningRate(0.00000001)
data = np.load("BerkeleyHousing.npz")
# dataTest = np.load("berkeleyHousingTest.npz")
trainingData = data["data"]
trainingRegressionResult = data["regressionResults"]
validationData = []
validationRegressionResult = []
testingData = data["dataTest"]
testingRegressionResult = data["regressionResults"]
# Append 1 to all data points to allow for a bias offset (and convert to Nx2 matrix)
trainingData = np.hstack((trainingData[:,None], np.ones( (trainingData.size,1) )))
if options.data!="BerkeleyHousing":
validationData = np.hstack((validationData[:,None], np.ones( (validationData.size,1) )))
testingData = np.hstack((testingData[:,None], np.ones( (testingData.size,1) )))
# Conduct training and testing
print "Training..."
if(options.method == "analytical"):
regressor.trainAnalytical(trainingData, trainingRegressionResult)
else:
regressor.trainGradient(trainingData, trainingRegressionResult, numIter, options.Print)
if options.Print:
if options.ghosts:
pacmanDisplay = pacmanPlot.PacmanPlotRegression();
pacmanDisplay.plot(trainingData, trainingRegressionResult, regressor.weights, title='Training: Linear Regression')
graphicsUtils.sleep(3)
else:
plotUtil.plotRegression(trainingData,trainingRegressionResult, regressor.weights,1,True,False,'Training: Linear Regression')
if len(validationData) > 0:
print "Validating..."
if options.Print:
if options.ghosts:
pacmanDisplay = pacmanPlot.PacmanPlotRegression();
pacmanDisplay.plot(validationData, validationRegressionResult, regressor.weights, title='Validating: Linear Regression')
graphicsUtils.sleep(3)
else:
plotUtil.plotRegression(validationData,validationRegressionResult, regressor.weights,1,True,False, 'Validating: Linear Regression')
validationLoss = regressor.regressionLoss(validationData, validationRegressionResult)
print "Validation loss: " + str(validationLoss)
else:
print "No validation data provided"
print "Testing..."
if options.Print:
if options.ghosts:
pacmanDisplay = pacmanPlot.PacmanPlotRegression();
pacmanDisplay.plot(testingData, testingRegressionResult, regressor.weights, title='Testing: Linear Regression')
graphicsUtils.sleep(3)
else:
plotUtil.plotRegression(testingData, testingRegressionResult, regressor.weights,1,True,False, 'Testing: Linear Regression')
testingLoss = regressor.regressionLoss(testingData, testingRegressionResult)
print "Testing loss: " + str(testingLoss)
if options.Print:
if options.ghosts:
# pacmanDisplay.takeControl()
graphicsUtils.end_graphics()