def submission02(createOutput):
numTrials = 25
X = common.readIrisFile()
X_normalized = normalize(X, norm='l2', axis=0)
distanceFunc = common.irisDataDistanceFunction
centerFunc = common.irisDataCenterFunction
clusterLabels = np.array(list(range(1, 4)), dtype=np.int8)
bestAssignments = None
bestErrorTotal = None
for z in range(numTrials):
model = kmclustering.BasicKMeansClusteringModel(distanceFunc, centerFunc)
#initFunc = lambda q, z: kminit.initKMeansSampling(q, z)
#assignments, centers = kminit.initKMeansSampling(X_normalized, clusterLabels, distanceFunc)
model.runBasicKMeansClustering(X_normalized, clusterLabels, kminit.initKMeansSampling)
print("====== Done with Trial # " + str(z + 1) + " / " + str(numTrials))
#print("Assignments = " + str(model.finalClusterAssignments))
#print("Centers = " + str(model.finalClusterCenters))
#print("Error Map = " + str(model.finalClusterErrorMap))
print("Error Total = " + str(model.finalClusterErrorTotal))
if bestErrorTotal is None or model.finalClusterErrorTotal < bestErrorTotal:
bestErrorTotal = model.finalClusterErrorTotal
bestAssignments = model.finalClusterAssignments
print("Improved total SSE! New Value = " + str(bestErrorTotal))
print("Finished K-Means. Best Error Total = " + str(bestErrorTotal))
print("Best Assignments = " + str(bestAssignments))
if createOutput:
common.writeResultsFile(bestAssignments)
def compareBasicAndBisecting():
X = common.readIrisFile()
scaler = StandardScaler()
X_normalized = scaler.fit_transform(X)
tsne = TSNE(n_components=2, perplexity=20, learning_rate=200, n_iter=1000, init='random')
X_new = tsne.fit_transform(X_normalized)
distanceFunc = common.irisDataDistanceFunction
centerFunc = common.irisDataCenterFunction
clusterLabels = np.array(list(range(1, 4)), dtype=np.int8)
numTrials = 5
##############################################################
# Basic K-means
##############################################################
bestAssignments = None
bestErrorTotal = None
errorSum = 0
for z in range(numTrials):
model = kmclustering.BasicKMeansClusteringModel(distanceFunc, centerFunc, 100)
model.runBasicKMeansClustering(X_new, clusterLabels, kminit.initKMeansSampling)
errorSum += model.finalClusterErrorTotal
print("Done with Basic K-Means Trial # " + str(z + 1) + " / " + str(numTrials))
print("Error Total = " + str(model.finalClusterErrorTotal))
if bestErrorTotal is None or model.finalClusterErrorTotal < bestErrorTotal:
bestErrorTotal = model.finalClusterErrorTotal
bestAssignments = model.finalClusterAssignments
avgError = errorSum / numTrials
print("Finished Basic K-Means. Avg Error = " + str(avgError) + " and Best Error = " + str(bestErrorTotal))
print("Creating output now for Basic K-Means.")
common.writeResultsFile(bestAssignments)
##############################################################
# Bisecting K-means
##############################################################
bestAssignments = None
bestErrorTotal = None
errorSum = 0
for z in range(numTrials):
model = kmclustering.BisectingKMeansClusteringModel(distanceFunc, centerFunc, 5)
model.runBisectingKMeansClustering(X_new, clusterLabels, kminit.initKMeansSampling)
errorSum += model.finalClusterErrorTotal
print("Done with Bisecting K-Means Trial # " + str(z + 1) + " / " + str(numTrials))
print("Error Total = " + str(model.finalClusterErrorTotal))
if bestErrorTotal is None or model.finalClusterErrorTotal < bestErrorTotal:
bestErrorTotal = model.finalClusterErrorTotal
bestAssignments = model.finalClusterAssignments
avgError = errorSum / numTrials
print("Finished Bisecting K-Means. Avg Error = " + str(avgError) + " and Best Error = " + str(bestErrorTotal))
print("Creating output now for Bisecting K-Means.")
common.writeResultsFile(bestAssignments)
def tuneTsneBasic(createOutput):
numTrials = 5
X = common.readDigitsFile()
print("Shape of Digits file = " + str(X.shape))
print("Starting t-SNE.")
#pca = PCA(n_components=50)
#X_temp = pca.fit_transform(X)
tsne = TSNE(n_components=2,
init='random',
random_state=0,
perplexity=35,
learning_rate=400,
n_iter=2000)
X_new = tsne.fit_transform(X)
#X_new = digitutil.preprocessDownsampling(X)
print("Finished t-SNE, and got X_new. Shape = " + str(X_new.shape))
#print("First 10 rows are: ")
#print(X_new[0:10, :])
#numTrials = 10
#X_normalized = normalize(X, norm='l2', axis=0)
distanceFunc = common.euclideanDistanceFunction
centerFunc = common.digitsDataCenterFunction
clusterLabels = np.array(list(range(1, 11)), dtype=np.int8)
bestAssignments = None
bestErrorTotal = None
for z in range(numTrials):
model = kmclustering.BasicKMeansClusteringModel(
distanceFunc, centerFunc, 100)
#initFunc = lambda q, z: kminit.initKMeansSampling(q, z)
#assignments, centers = kminit.initKMeansSampling(X_normalized, clusterLabels, distanceFunc)
model.runBasicKMeansClustering(X_new, clusterLabels,
kminit.initKMeansSampling)
print("====== Done with Trial # " + str(z + 1) + " / " +
str(numTrials) + ", Error Total = " +
str(model.finalClusterErrorTotal) + " ======")
#print("Assignments = " + str(model.finalClusterAssignments))
#print("Centers = " + str(model.finalClusterCenters))
#print("Error Map = " + str(model.finalClusterErrorMap))
#print()
if bestErrorTotal is None or model.finalClusterErrorTotal < bestErrorTotal:
bestErrorTotal = model.finalClusterErrorTotal
bestAssignments = model.finalClusterAssignments
#print("Improved total SSE! New Value = " + str(bestErrorTotal))
print("Finished K-Means with t-SNE, P=. Best Error Total = " +
str(bestErrorTotal))
#print("Best Assignments = " + str(bestAssignments))
if createOutput:
common.writeResultsFile(bestAssignments)
def chartClusterErrorVsClusterCount():
X = common.readDigitsFile()
X = X / 255.0
print("Shape of Digits file = " + str(X.shape))
print("Starting t-SNE.")
tsne = TSNE(n_components=2,
init='random',
random_state=0,
perplexity=100,
learning_rate=400,
n_iter=2000)
X_new = tsne.fit_transform(X)
print("Finished t-SNE, and got X_new. Shape = " + str(X_new.shape))
distanceFunc = common.euclideanDistanceFunction
centerFunc = common.digitsDataCenterFunction
numTrials = 5
errorMapForClusterSize = {}
clusterSizeList = list(range(2, 21, 2))
for clusterSize in clusterSizeList:
errorSum = 0
clusterLabels = np.array(list(range(1, clusterSize + 1)),
dtype=np.int8)
for z in range(numTrials):
model = kmclustering.BasicKMeansClusteringModel(
distanceFunc, centerFunc, 100)
model.runBasicKMeansClustering(X_new, clusterLabels,
kminit.initKMeansSampling)
print("====== Done with Trial # " + str(z + 1) + " / " + str(numTrials) + " for K = " + str(clusterSize) + \
", Error Total = " + str(model.finalClusterErrorTotal) + " ======")
errorSum += model.finalClusterErrorTotal
avgError = errorSum / numTrials
errorMapForClusterSize[clusterSize] = avgError
print("Done with K-Means.")
for clusterSize in clusterSizeList:
print("For K = " + str(clusterSize) + " Error is: " +
str(errorMapForClusterSize[clusterSize]))
def submission01(createOutput, numTrials):
X = common.readDigitsFile()
print("Shape of Digits file = " + str(X.shape))
X_new = digitutil.preprocessDownsampling(X)
print("Got X_new. Shape = " + str(X_new.shape))
#print("First 10 rows are: ")
#print(X_new[0:10, :])
#numTrials = 10
X_normalized = normalize(X, norm='l2', axis=0)
distanceFunc = common.euclideanDistanceFunction
centerFunc = common.digitsDataCenterFunction
clusterLabels = np.array(list(range(1, 11)), dtype=np.int8)
bestAssignments = None
bestErrorTotal = None
for z in range(numTrials):
model = kmclustering.BasicKMeansClusteringModel(
distanceFunc, centerFunc, 55)
#initFunc = lambda q, z: kminit.initKMeansSampling(q, z)
#assignments, centers = kminit.initKMeansSampling(X_normalized, clusterLabels, distanceFunc)
model.runBasicKMeansClustering(X_normalized, clusterLabels,
kminit.initKMeansSampling)
print("====== Done with Trial # " + str(z + 1) + " / " +
str(numTrials) + ", Error Total = " +
str(model.finalClusterErrorTotal) + " ======")
#print("Assignments = " + str(model.finalClusterAssignments))
#print("Centers = " + str(model.finalClusterCenters))
#print("Error Map = " + str(model.finalClusterErrorMap))
#print()
if bestErrorTotal is None or model.finalClusterErrorTotal < bestErrorTotal:
bestErrorTotal = model.finalClusterErrorTotal
bestAssignments = model.finalClusterAssignments
#print("Improved total SSE! New Value = " + str(bestErrorTotal))
print("Finished K-Means. Best Error Total = " + str(bestErrorTotal))
#print("Best Assignments = " + str(bestAssignments))
if createOutput:
common.writeResultsFile(bestAssignments)
def compareInitialization():
X = common.readIrisFile()
scaler = StandardScaler()
X_new = scaler.fit_transform(X)
distanceFunc = common.irisDataDistanceFunction
centerFunc = common.irisDataCenterFunction
clusterLabels = np.array(list(range(1, 4)), dtype=np.int8)
numTrials = 5
kmSampling = kminit.initKMeansSampling
kmRandom = lambda x, c: kminit.initKMeansRandomly(x, c, centerFunc, distanceFunc)
kmPlusPlus = lambda x, c: kminit.initKMeansKMeansPlusPlus(x, c, distanceFunc)
initFunctions = [(kmSampling, "Sampling"), (kmRandom, "Random"), (kmPlusPlus, "K-Means++")]
##############################################################
# Basic K-means
##############################################################
for initFunction, initFunctionDesc in initFunctions:
bestErrorTotal = None
errorSum = 0
for z in range(numTrials):
model = kmclustering.BasicKMeansClusteringModel(distanceFunc, centerFunc, 100)
model.runBasicKMeansClustering(X_new, clusterLabels, initFunction)
errorSum += model.finalClusterErrorTotal
print("Done with Basic K-Means with initialization type = " + initFunctionDesc + ", Trial # " + str(z + 1) + " / " + str(numTrials))
print("Error Total = " + str(model.finalClusterErrorTotal))
if bestErrorTotal is None or model.finalClusterErrorTotal < bestErrorTotal:
bestErrorTotal = model.finalClusterErrorTotal
avgError = errorSum / numTrials
print("Finished Basic K-Means with initialization type = " + initFunctionDesc + ". Avg Error = " + str(avgError) + " and Best Error = " + str(bestErrorTotal))