def learnModel(self, X, y, folds=3):
"""
Train using the given examples and labels, however first conduct grid
search in conjunction with cross validation to find the best parameters.
We also conduct filtering with a variety of values.
"""
#Hard coding this is bad
Cs = 2**numpy.arange(-2, 7, dtype=numpy.float)
#Cs = numpy.array([0.1, 2.0])
if self.waveletInds == None:
self.waveletInds = numpy.arange(X.shape[1])
nonWaveletInds = numpy.setdiff1d(numpy.arange(X.shape[1]), self.waveletInds)
Xw = X[:, self.waveletInds]
Xo = X[:, nonWaveletInds]
featureInds = numpy.flipud(numpy.argsort(numpy.sum(Xw**2, 0)))
meanAUCs = numpy.zeros((Cs.shape[0], self.candidatesN.shape[0]))
stdAUCs = numpy.zeros((Cs.shape[0], self.candidatesN.shape[0]))
#Standardise the data
Xw = Standardiser().standardiseArray(Xw)
Xo = Standardiser().standardiseArray(Xo)
for i in range(Cs.shape[0]):
for j in range(self.candidatesN.shape[0]):
self.linearSVM.setC(Cs[i])
newX = numpy.c_[Xw[:, featureInds[0:self.candidatesN[j]]], Xo]
meanAUCs[i, j], stdAUCs[i, j] = self.linearSVM.evaluateStratifiedCv(newX, y, folds, metricMethod=Evaluator.auc)
(bestI, bestJ) = numpy.unravel_index(numpy.argmax(meanAUCs), meanAUCs.shape)
self.linearSVM.setC(Cs[bestI])
self.featureInds = numpy.r_[self.waveletInds[featureInds[0:self.candidatesN[bestJ]]], nonWaveletInds]
logging.debug("Best learner found: " + str(self.linearSVM) + " N:" + str(self.candidatesN[bestJ]))
self.standardiser = Standardiser()
newX = self.standardiser.standardiseArray(X[:, self.featureInds])
self.linearSVM.learnModel(newX, y)
def saveResults(self, leafRankGenerators, standardise=True):
"""
Compute the results and save them for a particular hormone. Does so for all
leafranks
"""
j = 0
nonNaInds = self.YList[j][1]
hormoneInd = self.hormoneInds[j]
k = 2
if type(self.X) == numpy.ndarray:
X = self.X[nonNaInds, :]
else:
X = self.X[j][nonNaInds, :]
X = numpy.c_[X, self.ages[nonNaInds]]
if standardise:
X = Standardiser().standardiseArray(X)
Y = hormoneInd[k]
waveletInds = numpy.arange(X.shape[1]-1)
logging.debug("Shape of examples: " + str(X.shape))
logging.debug("Distribution of labels: " + str(numpy.bincount(Y)))
#pca = decomp.PCA(n_components=40)
#X = pca.fit_transform(X)
#print(X.shape)
#Go through all the leafRanks
for i in range(len(leafRankGenerators)):
#Compute TreeRankForest here
fileName = self.resultsDir + "TreeRankForest-" + self.hormoneNames[j] + "_" + str(k) + "-" + leafRankGenerators[i][1] + "-" + self.featuresName + ".dat"
try:
logging.debug("Computing file " + fileName)
#treeRankForest = TreeRankForest(self.funcLeafRankGenerators[0][0](waveletInds))
treeRankForest = TreeRankForest(self.leafRankGenerators[0][0])
treeRankForest.setMaxDepth(10)
treeRankForest.setNumTrees(5)
#Setting this low definitely helps
#treeRankForest.setFeatureSize(1.0)
treeRankForest.setFeatureSize(0.05)
#The following 2 lines definitely improve stability and the AUC
treeRankForest.setSampleSize(1.0)
#Setting this to true results in slightly worse results
treeRankForest.setSampleReplace(True)
mean, var = treeRankForest.evaluateStratifiedCv(X, Y, self.folds, metricMethod=Evaluator.auc)
print(mean)
#treeRank = TreeRank(self.leafRankGenerators[0][0])
#treeRank.setMaxDepth(self.maxDepth)
#(bestParams, allMetrics, bestMetaDicts) = treeRank.evaluateCvOuter(X, Y, self.folds)
#print(str(allMetrics))
#Util.savePickle(cvResults, fileName)
except:
logging.debug("Caught an error in the code ... skipping")
raise
else:
logging.debug("File exists: " + fileName)
return
def __init__(self, learningAlg, windowSize, preprocessor=Standardiser()):
self.windowSize = windowSize
self.learningAlg = learningAlg
self.preprocessor = preprocessor
self.printStep = 50
"""
Compare the clustering methods in scikits.learn to see which ones are fastest
and most accurate
"""
import time
import numpy
import sklearn.cluster as cluster
from apgl.data.Standardiser import Standardiser
import scipy.cluster.vq as vq
numExamples = 10000
numFeatures = 500
X = numpy.random.rand(numExamples, numFeatures)
X = Standardiser().standardiseArray(X)
k = 10
numRuns = 10
maxIter = 100
tol = 10**-4
intialCentroids = X[0:k, :]
#Quite fast
print("Running scikits learn k means")
clusterer = cluster.KMeans(k=k,
n_init=numRuns,
tol=tol,
init=intialCentroids,
max_iter=maxIter)
start = time.clock()
numExamples = 100 numFeatures = 3 std = 0.1 V = numpy.random.rand(numExamples, numFeatures) V[0:20, :] = numpy.random.randn(20, numFeatures) * std V[0:20, 0:3] += numpy.array([1, 0.2, -1]) V[20:70, :] = numpy.random.randn(50, numFeatures) * std V[20:70, 0:3] += numpy.array([-0.5, 1, -1]) V[70:, :] = numpy.random.randn(30, numFeatures) * std V[70:, 0:3] += numpy.array([-0.3, 0.4, -0.1]) U = V - numpy.mean(V, 0) U = Standardiser().normaliseArray(U.T).T fig = plt.figure(0) ax = fig.add_subplot(111, projection='3d') ax.scatter(U[0:20, 0], U[0:20, 1], U[0:20, 2], c="red") ax.scatter(U[20:70, 0], U[20:70, 1], U[20:70, 2], c="blue") ax.scatter(U[70:, 0], U[70:, 1], U[70:, 2], c="green") UU = U.dot(U.T) #s, X = numpy.linalg.eig(UU) X, a, Y = numpy.linalg.svd(U) #Now compute true cluster error k = 3 kmeans = sklearn.cluster.KMeans(k) kmeans.fit(U)
