def worstCaseDistancePlot():
import matplotlib.pyplot as plt
from data import thrombin
train, labels = thrombin.load()
dims = [1000, 750, 500, 250, 100, 75, 50, 25, 10, 5, 2]
epsilon = 0.1
numTrials = 20
dataPoints = []
means = []
stds = []
for dim in dims:
dataPoints = []
for i in range(numTrials):
print("%d, trial %d" % (dim, i))
newData = jlt(train, dim)
dataPoints.append(checkTheorem(train, newData, epsilon))
means.append(numpy.mean(dataPoints))
stds.append(numpy.std(dataPoints))
plt.clf()
plt.errorbar(dims, means, yerr=stds, fmt="-o")
plt.savefig("thrombin-worst-case.png")
def worstCaseDistancePlot():
import matplotlib.pyplot as plt
from data import thrombin
train, labels = thrombin.load()
dims = [1000, 750, 500, 250, 100, 75, 50, 25, 10, 5, 2]
epsilon = 0.1
numTrials = 20
dataPoints = []
means = []
stds = []
for dim in dims:
dataPoints = []
for i in range(numTrials):
print("%d, trial %d" % (dim, i))
newData = jlt(train, dim)
dataPoints.append(checkTheorem(train, newData, epsilon))
means.append(numpy.mean(dataPoints))
stds.append(numpy.std(dataPoints))
plt.clf()
plt.errorbar(dims, means, yerr=stds, fmt='-o')
plt.savefig('thrombin-worst-case.png')
def knnThrombinAccuracyPlot(trials=50):
import matplotlib.pyplot as plt
from data import thrombin
train, labels = thrombin.load()
dims = [1000, 750, 500, 250, 100, 75, 50, 25, 10, 5, 2]
epsilon = 0.1
print("original data")
baseAccuracy, baseFP, baseFN = nearestNeighborsAccuracy(train, labels)
print((baseAccuracy, baseFP, baseFN))
accuracyMeans = []
accuracyStds = []
falsePosMeans = []
falsePosStds = []
falseNegMeans = []
falseNegStds = []
for dim in dims:
accuracyPts = []
falsePosPts = []
falseNegPts = []
for i in range(trials):
print("dim %d, trial %d" % (dim, i))
newData = jlt(train, dim)
acc, fp, fn = nearestNeighborsAccuracy(newData, labels)
accuracyPts.append(acc)
falsePosPts.append(fp)
falseNegPts.append(fn)
# print((accuracies[-1], falsePos[-1], falseNeg[-1]))
accuracyMeans.append(numpy.mean(accuracyPts))
falsePosMeans.append(numpy.mean(falsePosPts))
falseNegMeans.append(numpy.mean(falseNegPts))
accuracyStds.append(numpy.std(accuracyPts))
falsePosStds.append(numpy.std(falsePosPts))
falseNegStds.append(numpy.std(falseNegPts))
plt.clf()
plt.errorbar(dims, accuracyMeans, yerr=accuracyStds, fmt="-o")
plt.axhline(y=baseAccuracy)
plt.savefig("thrombin-knn-accuracy.png")
plt.clf()
plt.errorbar(dims, falsePosMeans, yerr=falsePosStds, fmt="-o")
plt.axhline(y=baseFP)
plt.savefig("thrombin-knn-fp.png")
plt.clf()
plt.errorbar(dims, falseNegMeans, yerr=falseNegStds, fmt="-o")
plt.axhline(y=baseFN)
plt.savefig("thrombin-knn-fn.png")
def knnThrombinAccuracyPlot(trials=50):
import matplotlib.pyplot as plt
from data import thrombin
train, labels = thrombin.load()
dims = [1000, 750, 500, 250, 100, 75, 50, 25, 10, 5, 2]
epsilon = 0.1
print("original data")
baseAccuracy, baseFP, baseFN = nearestNeighborsAccuracy(train, labels)
print((baseAccuracy, baseFP, baseFN))
accuracyMeans = []
accuracyStds = []
falsePosMeans = []
falsePosStds = []
falseNegMeans = []
falseNegStds = []
for dim in dims:
accuracyPts = []
falsePosPts = []
falseNegPts = []
for i in range(trials):
print("dim %d, trial %d" % (dim, i))
newData = jlt(train, dim)
acc, fp, fn = nearestNeighborsAccuracy(newData, labels)
accuracyPts.append(acc)
falsePosPts.append(fp)
falseNegPts.append(fn)
#print((accuracies[-1], falsePos[-1], falseNeg[-1]))
accuracyMeans.append(numpy.mean(accuracyPts))
falsePosMeans.append(numpy.mean(falsePosPts))
falseNegMeans.append(numpy.mean(falseNegPts))
accuracyStds.append(numpy.std(accuracyPts))
falsePosStds.append(numpy.std(falsePosPts))
falseNegStds.append(numpy.std(falseNegPts))
plt.clf()
plt.errorbar(dims, accuracyMeans, yerr=accuracyStds, fmt='-o')
plt.axhline(y=baseAccuracy)
plt.savefig('thrombin-knn-accuracy.png')
plt.clf()
plt.errorbar(dims, falsePosMeans, yerr=falsePosStds, fmt='-o')
plt.axhline(y=baseFP)
plt.savefig('thrombin-knn-fp.png')
plt.clf()
plt.errorbar(dims, falseNegMeans, yerr=falseNegStds, fmt='-o')
plt.axhline(y=baseFN)
plt.savefig('thrombin-knn-fn.png')
def thrombinSubpsaceDistanceHistograms():
import matplotlib.pyplot as plt
from data import thrombin
train, labels = thrombin.load()
for subspaceDim in [5000, 1000, 750, 500, 250, 100, 75, 50, 10, 5, 2]:
newData = jlt(train, subspaceDim)
plt.clf()
plt.ylim(0,200000)
plt.xlim(0,250)
plt.hist(distances(newData), bins=100)
plt.savefig('thrombin-animation/%05d.png' % subspaceDim, bbox_inches='tight')
def checkThrombin(): from data import thrombin train, labels = thrombin.load() numPoints = len(train) epsilon = 0.2 subspaceDim = theoreticalBound(numPoints, epsilon) ambientDim = len(train[0]) print((subspaceDim, ambientDim)) newData = jlt(train, subspaceDim) print(checkTheorem(train, newData, epsilon))
def thrombinSubpsaceDistanceHistograms():
import matplotlib.pyplot as plt
from data import thrombin
train, labels = thrombin.load()
for subspaceDim in [5000, 1000, 750, 500, 250, 100, 75, 50, 10, 5, 2]:
newData = jlt(train, subspaceDim)
plt.clf()
plt.ylim(0, 200000)
plt.xlim(0, 250)
plt.hist(distances(newData), bins=100)
plt.savefig("thrombin-animation/%05d.png" % subspaceDim, bbox_inches="tight")
def checkThrombin():
from data import thrombin
train, labels = thrombin.load()
numPoints = len(train)
epsilon = 0.2
subspaceDim = theoreticalBound(numPoints, epsilon)
ambientDim = len(train[0])
print((subspaceDim, ambientDim))
newData = jlt(train, subspaceDim)
print(checkTheorem(train, newData, epsilon))
def thrombinTheoreticalBoundReduction():
import matplotlib.pyplot as plt
from data import thrombin
train, labels = thrombin.load()
numPoints = len(train)
subspaceDim = theoreticalBound(numPoints, 0.2)
ambientDim = len(train[0])
print((subspaceDim, ambientDim))
#newData = jlt(train, subspaceDim)
allDistances = distances(train)
plt.clf()
plt.hist(allDistances, bins=100)
plt.savefig('thrombin-original.png', bbox_inches='tight')
projectedDistances = distances(jlt(train, subspaceDim))
plt.clf()
plt.hist(projectedDistances, bins=100)
plt.savefig('thrombin-%05d.png' % subspaceDim, bbox_inches='tight')
def thrombinTheoreticalBoundReduction():
import matplotlib.pyplot as plt
from data import thrombin
train, labels = thrombin.load()
numPoints = len(train)
subspaceDim = theoreticalBound(numPoints, 0.2)
ambientDim = len(train[0])
print((subspaceDim, ambientDim))
# newData = jlt(train, subspaceDim)
allDistances = distances(train)
plt.clf()
plt.hist(allDistances, bins=100)
plt.savefig("thrombin-original.png", bbox_inches="tight")
projectedDistances = distances(jlt(train, subspaceDim))
plt.clf()
plt.hist(projectedDistances, bins=100)
plt.savefig("thrombin-%05d.png" % subspaceDim, bbox_inches="tight")
