def computeCentroid(self):
dim = self.samples[0].dimensionality()
centroid = sample.Sample('centroid', [0.0] * dim)
for e in self.samples:
centroid += e
centroid /= len(self.samples)
return centroid
def genDistribution(xMean=0, xSD=1, yMean=0, ySD=1, n=50, namePrefix='', label = 'a'):
samples = []
for s in range(n):
x = random.gauss(xMean, xSD)
y = random.gauss(yMean, ySD)
samples.append(sample.Sample(namePrefix+str(s), [x, y], label))
return samples
def __mul__(self, other):
''' bonus: can you do vector multiplication?
this is two vectors element-wise multiplication '''
f = []
for i in range(self.dimensionality()):
f.append(self.getFeatures()[i] * other.getFeatures()[i])
return sample.Sample(self.name + '*', f, self.label)
def computeCentroid(self):
'''
return an instance of Sample, its features should be
the center of all the samples in the cluster
'''
# return helper.computeCentroid(self)
s = sample.Sample("center", [0, 0])
for spl in self.samples:
s += spl
s /= len(self.samples)
return s
def make_data(n, scale=1):
""" A simple y = x curve, with noisy displacement on both
both x and y axis; change scale to change the range
"""
linear_data = [
sample.Sample('',
[float(x) / scale, float(x) / scale], '')
for x in range(n)
]
noise = util.genDistribution(xSD=0.3, ySD=0.3, n=n)
data = [linear_data[i] + noise[i] for i in range(n)]
return data
def onclick(event):
# Creating a new point and finding the k nearest neighbours
new = sample.Sample('', [event.xdata, event.ydata], '')
knn(new, data, K)
# draw the new point
data.append(new)
pylab.scatter([new.getFeatures()[0]], \
[new.getFeatures()[1]], \
label = new.getLabel(), \
marker = util.make_cmarkers()[LABELS.index(new.getLabel())], \
color = util.make_cmap()[LABELS.index(new.getLabel())])
pylab.draw()
def __sub__(self, other):
f = []
for i in range(self.dimensionality()):
f.append(self.getFeatures()[i] - other.getFeatures()[i])
return sample.Sample(self.name + '-' + other.name, f)
def vec_div(self, other):
f = []
for i in range(self.dimensionality()):
f.append(self.getFeatures()[i] / float(other.getFeatures()[i]))
return sample.Sample(self.name + '/', f, self.label)
def power(self, x):
f = []
for i in range(self.dimensionality()):
f.append(self.getFeatures()[i]**(x))
return sample.Sample(self.name + '-power(' + str(x) + ')', f, self.label)
def __mul__(self, other):
f = []
for i in range(self.dimensionality()):
f.append(self.getFeatures()[i] * other.getFeatures()[i])
return sample.Sample(self.name + '*', f, self.label)
