class Mean():
"""
A mean of the k-means.
"""
def __init__(self, id, dimensions, key=lambda x: x):
self.id = id
self.dimensions = dimensions
self.key = key
if self.dimensions is None:
self.position = []
else:
self.position = [random.random() for i in range(dimensions)]
self.coveredDataset = None
self.nextDataset = Dataset(normalized=True, data=[])
self.dirt = False
self.meanSquaredError = None
self.totalSquaredError = None
def update(self):
if self.coveredDataset == self.nextDataset:
self.nextDataset = Dataset(normalized=True, data=[])
return False
self.coveredDataset = self.nextDataset.copy()
self.position = self.coveredDataset.median()
return True
def clear(self):
self.nextDataset = Dataset(normalized=True, data=[])
def cover(self, point):
self.nextDataset.append(point)
self.dirt = True
def __repr__(self):
return "<Mean id: %i position:%s dataset:%s>" % (
self.id, str(self.position), self.coveredDataset.__repr__())
def distanceSqrd(self, point):
def distSqrd(v1, v2):
return sum([(j - v2[i]) ** 2 for i, j in enumerate(v1)])
return distSqrd(self.key(point), self.position)
def getMeanSquaredError(self, key=lambda x: x):
if len(self.coveredDataset) == 0:
return float('inf')
if self.dirt or self.meanSquaredError is None:
self.meanSquaredError = self.getTotalSquaredError() /\
len(self.coveredDataset)
self.dirt = False
return self.meanSquaredError
def getTotalSquaredError(self, key=lambda x: x):
if self.dirt or self.meanSquaredError is None:
squaredDists = [self.distanceSqrd(point)
for point in self.coveredDataset]
self.totalSquaredError = sum(squaredDists)
self.dirt = False
return self.totalSquaredError
def getCoveredDataset(self, limits=None, normalized=True):
if normalized:
return self.coveredDataset.genUnnormalized(limits)
else:
return self.coveredDataset
