def main():
data = readfile('data.txt')
plot_data(data) # show data
# metoda shlukove hladiny
logging.info('metoda shlukove hladiny')
cluster()
# metoda retezove mapy
logging.info('metoda retezove mapy')
chmap()
# metoda maximin
logging.info('metoda maximin')
maximin()
# nerovnomerne binarni deleni
logging.info('nerovnomerne binarni deleni')
unebin()
# kmeans
logging.info('kmeans')
kmeans()
# bayesuv klasifikator
logging.info('bayesuv klasifikator')
bayes()
# klasifikator podle minimalni vzdalenosti
logging.info('klasifikator podle minimalni vzdalenosti')
mindist()
# klasifikator podle k-nejblizsiho souseda
logging.info('klasifikator podle k-nejblizsiho souseda')
nearneigh()
# klasifikator s linearnimi diskriminacnimi funkcemi
logging.info('klasifikator s linearnimi diskriminacnimi funkcemi')
lindisc()
def unequal_binary(data: List[tuple]):
dist = kmeans(data, 2) # 1st split to two
# plot_kmeans(dist) # inter step
logging.info('First split')
crits = criterion(dist)
max_key = max(crits, key=crits.get) # take bigger value
dist2 = kmeans(dist.pop(max_key), 2) # 2nd split to two
logging.info('Second split')
return {**dist, **dist2} # combine dicts
def test_kmeans(self):
result = kmeans.kmeans(self.data, 3)
expect = {
(1, 1): [(0, 1), (2, 1), (1, 3), (1, -1)],
(1, 7): [(1, 5), (1, 9), (-1, 7), (3, 7)]
}
self.assertEqual(result, expect)
def main():
data = readfile('data.txt')
data = kmeans(data, 3)
ross = rossenblatt(data)
plot_kmeans(ross)
const_incr = constant_increment(data, 0.5)
plot_kmeans(const_incr)
mod_const_incr = constant_increment(data, 0.5)
plot_kmeans(mod_const_incr)
def minimal_distance(data, classes, space_size=(-20, 20), step=1):
dist = kmeans(data, classes)
trypoints = generate_points(space_size[0], space_size[1], step)
for point in trypoints:
distances = {key: distanc(point, key)
for key in dist.keys()
} # dict for each point -> key: distance to him
key_of_min = min(distances.keys(), key=(
lambda key: distances[key])) # select key with minimum distance
dist[key_of_min].append(point) # add point to this key
return dist
def main():
# data = [(-3, 0), (3, 2), (-2, 0), (3, 3), (2, 2), (3, -2), (4, -2), (3, -3)]
data = readfile('data.txt')
logging.info('k-means')
means = kmeans(data, 3)
j_kmeans = sum(criterion(means).values())
plot_kmeans(means)
logging.info('Unequal binary')
dist = unequal_binary(data)
plot_kmeans(dist)
j_binary = sum(criterion(dist).values())
logging.info('J kmeans: {}, J binary: {}'.format(j_kmeans, j_binary))
def nearest_neighbour(data, classes, space_size=(-20, 20), step=1):
k_means = kmeans(data, classes)
trypoints = generate_points(space_size[0], space_size[1], step)
points_in_kmeans = list(itertools.chain(*k_means.values()))
kmeans_toplot = dict(k_means)
for trypoint in trypoints:
sorted_means = sorted(points_in_kmeans,
key=lambda p: distanc(trypoint, p))
for key, value in k_means.items():
for val in value:
if val == sorted_means[0]:
kmeans_toplot[key].append(trypoint)
return kmeans_toplot
def knearest_neighbour(data, classes, space_size=(-20, 20), step=1):
k_means = kmeans(data, classes)
trypoints = generate_points(space_size[0], space_size[1], step)
means_toplot = dict(k_means)
for trypoint in trypoints:
for val in k_means.values():
val.sort(key=lambda p: distanc(trypoint, p))
newdict = {
key: average_dist(trypoint, k_means[key])
for key in k_means.keys()
}
keywithminvalue = min(newdict, key=newdict.get)
means_toplot[keywithminvalue].append(trypoint)
return means_toplot
def bayes(data, classes, space_size=(-20, 20), step=1):
"""
:param data:
:param classes:
:param space_size:
:param float step:
:return:
"""
dist = kmeans(data, classes)
trypoints = generate_points(space_size[0], space_size[1], step)
prob = probability(dist)
prumery = means(dist)
sigm = sigma(dist, prumery)
for point in trypoints:
rozhodovaci = {key: normal(point, sigm[key], prumery[key], prob[key]) for key in dist.keys()}
keywithmaxvalue = max(rozhodovaci, key=rozhodovaci.get)
dist[keywithmaxvalue].append(point)
return dist