def _CalcMutualNearestNeighbors(hull_points, all_points):
all_points_list = list(all_points)
ds = distance.pdist(list(all_points))
std_d = p.std(ds)
square_ds = distance.squareform(ds)
nearest_neighbors = {}
for i, point in enumerate(all_points_list):
if point not in hull_points:
continue
my_ds = [(d, j) for j, d in enumerate(square_ds[i])
if j != i]
my_ds.sort()
nearest_neighbors[point] = set([j for d,j in my_ds[:3]])
no_mutual = set()
for i, point in enumerate(all_points_list):
if point not in hull_points:
continue
no_nbrs = True
for neighbor_index in nearest_neighbors.get(point, []):
neighbor = all_points_list[neighbor_index]
neighbor_set = nearest_neighbors.get(neighbor, [])
if i in neighbor_set:
no_nbrs = False
if no_nbrs:
no_mutual.add(point)
return no_mutual
def _CalcMutualNearestNeighbors(hull_points, all_points):
all_points_list = list(all_points)
ds = distance.pdist(list(all_points))
std_d = p.std(ds)
square_ds = distance.squareform(ds)
nearest_neighbors = {}
for i, point in enumerate(all_points_list):
if point not in hull_points:
continue
my_ds = [(d, j) for j, d in enumerate(square_ds[i]) if j != i]
my_ds.sort()
nearest_neighbors[point] = set([j for d, j in my_ds[:3]])
no_mutual = set()
for i, point in enumerate(all_points_list):
if point not in hull_points:
continue
no_nbrs = True
for neighbor_index in nearest_neighbors.get(point, []):
neighbor = all_points_list[neighbor_index]
neighbor_set = nearest_neighbors.get(neighbor, [])
if i in neighbor_set:
no_nbrs = False
if no_nbrs:
no_mutual.add(point)
return no_mutual
def _CalcDensities(hull_points, all_points):
ds = distance.pdist(list(all_points))
std_d = p.std(ds)
square_ds = distance.squareform(ds)
densities = {}
for i, point in enumerate(all_points):
if point not in hull_points:
continue
my_ds = square_ds[i]
density = len([1 for i in my_ds if i <= std_d])
densities[point] = density
tmp_densities = [(d, pt) for pt,d in densities.iteritems()]
tmp_densities.sort(reverse=True)
return tmp_densities, std_d
def _CalcDensities(hull_points, all_points):
ds = distance.pdist(list(all_points))
std_d = p.std(ds)
square_ds = distance.squareform(ds)
densities = {}
for i, point in enumerate(all_points):
if point not in hull_points:
continue
my_ds = square_ds[i]
density = len([1 for i in my_ds if i <= std_d])
densities[point] = density
tmp_densities = [(d, pt) for pt, d in densities.iteritems()]
tmp_densities.sort(reverse=True)
return tmp_densities, std_d
# exercise 10.2.1
from matplotlib.pyplot import figure, show
from scipy.io import loadmat
from toolbox_02450 import clusterplot
from scipy.cluster.hierarchy import linkage, fcluster, dendrogram, distance
from project_3.data import origX
# data = 1 - origX.corr()
# corr_condensed = distance.squareform(data) # convert to condensed
# z = linkage(data, method='centroid')
# dendrogram(z, labels=data.columns)
# show()
data = origX
corr_condensed = distance.squareform(data) # convert to condensed
z = linkage(data, method='centroid')
dendrogram(z)
show()
print('Ran Exercise 10.2.1')
