'/home/aurora/workspace/PycharmProjects/data/hist_adjacent_matrix.npy')
# hist_weights_constraint_33 = np.load('/home/aurora/hdd/workspace/PycharmProjects/data/sub_matrix_distance_2015_1211.npy')
hist_weights_constraint_33 = np.load(
'/home/aurora/hdd/workspace/PycharmProjects/data/aurora_img_matches_matrix_20151212.npy'
)
# show_weights_img(img_weights)
# datas = [img_weights_3, img_weights_9, img_weights_13, img_weights_33]
datas = [hist_weights_constraint_33]
start = clock()
category = [100, 200, 300, 400, 500]
# category = [500, 600, 700, 800]
# category = [4, 6, 8, 10]
results = np.zeros((4, len(category), hist_weights_constraint_33.shape[0]))
for idx, data in enumerate(datas):
for k in category:
eigval, eigvec = ncut.ncut(data, k)
discret_eigvec = ncut.discretisation(eigvec)
group_img = discret_eigvec[:, 0]
for i in range(1, k):
group_img += (i + 1) * discret_eigvec[:, i]
# print results[category.index(k)].shape
results[idx, category.index(k)] = group_img.todense().T
# results[0, category.index(k)] = (results[0, category.index(k)]/k)*256
print results.shape
np.save(
'/home/aurora/hdd/workspace/PycharmProjects/data/img_sub_ncuts_matrix_distance_2015_1211_m_400',
results)
# print np.unique(results[0][0])
# print np.unique(results[0][1])
# print np.unique(results[0][2])
# print np.unique(results[0][3])
img_weights_9 = np.load('/home/aurora/hdd/workspace/PycharmProjects/data/similary_gausses_9.npy')
img_weights_13 = np.load('/home/aurora/hdd/workspace/PycharmProjects/data/similary_gausses_13.npy')
img_weights_33 = np.load('/home/aurora/hdd/workspace/PycharmProjects/data/similary_gausses_33.npy')
hist_weights_33 = np.load('/home/aurora/workspace/PycharmProjects/data/hist_adjacent_matrix.npy')
hist_weights_constraint_33 = np.load('/home/aurora/workspace/PycharmProjects'
'/data/hist_adjacent_matrix_constraint.npy')
# show_weights_img(img_weights)
# datas = [img_weights_3, img_weights_9, img_weights_13, img_weights_33]
datas = [hist_weights_constraint_33]
start = clock()
category = [100, 200, 300, 400]
# category = [4, 6, 8, 10]
results = np.zeros((4, len(category), img_weights_3.shape[0]))
for idx, data in enumerate(datas):
for k in category:
eigval, eigvec = ncut.ncut(data, k)
discret_eigvec = ncut.discretisation(eigvec)
group_img = discret_eigvec[:, 0]
for i in range(1, k):
group_img += (i+1)*discret_eigvec[:, i]
# print results[category.index(k)].shape
results[idx, category.index(k)] = group_img.todense().T
# results[0, category.index(k)] = (results[0, category.index(k)]/k)*256
print results.shape
np.save('/home/aurora/hdd/workspace/PycharmProjects/data/hist_ncuts_constraint_sigma_33', results)
print np.unique(results[0])
print np.unique(results[1])
print np.unique(results[2])
print np.unique(results[3])
end = clock()
def cluster_timeseries(X, n_clusters, similarity_metric = 'k_neighbors', affinity_threshold = 0.0, neighbors = 10):
"""
Cluster a given timeseries
Parameters
----------
X : array_like
A matrix of shape (`N`, `M`) with `N` samples and `M` dimensions
n_clusters : integer
Number of clusters
similarity_metric : {'k_neighbors', 'correlation', 'data'}
Type of similarity measure for spectral clustering. The pairwise similarity measure
specifies the edges of the similarity graph. 'data' option assumes X as the similarity
matrix and hence must be symmetric. Default is kneighbors_graph [1]_ (forced to be
symmetric)
affinity_threshold : float
Threshold of similarity metric when 'correlation' similarity metric is used.
Returns
-------
y_pred : array_like
Predicted cluster labels
Examples
--------
References
----------
.. [1] http://scikit-learn.org/dev/modules/generated/sklearn.neighbors.kneighbors_graph.html
"""
if similarity_metric == 'correlation':
# Calculate empirical correlation matrix between samples
Xn = X - X.mean(1)[:,np.newaxis]
Xn = Xn/np.sqrt( (Xn**2.).sum(1)[:,np.newaxis] )
C_X = np.dot(Xn, Xn.T)
C_X[C_X < affinity_threshold] = 0
from scipy.sparse import lil_matrix
C_X = lil_matrix(C_X)
elif similarity_metric == 'data':
C_X = X
elif similarity_metric == 'k_neighbors':
from sklearn.neighbors import kneighbors_graph
C_X = kneighbors_graph(X, n_neighbors=neighbors)
C_X = 0.5 * (C_X + C_X.T)
else:
raise ValueError("Unknown value for similarity_metric: '%s'." % similarity_metric)
#sklearn code is not stable for bad clusters which using correlation as a stability metric
#tends to give for more info see:
#http://scikit-learn.org/dev/modules/clustering.html#spectral-clustering warning
# from sklearn import cluster
# algorithm = cluster.SpectralClustering(k=n_clusters, mode='arpack')
# algorithm.fit(C_X)
# y_pred = algorithm.labels_.astype(np.int)
from python_ncut_lib import ncut, discretisation
eigen_val, eigen_vec = ncut(C_X, n_clusters)
eigen_discrete = discretisation(eigen_vec)
#np.arange(n_clusters)+1 isn't really necessary since the first cluster can be determined
#by the fact that the each cluster is a disjoint set
y_pred = np.dot(eigen_discrete.toarray(), np.diag(np.arange(n_clusters))).sum(1)
return y_pred
av_dist = dist / num
return av_dist
av_mat_class_distance = cal_av_mat_class_distance(people)
print av_mat_class_distance
dist1,vec_class_distance_people1 = cal_mat_class_distance(mat_people1)
std1 = np.std(vec_class_distance_people1)# std of the people1
dist2,vec_class_distance_people2 = cal_mat_class_distance(mat_people2)
std2 = np.std(vec_class_distance_people2) # std of the people2
std12 = (std1+std2)/2 # average std between people1 and people2
print std12
mat_W = np.exp(-mat_dist/std12) #mat_W is the similarity matrix , the kernal function is exp(-d/std)
print mat_W
#only for test
print mat_W.shape
import python_ncut_lib as nc # import the normalized cut
#unlimited display
#np.set_printoptions(threshehold = np.nan)
nbEigen = 3
eigen_value,vector=nc.ncut(mat_W,nbEigen)
vec_dis = nc.discretisation(vector)
print eigen_value
print vec_dis
