matchYZ[i] = (None, 0)
for j in sZ:
cd = cover_distance(i,j)
if matchYZ[i][1] < cd:
matchYZ[i] = (j, cd)
return matchXY, matchXZ, matchYZ
if __name__ == '__main__':
# 'NOGA', 'FSL'
p = Pacientes()
e = Exercises()
p.from_db(pilot='NOGA')
e.from_db(pilot='NOGA')
for ex in e.iterator():
t = Trajectory(ex.get_coordinates())
if t.straightness()[0] < 0.95:
e.delete_exercises([ex.id])
for ex in e.iterator():
print (ex.uid + '-' + str(ex.id))
trajec = Trajectory(np.array(ex.frame.loc[:, ['epx', 'epy']]), exer=ex.uid + ' ' + str(ex.id))
beg, nd, vdis = trajec.find_begginning_end()
print(beg, nd)
ltuplesX = segment_signal(ex.frame['rhfx'] - ex.frame['lhfx'], beg, nd)
prevw = word(sdisc[0])
lvoc = [prevw]
for i in range(1, sdisc.shape[0]):
nword = word(sdisc[i])
if nword != prevw:
lvoc.append(nword)
self.codes[c] = Counter(lvoc)
# print(c, self.codes[c])
if __name__ == '__main__':
from iWalker.Data import User, Exercise, Exercises, Pacientes, Trajectory
from iWalker.Util.Misc import show_list_signals
p = Pacientes()
e = Exercises()
p.from_db(pilot='NOGA')
e.from_db(pilot='NOGA')
e.delete_patients(['FSL30'])
wlen = 64
voclen = 3
ncoefs = 3
dseries = {}
for ex in e.iterator():
forces = ex.get_forces()
if forces.shape[0] > wlen:
dseries[ex.id] = forces[:, 0]
boss = Boss(dseries, 10)
boss.discretization_intervals(ncoefs, wlen, voclen)
"""
__author__ = 'bejar'
from iWalker.Data import User, Exercise, Exercises, Pacientes, Trajectory
from iWalker.Util.Misc import show_list_signals
from iWalker.Util import Boss, boss_distance, euclidean_distance, bin_hamming_distance, hamming_distance,\
cosine_similarity
from sklearn.manifold import MDS, Isomap, TSNE, SpectralEmbedding
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
if __name__ == '__main__':
p = Pacientes()
e = Exercises()
p2 = Pacientes()
e2 = Exercises()
p.from_db(pilot='NOGALES')
e.from_db(pilot='NOGALES')
# p2.from_db(pilot='FSL')
# e2.from_db(pilot='FSL')
# e2.delete_patients(['FSL30'])
#
# e.merge(e2)
e.delete_exercises([1425290750])
# e.delete_exercises([1416241920, 1416241871, 1416409354, 1416391685, 1416933676, 1416918342, 1416391884, 1416391948])
wlen = 128
voclen = 3
# coef = np.zeros((nwindows, ncoef), dtype=np.complex)
#
# for w in range(nwindows):
# y = np.fft.rfft(series[w:w+wsize])
# for l in range(ncoef):
# coef[w, l] = y[l]
#
#
# return coef
if __name__ == '__main__':
from iWalker.Data import User, Exercise, Exercises, Pacientes, Trajectory
from iWalker.Util.Misc import show_list_signals
p = Pacientes()
e = Exercises()
p.from_db(pilot='NOGA')
e.from_db(pilot='NOGA')
e.delete_patients(['FSL30'])
ex = e.iterator().__next__()
signal = ex.get_forces()[:, 0]
# show_list_signals([signal])
print(signal.shape)
itime = time.time()
coef1 = mft(signal, sampling=10, ncoef=15, wsize=32)
ftime = time.time()
print(ftime - itime)
# itime = time.time()
from sklearn.manifold import MDS, Isomap, TSNE, SpectralEmbedding
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn.mixture import BayesianGaussianMixture as Dirichlet
import matplotlib.colors as colors
from sklearn.metrics import silhouette_score
from itertools import product
__author__ = 'bejar'
# colors = "rgbymcykrgbymcyk"
if __name__ == '__main__':
p = Pacientes()
e = Exercises()
p.from_db(pilot='NOGALES')
e.from_db(pilot='NOGALES')
e.delete_exercises([1424971539, 1424968950])
e.delete_exercises([1425290750, 1425376956, 1425486861, 1425484520])
# e.delete_exercises([1425290750])
for wlen in [128]:
# wlen = 128
print('*' * 20)
print('WLEN=', wlen)
for ex in e.iterator():
t = Trajectory(ex.get_coordinates())
if t.straightness()[0] < 0.95:
ncoefs = 7
data=[wlen, voclen, ncoefs]
with open("ranscore_l0.csv", "a") as f:
writer = csv.writer(f)
writer.writerow(data)
writer.writerow(" ")
x=10
lol=[]
for u in range(0, x):
p = Pacientes()
e = Exercises()
p.from_db(pilot='NOGALES')
e.from_db(pilot='NOGALES')
e.delete_exercises([1425638547])
e.delete_exercises([1425638507])
e.delete_exercises([1425638379])
e.delete_exercises([1425638343])
e.delete_exercises([1425637677])
e.delete_exercises([1425637642])
e.delete_exercises([1425637526])
e.delete_exercises([1425637492])
e.delete_exercises([1425637369])
e.delete_exercises([1425637335])
e.delete_exercises([1425577862])