def learn(self, samples, epochs=25000, noise=0, test_samples=None, show_progress=True):
''' Learn given distribution using n data
List of sample sets
Number of epochs to be ran for each sample set
'''
# Check if samples is a list
if type(samples) not in [tuple,list]:
samples = (samples,)
epochs = (epochs,)
n = 0 # total number of epochs to be ran
for j in range(len(samples)):
n += epochs[j]
self.entropy = []
self.distortion = []
if show_progress:
bar = ProgressBar(widgets=[Percentage(), Bar()], maxval=n).start()
index = 0
for j in range(len(samples)):
self.samples = samples[j]
I = np.random.randint(0,self.samples.shape[0],n)
for i in range(epochs[j]):
# Set sigma and learning rate via time
t = index/float(n)
lrate = self.lrate_i*(self.lrate_f/self.lrate_i)**t
sigma = self.sigma_i*(self.sigma_f/self.sigma_i)**t
C = self.adj.copy()
# Learn something
S = self.samples[I[i]] + noise*(2*np.random.random(len(self.samples[I[i]]))-1)
S = np.minimum(np.maximum(S,0),1)
self.learn_data(S,lrate,sigma)
#self.learn_data(self.samples[I[i]],lrate,sigma)
if i%100 == 0:
self.entropy.append(((self.adj-C)**2).sum())
if test_samples is not None:
distortion = self.compute_distortion(test_samples)
else:
distortion = self.compute_distortion(self.samples)
self.distortion.append(distortion)
if show_progress:
bar.update(index+1)
index = index+1
if show_progress: bar.finish()
def learn(self, samples, epochs=25000, noise=0, test_samples=None, show_progress=True):
''' Learn given distribution using n data
:Parameters:
`samples` : [numpy array, ...]
List of sample sets
`epochs` : [int, ...]
Number of epochs to be ran for each sample set
'''
# Check if samples is a list
if type(samples) not in [tuple,list]:
samples = (samples,)
epochs = (epochs,)
n = 0 # total number of epochs to be ran
for j in range(len(samples)):
n += epochs[j]
self.entropy = []
self.distortion = []
if show_progress:
bar = ProgressBar(widgets=[Percentage(), Bar()], maxval=n).start()
index = 0
for j in range(len(samples)):
self.samples = samples[j]
I = np.random.randint(0,self.samples.shape[0],n)
for i in range(epochs[j]):
# Set sigma and learning rate according to current time
t = index/float(n)
lrate = self.lrate_i*(self.lrate_f/self.lrate_i)**t
sigma = self.sigma_i*(self.sigma_f/self.sigma_i)**t
C = self.codebook.copy()
# Learn data
S = self.samples[I[i]] + noise*(2*np.random.random(len(self.samples[I[i]]))-1)
S = np.minimum(np.maximum(S,0),1)
self.learn_data(S,lrate,sigma)
#self.learn_data(self.samples[I[i]],lrate,sigma)
if i%100 == 0:
self.entropy.append(((self.codebook-C)**2).sum())
if test_samples is not None:
distortion = self.compute_distortion(test_samples)
else:
distortion = self.compute_distortion(self.samples)
self.distortion.append(distortion)
if show_progress:
bar.update(index+1)
index = index+1
if show_progress:
bar.finish()
file.write('''set size ratio 1\n''')
file.write(
'''set title "Dynamic Self-Organising Map\\nNicolas Rougier & Yann Boniface"\n'''
)
file.write(
'''set label "Self-organisation onto a cube surface" at screen .5, screen .1 center\n'''
)
file.write(
'''set label "(http://www.loria.fr/~rougier/)" at screen .5, screen .065 center textcolor lt 3\n'''
)
file.write('''set view %d,%d\n''' % (rot_x, rot_z))
file.write('''set terminal pngcairo size 512,512\n''')
file.write('''set output '%s.png'\n''' % filename)
# file.write('''splot '%s' using 1:2:3, '%s' with point pt 6 lw .1\n''' % (datafile,datafile))
file.write('''splot '%s' using 1:2:3\n''' % (datafile))
file.close()
file = open(datafile, 'w')
C = net.codebook
for x in range(C.shape[0]):
for y in range(C.shape[1]):
file.write('%.3f %.3f %.3f\n' %
(C[x, y, 0], C[x, y, 1], C[x, y, 2]))
file.write('''\n''')
file.close()
subprocess.call(['/usr/bin/gnuplot', plotfile])
net.learn_data(samples[I[i]])
bar.update(i)
bar.finish()
# os.system('''mencoder 'mf:///tmp/image*.png' -mf type=png:fps=25 -Ovc lavc -lavcopts \
# vcodec=mpeg4:vbitrate=2500 -oac copy -o cube.avi''')
from progress import ProgressBar
from time import sleep
from random import random
my_list = range(20)
print 'TEST: Using a default ProgressBar'
sleep(1.0)
pb = ProgressBar(len(my_list), 20)
pb.start()
for i in my_list:
sleep(0.3)
pb.tick()
pb.finish()
print 'TEST: Using a custom design'
sleep(1.0)
pb = ProgressBar(len(my_list), 20, bookends='<{}>',
bar_char='/', empty_char='-')
pb.start()
for i in my_list:
sleep(0.3)
pb.tick()
pb.finish()
print 'TEST: Using a minimal design'
sleep(1.0)
pb = ProgressBar(len(my_list), 20, bookends='',
bar_char='-', empty_char=' ', show_percent=True, show_iter=False,
show_time=False)
pb.start()
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
from progress import ProgressBar
from animation import *
from time import sleep
p = ProgressBar(" Doing the 1st thing:", max_value=20, width=20)
for i in range(21):
p.update(i)
sleep(.25)
p.finish("Success")
a = Animation("Waiting for the 2nd thing:")
for i in range(21):
a.next()
sleep(.25)
a.finish("Success")
a = Animation("Waiting for the 3rd thing:", animation=ANIMATE_VGROW)
for i in range(21):
a.next()
sleep(.25)
a.finish("Success")
a = Animation("Waiting for the 4th thing:", animation=ANIMATE_HGROW)
for i in range(21):
a.next()
sleep(.25)
a.finish("Success")
a = Animation("Waiting for the 5th thing:", animation=ANIMATE_COUNT)
file.write('''set xrange [-.5:1.5]\n''')
file.write('''set yrange [-.5:1.5]\n''')
file.write('''set zrange [-.5:1.5]\n''')
file.write('''set style data line\n''')
file.write('''set ticslevel 0\n''')
file.write('''set size ratio 1\n''')
file.write('''set title "Dynamic Self-Organising Map\\nNicolas Rougier & Yann Boniface"\n''')
file.write('''set label "Self-reorganisation from sphere to spheres surface" at screen .5, screen .1 center\n''')
file.write('''set label "(http://www.loria.fr/~rougier/)" at screen .5, screen .065 center textcolor lt 3\n''')
file.write('''set view %d,%d\n''' % (rot_x,rot_z))
file.write('''set terminal pngcairo size 512,512\n''')
file.write('''set output '%s.png'\n''' % filename)
# file.write('''splot '%s' using 1:2:3, '%s' with point pt 6 lw .1\n''' % (datafile,datafile))
file.write('''splot '%s' using 1:2:3\n''' % (datafile))
file.close()
file = open(datafile, 'w')
C = net.codebook
for x in range(C.shape[0]):
for y in range(C.shape[1]):
file.write('%.3f %.3f %.3f\n' % (C[x,y,0],C[x,y,1],C[x,y,2]))
file.write('''\n''')
file.close()
subprocess.call(['/usr/bin/gnuplot', plotfile])
net.learn_data(samples[I[i]])
bar.update(i)
bar.finish()
# os.system('''mencoder 'mf:///tmp/sphere*.png' -mf type=png:fps=25 -Ovc lavc -lavcopts \
# vcodec=mpeg4:vbitrate=2500 -oac copy -o sphere.avi''')
from progress import ProgressBar
from time import sleep
from random import random
my_list = range(20)
print 'TEST: Using a default ProgressBar'
sleep(1.0)
pb = ProgressBar(len(my_list), 20)
pb.start()
for i in my_list:
sleep(0.3)
pb.tick()
pb.finish()
print 'TEST: Using a custom design'
sleep(1.0)
pb = ProgressBar(len(my_list),
20,
bookends='<{}>',
bar_char='/',
empty_char='-')
pb.start()
for i in my_list:
sleep(0.3)
pb.tick()
pb.finish()
print 'TEST: Using a minimal design'
sleep(1.0)
pb = ProgressBar(len(my_list),
def parse_crux_search_txt(filename):
"""Iterate over records in a search.{target,decoy}.txt.
Crux txt format files are tab-delimited with 30 fields*, described
in the online documentation [1]. This function returns an iterator
which yields a dictionary with the fields and their values.
* 'decoy q-value (p-value)' is not output by Crux, at least as of v1.33.
[1] http://noble.gs.washington.edu/proj/crux/txt-format.html
Arguments:
filename: Name of the crux search-for-matches output.
Returns:
Dictionary that maps field names to values. Only fields that
are non-empty in the input exist in the returned dictionary.
Many of the fields are not usually set in the output of crux
search-for-matches, and will not be available.
"""
fields = ['scan', # int
'charge', # int
'spectrum precursor m/z', # float
'spectrum neutral mass', # float
'peptide mass', # float
'delta_cn', # float
'sp score', # float
'sp rank', # float
'xcorr score', # float
'xcorr rank', # int
'p-value', # float
'Weibull est. q-value', # float
'decoy q-value (xcorr)', # float
'percolator score', # float
'percolator rank', # int
'percolator q-value', # float
'q-ranker score', # float
'q-ranker q-value', # float
'b/y ions matched', # int
'b/y ions total', # int
'matches/spectrum', # int
'sequence', # string
'cleavage type', # string
'protein id', # string
'flanking aa', # string
'unshuffled sequence', # string
'eta', # float
'beta', # float
'shift', # float
'corr'] # float
casts = [ int, int, float, float, float, float, float, float, float, int,
float, float, float, float, int, float, float, float, int, int,
int, str, str, str, str, str, float, float, float, float ]
assert(len(fields) == len(casts))
_mandatories = [ 'scan', 'charge', 'spectrum precursor m/z',
'spectrum neutral mass', 'xcorr score',
'xcorr rank', 'sequence' ]
def conv(f, value):
value = value.strip()
if len(value):
return f(value)
def validate(record):
return all(record.has_key(m) for m in _mandatories)
widgets = [ Percentage(), Bar(), ETA() ]
progress = ProgressBar(widgets = widgets,
maxval = os.path.getsize(filename)).start()
with open(filename) as f:
reader = csv.reader(f, delimiter='\t')
# Header
row = reader.next()
if row != fields:
raise ParseError('Header: ', filename, 1, ' '.join(row))
# Body
for row in reader:
progress.update(f.tell())
if len(row) != len(fields):
raise ParseError('Line: ', filename, reader.line_num,
' '.join(row))
r = dict((k, conv(f,x)) for k, f, x in zip(fields, casts, row))
if r:
if not validate(r):
raise ParseError('Missing: ', filename, reader.line_num,
' '.join(row))
yield r
progress.finish()
sys.stdout.write('\n')
