from __future__ import division
from sklearn import ensemble
import sklearn
import windowfile
import numpy as np
import matplotlib.pyplot as plt
import sys
import pickle
print('load')
A = windowfile.readwins(open(sys.argv[1]))
B = windowfile.readwins(open(sys.argv[2]))
tamA = A.shape[0]
tamB = B.shape[0]
trainingSize = 10000
singleSet = np.zeros((trainingSize, 256))
overlapSet = np.zeros((trainingSize, 256))
print('generate set')
for i in xrange(trainingSize):
# single
sA = int(np.random.rand() * tamA)
sB = int(np.random.rand() * tamB)
if np.random.rand() > 0.5: # from A
singleSet[i, :] = A[sA]
else:
singleSet[i, :] = B[sA]
from __future__ import division
import sys
import svm
import windowfile
import pickle
import numpy as np
import matplotlib.pyplot as plt
import scipy.signal as sg
print('load model')
model = svm.libsvm.svm_load_model('/ssd/15o04000_15o04001_h.svmmodel')
print('load A')
A = windowfile.readwins(open('/ssd/15o03000_h.features'))
print('load sig')
sig = windowfile.readwinsEx(open('/ssd/15o03000_h.spikes'))
print('load randomForest')
clf = pickle.load(open("RandomForestOverlapModel.pickle", 'rb'))
state = 'single'
probs = (svm.c_double * 2)(0, 0)
pA = 1.
pB = 1.
maxamp = 0.
sigs_now = []
#H = np.zeros(256)
print('-')
counter = 0
tam = A.shape[0]
for i in xrange(tam):
if i % 10000 == 0:
from __future__ import division
import sys
import svm
import windowfile
import pickle
import numpy as np
import matplotlib.pyplot as plt
import scipy.signal as sg
print('load model')
model = svm.libsvm.svm_load_model('/ssd/15o04000_15o04001_h.svmmodel')
print('load A')
A = windowfile.readwins(open('/ssd/15o03000_h.features'))
print('load sig')
sig = windowfile.readwinsEx(open('/ssd/15o03000_h.spikes'))
print('load randomForest')
clf = pickle.load( open("RandomForestOverlapModel.pickle", 'rb'))
state = 'single'
probs = (svm.c_double*2)(0,0)
pA = 1.
pB = 1.
maxamp = 0.
sigs_now = []
#H = np.zeros(256)
print('-')
counter = 0
tam = A.shape[0]
for i in xrange(tam):
import sys
import numpy as np
import matplotlib.pyplot as plt
import windowfile
# | awk '{print $4" "$2 }' | sort
A = windowfile.readwins(open(sys.argv[1]))
B = windowfile.readwins(open(sys.argv[2]))
assert (A.shape[1] == B.shape[1])
for i in xrange(A.shape[1]):
plt.clf()
pdf, bins, patches = plt.hist((A[:, i], B[:, i]), bins=50, normed=True)
minpdf = np.min(np.vstack(pdf), axis=0)
overlap = np.sum(minpdf * np.diff(bins))
print('feature %4d overlap: %.10f' % (i, overlap))
sys.stdout.flush()
plt.savefig('out/fea%04d.png' % i)
