def test(nfiles):
X = []
Y = []
X_tst = []
Y_tst = []
ntrain = nfiles
ntest = 5*nfiles
print("Training/testing with %d/%d files." % (ntrain,ntest))
start = time.clock()
filename = '../maps/MAPS_AkPnCGdD_2/AkPnCGdD/MUS'
#filename = '../maps/MAPS_AkPnCGdD_1/AkPnCGdD/ISOL/NO'
files = dirs.get_files_with_extension(filename, '.mid')
train_files = files[:ntrain]
print("\t" + str(train_files))
#test_files = files[ntrain:ntest+ntrain]
# for legit testing
test_files = files[-ntest:]
map(per_file, train_files,
it.repeat(X, ntrain), it.repeat(Y, ntrain))
map(per_file, test_files,
it.repeat(X_tst, ntest), it.repeat(Y_tst, ntest))
end = time.clock()
print("\tRead time: %f" % (end - start))
print("\tnWindows train: " + str([X[i].shape[0] for i in range(len(X))]))
start = time.clock()
crf = ChainCRF(n_states=2)
clf = OneSlackSSVM(model=crf, C=100, n_jobs=-1,
inference_cache=100, tol=.1)
clf.fit(np.array(X), np.array(Y))
end = time.clock()
print("\tTrain time: %f" % (end - start))
start = time.clock()
Y_pred = clf.predict(X_tst)
comp = []
for i in range(len(Y_tst)):
for j in range(len(Y_tst[i])):
comp.append((Y_tst[i][j], Y_pred[i][j]))
print Y_tst[i][j],
print
for j in range(len(Y_tst[i])):
print Y_pred[i][j],
print
print
print("\tTrue positives: %d" % comp.count((1,1)))
print("\tTrue negatives: %d" % comp.count((0,0)))
print("\tFalse positives: %d" % comp.count((0,1)))
print("\tFalse negatives: %d" % comp.count((1,0)))
end = time.clock()
print("\tTest time: %f" % (end - start))
def test():
global posX, negX, posY, negY
# train_dir = '/home/charles/maps-data/maps/MAPS_AkPnCGdD_1/AkPnCGdD/ISOL'
# test_dir = '/home/charles/maps-data/maps/MAPS_AkPnCGdD_1/AkPnCGdD/RAND'
# train_file = '/home/charles/maps-data/maps/MAPS_AkPnCGdD_2/AkPnCGdD/MUS/MAPS_MUS-chpn_op10_e12_AkPnCGdD.mid'
# test_file = '/home/charles/maps-data/maps/MAPS_AkPnCGdD_2/AkPnCGdD/MUS/MAPS_MUS-grieg_kobold_AkPnCGdD.mid'
filename = '/home/charles/maps-data/maps/MAPS_AkPnCGdD_2/AkPnCGdD/MUS'
files = dirs.get_files_with_extension(filename, '.mid')
note = 60
for nindex in range(1, 100):
posX = []
negX = []
posY = []
negY = []
nfiles = nindex
ntrain = nfiles
ntest = 5*nfiles
train_files = files[:nfiles]
# print 'train_files: ' + str(train_files)
map(per_file(note), train_files)
print len(posX)
print len(negX)
ind = random.sample(range(len(negX)), len(posX))
X = []
X.extend(posX)
X.extend([negX[i] for i in ind])
Y = []
Y.extend(posY)
Y.extend([negY[i] for i in ind])
clf = svm.SVC(kernel='linear')
clf.fit(np.array(X), np.array(Y))
test_files = files[nfiles:nfiles+ntrain]
# print 'test_files: ' + str(test_files)
results = svm_test(clf, note, test_files)
print str(nfiles) + ' ' + ' '.join([str(r) for r in results])
