import numpy as np
import scipy.io as sio
from plottools import plotall
import pylab as P
sys.path.append('../PythonSrc')
import evaluation
import masking
import imputation
if __name__ == '__main__':
btchroma145 = sio.loadmat(
'/home/thierry/Columbia/covers80/coversongs/covers32k/Caroline_No/beach_boys+Pet_Sounds+13-Caroline_No.mp3.mat'
)['btchroma']
mask, masked_cols = masking.random_col_mask(btchroma145, ncols=1, win=30)
recon, lt = imputation.lintransform_cols(btchroma145,
mask,
masked_cols,
win=1)
pos1 = masked_cols[0] - 7
pos2 = masked_cols[0] + 7
im1 = btchroma145[:, pos1:pos2].copy()
im2 = (btchroma145 * mask)[:, pos1:pos2].copy()
im3 = recon[:, pos1:pos2].copy()
# plot all this
fig = P.figure()
fig.subplots_adjust(hspace=0.4)
blackbarsfun = lambda: P.gca().axvline(linewidth=2, color='0.', x=6.5
) and P.gca().axvline(
linewidth=2, color='0.', x=7.5)
def test_maskedcol_on_dataset(datasetdir,method='random',ncols=1,win=3,rank=4,codebook=None,**kwargs):
"""
General method to test a method on a whole dataset for one masked column
Methods are:
- random
- randomfromsong
- average
- codebook
- knn_eucl
- knn_kl
- lintrans
- siplca
- siplca2
Used arguments vary based on the method. For SIPLCA, we can use **kwargs
to set priors.
"""
# get all matfiles
matfiles = get_all_matfiles(datasetdir)
# init
total_cnt = 0
errs_eucl = []
errs_kl = []
# some specific inits
if codebook != None and not type(codebook) == type([]):
codebook = [p.reshape(12,codebook.shape[1]/12) for p in codebook]
print 'codebook in ndarray format transformed to list'
# iterate
for matfile in matfiles:
btchroma = sio.loadmat(matfile)['btchroma']
if len(btchroma.shape) < 2:
continue
if btchroma.shape[1] < MINLENGTH or np.isnan(btchroma).any():
continue
mask,masked_cols = MASKING.random_col_mask(btchroma,ncols=ncols,win=25)
########## ALGORITHM DEPENDENT
if method == 'random':
recon = IMPUTATION.random_col(btchroma,mask,masked_cols)
elif method == 'randomfromsong':
recon = IMPUTATION.random_col_from_song(btchroma,mask,masked_cols)
elif method == 'average':
recon = IMPUTATION.average_col(btchroma,mask,masked_cols,win=win)
elif method == 'codebook':
recon,used_codes = IMPUTATION.codebook_cols(btchroma,mask,masked_cols,codebook)
elif method == 'knn_eucl':
recon,used_cols = IMPUTATION.knn_cols(btchroma,mask,masked_cols,win=win,measure='eucl')
elif method == 'knn_kl':
recon,used_cols = IMPUTATION.knn_cols(btchroma,mask,masked_cols,win=win,measure='kl')
elif method == 'lintrans':
recon,proj = IMPUTATION.lintransform_cols(btchroma,mask,masked_cols,win=win)
elif method == 'siplca':
res = IMPUTATION_PLCA.SIPLCA_mask.analyze((btchroma*mask).copy(),
rank,mask,win=win,
convergence_thresh=1e-15,
**kwargs)
W, Z, H, norm, recon, logprob = res
elif method == 'siplca2':
res = IMPUTATION_PLCA.SIPLCA2_mask.analyze((btchroma*mask).copy(),
rank,mask,win=win,
convergence_thresh=1e-15,
**kwargs)
W, Z, H, norm, recon, logprob = res
else:
print 'unknown method:',method
return
########## ALGORITHM DEPENDENT END
# measure recon
err = recon_error(btchroma,mask,recon,measure='eucl')
if err > 100:
print 'huge EUCL error:',err,', method =',method,',file =',matfile
errs_eucl.append( err )
err = recon_error(btchroma,mask,recon,measure='kl')
if err > 100:
print 'huge KL error:',err,', method =',method,',file =',matfile
errs_kl.append( err )
total_cnt += 1
# done
print 'number of songs tested:',total_cnt
print 'average sq euclidean dist:',np.mean(errs_eucl),'(',np.std(errs_eucl),')'
print 'average kl divergence:',np.mean(errs_kl),'(',np.std(errs_kl),')'
def test_maskedcol_on_dataset(datasetdir,
method='random',
ncols=1,
win=3,
rank=4,
codebook=None,
**kwargs):
"""
General method to test a method on a whole dataset for one masked column
Methods are:
- random
- randomfromsong
- average
- codebook
- knn_eucl
- knn_kl
- lintrans
- siplca
- siplca2
Used arguments vary based on the method. For SIPLCA, we can use **kwargs
to set priors.
"""
# get all matfiles
matfiles = get_all_matfiles(datasetdir)
# init
total_cnt = 0
errs_eucl = []
errs_kl = []
# some specific inits
if codebook != None and not type(codebook) == type([]):
codebook = [p.reshape(12, codebook.shape[1] / 12) for p in codebook]
print 'codebook in ndarray format transformed to list'
# iterate
for matfile in matfiles:
btchroma = sio.loadmat(matfile)['btchroma']
if len(btchroma.shape) < 2:
continue
if btchroma.shape[1] < MINLENGTH or np.isnan(btchroma).any():
continue
mask, masked_cols = MASKING.random_col_mask(btchroma,
ncols=ncols,
win=25)
########## ALGORITHM DEPENDENT
if method == 'random':
recon = IMPUTATION.random_col(btchroma, mask, masked_cols)
elif method == 'randomfromsong':
recon = IMPUTATION.random_col_from_song(btchroma, mask,
masked_cols)
elif method == 'average':
recon = IMPUTATION.average_col(btchroma,
mask,
masked_cols,
win=win)
elif method == 'codebook':
recon, used_codes = IMPUTATION.codebook_cols(
btchroma, mask, masked_cols, codebook)
elif method == 'knn_eucl':
recon, used_cols = IMPUTATION.knn_cols(btchroma,
mask,
masked_cols,
win=win,
measure='eucl')
elif method == 'knn_kl':
recon, used_cols = IMPUTATION.knn_cols(btchroma,
mask,
masked_cols,
win=win,
measure='kl')
elif method == 'lintrans':
recon, proj = IMPUTATION.lintransform_cols(btchroma,
mask,
masked_cols,
win=win)
elif method == 'siplca':
res = IMPUTATION_PLCA.SIPLCA_mask.analyze((btchroma * mask).copy(),
rank,
mask,
win=win,
convergence_thresh=1e-15,
**kwargs)
W, Z, H, norm, recon, logprob = res
elif method == 'siplca2':
res = IMPUTATION_PLCA.SIPLCA2_mask.analyze(
(btchroma * mask).copy(),
rank,
mask,
win=win,
convergence_thresh=1e-15,
**kwargs)
W, Z, H, norm, recon, logprob = res
else:
print 'unknown method:', method
return
########## ALGORITHM DEPENDENT END
# measure recon
err = recon_error(btchroma, mask, recon, measure='eucl')
if err > 100:
print 'huge EUCL error:', err, ', method =', method, ',file =', matfile
errs_eucl.append(err)
err = recon_error(btchroma, mask, recon, measure='kl')
if err > 100:
print 'huge KL error:', err, ', method =', method, ',file =', matfile
errs_kl.append(err)
total_cnt += 1
# done
print 'number of songs tested:', total_cnt
print 'average sq euclidean dist:', np.mean(errs_eucl), '(', np.std(
errs_eucl), ')'
print 'average kl divergence:', np.mean(errs_kl), '(', np.std(errs_kl), ')'
import numpy as np
import scipy.io as sio
from plottools import plotall
import pylab as P
sys.path.append('../PythonSrc')
import evaluation
import masking
import imputation
if __name__ == '__main__':
btchroma145 = sio.loadmat('/home/thierry/Columbia/covers80/coversongs/covers32k/Caroline_No/beach_boys+Pet_Sounds+13-Caroline_No.mp3.mat')['btchroma']
mask,masked_cols = masking.random_col_mask(btchroma145,ncols=1,win=30)
recon,lt = imputation.lintransform_cols(btchroma145,mask,masked_cols,win=1)
pos1 = masked_cols[0] - 7
pos2 = masked_cols[0] + 7
im1 = btchroma145[:,pos1:pos2].copy()
im2 = (btchroma145 * mask)[:,pos1:pos2].copy()
im3 = recon[:,pos1:pos2].copy()
# plot all this
fig = P.figure()
fig.subplots_adjust(hspace=0.4)
blackbarsfun = lambda: P.gca().axvline(linewidth=2,color='0.',x=6.5) and P.gca().axvline(linewidth=2,color='0.',x=7.5)
plotall([im1,im2,im3],subplot=(3,1),cmap='gray_r',
title=['original','original masked','reconstruction'],
axvlines=blackbarsfun,colorbar=False,xticks=[()]*3)
P.show()