def test_perplexity(res_file, playlist_test_file, tag_test_file):
res = analyze.loadresult(res_file, [-1])[0]
playlists, tags = train_hte.loaddata(playlist_test_file, tag_test_file)
Pi = res[0]
Gt = res[1]
Tt = res[2]
A = res[3]
predictor = predict.NeitherPredictor(Pi, A, Gt, Tt)
print predictor.calc_perplexity(playlists, tags)
def test_tag_accuracy(res_file, tag_test_file, n):
res = analyze.loadresult(res_file, [-1])[0]
tag_true = train_hte.loaddata(None, tag_test_file)[1]
Pi = res[0]
Gt = res[1]
Tt = res[2]
A = res[3]
predictor = predict.Predictor(Pi, A, Gt, Tt)
tag_est = predictor.predict_tag(n)
return test_tag_acc(tag_est, tag_true)
def report_all(res_dir, playlist_test_file, tag_test_file):
files = os.listdir(res_dir)
files = [path.join(res_dir,f) for f in files if f.startswith('res')
and path.isfile(path.join(res_dir,f))]
playlists, tags = train_hte.loaddata(playlist_test_file, tag_test_file)
b = np.zeros((tags.shape[0], 250))
b[:,:tags.shape[1]] = tags
tags = b
stat = {}
for f in files:
print f
ss = f.split('-')
lam = float([k[1:] for k in ss if k.startswith('L')][0])
sc = float([k[2:] for k in ss if k.startswith('sc')][0])
ss = int([k[2:] for k in ss if k.startswith('ss')][0])
res = analyze.loadresult(f, [-1])[0]
Pi = res[0]
Gt = res[1]
Tt = res[2]
A = res[3]
predictor = predict.NeitherPredictor(Pi, A, Gt, Tt)
r = predictor.calc_perplexity(playlists, tags)
#r = (predictor.calc_hmm_perplexity(playlists),
# predictor.calc_lda_perplexity(tags))
print r, r[0]+lam*r[1]
if (lam,sc,ss) in stat:
stat[(lam,sc,ss)].append(r)
else:
stat[(lam,sc,ss)] = [r]
report = []
for k in stat:
ph = [x[0] for x in stat[k]]
pl = [x[1] for x in stat[k]]
report.append([k[0],k[1],k[2],np.mean(ph),np.std(ph),np.mean(pl),np.std(pl)])
report = np.array(report)
from scipy import io as sio
sio.savemat('report.mat', {'report':report})
return report