def t_test(name):
# if name == 'c20ng':
# return
dresults = experiment.read_csv(experiment.csv_path(name, "dag", "compare"))
tresults = experiment.read_csv(experiment.csv_path(name, "tree", "compare"))
dtst = [float(r["tst_llh"]) for r in dresults]
ttst = [float(r["tst_llh"]) for r in tresults]
dsize = [int(r["num_nodes"]) for r in dresults]
tsize = [int(r["num_nodes"]) for r in tresults]
dtime = [float(r["time"]) for r in dresults]
ttime = [float(r["time"]) for r in tresults]
print (name + " ")[:8], "\t%.4f" % np.mean(dtst), "\t%.4f" % np.mean(ttst), "\t", np.mean(dtst) > np.mean(
ttst
), "\t\t", "%6d" % int(np.mean(dsize)), "%7d" % int(np.mean(tsize)), "\t", "%.4f" % (
np.mean(dsize) / np.mean(tsize)
), "\t%8.2f" % np.mean(
dtime
), " %8.2f" % np.mean(
ttime
), np.mean(
dtime
) / np.mean(
ttime
),
from scipy import stats
print "\t", stats.ttest_ind(dtst, ttst, equal_var=False)[1] < 0.05
def best_grid_point(name, structure, dirname):
bp = experiment.csv_path(name, structure, dirname)
rows = experiment.read_csv(bp)
return best_row(rows)