print misc.USAGE % __file__
sys.exit(-1)
else:
dataset = sys.argv[1]
print "Loading data ..."
data = misc.load_data(dataset)
# set sigma to something useful
from milk.unsupervised import pdist
sigma = np.median(pdist(data[0]))
print "Done, %s samples with %s features loaded into " "memory" % data[0].shape
score, res_shogun = misc.bench(bench_shogun, data)
print "Shogun: mean %.2f, std %.2f" % (np.mean(res_shogun), np.std(res_shogun))
print "Score: %.2f\n" % score
score, res_mdp = misc.bench(bench_mdp, data)
print "MDP: mean %.2f, std %.2f" % (np.mean(res_mdp), np.std(res_mdp))
print "Score: %.2f\n" % score
score, res_skl = misc.bench(bench_skl, data)
print "scikits.learn: mean %.2f, std %.2f" % (np.mean(res_skl), np.std(res_skl))
print "Score: %.2f\n" % score
score, res_mlpy = misc.bench(bench_mlpy, data)
print "MLPy: mean %.2f, std %.2f" % (np.mean(res_mlpy), np.std(res_mlpy))
print "Score: %.2f\n" % score
start = datetime.now()
clf = linear_model.LogisticRegression()
clf.fit(X, y)
score = np.mean(clf.predict(T) == valid)
return score, datetime.now() - start
if __name__ == '__main__':
import sys, misc
# don't bother me with warnings
import warnings; warnings.simplefilter('ignore')
np.seterr(all='ignore')
print __doc__ + '\n'
if not len(sys.argv) == 2:
print misc.USAGE % __file__
sys.exit(-1)
else:
dataset = sys.argv[1]
print 'Loading data ...'
data = misc.load_data(dataset)
print 'Done, %s samples with %s features loaded into ' \
'memory' % data[0].shape
res_skl = misc.bench(bench_skl, data)
print 'MLPy: mean %.2f, std %.2f\n' % (
np.mean(res_skl), np.std(res_skl))
]
elif dataset == 'cover_type':
array_data = [misc.load_cover_type(RND_SEED)]
elif dataset == 'higgs':
# We will select some samples for higgs as well
array_data = [
misc.load_higgs(random_state=RND_SEED, n_samples=ns)
for ns in N_SAMPLES
]
else:
raise ValueError('The dataset is not known. The possible choices are:'
' random')
# Save only the time for the moment
res_xgb = [[data[0].shape, p,
misc.bench(bench_xgb, data, n=n_try, **p)] for p in params_list
for data in array_data]
# Check that the path is existing
if not os.path.exists(store_dir):
os.makedirs(store_dir)
# Define the name depending of the type of classifier used
if type_tree == 'exact':
filename = 'xgboost_exact_nocache_' + dataset + '.pk'
elif type_tree == 'approx-global':
filename = 'xgboost_approx_global_' + dataset + '.pk'
elif type_tree == 'approx-local':
filename = 'xgboost_approx_local_' + dataset + '.pk'
store_filename = os.path.join(store_dir, filename)
if dataset == 'random':
array_data = [
misc.generate_samples(ns, nf, RND_SEED) for ns in N_SAMPLES
for nf in N_FEATURES
]
elif dataset == 'cover_type':
array_data = [misc.load_cover_type(RND_SEED)]
elif dataset == 'higgs':
# Select a subset of samples
array_data = [
misc.load_higgs(random_state=RND_SEED, n_samples=ns)
for ns in N_SAMPLES
]
else:
raise ValueError('The dataset is not known. The possible choices are:'
' random')
# Save only the time for the moment
res_lgbm = [[data[0].shape, p,
misc.bench(bench_lgbm, data, n=n_try, **p)]
for p in params_list for data in array_data]
# Check that the path is existing
if not os.path.exists(store_dir):
os.makedirs(store_dir)
filename = 'lightgbm_' + dataset + '.pk'
store_filename = os.path.join(store_dir, filename)
joblib.dump(res_lgbm, store_filename)
np.seterr(all='ignore')
print __doc__ + '\n'
if not len(sys.argv) == 2:
print misc.USAGE % __file__
sys.exit(-1)
else:
dataset = sys.argv[1]
print 'Loading data ...'
data = misc.load_data(dataset)
print 'Done, %s samples with %s features loaded into ' \
'memory' % data[0].shape
score, res_mdp = misc.bench(bench_mdp, data)
print 'MDP: mean %s, std %s' % (
np.mean(res_mdp), np.std(res_mdp))
print 'Explained variance: %s\n'% score
score, res_skl = misc.bench(bench_skl, data)
print 'scikits.learn: mean %.2f, std %.2f' % (
np.mean(res_skl), np.std(res_skl))
print 'Explained variance: %s\n'% score
score, res_pybrain = misc.bench(bench_pybrain, data)
print 'Pybrain: mean %s, std %s' % (
np.mean(res_pybrain), np.std(res_pybrain))
print 'Explained variance: %s\n'% score
score, res_milk = misc.bench(bench_milk, data)
import sys, misc
# don't bother me with warnings
import warnings; warnings.simplefilter('ignore')
np.seterr(all='ignore')
print __doc__ + '\n'
if not len(sys.argv) == 2:
print misc.USAGE
sys.exit(-1)
else:
dataset = sys.argv[1]
print 'Loading data ...'
data = misc.load_data(dataset)
print 'Done, %s samples with %s features loaded into ' \
'memory' % data[0].shape
score, res_skl = misc.bench(bench_skl, data)
print 'scikits.learn: mean %s, std %s' % (res_skl.mean(), res_skl.std())
print 'MSE ', score
score, res_mlpy = misc.bench(bench_mlpy, data)
print 'MLPy: mean %s, std %s' % (res_mlpy.mean(), res_mlpy.std())
print 'MSE ', score
score, res_pymvpa = misc.bench(bench_pymvpa, data)
print 'PyMVPA: mean %s, std %s' % (res_pymvpa.mean(), res_pymvpa.std())
print 'MSE ', score
import warnings
warnings.simplefilter('ignore')
np.seterr(all='ignore')
print __doc__ + '\n'
if not len(sys.argv) == 2:
print misc.USAGE % __file__
sys.exit(-1)
else:
dataset = sys.argv[1]
print 'Loading data ...'
data = misc.load_data(dataset)
print 'Done, %s samples with %s features loaded into ' \
'memory' % data[0].shape
score, res_skl = misc.bench(bench_skl, data)
print 'scikits.learn: mean %.2f, std %.2f' % (np.mean(res_skl),
np.std(res_skl))
print 'MSE: %s\n' % score
score, res_mlpy = misc.bench(bench_mlpy, data)
print 'MLPy: mean %.2f, std %.2f' % (np.mean(res_mlpy), np.std(res_mlpy))
print 'MSE: %s\n' % score
score, res_pymvpa = misc.bench(bench_pymvpa, data)
print 'PyMVPA: mean %.2f, std %.2f' % (np.mean(res_pymvpa),
np.std(res_pymvpa))
print 'MSE: %s\n' % score
print misc.USAGE % __file__
sys.exit(-1)
else:
dataset = sys.argv[1]
print 'Loading data ...'
data = misc.load_data(dataset)
# set sigma to something useful
from milk.unsupervised import pdist
sigma = np.median(pdist(data[0]))
print 'Done, %s samples with %s features loaded into ' \
'memory' % data[0].shape
score, res_shogun = misc.bench(bench_shogun, data)
print 'Shogun: mean %.2f, std %.2f' % (
np.mean(res_shogun), np.std(res_shogun))
print 'Score: %.2f\n' % score
score, res_mdp = misc.bench(bench_mdp, data)
print 'MDP: mean %.2f, std %.2f' % (
np.mean(res_mdp), np.std(res_mdp))
print 'Score: %.2f\n' % score
score, res_skl = misc.bench(bench_skl, data)
print 'scikits.learn: mean %.2f, std %.2f' % (
np.mean(res_skl), np.std(res_skl))
print 'Score: %.2f\n' % score
score, res_mlpy = misc.bench(bench_mlpy, data)
np.seterr(all='ignore')
print __doc__ + '\n'
if not len(sys.argv) == 2:
print misc.USAGE % __file__
sys.exit(-1)
else:
dataset = sys.argv[1]
print 'Loading data ...'
data = misc.load_data(dataset)
print 'Done, %s samples with %s features loaded into ' \
'memory' % data[0].shape
score, res_mdp = misc.bench(bench_mdp, data)
print 'MDP: mean %s, std %s' % (np.mean(res_mdp), np.std(res_mdp))
print 'Explained variance: %s\n' % score
score, res_skl = misc.bench(bench_skl, data)
print 'scikits.learn: mean %.2f, std %.2f' % (np.mean(res_skl),
np.std(res_skl))
print 'Explained variance: %s\n' % score
score, res_pybrain = misc.bench(bench_pybrain, data)
print 'Pybrain: mean %s, std %s' % (np.mean(res_pybrain),
np.std(res_pybrain))
print 'Explained variance: %s\n' % score
score, res_milk = misc.bench(bench_milk, data)
print 'milk: mean %s, std %s' % (np.mean(res_milk), np.std(res_milk))
if __name__ == '__main__':
import sys, misc
# don't bother me with warnings
import warnings; warnings.simplefilter('ignore')
np.seterr(all='ignore')
print __doc__ + '\n'
if not len(sys.argv) == 2:
print misc.USAGE
sys.exit(-1)
else:
dataset = sys.argv[1]
print 'Loading data ...'
data = misc.load_data(dataset)
print 'Done, %s samples with %s features loaded into ' \
'memory' % data[0].shape
## score, res_skl = misc.bench(bench_skl, data)
## print 'scikits.learn: mean %s, std %s' % (res_skl.mean(), res_skl.std())
score, res_mlpy = misc.bench(bench_mlpy, data)
print 'MLPy: mean %s, std %s' % (res_mlpy.mean(), res_mlpy.std())
## score, res_pymvpa = misc.bench(bench_pymvpa, data)
## print 'PyMVPA: mean %s, std %s' % (res_pymvpa.mean(), res_pymvpa.std())
#
from milk.unsupervised import pca as milk_pca
start = datetime.now()
_ = milk_pca(X)
return datetime.now() - start
if __name__ == '__main__':
# don't bother me with warnings
import warnings; warnings.simplefilter('ignore')
np.seterr(all='ignore')
print __doc__ + '\n'
res_mdp = bench(bench_mdp)
print 'MDP: mean %s, std %s' % (
np.mean(res_mdp), np.std(res_mdp))
res_skl = bench(bench_skl)
print 'scikits.learn: mean %s, std %s' % (
np.mean(res_skl), np.std(res_skl))
res_pybrain = bench(bench_pybrain)
print 'Pybrain: mean %s, std %s' % (
np.mean(res_pybrain), np.std(res_pybrain))
res_milk = bench(bench_milk)
print 'milk: mean %s, std %s' % (
np.mean(res_milk), np.std(res_milk))
np.seterr(all='ignore')
print __doc__ + '\n'
if not len(sys.argv) == 2:
print misc.USAGE % __file__
sys.exit(-1)
else:
dataset = sys.argv[1]
print 'Loading data ...'
data = misc.load_data(dataset)
print 'Done, %s samples with %s features loaded into ' \
'memory' % data[0].shape
score, res_shogun = misc.bench(bench_shogun, data)
print 'Shogun: mean %.2f, std %.2f' % (
np.mean(res_shogun), np.std(res_shogun))
print 'Score: %2f\n' % score
score, res_mdp = misc.bench(bench_mdp, data)
print 'MDP: mean %.2f, std %.2f' % (
np.mean(res_mdp), np.std(res_mdp))
print 'Score: %2f\n' % score
score, res_skl = misc.bench(bench_skl, data)
print 'scikits.learn: mean %.2f, std %.2f' % (
np.mean(res_skl), np.std(res_skl))
print 'Score: %2f\n' % score
score, res_mlpy = misc.bench(bench_mlpy, data)
np.seterr(all='ignore')
print __doc__ + '\n'
if not len(sys.argv) == 2:
print misc.USAGE % __file__
sys.exit(-1)
else:
dataset = sys.argv[1]
print 'Loading data ...'
data = misc.load_data(dataset)
print 'Done, %s samples with %s features loaded into ' \
'memory' % data[0].shape
res_shogun = misc.bench(bench_shogun, data)
print 'Shogun: mean %.2f, std %.2f\n' % (res_shogun.mean(), res_shogun.std())
res_mdp = misc.bench(bench_mdp, data)
print 'MDP: mean %.2f, std %.2f\n' % (res_mdp.mean(), res_mdp.std())
res_skl = misc.bench(bench_skl, data)
print 'scikits.learn: mean %.2f, std %.2f\n' % (res_skl.mean(), res_skl.std())
res_mlpy = misc.bench(bench_mlpy, data)
print 'MLPy: mean %.2f, std %.2f\n' % (res_mlpy.mean(), res_mlpy.std())
res_milk = misc.bench(bench_milk, data)
print 'milk: mean %.2f, std %.2f\n' % (res_milk.mean(), res_milk.std())
res_pymvpa = misc.bench(bench_pymvpa, data)