def main():
sarcos_dir = os.path.join(os.getenv("SIGVISA_HOME"), "papers", "product_tree", "sarcos")
sarcos_train_X, sarcos_train_y, sarcos_test_X, sarcos_test_y, hyperparams = load_sarcos(sdir=sarcos_dir)
np.save(os.path.join(sarcos_dir, "testX.npy"), sarcos_test_X)
np.save(os.path.join(sarcos_dir, "testy.npy"), sarcos_test_y)
np.save(os.path.join(sarcos_dir, "hyperparams.npy"), hyperparams)
print "loaded sarcos data and converted to numpy format"
train_realdata_gp(sarcos_dir, sarcos_train_X, sarcos_train_y, hyperparams)
print "trained model"
test_predict(sarcos_dir)
print "evaluated predictions"
eval_gp(bdir=sarcos_dir, test_n=100)
print "timings finished"
def cov_timing(cv_dir, lscale, order, n_azi_buckets):
sgp = SparseGP(fname=os.path.join(cv_dir, "fold_00.gp%d_%d_%d" % (lscale, order, n_azi_buckets)))
X = np.loadtxt(os.path.join(cv_dir, "X.txt"))
test_idx = np.array([int(z) for z in np.loadtxt(os.path.join(cv_dir, "fold_00_test.txt"))])
testX = X[test_idx]
resultfile = os.path.join(cv_dir, "results_gp%d_%d_%d.txt" % (lscale, order, n_azi_buckets))
errorfile = os.path.join(cv_dir, "error_gp%d_%d_%d.npz" % (lscale, order, n_azi_buckets))
eval_gp(gp=sgp, testX=testX, resultfile=resultfile, errorfile=errorfile)
poly = LinearBasisModel(fname=os.path.join(cv_dir, "fold_00.poly_%d_%d" % (order, n_azi_buckets)))
resultfile_poly = os.path.join(cv_dir, "results_poly_%d_%d.txt" % (order, n_azi_buckets))
f = open(resultfile_poly, 'w')
test_n = len(test_idx)
poly_covars = np.zeros((test_n,))
t0 = time.time()
for i in range(test_n):
poly_covars[i] = poly.covariance(testX[i:i+1,:])
t1 = time.time()
f.write("cov time %f\n" % ((t1-t0)/test_n))
f.close()
def learn_gp(X, y):
p = np.random.permutation(len(y))
train_n = int(len(y) * 0.2)
trainX = X[p[:train_n], :]
trainy = y[p[:train_n]]
testX = X[p[train_n:], :]
testy = y[p[train_n:]]
fitz_dir = os.path.join(os.getenv("SIGVISA_HOME"), "papers", "product_tree", "fitz_learned")
# hyperparams = np.array([0.5, 3.0, 50.0, 50.0], dtype=float)
# hyperparams = learn_hyperparams(fitz_dir, trainX, trainy, dfn_str='lld', hyperparams=hyperparams, sparse_invert=False, basisfns = [lambda x : 1,], param_cov=np.array(((10000,),)), param_mean = np.array((0,)), k=1000)
# print "got hyperparams", hyperparams
# hyperparams = np.array([1.16700753, 2.53145332, 212.46536884,157.68719303], dtype=float)
np.save(os.path.join(fitz_dir, "testX.npy"), testX)
np.save(os.path.join(fitz_dir, "testy.npy"), testy)
np.save(os.path.join(fitz_dir, "hyperparams.npy"), hyperparams)
print "loaded data"
train_realdata_gp(
fitz_dir,
trainX,
trainy,
hyperparams=hyperparams,
sparse_invert=False,
basisfns=[lambda x: 1],
param_cov=np.array(((10000,),)),
param_mean=np.array((0,)),
dfn_str="lld",
)
test_predict(fitz_dir)
eval_gp(bdir=fitz_dir, test_n=100)
def main(n_max=18000):
rundir = sys.argv[1]
task_name = sys.argv[2]
basedir = os.path.join(os.getenv('SIGVISA_HOME'), 'papers', 'product_tree', 'run', rundir)
basename = os.path.join(basedir, task_name)
X_train = np.loadtxt(basename + '_X_train.txt', delimiter=',')
y_train = np.loadtxt(basename + '_y_train.txt', delimiter=',')
n_X = X_train.shape[0]
if n_X > n_max:
X_train = np.array(X_train[:n_max,:], copy=True)
y_train = np.array(y_train[:n_max], copy=True)
print "using restricted subset of %d training points" % (n_max)
actual_n = min(n_X, n_max)
X_test = np.loadtxt(basename + '_X_test.txt', delimiter=',')
y_test = np.loadtxt(basename + '_y_test.txt', delimiter=',')
"""
#for nu in (90,):
nu = 90
csficbase = basename + '_csfic_%d' % nu if nu is not None else basename + '_csfic'
csficmodel_dir = basename + "_py_csfic_%d" % nu if nu is not None else basename + "_py_csfic"
print csficmodel_dir
#if not os.path.exists(csficbase):
# continue
csgp = os.path.join(csficmodel_dir, 'trained_%d.gp' % actual_n)
mkdir_p(csficmodel_dir)
if os.path.exists(csgp):
gp_csfic = SparseGP_CSFIC(fname=csgp, build_tree=True, leaf_bin_size=15)
else:
gp_csfic = load_matlab_csficmodel(csficbase, X_train, y_train)
gp_csfic.save_trained_model(csgp)
#print "testing predictions"
#test_predict(csficmodel_dir, sgp=gp_csfic, testX=X_test, testy=y_test)
#print "testing cutoff rule 0"
#eval_gp(bdir=csficmodel_dir, testX=X_test, test_n=200, gp=gp_csfic, cutoff_rule=0)
#print "testing cutoff rule 1"
#eval_gp(bdir=csficmodel_dir, testX=X_test, test_n=200, gp=gp_csfic, cutoff_rule=1)
#print "testing cutoff rule 2"
#eval_gp(bdir=csficmodel_dir, testX=X_test, test_n=200, gp=gp_csfic, cutoff_rule=2)
print "testing leaf bins 15"
gp_csfic10 = SparseGP_CSFIC(fname=csgp, build_tree=True, leaf_bin_size=10)
eval_gp(bdir=csficmodel_dir, testX=X_test, test_n=200, gp=gp_csfic10, cutoff_rule=2, flag="_bin15")
#print "testing leaf bins 100"
#gp_csfic50 = SparseGP_CSFIC(fname=csgp, build_tree=True, leaf_bin_size=50)
#eval_gp(bdir=csficmodel_dir, testX=X_test, test_n=200, gp=gp_csfic50, cutoff_rule=2, flag="_bin50")
"""
semodel_dir = basename + "_py_se"
segp = os.path.join(semodel_dir, 'trained.gp')
mkdir_p(semodel_dir)
if os.path.exists(segp):
gp_se = SparseGP(fname=segp, build_tree=True, leaf_bin_size=0, sparse_invert=False)
else:
gp_se = load_matlab_semodel(basename, X_train, y_train)
gp_se.save_trained_model(segp)
test_predict(semodel_dir, sgp=gp_se, testX=X_test, testy=y_test)
eval_gp(bdir=semodel_dir, testX=X_test, test_n=200, gp=gp_se)
