def run_theano_binary_asgd_speed():
N_POINTS = 500
sizes=[1e2, 1e3, 1e4, 1e5]
dtypes=['float32', 'float64']
rstate = RandomState(42)
XX, y = get_fake_data(N_POINTS, max(sizes), rstate)
dtype_orig = theano.config.floatX
for dtype in dtypes:
theano.config.floatX = dtype
for N_FEATURES in sizes:
X = XX[:,:N_FEATURES].astype(dtype)
kwargs = dict(DEFAULT_KWARGS)
kwargs['sgd_step_size0'] = None
kwargs['dtype'] = dtype
clf0 = NaiveBinaryASGD(N_FEATURES, rstate=copy(rstate), **kwargs)
clf1 = TheanoBinaryASGD(N_FEATURES, rstate=copy(rstate), **kwargs)
t = time.time()
clf0.fit(X, y)
t0 = time.time() - t
t = time.time()
clf1.fit(X, y)
t1 = time.time() - t
print 'N_FEAT:%i dtype:%s Naive:%.3f Theano:%.3f' % (
N_FEATURES, dtype, t0, t1)
theano.config.floatX = dtype_orig
def test_theano_binary_asgd_early_stopping():
rstate = RandomState(42)
X, y = get_fake_data(N_POINTS, N_FEATURES, rstate)
Xtst, ytst = get_fake_data(N_POINTS, N_FEATURES, rstate)
kwargs = dict(DEFAULT_KWARGS)
kwargs['n_iterations'] = 30
clf0 = NaiveBinaryASGD(*DEFAULT_ARGS, rstate=copy(rstate), **kwargs)
clf1 = TheanoBinaryASGD(*DEFAULT_ARGS, rstate=copy(rstate), **kwargs)
clf0.fit(X, y)
clf1.fit(X, y)
assert clf0.n_observations == clf1.n_observations
assert clf0.n_observations < N_POINTS * kwargs['n_iterations']
def test_theano_binary_asgd_like_naive_asgd():
rstate = RandomState(42)
X, y = get_fake_data(N_POINTS, N_FEATURES, rstate)
Xtst, ytst = get_fake_data(N_POINTS, N_FEATURES, rstate)
clf0 = NaiveBinaryASGD(*DEFAULT_ARGS, rstate=copy(rstate), **DEFAULT_KWARGS)
clf1 = TheanoBinaryASGD(*DEFAULT_ARGS, rstate=copy(rstate), **DEFAULT_KWARGS)
clf1.min_n_iterations = clf1.n_iterations
for clf in [clf0, clf1]:
clf.fit(X, y)
ytrn_preds = clf.predict(X)
ytst_preds = clf.predict(Xtst)
ytrn_acc = (ytrn_preds == y).mean()
ytst_acc = (ytst_preds == y).mean()
assert_equal(ytrn_acc, 0.72)
assert_equal(ytst_acc, 0.522)
def test_binary_fit():
rstate = RandomState(42)
n_features = 20
for L in [100, DEFAULT_MAX_EXAMPLES, int(DEFAULT_MAX_EXAMPLES * 1.5),
int(DEFAULT_MAX_EXAMPLES * 3)]:
clf = get_new_model(n_features, rstate, L)
X, y = get_fake_data(L, n_features, rstate, separation=0.1)
best = find_sgd_step_size0(clf, (X, y))
_clf = binary_fit(clf, (X, y))
assert _clf is clf
assert 0 < clf.sgd_step_size0 <= best
def test_binary_sgd_step_size0():
rstate = RandomState(42)
n_features = 20
X, y = get_fake_data(100, n_features, rstate)
clf = get_new_model(n_features, rstate, 100)
best0 = find_sgd_step_size0(clf, (X, y))
print best0
assert np.allclose(best0, 0.04, atol=.1, rtol=.5)
# find_sgd_step_size0 does not change clf
assert clf.sgd_step_size0 == 1000.0
def test_fit_replicable():
n_features = 20
X, y = get_fake_data(100, n_features, RandomState(4))
m0 = get_new_model(n_features, RandomState(45))
m0 = binary_fit(m0, X, y)
m1 = get_new_model(n_features, RandomState(45))
m1 = binary_fit(m1, X, y)
assert_array_equal(m0.sgd_weights, m1.sgd_weights)
assert_array_equal(m0.sgd_bias, m1.sgd_bias)
def test_binary_fit():
rstate = RandomState(42)
n_features = 20
clf100 = get_new_model(n_features, rstate)
X, y = get_fake_data(100, n_features, rstate)
_clf100 = binary_fit(clf100, X, y)
assert _clf100 is clf100
assert_almost_equal(clf100.sgd_step_size0, 0.04812, decimal=4)
# smoke test
clf1000 = get_new_model(n_features, rstate)
X, y = get_fake_data(DEFAULT_MAX_EXAMPLES, n_features, rstate)
_clf1000 = binary_fit(clf1000, X, y)
assert _clf1000 is clf1000
assert_almost_equal(clf1000.sgd_step_size0, 0.0047, decimal=4)
# smoke test that at least it runs
clf2000 = get_new_model(n_features, rstate)
X, y = get_fake_data(2000, n_features, rstate)
_clf2000 = binary_fit(clf2000, X, y)
assert _clf2000 == clf2000
assert_almost_equal(clf2000.sgd_step_size0, 0.0067, decimal=4)
def test_fit_replicable():
n_features = 20
X, y = get_fake_data(100, n_features, RandomState(4))
m0 = get_new_model(n_features, RandomState(45), 100)
m0 = binary_fit(m0, (X, y))
m1 = get_new_model(n_features, RandomState(45), 100)
m1 = binary_fit(m1, (X, y))
assert_array_equal(m0.sgd_weights, m1.sgd_weights)
assert_array_equal(m0.sgd_bias, m1.sgd_bias)
def test_binary_fit():
rstate = RandomState(42)
n_features = 20
clf100 = get_new_model(n_features, rstate)
X, y = get_fake_data(100, n_features, rstate)
_clf100 = binary_fit(clf100, X, y)
assert _clf100 is clf100
assert_almost_equal(clf100.sgd_step_size0, 0.04812, decimal=4)
# smoke test
clf1000 = get_new_model(n_features, rstate)
X, y = get_fake_data(DEFAULT_MAX_EXAMPLES, n_features, rstate)
_clf1000 = binary_fit(clf1000, X, y)
assert _clf1000 is clf1000
assert_almost_equal(clf1000.sgd_step_size0, 0.0047, decimal=4)
# smoke test that at least it runs
clf2000 = get_new_model(n_features, rstate)
X, y = get_fake_data(2000, n_features, rstate)
_clf2000 = binary_fit(clf2000, X, y)
assert _clf2000 == clf2000
assert_almost_equal(clf2000.sgd_step_size0, 0.0067, decimal=4)
def test_binary_sgd_step_size0():
rstate = RandomState(42)
n_features = 20
X, y = get_fake_data(100, n_features, rstate)
clf = get_new_model(n_features, rstate)
best = find_sgd_step_size0(clf, X, y, (.25, .5))
assert_almost_equal(best, -4.9927, decimal=4)
# start a little lower, still works
best = find_sgd_step_size0(clf, X, y, (.125, .25))
assert_almost_equal(best, -4.6180, decimal=4)
# find_sgd_step_size0 does not change clf
assert clf.sgd_step_size0 == 1000.0
def test_binary_sgd_step_size0():
rstate = RandomState(42)
n_features = 20
X, y = get_fake_data(100, n_features, rstate)
clf = get_new_model(n_features, rstate)
best = find_sgd_step_size0(clf, X, y, (.25, .5))
assert_almost_equal(best, -4.9927, decimal=4)
# start a little lower, still works
best = find_sgd_step_size0(clf, X, y, (.125, .25))
assert_almost_equal(best, -4.6180, decimal=4)
# find_sgd_step_size0 does not change clf
assert clf.sgd_step_size0 == 1000.0
