def test_compare_sklearn(solver):
"""Test results against sklearn."""
def rmse(a, b):
return np.sqrt(np.mean((a - b) ** 2))
X, Y, coef_ = make_regression(
n_samples=1000, n_features=500,
noise=0.1, n_informative=10, coef=True,
random_state=42)
alpha = 0.1
l1_ratio = 0.5
clf = ElasticNet(alpha=alpha, l1_ratio=l1_ratio, tol=1e-5)
clf.fit(X, Y)
glm = GLM(distr='gaussian', alpha=l1_ratio, reg_lambda=alpha,
solver=solver, tol=1e-6, max_iter=500)
glm.fit(X, Y)
y_sk = clf.predict(X)
y_pg = glm.predict(X)
assert abs(rmse(Y, y_sk) - rmse(Y, y_pg)) < 0.5
glm = GLM(distr='gaussian', alpha=l1_ratio, reg_lambda=alpha,
solver=solver, tol=1e-6, max_iter=5, fit_intercept=False)
glm.fit(X, Y)
assert glm.beta0_ == 0.
glm.predict(X)
def test_api_input():
"""Test that the input value of y can be of different types."""
random_state = 1
state = np.random.RandomState(random_state)
n_samples, n_features = 100, 5
X = state.normal(0, 1, (n_samples, n_features))
y = state.normal(0, 1, (n_samples, ))
glm = GLM(distr='gaussian')
# Test that ValueError is raised when the shapes mismatch
with pytest.raises(ValueError):
GLM().fit(X, y[3:])
# This would work without errors
glm.fit(X, y)
glm.predict(X)
glm.score(X, y)
glm.plot_convergence()
glm = GLM(distr='gaussian', solver='test')
with pytest.raises(ValueError, match="solver must be one of"):
glm.fit(X, y)
with pytest.raises(ValueError, match="fit_intercept must be"):
glm = GLM(distr='gaussian', fit_intercept='blah')
glm = GLM(distr='gaussian', max_iter=2)
with pytest.warns(UserWarning, match='Reached max number of iterat'):
glm.fit(X, y)
def glm_bernoulli_pyglmnet(Xr, Yr, Xt):
#poissonexp isn't listed as an option for distr?
#glm = GLM(distr='poissonexp', alpha=0., reg_lambda=[0.], tol=1e-6)
glm = GLM(distr='binomial', alpha=0., reg_lambda=[0.], tol=1e-6)
glm.fit(Xr, Yr)
Yt = glm.predict(Xt)[0]
return Yt
def test_multinomial():
"""Test all multinomial functionality"""
glm_mn = GLM(distr='multinomial', reg_lambda=np.array([0.0, 0.1, 0.2]),
learning_rate = 2e-1, tol=1e-10)
X = np.array([[-1, -2, -3], [4, 5, 6]])
y = np.array([1, 0])
# test gradient
beta = np.zeros([4, 2])
grad_beta0, grad_beta = glm_mn._grad_L2loss(beta[0], beta[1:], 0, X, y)
assert_true(grad_beta0[0] != grad_beta0[1])
glm_mn.fit(X, y)
y_pred = glm_mn.predict(X)
assert_equal(y_pred.shape, (3, X.shape[0], 2)) # n_lambdas x n_samples x n_classes
# pick one as yhat
yhat = y_pred[0]
# uniform prediction
ynull = np.ones(yhat.shape) / yhat.shape[1]
# pseudo_R2 should be greater than 0
assert_true(glm_mn.score(y, yhat, ynull, method='pseudo_R2') > 0.)
glm_mn.score(y, yhat)
assert_equal(len(glm_mn.simulate(glm_mn.fit_[0]['beta0'],
glm_mn.fit_[0]['beta'],
X)),
X.shape[0])
# these should raise an exception
assert_raises(ValueError, glm_mn.score, y, y, y, 'pseudo_R2')
assert_raises(ValueError, glm_mn.score, y, y, None, 'deviance')
def test_multinomial():
"""Test all multinomial functionality"""
glm = GLM(distr='multinomial', reg_lambda=np.array([0.0, 0.1, 0.2]), tol=1e-10)
X = np.array([[-1, -2, -3], [4, 5, 6]])
y = np.array([1, 0])
# test gradient
beta = np.zeros([4, 2])
grad_beta0, grad_beta = glm.grad_L2loss(beta[0], beta[1:], 0, X, y)
assert grad_beta0[0] != grad_beta0[1]
glm.fit(X, y)
y_pred = glm.predict(X)
assert_equal(y_pred.shape, (3, X.shape[0], 2)) # n_lambdas x n_samples x n_classes
# pick one as yhat
yhat = y_pred[0]
# uniform prediction
ynull = np.ones(yhat.shape) / yhat.shape[1]
# pseudo_R2 should be greater than 0
assert_true(glm.pseudo_R2(y, yhat, ynull) > 0.)
glm.deviance(y, yhat)
assert_equal(len(glm.simulate(glm.fit_[0]['beta0'],
glm.fit_[0]['beta'],
X)),
X.shape[0])
# these should raise an exception
try:
glm.pseudo_R2(y, y, y)
assert False
except Exception:
assert True
try:
glm.deviance(y, y)
assert False
except Exception:
assert True
def test_multinomial():
"""Test all multinomial functionality"""
glm_mn = GLM(distr='multinomial',
reg_lambda=np.array([0.0, 0.1, 0.2]),
learning_rate=2e-1,
tol=1e-10)
X = np.array([[-1, -2, -3], [4, 5, 6]])
y = np.array([1, 0])
# test gradient
beta = np.zeros([4, 2])
grad_beta0, grad_beta = glm_mn._grad_L2loss(beta[0], beta[1:], 0, X, y)
assert_true(grad_beta0[0] != grad_beta0[1])
glm_mn.fit(X, y)
y_pred = glm_mn.predict(X)
assert_equal(y_pred.shape,
(3, X.shape[0], 2)) # n_lambdas x n_samples x n_classes
# pick one as yhat
yhat = y_pred[0]
# uniform prediction
ynull = np.ones(yhat.shape) / yhat.shape[1]
# pseudo_R2 should be greater than 0
assert_true(glm_mn.score(y, yhat, ynull, method='pseudo_R2') > 0.)
glm_mn.score(y, yhat)
assert_equal(
len(glm_mn.simulate(glm_mn.fit_[0]['beta0'], glm_mn.fit_[0]['beta'],
X)), X.shape[0])
# these should raise an exception
assert_raises(ValueError, glm_mn.score, y, y, y, 'pseudo_R2')
assert_raises(ValueError, glm_mn.score, y, y, None, 'deviance')
def test_glmnet():
"""Test glmnet."""
scaler = StandardScaler()
n_samples, n_features = 1000, 100
density = 0.1
n_lambda = 10
# coefficients
beta0 = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0)
beta = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0, [n_features, 1])
distrs = ['softplus', 'poisson', 'gaussian', 'binomial']
solvers = ['batch-gradient', 'cdfast']
score_metric = 'pseudo_R2'
learning_rate = 2e-1
for solver in solvers:
for distr in distrs:
glm = GLM(distr, learning_rate=learning_rate,
solver=solver, score_metric=score_metric)
assert_true(repr(glm))
np.random.seed(glm.random_state)
X_train = np.random.normal(0.0, 1.0, [n_samples, n_features])
y_train = glm.simulate(beta0, beta, X_train)
X_train = scaler.fit_transform(X_train)
glm.fit(X_train, y_train)
beta_ = glm.fit_[-1]['beta'][:]
assert_allclose(beta[:], beta_, atol=0.5) # check fit
y_pred = glm.predict(scaler.transform(X_train))
assert_equal(y_pred.shape, (n_lambda, X_train.shape[0]))
# checks for slicing.
glm = glm[:3]
glm_copy = glm.copy()
assert_true(glm_copy is not glm)
assert_equal(len(glm.reg_lambda), 3)
y_pred = glm[:2].predict(scaler.transform(X_train))
assert_equal(y_pred.shape, (2, X_train.shape[0]))
y_pred = glm[2].predict(scaler.transform(X_train))
assert_equal(y_pred.shape, (X_train.shape[0], ))
assert_raises(IndexError, glm.__getitem__, [2])
glm.score(X_train, y_train)
# don't allow slicing if model has not been fit yet.
glm_poisson = GLM(distr='softplus')
assert_raises(ValueError, glm_poisson.__getitem__, 2)
# test fit_predict
glm_poisson.fit_predict(X_train, y_train)
assert_raises(ValueError, glm_poisson.fit_predict, X_train[None, ...], y_train)
def test_glmnet():
"""Test glmnet."""
scaler = StandardScaler()
n_samples, n_features = 1000, 100
density = 0.1
n_lambda = 10
# coefficients
beta0 = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0)
beta = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0, [n_features, 1])
distrs = ['poisson', 'poissonexp', 'normal', 'binomial']
solvers = ['batch-gradient', 'cdfast']
learning_rate = 2e-1
for solver in solvers:
for distr in distrs:
glm = GLM(distr, learning_rate=learning_rate, solver=solver)
assert_true(repr(glm))
np.random.seed(glm.random_state)
X_train = np.random.normal(0.0, 1.0, [n_samples, n_features])
y_train = glm.simulate(beta0, beta, X_train)
X_train = scaler.fit_transform(X_train)
glm.fit(X_train, y_train)
beta_ = glm.fit_[-1]['beta'][:]
assert_allclose(beta[:], beta_, atol=0.5) # check fit
y_pred = glm.predict(scaler.transform(X_train))
assert_equal(y_pred.shape, (n_lambda, X_train.shape[0]))
# checks for slicing.
glm = glm[:3]
glm_copy = glm.copy()
assert_true(glm_copy is not glm)
assert_equal(len(glm.reg_lambda), 3)
y_pred = glm[:2].predict(scaler.transform(X_train))
assert_equal(y_pred.shape, (2, X_train.shape[0]))
y_pred = glm[2].predict(scaler.transform(X_train))
assert_equal(y_pred.shape, (X_train.shape[0], ))
assert_raises(IndexError, glm.__getitem__, [2])
glm.score(y_train, y_pred)
# don't allow slicing if model has not been fit yet.
glm_poisson = GLM(distr='poisson')
assert_raises(ValueError, glm_poisson.__getitem__, 2)
# test fit_predict
glm_poisson.fit_predict(X_train, y_train)
assert_raises(ValueError, glm_poisson.fit_predict, X_train[None, ...],
y_train)
def test_glmnet():
"""Test glmnet."""
scaler = StandardScaler()
n_samples, n_features = 10000, 100
density = 0.1
n_lambda = 10
# coefficients
beta0 = np.random.rand()
beta = sps.rand(n_features, 1, density=density).toarray()
distrs = ['poisson', 'poissonexp', 'normal', 'binomial']
for distr in distrs:
# FIXME: why do we need such this learning rate for 'poissonexp'?
learning_rate = 1e-5 if distr == 'poissonexp' else 1e-4
glm = GLM(distr, learning_rate=learning_rate)
assert_true(repr(glm))
np.random.seed(glm.random_state)
X_train = np.random.normal(0.0, 1.0, [n_samples, n_features])
y_train = glm.simulate(beta0, beta, X_train)
X_train = scaler.fit_transform(X_train)
glm.fit(X_train, y_train)
beta_ = glm.fit_[-2]['beta'][:]
assert_allclose(beta[:], beta_, atol=0.1) # check fit
density_ = np.sum(beta_ > 0.1) / float(n_features)
assert_allclose(density_, density, atol=0.05) # check density
y_pred = glm.predict(scaler.transform(X_train))
assert_equal(y_pred.shape, (n_lambda, X_train.shape[0]))
# checks for slicing.
glm = glm[:3]
glm_copy = glm.copy()
assert_true(glm_copy is not glm)
assert_equal(len(glm.reg_lambda), 3)
y_pred = glm[:2].predict(scaler.transform(X_train))
assert_equal(y_pred.shape, (2, X_train.shape[0]))
y_pred = glm[2].predict(scaler.transform(X_train))
assert_equal(y_pred.shape, (X_train.shape[0], ))
assert_raises(IndexError, glm.__getitem__, [2])
glm.deviance(y_train, y_pred)
# don't allow slicing if model has not been fit yet.
glm = GLM(distr='poisson')
assert_raises(ValueError, glm.__getitem__, 2)
# test fit_predict
glm.fit_predict(X_train, y_train)
assert_raises(ValueError, glm.fit_predict, X_train[None, ...], y_train)
def test_api_input_types_y():
"""Test that the input value of y can be of different types."""
random_state = 1
state = np.random.RandomState(random_state)
n_samples, n_features = 100, 5
X = state.normal(0, 1, (n_samples, n_features))
y = state.normal(0, 1, (n_samples, ))
glm = GLM(distr='gaussian')
# Test that a list will not work - the types have to be ndarray
with pytest.raises(ValueError):
glm.fit(X, list(y))
# Test that ValueError is raised when the shapes mismatch
with pytest.raises(ValueError):
GLM().fit(X, y[3:])
# This would work without errors
glm.fit(X, y)
glm.predict(X)
glm.score(X, y)
def test_glmnet():
"""Test glmnet."""
scaler = StandardScaler()
n_samples, n_features = 100, 10
# coefficients
beta0 = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0)
beta = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0, (n_features,))
distrs = ['softplus', 'gaussian', 'poisson', 'binomial', 'probit']
solvers = ['batch-gradient', 'cdfast']
score_metric = 'pseudo_R2'
learning_rate = 2e-1
for solver in solvers:
for distr in distrs:
glm = GLM(distr,
learning_rate=learning_rate,
solver=solver,
score_metric=score_metric)
assert_true(repr(glm))
np.random.seed(glm.random_state)
X_train = np.random.normal(0.0, 1.0, [n_samples, n_features])
y_train = simulate_glm(glm.distr, beta0, beta, X_train)
X_train = scaler.fit_transform(X_train)
glm.fit(X_train, y_train)
beta_ = glm.beta_
assert_allclose(beta, beta_, atol=0.5) # check fit
y_pred = glm.predict(scaler.transform(X_train))
assert_equal(y_pred.shape[0], X_train.shape[0])
# test fit_predict
glm_poisson = GLM(distr='softplus')
glm_poisson.fit_predict(X_train, y_train)
assert_raises(ValueError, glm_poisson.fit_predict, X_train[None, ...],
y_train)
def test_glmnet():
"""Test glmnet."""
scaler = StandardScaler()
n_samples, n_features = 100, 10
# coefficients
beta0 = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0)
beta = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0, (n_features,))
distrs = ['softplus', 'gaussian', 'poisson', 'binomial', 'probit']
solvers = ['batch-gradient', 'cdfast']
score_metric = 'pseudo_R2'
learning_rate = 2e-1
for solver in solvers:
for distr in distrs:
glm = GLM(distr, learning_rate=learning_rate,
solver=solver, score_metric=score_metric)
assert_true(repr(glm))
np.random.seed(glm.random_state)
X_train = np.random.normal(0.0, 1.0, [n_samples, n_features])
y_train = simulate_glm(glm.distr, beta0, beta, X_train)
X_train = scaler.fit_transform(X_train)
glm.fit(X_train, y_train)
beta_ = glm.beta_
assert_allclose(beta, beta_, atol=0.5) # check fit
y_pred = glm.predict(scaler.transform(X_train))
assert_equal(y_pred.shape[0], X_train.shape[0])
# test fit_predict
glm_poisson = GLM(distr='softplus')
glm_poisson.fit_predict(X_train, y_train)
assert_raises(ValueError, glm_poisson.fit_predict,
X_train[None, ...], y_train)
def test_multinomial():
"""Test all multinomial functionality"""
glm_mn = GLM(distr='multinomial',
reg_lambda=np.array([0.0, 0.1, 0.2]),
learning_rate=2e-1,
tol=1e-10)
X = np.array([[-1, -2, -3], [4, 5, 6]])
y = np.array([1, 0])
# test gradient
beta = np.zeros([4, 2])
grad_beta0, grad_beta = glm_mn._grad_L2loss(beta[0], beta[1:], 0, X, y)
assert_true(grad_beta0[0] != grad_beta0[1])
glm_mn.fit(X, y)
y_pred = glm_mn.predict(X)
assert_equal(y_pred.shape,
(3, X.shape[0], 2)) # n_lambdas x n_samples x n_classes
# pick one as yhat
yhat = y_pred[0]
# uniform prediction
ynull = np.ones(yhat.shape) / yhat.shape[1]
# pseudo_R2 should be greater than 0
assert_true(glm_mn[-1].score(X, y) > 0.)
assert_equal(
len(glm_mn.simulate(glm_mn.fit_[0]['beta0'], glm_mn.fit_[0]['beta'],
X)), X.shape[0])
# check that score is computed for sliced estimator
scorelist = glm_mn[-1].score(X, y)
assert_equal(scorelist.shape[0], 1)
# check that score is computed for all lambdas
scorelist = glm_mn.score(X, y)
assert_equal(scorelist.shape[0], y_pred.shape[0])
train_y = simulate_glm("neg-binomial", beta0, beta, train_x)
# plot the data distribution
sns.set(color_codes=True)
sns.distplot(train_y)
plt.show()
# Create the GLM and train it
glm = GLM(distr="neg-binomial", max_iter=10000)
glm.fit(train_x, train_y)
# Print the betas and the beta0 to check for correctness
print("")
print(glm.beta0_)
print(glm.beta_)
print("")
print(beta0)
print(beta)
# Generate test data
# simulate testing data
X_test = np.random.normal(0.0, 1.0, [1000, 10])
y_test = simulate_glm("poisson", beta0, beta, X_test)
# predict using fitted model on the test data
yhat_test = glm.predict(X_test)
# score the model
deviance = glm.score(X_test, y_test)
print(deviance)
print(position_array.shape)
pl.figure()
for n in range(n_frames):
pl.scatter(all_position[n, 0:4], all_position[n, 4:8], s=2, c='k')
pl.show()
# GLM
glm = GLM(distr='gaussian', alpha=0.05)
X = np.delete(all_position, 0, axis=1)
y = all_position[:, 0]
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.25,
random_state=42)
scaler = StandardScaler().fit(X_train)
glm.fit(scaler.transform(X_train), y_train)
yhat = glm.predict(scaler.transform(X))
# print(glm.score(X_test, Y_test))
#
# plot
pl.figure()
pl.plot(y, marker='x', color='b', label='observed')
pl.plot(yhat[9, :], marker='o', color='r', label='trained')
pl.show()
def test_glmnet(distr, reg_lambda, fit_intercept, solver):
"""Test glmnet."""
raises(ValueError, GLM, distr='blah')
raises(ValueError, GLM, distr='gaussian', max_iter=1.8)
n_samples, n_features = 100, 10
# coefficients
beta0 = 0.
if fit_intercept:
beta0 = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0)
beta = 1. / (np.float(n_features) + int(fit_intercept)) * \
np.random.normal(0.0, 1.0, (n_features,))
score_metric = 'pseudo_R2'
learning_rate = 2e-1
random_state = 0
betas_ = list()
if not (distr == 'gamma' and solver == 'cdfast'):
np.random.seed(random_state)
theta = 1.0
X_train = np.random.normal(0.0, 1.0, [n_samples, n_features])
y_train = simulate_glm(distr, beta0, beta, X_train, theta=theta,
sample=False)
alpha = 0.
loss_trace = list()
eta = 2.0
group = None
Tau = None
def callback(beta):
Tau = None
loss_trace.append(
_loss(distr, alpha, Tau, reg_lambda,
X_train, y_train, eta, theta, group, beta,
fit_intercept=fit_intercept))
glm = GLM(distr, learning_rate=learning_rate,
reg_lambda=reg_lambda, tol=1e-5, max_iter=5000,
alpha=alpha, solver=solver, score_metric=score_metric,
random_state=random_state, callback=callback,
fit_intercept=fit_intercept, theta=theta)
assert(repr(glm))
glm.fit(X_train, y_train)
# verify loss decreases
assert(np.all(np.diff(loss_trace) <= 1e-7))
# true loss and beta should be recovered when reg_lambda == 0
if reg_lambda == 0.:
# verify loss at convergence = loss when beta=beta_
l_true = _loss(distr, alpha, Tau, reg_lambda,
X_train, y_train, eta, theta, group,
np.concatenate(([beta0], beta)))
assert_allclose(loss_trace[-1], l_true, rtol=1e-4, atol=1e-5)
# beta=beta_ when reg_lambda = 0.
assert_allclose(beta, glm.beta_, rtol=0.05, atol=1e-2)
betas_.append(glm.beta_)
y_pred = glm.predict(X_train)
assert(y_pred.shape[0] == X_train.shape[0])
# compare all solvers pairwise to make sure they're close
for i, first_beta in enumerate(betas_[:-1]):
for second_beta in betas_[i + 1:]:
assert_allclose(first_beta, second_beta, rtol=0.05, atol=1e-2)
# test fit_predict
glm_poisson = GLM(distr='softplus')
glm_poisson.fit_predict(X_train, y_train)
raises(ValueError, glm_poisson.fit_predict,
X_train[None, ...], y_train)
def get_benchmarks(self, X_train, y_train, X_test, y_test):
"""
"""
n_repeats = self.n_repeats
distr = self.distr
res = dict()
for env in self.envs:
res[env] = dict()
if env == 'pyglmnet':
# initialize model
model = GLM(distr=distr,
reg_lambda=[self.reg_lambda],
alpha=self.alpha,
solver='batch-gradient',
score_metric='pseudo_R2')
# fit-predict-score
model.fit(X_train, y_train)
y_test_hat = model[-1].predict(X_test)
y_test_hat = np.squeeze(y_test_hat)
if distr in ['gaussian', 'poisson']:
res[env]['score'] = \
r2_score(y_test, y_test_hat)
elif distr == 'binomial':
res[env]['score'] = \
accuracy_score(y_test,
(y_test_hat > 0.5).astype(int))
# time
tmp = list()
for r in range(n_repeats):
start = time.time()
model.fit(X_train, y_train)
stop = time.time()
tmp.append(stop - start)
res[env]['time'] = np.min(tmp) * 1e3
if env == 'sklearn':
if distr in ['gaussian', 'binomial']:
# initialize model
if distr == 'gaussian':
model = ElasticNet(alpha=self.reg_lambda,
l1_ratio=self.alpha)
elif distr == 'binomial':
model = SGDClassifier(loss='log',
penalty='elasticnet',
alpha=self.reg_lambda,
l1_ratio=self.alpha)
# fit-predict-score
model.fit(X_train, y_train)
y_test_hat = model.predict(X_test)
res[env]['score'] = model.score(X_test, y_test)
# time
tmp = list()
for r in range(n_repeats):
start = time.time()
model.fit(X_train, y_train)
stop = time.time()
tmp.append(stop - start)
res[env]['time'] = np.min(tmp) * 1e3
else:
res[env]['score'] = -999.
res[env]['time'] = -999.
if env == 'statsmodels':
# initialize model
if distr == 'gaussian':
model = sm.GLM(y_train,
sm.add_constant(X_train),
family=sm.families.Gaussian())
elif distr == 'binomial':
model = sm.GLM(y_train,
sm.add_constant(X_train),
family=sm.families.Binomial())
elif distr == 'poisson':
model = sm.GLM(y_train,
sm.add_constant(X_train),
family=sm.families.Poisson())
# fit-predict-score
statsmodels_res = model.fit()
y_test_hat = model.predict(statsmodels_res.params,
exog=sm.add_constant(X_test))
y_test_hat = np.array(y_test_hat)
if distr in ['gaussian', 'poisson']:
res[env]['score'] = \
r2_score(y_test, y_test_hat)
elif distr == 'binomial':
res[env]['score'] = \
accuracy_score(y_test,
(y_test_hat > 0.5).astype(int))
# time
tmp = list()
for r in range(n_repeats):
start = time.time()
statsmodels_res = model.fit()
stop = time.time()
tmp.append(stop - start)
res[env]['time'] = np.min(tmp) * 1e3
if env == 'R':
# initialize model
glmnet = importr('glmnet')
predict = robjects.r('predict')
# fit-predict-score
try:
fit = glmnet.glmnet(X_train,
y_train,
family=distr,
alpha=self.alpha,
nlambda=1)
tmp = predict(fit, newx=X_test, s=0)
y_test_hat = np.zeros(y_test.shape[0])
for i in range(y_test.shape[0]):
y_test_hat[i] = tmp[i]
if distr in ['gaussian', 'poisson']:
res[env]['score'] = \
r2_score(y_test, y_test_hat)
elif distr == 'binomial':
res[env]['score'] = \
accuracy_score(y_test,
(y_test_hat > 0.5).astype(int))
# time
tmp = list()
for r in range(n_repeats):
start = time.time()
fit = glmnet.glmnet(X_train,
y_train,
family=distr,
alpha=self.alpha,
nlambda=1)
stop = time.time()
tmp.append(stop - start)
res[env]['time'] = np.min(tmp) * 1e3
except:
res[env]['score'] = -999.
res[env]['time'] = -999.
return res
def get_benchmarks(self, X_train, y_train, X_test, y_test):
"""
"""
n_repeats = self.n_repeats
distr = self.distr
res = dict()
for env in self.envs:
res[env] = dict()
if env == 'pyglmnet':
# initialize model
model = GLM(distr=distr,
reg_lambda=[self.reg_lambda],
alpha=self.alpha,
solver='batch-gradient',
score_metric='pseudo_R2')
# fit-predict-score
model.fit(X_train, y_train)
y_test_hat = model[-1].predict(X_test)
y_test_hat = np.squeeze(y_test_hat)
if distr in ['gaussian', 'poisson']:
res[env]['score'] = \
r2_score(y_test, y_test_hat)
elif distr == 'binomial':
res[env]['score'] = \
accuracy_score(y_test,
(y_test_hat > 0.5).astype(int))
# time
tmp = list()
for r in range(n_repeats):
start = time.time()
model.fit(X_train, y_train)
stop = time.time()
tmp.append(stop - start)
res[env]['time'] = np.min(tmp) * 1e3
if env == 'sklearn':
if distr in ['gaussian', 'binomial']:
# initialize model
if distr == 'gaussian':
model = ElasticNet(alpha=self.reg_lambda,
l1_ratio=self.alpha)
elif distr == 'binomial':
model = SGDClassifier(loss='log',
penalty='elasticnet',
alpha=self.reg_lambda,
l1_ratio=self.alpha)
# fit-predict-score
model.fit(X_train, y_train)
y_test_hat = model.predict(X_test)
res[env]['score'] = model.score(X_test, y_test)
# time
tmp = list()
for r in range(n_repeats):
start = time.time()
model.fit(X_train, y_train)
stop = time.time()
tmp.append(stop - start)
res[env]['time'] = np.min(tmp) * 1e3
else:
res[env]['score'] = -999.
res[env]['time'] = -999.
if env == 'statsmodels':
# initialize model
if distr == 'gaussian':
model = sm.GLM(y_train,
sm.add_constant(X_train),
family=sm.families.Gaussian())
elif distr == 'binomial':
model = sm.GLM(y_train,
sm.add_constant(X_train),
family=sm.families.Binomial())
elif distr == 'poisson':
model = sm.GLM(y_train,
sm.add_constant(X_train),
family=sm.families.Poisson())
# fit-predict-score
statsmodels_res = model.fit()
y_test_hat = model.predict(statsmodels_res.params,
exog=sm.add_constant(X_test))
y_test_hat = np.array(y_test_hat)
if distr in ['gaussian', 'poisson']:
res[env]['score'] = \
r2_score(y_test, y_test_hat)
elif distr == 'binomial':
res[env]['score'] = \
accuracy_score(y_test,
(y_test_hat > 0.5).astype(int))
# time
tmp = list()
for r in range(n_repeats):
start = time.time()
statsmodels_res = model.fit()
stop = time.time()
tmp.append(stop - start)
res[env]['time'] = np.min(tmp) * 1e3
if env == 'R':
# initialize model
glmnet = importr('glmnet')
predict = robjects.r('predict')
# fit-predict-score
try:
fit = glmnet.glmnet(X_train,
y_train,
family=distr,
alpha=self.alpha,
nlambda=1)
tmp = predict(fit, newx=X_test, s=0)
y_test_hat = np.zeros(y_test.shape[0])
for i in range(y_test.shape[0]):
y_test_hat[i] = tmp[i]
if distr in ['gaussian', 'poisson']:
res[env]['score'] = \
r2_score(y_test, y_test_hat)
elif distr == 'binomial':
res[env]['score'] = \
accuracy_score(y_test,
(y_test_hat > 0.5).astype(int))
# time
tmp = list()
for r in range(n_repeats):
start = time.time()
fit = glmnet.glmnet(X_train,
y_train,
family=distr,
alpha=self.alpha,
nlambda=1)
stop = time.time()
tmp.append(stop - start)
res[env]['time'] = np.min(tmp) * 1e3
except Exception:
res[env]['score'] = -999.
res[env]['time'] = -999.
return res
def test_glmnet():
"""Test glmnet."""
raises(ValueError, GLM, distr='blah')
raises(ValueError, GLM, distr='gaussian', max_iter=1.8)
n_samples, n_features = 100, 10
# coefficients
beta0 = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0)
beta = 1. / (np.float(n_features) + 1.) * \
np.random.normal(0.0, 1.0, (n_features,))
distrs = ['softplus', 'gaussian', 'poisson', 'binomial', 'probit']
solvers = ['batch-gradient', 'cdfast']
score_metric = 'pseudo_R2'
learning_rate = 2e-1
random_state = 0
for distr in distrs:
betas_ = list()
for solver in solvers:
np.random.seed(random_state)
X_train = np.random.normal(0.0, 1.0, [n_samples, n_features])
y_train = simulate_glm(distr, beta0, beta, X_train, sample=False)
alpha = 0.
reg_lambda = 0.
loss_trace = list()
def callback(beta):
Tau = None
eta = 2.0
group = None
loss_trace.append(
_loss(distr, alpha, Tau, reg_lambda, X_train, y_train, eta,
group, beta))
glm = GLM(distr,
learning_rate=learning_rate,
reg_lambda=reg_lambda,
tol=1e-3,
max_iter=5000,
alpha=alpha,
solver=solver,
score_metric=score_metric,
random_state=random_state,
callback=callback)
assert (repr(glm))
glm.fit(X_train, y_train)
# verify loss decreases
assert (np.all(np.diff(loss_trace) <= 1e-7))
# verify loss at convergence = loss when beta=beta_
l_true = _loss(distr, 0., np.eye(beta.shape[0]), 0., X_train,
y_train, 2.0, None, np.concatenate(([beta0], beta)))
assert_allclose(loss_trace[-1], l_true, rtol=1e-4, atol=1e-5)
# beta=beta_ when reg_lambda = 0.
assert_allclose(beta, glm.beta_, rtol=0.05, atol=1e-2)
betas_.append(glm.beta_)
y_pred = glm.predict(X_train)
assert (y_pred.shape[0] == X_train.shape[0])
# compare all solvers pairwise to make sure they're close
for i, first_beta in enumerate(betas_[:-1]):
for second_beta in betas_[i + 1:]:
assert_allclose(first_beta, second_beta, rtol=0.05, atol=1e-2)
# test fit_predict
glm_poisson = GLM(distr='softplus')
glm_poisson.fit_predict(X_train, y_train)
raises(ValueError, glm_poisson.fit_predict, X_train[None, ...], y_train)
########################################################
# **Fitting and predicting with a linear-Gaussian GLM**
#
# For a general linear model, the observed spikes can be
# thought of an underlying parameter
# :math:`\beta_0, \beta` that control the spiking.
#
# You can simply use linear Gaussian GLM with no regularization
# to predict the spike counts.
glm_lg = GLM(distr='gaussian', reg_lambda=0.0, score_metric='pseudo_R2')
glm_lg.fit(Xdsgn, y)
# predict spike counts
ypred_lg = glm_lg.predict(Xdsgn)
########################################################
# **Fitting and predicting with a Poisson GLM**
#
# We can also assume that there is a non-linear function governing
# the underlying the firing patterns.
# In pyglmnet, we use an exponential inverse link function
# for the Poisson distribution.
glm_poisson = GLM(distr='poisson',
alpha=0.05,
learning_rate=1.0,
score_metric='pseudo_R2',
reg_lambda=1e-7)
glm_poisson.fit(Xdsgn, y)