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_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_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 test_tikhonov():
"""Tikhonov regularization test."""
n_samples, n_features = 100, 10
# design covariance matrix of parameters
Gam = 15.
PriorCov = np.zeros([n_features, n_features])
for i in np.arange(0, n_features):
for j in np.arange(i, n_features):
PriorCov[i, j] = np.exp(-Gam * 1. / (np.float(n_features) ** 2) *
(np.float(i) - np.float(j)) ** 2)
PriorCov[j, i] = PriorCov[i, j]
if i == j:
PriorCov[i, j] += 0.01
PriorCov = 1. / np.max(PriorCov) * PriorCov
# sample parameters as multivariate normal
beta0 = np.random.randn()
beta = np.random.multivariate_normal(np.zeros(n_features), PriorCov)
# sample train and test data
glm_sim = GLM(distr='softplus', score_metric='pseudo_R2')
X = np.random.randn(n_samples, n_features)
y = simulate_glm(glm_sim.distr, beta0, beta, X)
from sklearn.cross_validation import train_test_split
Xtrain, Xtest, ytrain, ytest = \
train_test_split(X, y, test_size=0.5, random_state=42)
# design tikhonov matrix
[U, S, V] = np.linalg.svd(PriorCov, full_matrices=False)
Tau = np.dot(np.diag(1. / np.sqrt(S)), U)
Tau = 1. / np.sqrt(np.float(n_samples)) * Tau / Tau.max()
# fit model with batch gradient
glm_tikhonov = GLM(distr='softplus',
alpha=0.0,
Tau=Tau,
solver='batch-gradient',
tol=1e-5,
score_metric='pseudo_R2')
glm_tikhonov.fit(Xtrain, ytrain)
R2_train, R2_test = dict(), dict()
R2_train['tikhonov'] = glm_tikhonov.score(Xtrain, ytrain)
R2_test['tikhonov'] = glm_tikhonov.score(Xtest, ytest)
# fit model with cdfast
glm_tikhonov = GLM(distr='softplus',
alpha=0.0,
Tau=Tau,
solver='cdfast',
tol=1e-5,
score_metric='pseudo_R2')
glm_tikhonov.fit(Xtrain, ytrain)
R2_train, R2_test = dict(), dict()
R2_train['tikhonov'] = glm_tikhonov.score(Xtrain, ytrain)
R2_test['tikhonov'] = glm_tikhonov.score(Xtest, ytest)
def test_tikhonov():
"""Tikhonov regularization test."""
n_samples, n_features = 100, 10
# design covariance matrix of parameters
Gam = 15.
PriorCov = np.zeros([n_features, n_features])
for i in np.arange(0, n_features):
for j in np.arange(i, n_features):
PriorCov[i, j] = np.exp(-Gam * 1. / (np.float(n_features) ** 2) *
(np.float(i) - np.float(j)) ** 2)
PriorCov[j, i] = PriorCov[i, j]
if i == j:
PriorCov[i, j] += 0.01
PriorCov = 1. / np.max(PriorCov) * PriorCov
# sample parameters as multivariate normal
beta0 = np.random.randn()
beta = np.random.multivariate_normal(np.zeros(n_features), PriorCov)
# sample train and test data
glm_sim = GLM(distr='softplus', score_metric='pseudo_R2')
X = np.random.randn(n_samples, n_features)
y = simulate_glm(glm_sim.distr, beta0, beta, X)
from sklearn.model_selection import train_test_split
Xtrain, Xtest, ytrain, ytest = \
train_test_split(X, y, test_size=0.5, random_state=42)
# design tikhonov matrix
[U, S, V] = np.linalg.svd(PriorCov, full_matrices=False)
Tau = np.dot(np.diag(1. / np.sqrt(S)), U)
Tau = 1. / np.sqrt(np.float(n_samples)) * Tau / Tau.max()
# fit model with batch gradient
glm_tikhonov = GLM(distr='softplus',
alpha=0.0,
Tau=Tau,
solver='batch-gradient',
tol=1e-3,
score_metric='pseudo_R2')
glm_tikhonov.fit(Xtrain, ytrain)
R2_train, R2_test = dict(), dict()
R2_train['tikhonov'] = glm_tikhonov.score(Xtrain, ytrain)
R2_test['tikhonov'] = glm_tikhonov.score(Xtest, ytest)
# fit model with cdfast
glm_tikhonov = GLM(distr='softplus',
alpha=0.0,
Tau=Tau,
solver='cdfast',
tol=1e-3,
score_metric='pseudo_R2')
glm_tikhonov.fit(Xtrain, ytrain)
R2_train, R2_test = dict(), dict()
R2_train['tikhonov'] = glm_tikhonov.score(Xtrain, ytrain)
R2_test['tikhonov'] = glm_tikhonov.score(Xtest, ytest)
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']
learning_rate = 2e-1
for distr in distrs:
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=0.5) # 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.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_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_proba = glm_mn.predict_proba(X)
assert_equal(y_pred_proba.shape, (3, X.shape[0], 2)) # n_lambdas x n_samples x n_classes
# pick one as yhat
yhat = y_pred_proba[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_proba.shape[0])
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_accuracy():
"""Testing accuracy."""
n_samples, n_features, n_classes = 1000, 100, 2
beta0 = np.random.normal(0.0, 1.0, 1)
beta = np.random.normal(0.0, 1.0, (n_features, n_classes))
# sample train and test data
glm_sim = GLM(distr='binomial', score_metric='accuracy')
X = np.random.randn(n_samples, n_features)
y = simulate_glm(glm_sim.distr, beta0, beta, X)
y = np.argmax(y, axis=1)
glm_sim.fit(X, y)
score = glm_sim.score(X, y)
assert_true(isinstance(score, float))
def test_deviance():
"""Test deviance."""
n_samples, n_features = 1000, 100
beta0 = np.random.normal(0.0, 1.0, 1)
beta = np.random.normal(0.0, 1.0, n_features)
# sample train and test data
glm_sim = GLM(score_metric='deviance')
X = np.random.randn(n_samples, n_features)
y = simulate_glm(glm_sim.distr, beta0, beta, X)
glm_sim.fit(X, y)
score = glm_sim.score(X, y)
assert_true(isinstance(score, float))
def test_pseudoR2():
"""Test pseudo r2."""
n_samples, n_features = 1000, 100
beta0 = np.random.rand()
beta = np.random.normal(0.0, 1.0, n_features)
# sample train and test data
glm_sim = GLM(score_metric='pseudo_R2')
X = np.random.randn(n_samples, n_features)
y = simulate_glm(glm_sim.distr, beta0, beta, X)
glm_sim.fit(X, y)
score = glm_sim.score(X, y)
assert (isinstance(score, float))
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_proba = glm_mn.predict_proba(X)
assert_equal(y_pred_proba.shape,
(3, X.shape[0], 2)) # n_lambdas x n_samples x n_classes
# pick one as yhat
yhat = y_pred_proba[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_proba.shape[0])
########################################################
# Fit models
from sklearn.cross_validation import train_test_split
Xtrain, Xtest, Ytrain, Ytest = train_test_split(features, spike_counts, test_size=0.2, random_state=42)
########################################################
from pyglmnet import utils
n_samples = Xtrain.shape[0]
Tau = utils.tikhonov_from_prior(prior_cov, n_samples)
glm = GLM(distr='poisson', alpha=0., Tau=Tau, score_metric='pseudo_R2')
glm.fit(Xtrain, Ytrain)
cvopt_lambda = glm.score(Xtest, Ytest).argmax()
print("train score: %f" % glm[cvopt_lambda].score(Xtrain, Ytrain))
print("test score: %f" % glm[cvopt_lambda].score(Xtest, Ytest))
weights = glm[cvopt_lambda].fit_['beta']
########################################################
# Visualize
for time_bin_ in range(n_temporal_basis):
RF = strf_model.make_image_from_spatial_basis(spatial_basis,
weights[range(time_bin_,
n_spatial_basis * n_temporal_basis,
n_temporal_basis)])
plt.subplot(1, n_temporal_basis, time_bin_+1)
plt.imshow(RF, cmap='Blues', interpolation='none')
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)
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
reg_lambda=np.logspace(np.log(100), np.log(0.01), 5, base=np.exp(1)))
print("gl_glm: ", gl_glm)
print("glm: ", glm)
##########################################################
# Fit models
gl_glm.fit(Xtrain, ytrain)
glm.fit(Xtrain, ytrain)
##########################################################
# Visualize model scores on test set
plt.figure()
plt.semilogx(gl_glm.reg_lambda, gl_glm.score(Xtest, ytest), 'go-')
plt.semilogx(gl_glm.reg_lambda, gl_glm.score(Xtrain, ytrain), 'go--')
plt.semilogx(glm.reg_lambda, glm.score(Xtest, ytest), 'ro-')
plt.semilogx(glm.reg_lambda, glm.score(Xtrain, ytrain), 'ro--')
plt.legend(
['Group Lasso: test', 'Group Lasso: train', 'Lasso: test', 'Lasso: train'],
frameon=False,
loc='best')
plt.xlabel('$\lambda$')
plt.ylabel('pseudo-$R^2$')
plt.ylim([-0.1, 0.7])
plt.tick_params(axis='y', right='off')
plt.tick_params(axis='x', top='off')
ax = plt.gca()
ax.spines['top'].set_visible(False)
from sklearn.cross_validation import train_test_split
Xtrain, Xtest, Ytrain, Ytest = train_test_split(features,
spike_counts,
test_size=0.2,
random_state=42)
########################################################
from pyglmnet import utils
n_samples = Xtrain.shape[0]
Tau = utils.tikhonov_from_prior(prior_cov, n_samples)
glm = GLM(distr='poisson', alpha=0., Tau=Tau, score_metric='pseudo_R2')
glm.fit(Xtrain, Ytrain)
cvopt_lambda = glm.score(Xtest, Ytest).argmax()
print("train score: %f" % glm[cvopt_lambda].score(Xtrain, Ytrain))
print("test score: %f" % glm[cvopt_lambda].score(Xtest, Ytest))
weights = glm[cvopt_lambda].fit_['beta']
########################################################
# Visualize
for time_bin_ in range(n_temporal_basis):
RF = strf_model.make_image_from_spatial_basis(
spatial_basis,
weights[range(time_bin_, n_spatial_basis * n_temporal_basis,
n_temporal_basis)])
plt.subplot(1, n_temporal_basis, time_bin_ + 1)
plt.imshow(RF, cmap='Blues', interpolation='none')
markerline.set_markerfacecolor('none')
plt.plot(t_sample,
ypred_lg[sample_idx],
color='gold',
linewidth=2,
label='lgGLM with offset')
plt.plot(t_sample,
ypred_poisson[sample_idx],
color='green',
linewidth=2,
label='poissonGLM')
plt.plot(t_sample,
ypred_poisson_hist[sample_idx],
color='red',
linewidth=2,
label='poissonGLM_hist')
plt.xlim([0., tmax])
plt.title('Spike count prediction')
plt.xlabel('Time (sec)')
plt.ylabel('Binned Spike Counts')
plt.legend()
plt.show()
# print scores of all the fitted models
print('Training perf (R^2): lin-gauss GLM, w/ offset: {:.2f}'.format(
glm_lg.score(Xdsgn, y)))
print('Training perf (R^2): Pyglmnet possion GLM {:.2f}'.format(
glm_poisson.score(Xdsgn, y)))
print('Training perf (R^2): Pyglmnet poisson GLM w/ spikes history {:.2f}'.
format(glm_poisson_hist.score(Xdsgn_hist, y)))