def test_kmp_precomputed_dictionary():
n_samples = mult_dense.shape[0]
cv = ShuffleSplit(n_samples,
n_iterations=1,
test_fraction=0.2,
random_state=0)
train, test = list(cv)[0]
X_train, y_train = mult_dense[train], mult_target[train]
X_test, y_test = mult_dense[test], mult_target[test]
components = select_components(X_train, y_train,
n_components=0.3,
random_state=0)
K_train = pairwise_kernels(X_train, components)
kmp = KMPClassifier(metric="precomputed")
kmp.fit(K_train, y_train)
y_pred = kmp.predict(K_train)
acc = np.mean(y_pred == y_train)
assert_true(acc >= 0.75)
K_test = pairwise_kernels(X_test, components)
y_pred = kmp.predict(K_test)
acc = np.mean(y_pred == y_test)
assert_true(acc >= 0.63)
def fit_kmp(X_train, y_train, X_test, y_test, class_distrib, opts, random_state):
components = select_components(X_train, y_train,
n_components=opts.n_components,
class_distrib=class_distrib,
random_state=random_state)
clf = KMPClassifier(n_nonzero_coefs=opts.n_nonzero_coefs,
init_components=components,
n_refit=opts.n_refit,
estimator=Ridge(alpha=opts.alpha),
X_val=X_test, y_val=y_test,
metric=opts.metric,
gamma=opts.gamma,
degree=opts.degree,
coef0=opts.coef0,
scale=opts.scale,
n_validate=opts.n_validate,
epsilon=opts.epsilon,
#score_func=f1_score,
verbose=1,
random_state=random_state,
n_jobs=-1)
clf.fit(X_train, y_train)
return clf
proportion_train=0.75,
random_state=random_state)
except KeyError:
raise ValueError("Wrong dataset name!")
print "X_train", X_train.shape
print "X_test", X_test.shape
# PCA view
print "Computing PCA..."
pca = RandomizedPCA(n_components=300)
X_train_pca = pca.fit_transform(X_train)
X_test_pca = pca.transform(X_test)
components_pca = select_components(X_train_pca, y_train,
n_components=opts.n_components,
class_distrib="balanced")
print "Computing kernels (PCA view)..."
K_pca_train = pairwise_kernels(X_train_pca, components_pca, metric="rbf",
gamma=0.1)
K_pca_test = pairwise_kernels(X_test_pca, components_pca, metric="rbf",
gamma=0.1)
# Regular view
components = select_components(X_train, y_train,
n_components=opts.n_components,
class_distrib="balanced")
print "Computing kernels (regular view)..."
K_train = pairwise_kernels(X_train, components, metric="rbf", gamma=0.1)
clf_s = []
clf_kg = []
clf_kb = []
clf_ks = []
j = 0
for X_tr, y_tr, X_te, y_te in split_data(X_train, y_train,
X_test, y_test,
opts.n_folds,
opts.cvtype,
opts.force_cv):
print "Fold", j
# selected from datasets
print "Selected components"
components = select_components(X_tr, y_tr, opts.n_components,
class_distrib=class_distrib, random_state=j)
clf_s.append(fit_kmp(X_tr, y_tr, X_te, y_te, components, opt_dict,
opts.regression, random_state=j))
# k-means global
print "Global k-means"
components = create_kmeans_comp(X_tr, y_tr,
n_components=opts.n_components,
class_distrib="global",
random_state=j)
clf_kg.append(fit_kmp(X_tr, y_tr, X_te, y_te, components, opt_dict,
opts.regression, random_state=j))
if not opts.regression:
# k-means balanced
print "Balanced k-means"
def test_kmp_select_components_stratified():
components = select_components(mult_dense, mult_target,
n_components=0.5,
class_distrib="stratified",
random_state=0)
assert_equal(components.shape[0], mult_dense.shape[0]/2-1)
dataset, opts, random_state = parse_kmp()
try:
X_train, y_train, X_test, y_test = load_dataset(dataset,
proportion_train=0.75,
random_state=random_state)
except KeyError:
raise ValueError("Wrong dataset name!")
print "X_train", X_train.shape
print "X_test", X_test.shape
class_distrib = "random" if opts.regression else "balanced"
components = select_components(X_train, y_train,
n_components=opts.n_components,
class_distrib=class_distrib)
print "Computing linear kernels..."
linear_train = pairwise_kernels(X_train, components, metric="linear")
linear_test = pairwise_kernels(X_test, components, metric="linear")
print "Computing rbf kernels..."
rbf_train = pairwise_kernels(X_train, components, metric="rbf",
gamma=opts.gamma)
rbf_test = pairwise_kernels(X_test, components, metric="rbf",
gamma=opts.gamma)
print "Computing polynomial kernels..."
poly_train = pairwise_kernels(X_train, components, metric="poly",
degree=opts.degree)