dataset_name = args.dataset
if dataset_name == 'mnist' or dataset_name == 'iris' or dataset_name == '20news':
np.random.seed(0)
idx = np.random.permutation(xrange(X.shape[0]))[:args.subset]
X = X[idx]
y = y[idx]
if dataset_name == 'mnist' or dataset_name == '20news':
pca = PCA(10)
X = pca.fit_transform(X)
if dataset_name == 'zoo':
# pca = PCA(10)
# X = pca.fit_transform(X)
X += np.random.normal(size=X.shape) * 0.01
master_tree = make_master(X, y, args.dataset)
N, D = X.shape
C = pdist(X)
def make_tree(X, C, method='single'):
if method == 'single':
tree = to_tree(single(C))
elif method == 'ward':
tree = to_tree(ward(X))
elif method == 'average':
tree = to_tree(average(C))
return Tree(root=construct_node(tree))
def construct_node(snode):
if snode.left is None and snode.right is None:
X, y = dataset.X, dataset.y
if dataset_name == 'mnist' or dataset_name == 'iris' or dataset_name == '20news':
np.random.seed(0)
idx = np.random.permutation(xrange(X.shape[0]))[:args.subset]
X = X[idx]
y = y[idx]
if dataset_name == 'mnist' or dataset_name == '20news':
pca = PCA(10)
X = pca.fit_transform(X)
if dataset_name == 'zoo':
# pca = PCA(5)
# X = pca.fit_transform(X)
X += np.random.normal(size=X.shape) * 0.01
master_tree = make_master(X, y, dataset_name)
experiments = [('ddt', None),
('tr',
TotallyRandom(master_tree,
y,
classification=dataset_name != 'zoo')),
('str',
StupidRandom(master_tree,
y,
K=10,
classification=dataset_name != 'zoo')),
('sr',
SmartRandom(master_tree,
y,
classification=dataset_name != 'zoo')),
X, y = dataset.X, dataset.y
if dataset_name == 'mnist' or dataset_name == 'iris' or dataset_name == '20news':
np.random.seed(0)
idx = np.random.permutation(xrange(X.shape[0]))[:args.subset]
X = X[idx]
y = y[idx]
if dataset_name == 'mnist' or dataset_name == '20news':
pca = PCA(10)
X = pca.fit_transform(X)
if dataset_name == 'zoo':
# pca = PCA(5)
# X = pca.fit_transform(X)
X += np.random.normal(size=X.shape) * 0.01
master_tree = make_master(X, y, dataset_name)
experiments = [('ddt', None),
('tr', TotallyRandom(master_tree, y, classification=dataset_name != 'zoo')),
('str', StupidRandom(master_tree, y, K=10, classification=dataset_name != 'zoo')),
('sr', SmartRandom(master_tree, y, classification=dataset_name != 'zoo')),
('var', Variance(master_tree, y, N=20, K=10, classification=dataset_name != 'zoo')),
('hybrid', Hybrid(master_tree, y, N=20, K=10, classification=dataset_name != 'zoo'))
]
# plt.figure()
overall_cost, overall_score = [], []
samplers = []
for name, type in experiments:
logging.info("Running %s", name)
costs, scores, sampler = run_experiment(args.i, dataset_name, name, type, master_tree, X, y, out_dir,
dataset_name = args.dataset
if dataset_name == 'mnist' or dataset_name == 'iris' or dataset_name == '20news':
np.random.seed(0)
idx = np.random.permutation(xrange(X.shape[0]))[:args.subset]
X = X[idx]
y = y[idx]
if dataset_name == 'mnist' or dataset_name == '20news':
pca = PCA(10)
X = pca.fit_transform(X)
if dataset_name == 'zoo':
# pca = PCA(10)
# X = pca.fit_transform(X)
X += np.random.normal(size=X.shape) * 0.01
master_tree = make_master(X, y, args.dataset)
N, D = X.shape
C = pdist(X)
def make_tree(X, C, method='single'):
if method == 'single':
tree = to_tree(single(C))
elif method == 'ward':
tree = to_tree(ward(X))
elif method == 'average':
tree = to_tree(average(C))
return Tree(root=construct_node(tree))
