def single_run(dkey, train_size, param, seed, profile=False):
print(
"Processing data set %s with train_size %s, seed %s, and parameters %s ..."
% (str(dkey), str(train_size), str(seed), str(param)))
if dkey == "covtype":
Xtrain, ytrain, Xtest, ytest = covtype(train_size=train_size,
seed=seed)
elif dkey == "higgs":
Xtrain, ytrain, Xtest, ytest = higgs(train_size=train_size, seed=seed)
elif dkey == "susy":
Xtrain, ytrain, Xtest, ytest = susy(train_size=train_size, seed=seed)
else:
raise Exception("Unknown data set!")
print("")
print("Number of training patterns:\t%i" % Xtrain.shape[0])
print("Number of test patterns:\t%i" % Xtest.shape[0])
print("Dimensionality of the data:\t%i\n" % Xtrain.shape[1])
model = WoodClassifier(n_estimators=param['n_estimators'],
criterion="gini",
max_features=param['max_features'],
min_samples_split=2,
n_jobs=param['n_jobs'],
seed=seed,
bootstrap=param['bootstrap'],
tree_traversal_mode="dfs",
tree_type=param['tree_type'],
min_samples_leaf=1,
float_type="double",
max_depth=None,
verbose=0)
if profile == True:
import yep
assert param['n_jobs'] == 1
yep.start("train.prof")
# training
fit_start_time = time.time()
model.fit(Xtrain, ytrain)
fit_end_time = time.time()
if profile == True:
yep.stop()
ypreds_train = model.predict(Xtrain)
# testing
test_start_time = time.time()
ypred_test = model.predict(Xtest)
test_end_time = time.time()
results = {}
results['dataset'] = dkey
results['param'] = param
results['training_time'] = fit_end_time - fit_start_time
results['testing_time'] = test_end_time - test_start_time
print("Training time: %f" % results['training_time'])
print("Testing time: %f" % results['testing_time'])
evaluate(ypreds_train, ytrain, results, "training")
evaluate(ypred_test, ytest, results, "testing")
fname = '%s_%s_%s_%s_%s_%s.json' % (
str(param['n_estimators']),
str(param['max_features']),
str(param['n_jobs']),
str(param['bootstrap']),
str(param['tree_type']),
str(seed),
)
fname = os.path.join(params.odir, str(dkey), str(train_size), "wood",
fname)
ensure_dir_for_file(fname)
with open(fname, 'w') as fp:
json.dump(results, fp)
Xtest = Xtest.astype(np.float32)
ytest = ytest.astype(np.float32)
print("")
print("Number of training patterns:\t%i" % Xtrain.shape[0])
print("Number of test patterns:\t%i" % Xtest.shape[0])
print("Dimensionality of the data:\t%i" % Xtrain.shape[1])
model = WoodClassifier(n_estimators=nr_tree,
criterion="gini",
max_features=None,
min_samples_split=2,
n_jobs=4,
seed=seed,
bootstrap=True,
tree_traversal_mode="dfs",
tree_type="standard",
min_samples_leaf=1,
float_type="double",
max_depth=None,
verbose=1)
fit_start_time = time.time()
model.fit(Xtrain, ytrain)
fit_end_time = time.time()
if (f_type == 0):
file_name = "./models/model_susy" + str(nr_tree) + "tree_4jobs.data"
elif (f_type == 1):
file_name = "./models/model_" + str(nr_tree) + "tree_4jobs.data"
model.save(file_name)