def benchmark_hybrid(dataset, bfs_threshold=None):
x_train, y_train = load_data(dataset)
# Just use this forest to compile the code.
throw_away = hybridForest(n_estimators=1, bootstrap=bootstrap, max_features=None, cpu_classifier=WiseRF)
throw_away.fit(x_train, y_train, bfs_threshold=bfs_threshold)
with timer("%s benchmark hybrid (bfs_threshold = %s)" % (dataset, bfs_threshold)):
forest = hybridForest(n_estimators=n_estimators, bootstrap=bootstrap, max_features=None, cpu_classifier=WiseRF)
forest.fit(x_train, y_train, bfs_threshold=bfs_threshold)
forest = None
def benchmark_cuda(dataset, bfs_threshold = None):
x_train, y_train = load_data(dataset)
#Just use this forest to compile the code.
throw_away = RandomForestClassifier(n_estimators = 1, bootstrap = bootstrap, verbose = False,
max_features = None, debug = debug)
throw_away.fit(x_train, y_train, bfs_threshold = bfs_threshold)
with timer("%s benchmark cuda (bfs_threshold = %s)" % (dataset, bfs_threshold)):
forest = RandomForestClassifier(n_estimators = n_estimators, bootstrap = bootstrap, verbose = verbose,
max_features = None, debug = debug)
forest.fit(x_train, y_train, bfs_threshold = bfs_threshold)
forest = None
def benchmark_hybrid(dataset, bfs_threshold=None):
x_train, y_train = load_data(dataset)
#Just use this forest to compile the code.
throw_away = hybridForest(n_estimators=2,
bootstrap=bootstrap,
max_features=None)
throw_away.fit(x_train, y_train, bfs_threshold=bfs_threshold)
with timer("%s benchmark hybrid (bfs_threshold = %s)" %
(dataset, bfs_threshold)):
forest = hybridForest(n_estimators=n_estimators,
bootstrap=bootstrap,
n_jobs=2,
max_features=None)
forest.fit(x_train, y_train, bfs_threshold=bfs_threshold)
forest = None
def benchmark_cuda(dataset, bfs_threshold=None):
x_train, y_train = load_data(dataset)
#Just use this forest to compile the code.
throw_away = RandomForestClassifier(n_estimators=1,
bootstrap=bootstrap,
verbose=False,
max_features=None,
debug=debug)
throw_away.fit(x_train, y_train, bfs_threshold=bfs_threshold)
with timer("%s benchmark cuda (bfs_threshold = %s)" %
(dataset, bfs_threshold)):
forest = RandomForestClassifier(n_estimators=n_estimators,
bootstrap=bootstrap,
verbose=verbose,
max_features=None,
debug=debug)
forest.fit(x_train, y_train, bfs_threshold=bfs_threshold)
forest = None
import numpy as np
from cudatree import load_data, RandomForestClassifier, timer
from cudatree import util
x, y = load_data("covtype")
x = x[:10000]
y = y[:10000]
def test_covtype_memorize():
with timer("Cuda treelearn"):
forest = RandomForestClassifier(bootstrap=False)
forest.fit(x, y, bfs_threshold=500000)
with timer("Predict"):
diff, total = util.test_diff(forest.predict(x), y)
print "%s(Wrong)/%s(Total). The error rate is %f." % (
diff, total, diff / float(total))
assert diff == 0, "Didn't perfectly memorize, got %d wrong" % diff
from helpers import compare_accuracy, compare_hybrid_accuracy
def test_covtype_accuracy():
compare_accuracy(x, y)
compare_hybrid_accuracy(x, y)
if __name__ == "__main__":
test_covtype_memorize()
test_covtype_accuracy()
import numpy as np
from cudatree import load_data, RandomForestClassifier, timer
from cudatree import util
x, y = load_data("digits")
n_estimators = 13
bootstrap = True
def test_digits_memorize():
with timer("Cuda treelearn"):
forest = RandomForestClassifier(n_estimators=n_estimators / 2,
bootstrap=False)
forest.fit(x, y)
with timer("Predict"):
diff, total = util.test_diff(forest.predict(x), y)
print("%s (Wrong) / %s (Total). The error rate is %f." %
(diff, total, diff / float(total)))
assert diff == 0, "Didn't memorize, got %d wrong" % diff
from .helpers import compare_accuracy
def test_digits_vs_sklearn():
compare_accuracy(x, y)
if __name__ == "__main__":
test_digits_memorize()
import numpy as np
from cudatree import load_data, RandomForestClassifier, timer
from cudatree import util
x,y = load_data("digits")
n_estimators = 13
bootstrap = True
def test_digits_memorize():
with timer("Cuda treelearn"):
forest = RandomForestClassifier(n_estimators = n_estimators/2, bootstrap = False)
forest.fit(x, y)
with timer("Predict"):
diff, total = util.test_diff(forest.predict(x), y)
print "%s (Wrong) / %s (Total). The error rate is %f." % (diff, total, diff/float(total))
assert diff == 0, "Didn't memorize, got %d wrong" % diff
from helpers import compare_accuracy
def test_digits_vs_sklearn():
compare_accuracy(x,y)
if __name__ == "__main__":
test_digits_memorize()
test_digits_vs_sklearn()
import numpy as np
from cudatree import load_data, RandomForestClassifier, timer
from cudatree import util
x, y = load_data("diabetes")
def test_diabetes_memorize():
with timer("Cuda treelearn"):
forest = RandomForestClassifier(bootstrap=False)
forest.fit(x, y)
with timer("Predict"):
diff, total = util.test_diff(forest.predict(x), y)
print "%s(Wrong)/%s(Total). The error rate is %f." % (
diff, total, diff / float(total))
assert diff == 0, "Didn't perfectly memorize, got %d wrong" % diff
from helpers import compare_accuracy, compare_hybrid_accuracy
def test_diabetes_accuracy():
compare_accuracy(x, y)
compare_hybrid_accuracy(x, y)
if __name__ == "__main__":
test_diabetes_memorize()
test_diabetes_accuracy()
import numpy as np
from cudatree import load_data, RandomForestClassifier, timer
from cudatree import util
x, y = load_data("iris")
def test_iris_memorize():
with timer("Cuda treelearn"):
forest = RandomForestClassifier(bootstrap=False)
forest.fit(x, y)
with timer("Predict"):
diff, total = util.test_diff(forest.predict(x), y)
print("%s(Wrong)/%s(Total). The error rate is %f." %
(diff, total, diff / float(total)))
assert diff == 0, "Didn't perfectly memorize, got %d wrong" % diff
from .helpers import compare_accuracy
def test_iris_accuracy():
compare_accuracy(x, y)
if __name__ == "__main__":
test_iris_memorize()
test_iris_accuracy()
import numpy as np
from cudatree import load_data, RandomForestClassifier, timer
from cudatree import util
x, y = load_data("diabetes")
def test_diabetes_memorize():
with timer("Cuda treelearn"):
forest = RandomForestClassifier(bootstrap = False)
forest.fit(x, y)
with timer("Predict"):
diff, total = util.test_diff(forest.predict(x), y)
print "%s(Wrong)/%s(Total). The error rate is %f." % (diff, total, diff/float(total))
assert diff == 0, "Didn't perfectly memorize, got %d wrong" % diff
from helpers import compare_accuracy, compare_hybrid_accuracy
def test_diabetes_accuracy():
compare_accuracy(x,y)
compare_hybrid_accuracy(x,y)
if __name__ == "__main__":
test_diabetes_memorize()
test_diabetes_accuracy()
import numpy as np
from cudatree import load_data, RandomForestClassifier, timer
from cudatree import util
x, y = load_data("covtype")
x = x[:10000]
y = y[:10000]
def test_covtype_memorize():
with timer("Cuda treelearn"):
forest = RandomForestClassifier(bootstrap = False)
forest.fit(x, y, bfs_threshold = 500000)
with timer("Predict"):
diff, total = util.test_diff(forest.predict(x), y)
print "%s(Wrong)/%s(Total). The error rate is %f." % (diff, total, diff/float(total))
assert diff == 0, "Didn't perfectly memorize, got %d wrong" % diff
from helpers import compare_accuracy, compare_hybrid_accuracy
def test_covtype_accuracy():
compare_accuracy(x,y)
compare_hybrid_accuracy(x, y)
if __name__ == "__main__":
test_covtype_memorize()
test_covtype_accuracy()
import numpy as np
from cudatree import load_data, RandomForestClassifier, timer
from cudatree import util
x, y = load_data("iris")
def test_iris_memorize():
with timer("Cuda treelearn"):
forest = RandomForestClassifier(bootstrap = False)
forest.fit(x, y)
with timer("Predict"):
diff, total = util.test_diff(forest.predict(x), y)
print "%s(Wrong)/%s(Total). The error rate is %f." % (diff, total, diff/float(total))
assert diff == 0, "Didn't perfectly memorize, got %d wrong" % diff
from helpers import compare_accuracy
def test_iris_accuracy():
compare_accuracy(x,y)
if __name__ == "__main__":
test_iris_memorize()
test_iris_accuracy()
