def compare_accuracy(x, y, n_estimators=11, bootstrap=True, slop=0.98, n_repeat=10):
n = x.shape[0] / 2
xtrain = x[:n]
ytrain = y[:n]
xtest = x[n:]
ytest = y[n:]
cudarf = RandomForestClassifier(n_estimators=n_estimators, bootstrap=bootstrap)
import sklearn.ensemble
skrf = sklearn.ensemble.RandomForestClassifier(n_estimators=n_estimators, bootstrap=bootstrap)
cuda_score_total = 0
sk_score_total = 0
for i in xrange(n_repeat):
cudarf.fit(xtrain, ytrain)
skrf.fit(xtrain, ytrain)
sk_score = skrf.score(xtest, ytest)
cuda_score = cudarf.score(xtest, ytest)
print "Iteration", i
print "Sklearn score", sk_score
print "CudaTree score", cuda_score
sk_score_total += sk_score
cuda_score_total += cuda_score
assert cuda_score_total >= (sk_score_total * slop), (
"Getting significantly worse test accuracy than sklearn: %s vs. %s"
% (cuda_score_total / n_repeat, sk_score_total / n_repeat)
)
def compare_accuracy(x,
y,
n_estimators=11,
bootstrap=True,
slop=0.98,
n_repeat=10):
n = x.shape[0] / 2
xtrain = x[:n]
ytrain = y[:n]
xtest = x[n:]
ytest = y[n:]
cudarf = RandomForestClassifier(n_estimators=n_estimators,
bootstrap=bootstrap)
import sklearn.ensemble
skrf = sklearn.ensemble.RandomForestClassifier(n_estimators=n_estimators,
bootstrap=bootstrap)
cuda_score_total = 0
sk_score_total = 0
for i in xrange(n_repeat):
cudarf.fit(xtrain, ytrain)
skrf.fit(xtrain, ytrain)
sk_score = skrf.score(xtest, ytest)
cuda_score = cudarf.score(xtest, ytest)
print "Iteration", i
print "Sklearn score", sk_score
print "CudaTree score", cuda_score
sk_score_total += sk_score
cuda_score_total += cuda_score
assert cuda_score_total >= (sk_score_total * slop), \
"Getting significantly worse test accuracy than sklearn: %s vs. %s"\
% (cuda_score_total / n_repeat, sk_score_total / n_repeat)
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
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
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
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_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
