def main():
from sklearn.svm import NuSVR
X_train, X_test, y_train, y_test = bench.load_data(params)
y_train = np.asfortranarray(y_train).ravel()
if params.gamma is None:
params.gamma = 1.0 / X_train.shape[1]
cache_size_bytes = bench.get_optimal_cache_size(
X_train.shape[0], max_cache=params.max_cache_size)
params.cache_size_mb = cache_size_bytes / 1024**2
params.n_classes = len(np.unique(y_train))
regr = NuSVR(C=params.C,
nu=params.nu,
kernel=params.kernel,
cache_size=params.cache_size_mb,
tol=params.tol,
gamma=params.gamma,
degree=params.degree)
fit_time, _ = bench.measure_function_time(regr.fit,
X_train,
y_train,
params=params)
params.sv_len = regr.support_.shape[0]
predict_train_time, y_pred = bench.measure_function_time(regr.predict,
X_train,
params=params)
train_rmse = bench.rmse_score(y_train, y_pred)
train_r2 = bench.r2_score(y_train, y_pred)
_, y_pred = bench.measure_function_time(regr.predict,
X_test,
params=params)
test_rmse = bench.rmse_score(y_test, y_pred)
test_r2 = bench.r2_score(y_test, y_pred)
bench.print_output(
library='sklearn',
algorithm='nuSVR',
stages=['training', 'prediction'],
params=params,
functions=['NuSVR.fit', 'NuSVR.predict'],
times=[fit_time, predict_train_time],
metric_type=['rmse', 'r2_score', 'n_sv'],
metrics=[
[train_rmse, test_rmse],
[train_r2, test_r2],
[int(regr.n_support_.sum()),
int(regr.n_support_.sum())],
],
data=[X_train, X_train],
alg_instance=regr,
)
default=1e-3,
help='Tolerance passed to sklearn.svm.SVC')
parser.add_argument('--probability',
action='store_true',
default=False,
dest='probability',
help="Use probability for SVC")
params = bench.parse_args(parser)
X_train, X_test, y_train, y_test = bench.load_data(params)
if params.gamma is None:
params.gamma = 1.0 / X_train.shape[1]
cache_size_bytes = bench.get_optimal_cache_size(
X_train.shape[0], max_cache=params.max_cache_size)
params.cache_size_mb = cache_size_bytes / 1024**2
params.n_classes = y_train[y_train.columns[0]].nunique()
clf = SVC(C=params.C,
kernel=params.kernel,
cache_size=params.cache_size_mb,
tol=params.tol,
gamma=params.gamma,
probability=params.probability,
degree=params.degree)
fit_time, _ = bench.measure_function_time(clf.fit,
X_train,
y_train,
params=params)
def main():
from sklearn.svm import SVC
X_train, X_test, y_train, y_test = bench.load_data(params)
y_train = np.asfortranarray(y_train).ravel()
if params.gamma is None:
params.gamma = 1.0 / X_train.shape[1]
cache_size_bytes = bench.get_optimal_cache_size(
X_train.shape[0], max_cache=params.max_cache_size)
params.cache_size_mb = cache_size_bytes / 1024**2
params.n_classes = len(np.unique(y_train))
clf = SVC(C=params.C,
kernel=params.kernel,
cache_size=params.cache_size_mb,
tol=params.tol,
gamma=params.gamma,
probability=params.probability,
random_state=43,
degree=params.degree)
fit_time, _ = bench.measure_function_time(clf.fit,
X_train,
y_train,
params=params)
params.sv_len = clf.support_.shape[0]
if params.probability:
state_predict = 'predict_proba'
clf_predict = clf.predict_proba
train_acc = None
test_acc = None
predict_train_time, y_pred = bench.measure_function_time(clf_predict,
X_train,
params=params)
train_log_loss = bench.log_loss(y_train, y_pred)
train_roc_auc = bench.roc_auc_score(y_train, y_pred)
_, y_pred = bench.measure_function_time(clf_predict,
X_test,
params=params)
test_log_loss = bench.log_loss(y_test, y_pred)
test_roc_auc = bench.roc_auc_score(y_test, y_pred)
else:
state_predict = 'prediction'
clf_predict = clf.predict
train_log_loss = None
test_log_loss = None
train_roc_auc = None
test_roc_auc = None
predict_train_time, y_pred = bench.measure_function_time(clf_predict,
X_train,
params=params)
train_acc = bench.accuracy_score(y_train, y_pred)
_, y_pred = bench.measure_function_time(clf_predict,
X_test,
params=params)
test_acc = bench.accuracy_score(y_test, y_pred)
bench.print_output(
library='sklearn',
algorithm='SVC',
stages=['training', state_predict],
params=params,
functions=['SVM.fit', f'SVM.{state_predict}'],
times=[fit_time, predict_train_time],
metric_type=['accuracy', 'log_loss', 'roc_auc', 'n_sv'],
metrics=[
[train_acc, test_acc],
[train_log_loss, test_log_loss],
[train_roc_auc, test_roc_auc],
[int(clf.n_support_.sum()),
int(clf.n_support_.sum())],
],
data=[X_train, X_train],
alg_instance=clf,
)
def main():
from sklearn.svm import SVC
X_train, X_test, y_train, y_test = bench.load_data(params)
if params.gamma is None:
params.gamma = 1.0 / X_train.shape[1]
cache_size_bytes = bench.get_optimal_cache_size(
X_train.shape[0], max_cache=params.max_cache_size)
params.cache_size_mb = cache_size_bytes / 1024**2
params.n_classes = len(np.unique(y_train))
clf = SVC(C=params.C,
kernel=params.kernel,
cache_size=params.cache_size_mb,
tol=params.tol,
gamma=params.gamma,
probability=params.probability,
random_state=43)
fit_time, _ = bench.measure_function_time(clf.fit,
X_train,
y_train,
params=params)
params.sv_len = clf.support_.shape[0]
if params.probability:
state_predict = 'predict_proba'
accuracy_type = 'log_loss'
def metric_call(x, y):
return bench.log_loss(x, y)
clf_predict = clf.predict_proba
else:
state_predict = 'predict'
accuracy_type = 'accuracy[%]'
def metric_call(x, y):
return bench.accuracy_score(x, y)
clf_predict = clf.predict
predict_train_time, y_pred = bench.measure_function_time(clf_predict,
X_train,
params=params)
train_acc = metric_call(y_train, y_pred)
predict_test_time, y_pred = bench.measure_function_time(clf_predict,
X_test,
params=params)
test_acc = metric_call(y_test, y_pred)
bench.print_output(library='sklearn',
algorithm='svc',
stages=['training', state_predict],
params=params,
functions=['SVM.fit', f'SVM.{state_predict}'],
times=[fit_time, predict_train_time],
accuracy_type=accuracy_type,
accuracies=[train_acc, test_acc],
data=[X_train, X_train],
alg_instance=clf)
