def main():
from sklearn.decomposition import PCA
# Load random data
X_train, X_test, _, _ = bench.load_data(params, generated_data=['X_train'])
if params.n_components is None:
p, n = X_train.shape
params.n_components = min((n, (2 + min((n, p))) // 3))
# Create our PCA object
pca = PCA(svd_solver=params.svd_solver, whiten=params.whiten,
n_components=params.n_components)
# Time fit
fit_time, _ = bench.measure_function_time(pca.fit, X_train, params=params)
# Time transform
transform_time, _ = bench.measure_function_time(
pca.transform, X_train, params=params)
bench.print_output(library='sklearn', algorithm='pca',
stages=['training', 'transformation'],
params=params, functions=['PCA.fit', 'PCA.transform'],
times=[fit_time, transform_time], accuracy_type=None,
accuracies=[None, None], data=[X_train, X_test],
alg_instance=pca)
def main():
from sklearn.ensemble import RandomForestClassifier
# Load and convert data
X_train, X_test, y_train, y_test = bench.load_data(params)
# Create our random forest classifier
clf = RandomForestClassifier(criterion=params.criterion,
n_estimators=params.num_trees,
max_depth=params.max_depth,
max_features=params.max_features,
min_samples_split=params.min_samples_split,
max_leaf_nodes=params.max_leaf_nodes,
min_impurity_decrease=params.min_impurity_decrease,
bootstrap=params.bootstrap,
random_state=params.seed,
n_jobs=params.n_jobs)
params.n_classes = len(np.unique(y_train))
fit_time, _ = bench.measure_function_time(clf.fit, X_train, y_train, params=params)
y_pred = clf.predict(X_train)
train_acc = 100 * accuracy_score(y_pred, y_train)
predict_time, y_pred = bench.measure_function_time(
clf.predict, X_test, params=params)
test_acc = 100 * accuracy_score(y_pred, y_test)
bench.print_output(library='sklearn', algorithm='decision_forest_classification',
stages=['training', 'prediction'], params=params,
functions=['df_clsf.fit', 'df_clsf.predict'],
times=[fit_time, predict_time], accuracy_type='accuracy[%]',
accuracies=[train_acc, test_acc], data=[X_train, X_test],
alg_instance=clf)
def main():
from sklearn.linear_model import LogisticRegression
# Load generated data
X_train, X_test, y_train, y_test = bench.load_data(params)
params.n_classes = len(np.unique(y_train))
if params.multiclass == 'auto':
params.multiclass = 'ovr' if params.n_classes == 2 else 'multinomial'
if not params.tol:
params.tol = 1e-3 if params.solver == 'newton-cg' else 1e-10
# Create our classifier object
clf = LogisticRegression(penalty='l2',
C=params.C,
n_jobs=params.n_jobs,
fit_intercept=params.fit_intercept,
verbose=params.verbose,
tol=params.tol,
max_iter=params.maxiter,
solver=params.solver,
multi_class=params.multiclass)
# Time fit and predict
fit_time, _ = bench.measure_function_time(clf.fit,
X_train,
y_train,
params=params)
y_pred = clf.predict(X_train)
y_proba = clf.predict_proba(X_train)
train_acc = bench.accuracy_score(y_train, y_pred)
train_log_loss = bench.log_loss(y_train, y_proba)
train_roc_auc = bench.roc_auc_score(y_train, y_proba)
predict_time, y_pred = bench.measure_function_time(clf.predict,
X_test,
params=params)
y_proba = clf.predict_proba(X_test)
test_acc = bench.accuracy_score(y_test, y_pred)
test_log_loss = bench.log_loss(y_test, y_proba)
test_roc_auc = bench.roc_auc_score(y_test, y_proba)
bench.print_output(
library='sklearn',
algorithm='logistic_regression',
stages=['training', 'prediction'],
params=params,
functions=['LogReg.fit', 'LogReg.predict'],
times=[fit_time, predict_time],
metric_type=['accuracy', 'log_loss', 'roc_auc'],
metrics=[
[train_acc, test_acc],
[train_log_loss, test_log_loss],
[train_roc_auc, test_roc_auc],
],
data=[X_train, X_test],
alg_instance=clf,
)
def main():
from sklearn.ensemble import RandomForestRegressor
# Load and convert data
X_train, X_test, y_train, y_test = bench.load_data(params)
# Create our random forest regressor
regr = RandomForestRegressor(criterion=params.criterion,
n_estimators=params.num_trees,
max_depth=params.max_depth,
max_features=params.max_features,
min_samples_split=params.min_samples_split,
max_leaf_nodes=params.max_leaf_nodes,
min_impurity_decrease=params.min_impurity_decrease,
bootstrap=params.bootstrap,
random_state=params.seed,
n_jobs=params.n_jobs)
fit_time, _ = bench.measure_function_time(regr.fit, X_train, y_train, params=params)
y_pred = regr.predict(X_train)
train_rmse = bench.rmse_score(y_pred, y_train)
predict_time, y_pred = bench.measure_function_time(
regr.predict, X_test, params=params)
test_rmse = bench.rmse_score(y_pred, y_test)
bench.print_output(library='sklearn', algorithm='decision_forest_regression',
stages=['training', 'prediction'], params=params,
functions=['df_regr.fit', 'df_regr.predict'],
times=[fit_time, predict_time], accuracy_type='rmse',
accuracies=[train_rmse, test_rmse], data=[X_train, X_test],
alg_instance=regr)
def main():
from sklearn.linear_model import ElasticNet
# Load data
X_train, X_test, y_train, y_test = bench.load_data(params)
# Create our regression object
regr = ElasticNet(fit_intercept=params.fit_intercept, l1_ratio=params.l1_ratio,
alpha=params.alpha, tol=params.tol,
max_iter=params.maxiter, copy_X=False)
# Time fit
fit_time, _ = bench.measure_function_time(regr.fit, X_train, y_train, params=params)
# Time predict
predict_time, pred_train = bench.measure_function_time(regr.predict,
X_train, params=params)
train_rmse = bench.rmse_score(pred_train, y_train)
pred_test = regr.predict(X_test)
test_rmse = bench.rmse_score(pred_test, y_test)
bench.print_output(library='sklearn', algorithm='elastic-net',
stages=['training', 'prediction'], params=params,
functions=['ElasticNet.fit', 'ElasticNet.predict'],
times=[fit_time, predict_time], accuracy_type='rmse',
accuracies=[train_rmse, test_rmse], data=[X_train, X_train],
alg_instance=regr)
def main():
from sklearn.neighbors import KNeighborsRegressor
# Load generated data
X_train, X_test, y_train, y_test = bench.load_data(params)
params.n_classes = len(np.unique(y_train))
# Create a regression object
knn_regr = KNeighborsRegressor(n_neighbors=params.n_neighbors,
weights=params.weights,
algorithm=params.method,
metric=params.metric,
n_jobs=params.n_jobs)
# Measure time and accuracy on fitting
train_time, _ = bench.measure_function_time(
knn_regr.fit, X_train, y_train, params=params)
if params.task == 'regression':
y_pred = knn_regr.predict(X_train)
train_rmse = bench.rmse_score(y_train, y_pred)
train_r2 = bench.r2_score(y_train, y_pred)
# Measure time and accuracy on prediction
if params.task == 'regression':
predict_time, yp = bench.measure_function_time(knn_regr.predict, X_test,
params=params)
test_rmse = bench.rmse_score(y_test, yp)
test_r2 = bench.r2_score(y_test, yp)
else:
predict_time, _ = bench.measure_function_time(knn_regr.kneighbors, X_test,
params=params)
if params.task == 'regression':
bench.print_output(
library='sklearn',
algorithm=knn_regr._fit_method + '_knn_regr',
stages=['training', 'prediction'],
params=params,
functions=['knn_regr.fit', 'knn_regr.predict'],
times=[train_time, predict_time],
metric_type=['rmse', 'r2_score'],
metrics=[[train_rmse, test_rmse], [train_r2, test_r2]],
data=[X_train, X_test],
alg_instance=knn_regr,
)
else:
bench.print_output(
library='sklearn',
algorithm=knn_regr._fit_method + '_knn_search',
stages=['training', 'search'],
params=params,
functions=['knn_regr.fit', 'knn_regr.kneighbors'],
times=[train_time, predict_time],
metric_type=None,
metrics=[],
data=[X_train, X_test],
alg_instance=knn_regr,
)
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,
)
def main():
from sklearn.cluster import KMeans
from sklearn.metrics.cluster import davies_bouldin_score
# Load and convert generated data
X_train, X_test, _, _ = bench.load_data(params)
X_init: Any
if params.filei == 'k-means++':
X_init = 'k-means++'
# Load initial centroids from specified path
elif params.filei is not None:
X_init = {k: v.astype(params.dtype) for k, v in np.load(params.filei).items()}
if isinstance(X_init, np.ndarray):
params.n_clusters = X_init.shape[0]
# or choose random centroids from training data
else:
np.random.seed(params.seed)
centroids_idx = np.random.randint(low=0, high=X_train.shape[0],
size=params.n_clusters)
if hasattr(X_train, "iloc"):
X_init = X_train.iloc[centroids_idx].values
else:
X_init = X_train[centroids_idx]
def fit_kmeans(X, X_init):
alg = KMeans(n_clusters=params.n_clusters, tol=params.tol,
max_iter=params.maxiter, init=X_init, n_init=1)
alg.fit(X)
return alg
# Time fit
fit_time, kmeans = bench.measure_function_time(fit_kmeans, X_train,
X_init, params=params)
train_predict = kmeans.predict(X_train)
acc_train = davies_bouldin_score(X_train, train_predict)
# Time predict
predict_time, test_predict = bench.measure_function_time(
kmeans.predict, X_test, params=params)
acc_test = davies_bouldin_score(X_test, test_predict)
bench.print_output(library='sklearn', algorithm='kmeans',
stages=['training', 'prediction'],
params=params, functions=['KMeans.fit', 'KMeans.predict'],
times=[fit_time, predict_time],
accuracy_type='davies_bouldin_score',
accuracies=[acc_train, acc_test], data=[X_train, X_test],
alg_instance=kmeans)
def main():
from sklearn.cluster import DBSCAN
from sklearn.metrics.cluster import davies_bouldin_score
# Load generated data
X, _, _, _ = bench.load_data(params, add_dtype=True)
# Create our clustering object
dbscan = DBSCAN(eps=params.eps, n_jobs=params.n_jobs,
min_samples=params.min_samples, metric='euclidean',
algorithm='auto')
# N.B. algorithm='auto' will select oneAPI Data Analytics Library (oneDAL)
# brute force method when running daal4py-patched scikit-learn, and probably
# 'kdtree' when running unpatched scikit-learn.
# Time fit
time, _ = bench.measure_function_time(dbscan.fit, X, params=params)
labels = dbscan.labels_
params.n_clusters = len(set(labels)) - (1 if -1 in labels else 0)
acc = davies_bouldin_score(X, labels)
bench.print_output(library='sklearn', algorithm='dbscan', stages=['training'],
params=params, functions=['DBSCAN'], times=[time],
accuracies=[acc], accuracy_type='davies_bouldin_score',
data=[X], alg_instance=dbscan)
def main():
from sklearn.manifold import TSNE
# Load and convert data
X, _, _, _ = bench.load_data(params)
# Create our TSNE model
tsne = TSNE(n_components=params.n_components,
early_exaggeration=params.early_exaggeration,
learning_rate=params.learning_rate,
angle=params.angle,
min_grad_norm=params.min_grad_norm,
random_state=params.random_state)
fit_time, _ = bench.measure_function_time(tsne.fit, X, params=params)
divergence = tsne.kl_divergence_
bench.print_output(
library='sklearn',
algorithm='TSNE',
stages=['training'],
params=params,
functions=['TSNE.fit'],
times=[fit_time],
metric_type='divergence',
metrics=[divergence],
data=[X],
alg_instance=tsne,
)
def main():
from sklearn.model_selection import train_test_split
# Load generated data
X, y, _, _ = bench.load_data(params)
data_args: Iterable
if params.include_y:
data_args = (X, y)
else:
data_args = (X, )
tts_params = {
'train_size': params.train_size,
'test_size': params.test_size,
'shuffle': not params.do_not_shuffle,
'random_state': params.seed
}
if params.rng is not None:
tts_params['rng'] = params.rng
time, _ = bench.measure_function_time(
train_test_split, *data_args, params=params, **tts_params)
bench.print_output(library='sklearn', algorithm='train_test_split',
stages=['training'], params=params,
functions=['train_test_split'], times=[time], metrics=[None],
metric_type=None, data=[X], alg_params=tts_params)
def main():
from sklearn.linear_model import Lasso
# Load data
X_train, X_test, y_train, y_test = bench.load_data(params)
# Create our regression object
regr = Lasso(fit_intercept=params.fit_intercept,
alpha=params.alpha,
tol=params.tol,
max_iter=params.maxiter,
copy_X=False)
# Time fit
fit_time, _ = bench.measure_function_time(regr.fit,
X_train,
y_train,
params=params)
# Time predict
predict_time, yp = bench.measure_function_time(regr.predict,
X_train,
params=params)
train_rmse = bench.rmse_score(y_train, yp)
train_r2 = bench.r2_score(y_train, yp)
yp = regr.predict(X_test)
test_rmse = bench.rmse_score(y_test, yp)
test_r2 = bench.r2_score(y_test, yp)
bench.print_output(
library='sklearn',
algorithm='lasso',
stages=['training', 'prediction'],
params=params,
functions=['Lasso.fit', 'Lasso.predict'],
times=[fit_time, predict_time],
metric_type=['rmse', 'r2_score', 'iter'],
metrics=[
[train_rmse, test_rmse],
[train_r2, test_r2],
[int(regr.n_iter_), int(regr.n_iter_)],
],
data=[X_train, X_test],
alg_instance=regr,
)
def main():
from sklearn.neighbors import KNeighborsClassifier
# Load generated data
X_train, X_test, y_train, y_test = bench.load_data(params)
params.n_classes = len(np.unique(y_train))
# Create classification object
knn_clsf = KNeighborsClassifier(n_neighbors=params.n_neighbors,
weights=params.weights,
algorithm=params.method,
metric=params.metric,
n_jobs=params.n_jobs)
# Measure time and accuracy on fitting
train_time, _ = bench.measure_function_time(knn_clsf.fit, X_train, y_train, params=params)
if params.task == 'classification':
y_pred = knn_clsf.predict(X_train)
train_acc = 100 * accuracy_score(y_pred, y_train)
# Measure time and accuracy on prediction
if params.task == 'classification':
predict_time, yp = bench.measure_function_time(knn_clsf.predict, X_test,
params=params)
test_acc = 100 * accuracy_score(yp, y_test)
else:
predict_time, _ = bench.measure_function_time(knn_clsf.kneighbors, X_test,
params=params)
if params.task == 'classification':
bench.print_output(library='sklearn',
algorithm=knn_clsf._fit_method + '_knn_classification',
stages=['training', 'prediction'], params=params,
functions=['knn_clsf.fit', 'knn_clsf.predict'],
times=[train_time, predict_time],
accuracies=[train_acc, test_acc], accuracy_type='accuracy[%]',
data=[X_train, X_test], alg_instance=knn_clsf)
else:
bench.print_output(library='sklearn',
algorithm=knn_clsf._fit_method + '_knn_search',
stages=['training', 'search'], params=params,
functions=['knn_clsf.fit', 'knn_clsf.kneighbors'],
times=[train_time, predict_time],
accuracies=[], accuracy_type=None,
data=[X_train, X_test], alg_instance=knn_clsf)
def main():
from sklearn.linear_model import LinearRegression
# Load data
X_train, X_test, y_train, y_test = bench.load_data(
params, generated_data=['X_train', 'y_train'])
# Create our regression object
regr = LinearRegression(fit_intercept=params.fit_intercept,
n_jobs=params.n_jobs,
copy_X=False)
# Time fit
fit_time, _ = bench.measure_function_time(regr.fit,
X_train,
y_train,
params=params)
# Time predict
predict_time, yp = bench.measure_function_time(regr.predict,
X_test,
params=params)
test_rmse = bench.rmse_score(y_test, yp)
test_r2 = bench.r2_score(y_test, yp)
yp = regr.predict(X_train)
train_rmse = bench.rmse_score(y_train, yp)
train_r2 = bench.r2_score(y_train, yp)
bench.print_output(
library='sklearn',
algorithm='lin_reg',
stages=['training', 'prediction'],
params=params,
functions=['Linear.fit', 'Linear.predict'],
times=[fit_time, predict_time],
metric_type=['rmse', 'r2_score'],
metrics=[[train_rmse, test_rmse], [train_r2, test_r2]],
data=[X_train, X_test],
alg_instance=regr,
)
def main():
from sklearn.linear_model import ElasticNet
# Load data
X_train, X_test, y_train, y_test = bench.load_data(params)
# Create our regression object
regr = ElasticNet(fit_intercept=params.fit_intercept, l1_ratio=params.l1_ratio,
alpha=params.alpha, tol=params.tol,
max_iter=params.maxiter)
# Time fit
fit_time, _ = bench.measure_function_time(regr.fit, X_train, y_train, params=params)
# Time predict
predict_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 = regr.predict(X_test)
test_rmse = bench.rmse_score(y_test, y_pred)
test_r2 = bench.r2_score(y_test, y_pred)
bench.print_output(
library='sklearn',
algorithm='elasticnet',
stages=['training', 'prediction'],
params=params,
functions=['ElasticNet.fit', 'ElasticNet.predict'],
times=[fit_time, predict_time],
metric_type=['rmse', 'r2_score', 'iter'],
metrics=[
[train_rmse, test_rmse],
[train_r2, test_r2],
[int(regr.n_iter_), int(regr.n_iter_)],
],
data=[X_train, X_train],
alg_instance=regr,
)
def main():
from sklearn.linear_model import Ridge
# Load data
X_train, X_test, y_train, y_test = bench.load_data(
params, generated_data=['X_train', 'y_train'])
# Create our regression object
regr = Ridge(fit_intercept=params.fit_intercept,
alpha=params.alpha,
solver=params.solver)
# Time fit
fit_time, _ = bench.measure_function_time(regr.fit,
X_train,
y_train,
params=params)
# Time predict
predict_time, yp = bench.measure_function_time(regr.predict,
X_test,
params=params)
test_rmse = bench.rmse_score(yp, y_test)
yp = regr.predict(X_train)
train_rmse = bench.rmse_score(yp, y_train)
bench.print_output(library='sklearn',
algorithm='ridge_regression',
stages=['training', 'prediction'],
params=params,
functions=['Ridge.fit', 'Ridge.predict'],
times=[fit_time, predict_time],
accuracy_type='rmse',
accuracies=[train_rmse, test_rmse],
data=[X_train, X_test],
alg_instance=regr)
def main():
from sklearn.metrics.pairwise import pairwise_distances
# Load data
X, _, _, _ = bench.load_data(params,
generated_data=['X_train'],
add_dtype=True)
time, _ = bench.measure_function_time(pairwise_distances,
X,
metric=params.metric,
n_jobs=params.n_jobs,
params=params)
bench.print_output(library='sklearn',
algorithm='distances',
stages=['computation'],
params=params,
functions=[params.metric.capitalize()],
times=[time],
metric_type=None,
metrics=[None],
data=[X],
alg_params={'metric': params.metric})
min_impurity_decrease=params.min_impurity_decrease,
bootstrap=params.bootstrap,
)
def fit(regr, X, y):
return regr.fit(X, y)
def predict(regr, X):
return regr.predict(X, predict_model='GPU')
fit_time, _ = bench.measure_function_time(fit,
regr,
X_train,
y_train,
params=params)
y_pred = predict(regr, X_train)
train_rmse = bench.rmse_score(y_pred, y_train)
predict_time, y_pred = bench.measure_function_time(predict,
regr,
X_test,
params=params)
test_rmse = bench.rmse_score(y_pred, y_test)
bench.print_output(library='cuml',
algorithm='df_regr',
stages=['training', 'prediction'],
parser = argparse.ArgumentParser(description='daal4py pairwise distances '
'benchmark')
parser.add_argument('--metric',
default='cosine',
choices=['cosine', 'correlation'],
help='Metric to test for pairwise distances')
params = bench.parse_args(parser)
# Load data
X, _, _, _ = bench.load_data(params,
generated_data=['X_train'],
add_dtype=True)
pairwise_distances = cosine_distance if params.metric == 'cosine' else correlation_distance
time, _ = bench.measure_function_time(compute_distances,
pairwise_distances,
X,
params=params)
bench.print_output(library='daal4py',
algorithm='distances',
stages=['computation'],
params=params,
functions=[params.metric.capitalize()],
times=[time],
metric_type=None,
metrics=[None],
data=[X],
alg_params={'metric': params.metric})
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,
)
params = bench.parse_args(parser)
from sklearn.linear_model import Ridge
# Load data
X_train, X_test, y_train, y_test = bench.load_data(
params, generated_data=['X_train', 'y_train'])
# Create our regression object
regr = Ridge(fit_intercept=params.fit_intercept,
alpha=params.alpha,
solver=params.solver)
# Time fit
fit_time, _ = bench.measure_function_time(regr.fit,
X_train,
y_train,
params=params)
# Time predict
predict_time, yp = bench.measure_function_time(regr.predict,
X_test,
params=params)
test_rmse = bench.rmse_score(yp, y_test)
yp = regr.predict(X_train)
train_rmse = bench.rmse_score(yp, y_train)
bench.print_output(library='sklearn',
algorithm='ridge_regression',
stages=['training', 'prediction'],
params=params,
def test_transform(Xp, pca_result, eigenvalues, eigenvectors):
return pca_transform_daal(pca_result,
Xp,
params.n_components,
X_train.shape[0],
eigenvalues,
eigenvectors,
whiten=params.whiten)
columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size',
'svd_solver', 'n_components', 'whiten', 'time')
# Time fit
fit_time, res = measure_function_time(test_fit, X_train, params=params)
# Time transform
transform_time, tr = measure_function_time(test_transform,
X_test,
*res[:3],
params=params)
print_output(library='daal4py',
algorithm='pca',
stages=['training', 'transformation'],
columns=columns,
params=params,
functions=['PCA.fit', 'PCA.transform'],
times=[fit_time, transform_time],
accuracy_type=None,
if params.objective.startswith('reg'):
task = 'regression'
metric_name, metric_func = 'rmse', bench.rmse_score
else:
task = 'classification'
metric_name, metric_func = 'accuracy[%]', utils.get_accuracy
if 'cudf' in str(type(y_train)):
params.n_classes = y_train[y_train.columns[0]].nunique()
else:
params.n_classes = len(np.unique(y_train))
if params.n_classes > 2:
lgbm_params['num_class'] = params.n_classes
t_creat_train, lgbm_train = bench.measure_function_time(lgbm.Dataset,
X_train,
y_train,
params=params,
free_raw_data=False)
t_creat_test, lgbm_test = bench.measure_function_time(lgbm.Dataset,
X_test,
y_test,
params=params,
reference=lgbm_train,
free_raw_data=False)
t_train, model_lgbm = bench.measure_function_time(
lgbm.train,
lgbm_params,
lgbm_train,
params=params,
# Load data
X_train, X_test, y_train, y_test = load_data(params)
# Create our regression object
regr = Lasso(fit_intercept=params.fit_intercept,
alpha=params.alpha,
tol=params.tol,
max_iter=params.maxiter,
copy_X=False)
columns = ('batch', 'arch', 'prefix', 'function', 'threads', 'dtype', 'size',
'time')
# Time fit
fit_time, _ = measure_function_time(regr.fit, X_train, y_train, params=params)
# Time predict
predict_time, pred_train = measure_function_time(regr.predict,
X_train,
params=params)
train_rmse = rmse_score(pred_train, y_train)
pred_test = regr.predict(X_test)
test_rmse = rmse_score(pred_test, y_test)
print_output(library='sklearn',
algorithm='lasso',
stages=['training', 'prediction'],
columns=columns,
params=params,
clf = RandomForestClassifier(
criterion=params.criterion,
n_estimators=params.num_trees,
max_depth=params.max_depth,
max_features=params.max_features,
min_samples_split=params.min_samples_split,
max_leaf_nodes=params.max_leaf_nodes,
min_impurity_decrease=params.min_impurity_decrease,
bootstrap=params.bootstrap,
random_state=params.seed,
n_jobs=params.n_jobs)
params.n_classes = len(np.unique(y_train))
fit_time, _ = bench.measure_function_time(clf.fit,
X_train,
y_train,
params=params)
y_pred = clf.predict(X_train)
train_acc = 100 * accuracy_score(y_pred, y_train)
predict_time, y_pred = bench.measure_function_time(clf.predict,
X_test,
params=params)
test_acc = 100 * accuracy_score(y_pred, y_test)
bench.print_output(library='sklearn',
algorithm='decision_forest_classification',
stages=['training', 'prediction'],
params=params,
functions=['df_clsf.fit', 'df_clsf.predict'],
times=[fit_time, predict_time],
params = bench.parse_args(parser, prefix='daal4py')
# Load data
X_train, X_test, y_train, y_test = bench.load_data(
params, add_dtype=True, label_2d=True)
params.n_classes = len(np.unique(y_train))
if isinstance(params.max_features, float):
params.max_features = int(X_train.shape[1] * params.max_features)
# Time fit and predict
fit_time, res = bench.measure_function_time(
df_clsf_fit, X_train, y_train,
params.n_classes,
n_trees=params.num_trees,
n_features_per_node=params.max_features,
max_depth=params.max_depth,
min_impurity=params.min_impurity_decrease,
bootstrap=params.bootstrap,
seed=params.seed,
params=params)
yp = df_clsf_predict(X_train, res, params.n_classes)
train_acc = 100 * accuracy_score(yp, y_train)
predict_time, yp = bench.measure_function_time(
df_clsf_predict, X_test, res, params.n_classes, params=params)
test_acc = 100 * accuracy_score(yp, y_test)
bench.print_output(library='daal4py', algorithm='decision_forest_classification',
stages=['training', 'prediction'], params=params,
functions=['df_clsf.fit', 'df_clsf.predict'],
def test_fit(X, y):
regr_train = ridge_regression_training(fptype=getFPType(X),
ridgeParameters=np.array(
[[params.alpha]]),
interceptFlag=params.fit_intercept)
return regr_train.compute(X, y)
def test_predict(Xp, model):
regr_predict = ridge_regression_prediction(fptype=getFPType(Xp))
return regr_predict.compute(Xp, model)
# Time fit
fit_time, res = bench.measure_function_time(test_fit,
X_train,
y_train,
params=params)
# Time predict
predict_time, yp = bench.measure_function_time(test_predict,
X_test,
res.model,
params=params)
test_rmse = bench.rmse_score(yp.prediction, y_test)
pres = test_predict(X_train, res.model)
train_rmse = bench.rmse_score(pres.prediction, y_train)
bench.print_output(library='daal4py',
algorithm='ridge_regression',
stages=['training', 'prediction'],
metric_name = 'accuracy[%]'
metric_func = lambda y1, y2: 100 * accuracy_score(y1, y2)
columns += ('n_classes', 'accuracy', 'time')
if 'cudf' in str(type(y_train)):
params.n_classes = y_train[y_train.columns[0]].nunique()
else:
params.n_classes = len(np.unique(y_train))
if params.n_classes > 2:
xgb_params['num_class'] = params.n_classes
dtrain = xgb.DMatrix(X_train, y_train)
dtest = xgb.DMatrix(X_test, y_test)
fit_time, booster = measure_function_time(xgb.train,
xgb_params,
dtrain,
params.n_estimators,
params=params)
y_pred = convert_xgb_predictions(booster.predict(dtrain), params.objective)
train_metric = metric_func(y_pred, y_train)
predict_time, y_pred = measure_function_time(booster.predict,
dtest,
params=params)
test_metric = metric_func(convert_xgb_predictions(y_pred, params.objective),
y_test)
print_output(library='xgboost',
algorithm=f'gradient_boosted_trees_{task}',
stages=['training', 'prediction'],
columns=columns,
# Workaround for cuML kmeans fail
# when second call of 'fit' method causes AttributeError
def kmeans_fit(X):
alg = KMeans(n_clusters=params.n_clusters,
tol=params.tol,
max_iter=params.maxiter,
init=X_init,
max_samples_per_batch=params.samples_per_batch)
alg.fit(X)
return alg
# Time fit
fit_time, kmeans = measure_function_time(kmeans_fit, X_train, params=params)
train_predict = kmeans.predict(X_train)
# Time predict
predict_time, test_predict = measure_function_time(kmeans.predict,
X_test,
params=params)
X_train_host = convert_to_numpy(X_train)
train_predict_host = convert_to_numpy(train_predict)
acc_train = davies_bouldin_score(X_train_host, train_predict_host)
X_test_host = convert_to_numpy(X_test)
test_predict_host = convert_to_numpy(test_predict)
acc_test = davies_bouldin_score(X_test_host, test_predict_host)
parser.add_argument('-m',
'--min-samples',
default=5,
type=int,
help='The minimum number of samples required in a '
'neighborhood to consider a point a core point')
params = bench.parse_args(parser)
# Load generated data
X, _, _, _ = bench.load_data(params)
# Create our clustering object
dbscan = DBSCAN(eps=params.eps, min_samples=params.min_samples)
# Time fit
time, _ = bench.measure_function_time(dbscan.fit, X, params=params)
labels = dbscan.labels_
X_host = bench.convert_to_numpy(X)
labels_host = bench.convert_to_numpy(labels)
acc = davies_bouldin_score(X_host, labels_host)
params.n_clusters = len(set(labels_host)) - (1 if -1 in labels_host else 0)
bench.print_output(library='cuml',
algorithm='dbscan',
stages=['training'],
params=params,
functions=['DBSCAN'],
times=[time],
metrics=[acc],