from sklearn_benchmarks.reporting.hp_match import HpMatchReporting
from sklearn_benchmarks.utils import default_results_directory
from pathlib import Path
import pandas as pd
pd.set_option('display.max_colwidth', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)

scikit-learn-intelex (Intel® oneAPI) vs. scikit-learn

results_dir = default_results_directory()

# Parameters
results_dir = "./results/local/20220315T132911/"

results_dir = Path(results_dir)

reporting = HpMatchReporting(other_library="sklearnex", config="config.yml", log_scale=True, results_dir=results_dir)
reporting.make_report()

We assume here there is a perfect match between the hyperparameters of both librairies. For a given set of parameters and a given dataset, we compute the speed-up time scikit-learn / time sklearnex. For instance, a speed-up of 2 means that sklearnex is twice as fast as scikit-learn for a given set of parameters and a given dataset.

KNeighborsClassifier (brute force) ¶

scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)

Speedup barplots ¶

All estimators share the following parameters: algorithm=brute.

Raw results ¶

fit

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_jobs	n_neighbors	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	fit	100000	100000	100	1.600	0.020	0.050	0.0	-1	1	0.063	0.011	25.230	25.638	Download	Download
3	fit	100000	100000	100	1.650	0.030	0.048	0.0	-1	5	0.059	0.001	27.755	27.761	Download	Download
6	fit	100000	100000	100	1.636	0.030	0.049	0.0	1	100	0.061	0.003	26.617	26.657	Download	Download
9	fit	100000	100000	100	1.642	0.028	0.049	0.0	-1	100	0.061	0.003	27.099	27.123	Download	Download
12	fit	100000	100000	100	1.592	0.057	0.050	0.0	1	5	0.062	0.004	25.478	25.523	Download	Download
15	fit	100000	100000	100	1.613	0.036	0.050	0.0	1	1	0.060	0.001	26.960	26.968	Download	Download
18	fit	100000	100000	2	0.063	0.005	0.025	0.0	-1	1	0.010	0.001	6.068	6.079	Download	Download
21	fit	100000	100000	2	0.059	0.002	0.027	0.0	-1	5	0.010	0.001	5.883	5.894	Download	Download
24	fit	100000	100000	2	0.059	0.003	0.027	0.0	1	100	0.010	0.001	5.851	5.883	Download	Download
27	fit	100000	100000	2	0.061	0.003	0.026	0.0	-1	100	0.010	0.001	6.189	6.213	Download	Download
30	fit	100000	100000	2	0.060	0.004	0.027	0.0	1	5	0.010	0.001	6.158	6.181	Download	Download
33	fit	100000	100000	2	0.065	0.001	0.025	0.0	1	1	0.009	0.001	6.940	6.952	Download	Download

predict

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_jobs	n_neighbors	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	predict	100000	1000	100	2.872	0.287	0.0	0.003	-1	1	0.463	0.010	6.207	6.208	Download	Download
2	predict	100000	1	100	0.032	0.006	0.0	0.032	-1	1	0.012	0.001	2.606	2.618	Download	Download
4	predict	100000	1000	100	3.563	0.068	0.0	0.004	-1	5	0.460	0.005	7.746	7.747	Download	Download
5	predict	100000	1	100	0.030	0.002	0.0	0.030	-1	5	0.012	0.002	2.419	2.454	Download	Download
7	predict	100000	1000	100	2.626	0.047	0.0	0.003	1	100	0.518	0.011	5.067	5.069	Download	Download
8	predict	100000	1	100	0.027	0.002	0.0	0.027	1	100	0.012	0.001	2.167	2.174	Download	Download
10	predict	100000	1000	100	3.373	0.081	0.0	0.003	-1	100	0.518	0.008	6.510	6.511	Download	Download
11	predict	100000	1	100	0.030	0.006	0.0	0.030	-1	100	0.012	0.001	2.380	2.387	Download	Download
13	predict	100000	1000	100	2.572	0.048	0.0	0.003	1	5	0.469	0.011	5.478	5.480	Download	Download
14	predict	100000	1	100	0.024	0.001	0.0	0.024	1	5	0.012	0.001	2.063	2.066	Download	Download
16	predict	100000	1000	100	1.711	0.030	0.0	0.002	1	1	0.466	0.007	3.674	3.675	Download	Download
17	predict	100000	1	100	0.027	0.004	0.0	0.027	1	1	0.012	0.001	2.187	2.202	Download	Download
19	predict	100000	1000	2	1.957	0.046	0.0	0.002	-1	1	0.111	0.006	17.707	17.729	Download	Download
20	predict	100000	1	2	0.005	0.001	0.0	0.005	-1	1	0.001	0.000	5.581	5.642	Download	Download
22	predict	100000	1000	2	2.921	0.075	0.0	0.003	-1	5	0.111	0.006	26.245	26.289	Download	Download
23	predict	100000	1	2	0.008	0.002	0.0	0.008	-1	5	0.002	0.001	3.389	3.723	Download	Download
25	predict	100000	1000	2	2.327	0.074	0.0	0.002	1	100	0.165	0.007	14.061	14.073	Download	Download
26	predict	100000	1	2	0.004	0.000	0.0	0.004	1	100	0.001	0.000	3.660	3.682	Download	Download
28	predict	100000	1000	2	3.012	0.064	0.0	0.003	-1	100	0.168	0.010	17.918	17.952	Download	Download
29	predict	100000	1	2	0.007	0.002	0.0	0.007	-1	100	0.001	0.000	6.625	6.696	Download	Download
31	predict	100000	1000	2	2.346	0.067	0.0	0.002	1	5	0.108	0.004	21.681	21.695	Download	Download
32	predict	100000	1	2	0.003	0.000	0.0	0.003	1	5	0.001	0.002	2.290	3.377	Download	Download
34	predict	100000	1000	2	1.390	0.014	0.0	0.001	1	1	0.108	0.005	12.890	12.905	Download	Download
35	predict	100000	1	2	0.002	0.000	0.0	0.002	1	1	0.001	0.000	2.657	2.684	Download	Download

Profiling traces can be visualized using Perfetto UI.

KNeighborsClassifier (KD tree) ¶

scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)

Speedup barplots ¶

All estimators share the following parameters: algorithm=kd_tree.

Raw results ¶

fit

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_jobs	n_neighbors	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	fit	1000000	1000000	10	3.142	0.068	0.025	0.0	-1	1	0.870	0.012	3.613	3.613	Download	Download
3	fit	1000000	1000000	10	3.226	0.107	0.025	0.0	-1	5	0.897	0.024	3.595	3.596	Download	Download
6	fit	1000000	1000000	10	3.217	0.041	0.025	0.0	1	100	0.890	0.018	3.616	3.617	Download	Download
9	fit	1000000	1000000	10	3.120	0.054	0.026	0.0	-1	100	0.884	0.013	3.531	3.532	Download	Download
12	fit	1000000	1000000	10	3.113	0.051	0.026	0.0	1	5	0.876	0.017	3.552	3.553	Download	Download
15	fit	1000000	1000000	10	3.059	0.049	0.026	0.0	1	1	0.872	0.014	3.509	3.510	Download	Download
18	fit	1000	1000	2	0.001	0.000	0.024	0.0	-1	1	0.001	0.000	0.615	0.616	Download	Download
21	fit	1000	1000	2	0.001	0.000	0.027	0.0	-1	5	0.001	0.000	0.546	0.547	Download	Download
24	fit	1000	1000	2	0.001	0.000	0.023	0.0	1	100	0.001	0.000	0.612	0.613	Download	Download
27	fit	1000	1000	2	0.001	0.000	0.022	0.0	-1	100	0.001	0.000	0.659	0.660	Download	Download
30	fit	1000	1000	2	0.001	0.000	0.023	0.0	1	5	0.001	0.000	0.583	0.587	Download	Download
33	fit	1000	1000	2	0.001	0.000	0.021	0.0	1	1	0.002	0.003	0.377	0.624	Download	Download

predict

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_jobs	n_neighbors	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	predict	1000000	1000	10	0.480	0.013	0.000	0.000	-1	1	0.129	0.004	3.728	3.729	Download	Download
2	predict	1000000	1	10	0.003	0.000	0.000	0.003	-1	1	0.000	0.000	10.433	10.573	Download	Download
4	predict	1000000	1000	10	0.925	0.015	0.000	0.001	-1	5	0.232	0.008	3.993	3.995	Download	Download
5	predict	1000000	1	10	0.003	0.000	0.000	0.003	-1	5	0.000	0.000	8.158	8.409	Download	Download
7	predict	1000000	1000	10	5.156	0.034	0.000	0.005	1	100	0.700	0.006	7.360	7.361	Download	Download
8	predict	1000000	1	10	0.003	0.001	0.000	0.003	1	100	0.001	0.000	3.979	4.033	Download	Download
10	predict	1000000	1000	10	2.941	0.024	0.000	0.003	-1	100	0.719	0.025	4.089	4.091	Download	Download
11	predict	1000000	1	10	0.005	0.001	0.000	0.005	-1	100	0.001	0.000	7.382	7.553	Download	Download
13	predict	1000000	1000	10	1.499	0.026	0.000	0.001	1	5	0.230	0.005	6.525	6.526	Download	Download
14	predict	1000000	1	10	0.001	0.000	0.000	0.001	1	5	0.000	0.000	3.677	3.749	Download	Download
16	predict	1000000	1000	10	0.810	0.014	0.000	0.001	1	1	0.129	0.005	6.291	6.296	Download	Download
17	predict	1000000	1	10	0.001	0.000	0.000	0.001	1	1	0.000	0.000	3.568	3.692	Download	Download
19	predict	1000	1000	2	0.031	0.003	0.001	0.000	-1	1	0.001	0.000	42.756	43.907	Download	Download
20	predict	1000	1	2	0.003	0.000	0.000	0.003	-1	1	0.000	0.000	12.604	12.769	Download	Download
22	predict	1000	1000	2	0.032	0.001	0.000	0.000	-1	5	0.001	0.000	32.389	32.471	Download	Download
23	predict	1000	1	2	0.003	0.000	0.000	0.003	-1	5	0.000	0.000	13.187	13.381	Download	Download
25	predict	1000	1000	2	0.043	0.003	0.000	0.000	1	100	0.006	0.000	6.990	7.008	Download	Download
26	predict	1000	1	2	0.001	0.000	0.000	0.001	1	100	0.000	0.000	3.032	3.094	Download	Download
28	predict	1000	1000	2	0.046	0.002	0.000	0.000	-1	100	0.006	0.000	7.538	7.553	Download	Download
29	predict	1000	1	2	0.003	0.000	0.000	0.003	-1	100	0.000	0.000	12.252	12.569	Download	Download
31	predict	1000	1000	2	0.031	0.002	0.001	0.000	1	5	0.001	0.000	29.924	30.138	Download	Download
32	predict	1000	1	2	0.001	0.000	0.000	0.001	1	5	0.000	0.000	3.599	3.659	Download	Download
34	predict	1000	1000	2	0.029	0.003	0.001	0.000	1	1	0.001	0.001	34.903	42.466	Download	Download
35	predict	1000	1	2	0.001	0.000	0.000	0.001	1	1	0.000	0.000	3.565	3.618	Download	Download

Profiling traces can be visualized using Perfetto UI.

KMeans (tall) ¶

scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)

Speedup barplots ¶

All estimators share the following parameters: algorithm=full, n_clusters=3, max_iter=30, n_init=1, tol=1e-16.

Raw results ¶

fit

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_iter	init	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	fit	1000000	1000000	2	0.605	0.009	0.026	0.0	30	random	0.332	0.007	1.823	1.823	Download	Download
3	fit	1000000	1000000	2	0.705	0.011	0.023	0.0	30	k-means++	0.377	0.005	1.871	1.871	Download	Download
6	fit	1000000	1000000	100	8.307	0.505	0.096	0.0	30	random	4.319	0.056	1.923	1.923	Download	Download
9	fit	1000000	1000000	100	8.291	0.157	0.096	0.0	30	k-means++	4.578	0.086	1.811	1.811	Download	Download

predict

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_iter	init	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	predict	1000000	1000	2	0.000	0.0	0.050	0.0	30	random	0.0	0.0	1.204	1.223	Download	Download
2	predict	1000000	1	2	0.000	0.0	0.000	0.0	30	random	0.0	0.0	1.236	1.282	Download	Download
4	predict	1000000	1000	2	0.000	0.0	0.047	0.0	30	k-means++	0.0	0.0	1.167	1.227	Download	Download
5	predict	1000000	1	2	0.000	0.0	0.000	0.0	30	k-means++	0.0	0.0	1.345	1.358	Download	Download
7	predict	1000000	1000	100	0.001	0.0	1.327	0.0	30	random	0.0	0.0	1.279	1.492	Download	Download
8	predict	1000000	1	100	0.000	0.0	0.003	0.0	30	random	0.0	0.0	1.273	1.308	Download	Download
10	predict	1000000	1000	100	0.001	0.0	1.402	0.0	30	k-means++	0.0	0.0	1.384	1.435	Download	Download
11	predict	1000000	1	100	0.000	0.0	0.003	0.0	30	k-means++	0.0	0.0	1.295	1.321	Download	Download

Profiling traces can be visualized using Perfetto UI.

KMeans (short) ¶

scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)

Speedup barplots ¶

All estimators share the following parameters: algorithm=full, n_clusters=300, max_iter=20, n_init=1, tol=1e-16.

Mismatches between validation scores

WARNING! Mismatch between validation scores for 2 predictions (25.0%).
The observed differences can be found in the diff_adjusted_rand_scores column.
The chosen difference threshold is 0.01 for adjusted_rand_score.
The biggest difference is 0.033 for adjusted_rand_score.
See details in the dataframe below.

	estimator	library	diff_adjusted_rand_scores	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_iter	algorithm	init	max_iter	n_clusters	n_init	tol	adjusted_rand_score_sklearn	mean_duration_sklearnex	std_duration_sklearnex	adjusted_rand_score_sklearnex	speedup	std_speedup
7	sklearn_KMeans_short	sklearn	0.032069	predict	10000	1000	100	0.002492	0.000328	0.321010	0.000002	20	full	random	20	300	1	1.000000e-16	0.293414	0.001679	0.000109	0.325483	1.484295	1.487423
10	sklearn_KMeans_short	sklearn	0.032656	predict	10000	1000	100	0.002050	0.000159	0.390215	0.000002	20	full	k-means++	20	300	1	1.000000e-16	0.283247	0.001900	0.000445	0.315903	1.078933	1.108130

Raw results ¶

fit

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_iter	init	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	fit	10000	10000	2	0.112	0.006	0.001	0.0	20	random	0.057	0.003	1.955	1.958	Download	Download
3	fit	10000	10000	2	0.336	0.006	0.000	0.0	20	k-means++	0.146	0.003	2.294	2.294	Download	Download
6	fit	10000	10000	100	0.375	0.012	0.021	0.0	20	random	0.296	0.006	1.270	1.270	Download	Download
9	fit	10000	10000	100	1.264	0.034	0.006	0.0	20	k-means++	0.660	0.008	1.915	1.915	Download	Download

predict

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_iter	init	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	predict	10000	1000	2	0.001	0.0	0.020	0.000	20	random	0.001	0.0	1.026	1.032	Download	Download
2	predict	10000	1	2	0.000	0.0	0.000	0.000	20	random	0.000	0.0	1.822	1.841	Download	Download
4	predict	10000	1000	2	0.001	0.0	0.021	0.000	20	k-means++	0.001	0.0	0.990	0.992	Download	Download
5	predict	10000	1	2	0.000	0.0	0.000	0.000	20	k-means++	0.000	0.0	1.219	1.250	Download	Download
7	predict	10000	1000	100	0.002	0.0	0.321	0.000	20	random	0.002	0.0	1.484	1.487	Download	Download
8	predict	10000	1	100	0.001	0.0	0.001	0.001	20	random	0.000	0.0	2.343	2.356	Download	Download
10	predict	10000	1000	100	0.002	0.0	0.390	0.000	20	k-means++	0.002	0.0	1.079	1.108	Download	Download
11	predict	10000	1	100	0.000	0.0	0.002	0.000	20	k-means++	0.000	0.0	1.405	1.497	Download	Download

Profiling traces can be visualized using Perfetto UI.

Logistic Regression ¶

scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)

Speedup barplots ¶

All estimators share the following parameters: penalty=l2, dual=False, tol=0.0001, C=1.0, fit_intercept=True, intercept_scaling=1.0, class_weight=nan, random_state=nan, solver=lbfgs, max_iter=100, multi_class=auto, verbose=0, warm_start=False, n_jobs=nan, l1_ratio=nan.

Raw results ¶

fit

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_iter	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	fit	1000000	1000000	100	17.838	0.249	0.045	0.000	[20]	3.214	0.034	5.550	5.551	Download	Download
3	fit	1000	1000	10000	1.448	0.049	0.055	0.001	[27]	1.335	0.045	1.085	1.085	Download	Download

predict

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_iter	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	predict	1000000	1000	100	0.000	0.000	2.095	0.0	[20]	0.001	0.001	0.424	0.771	Download	Download
2	predict	1000000	1	100	0.000	0.000	0.008	0.0	[20]	0.000	0.000	0.310	0.315	Download	Download
4	predict	1000	100	10000	0.003	0.001	2.659	0.0	[27]	0.004	0.000	0.688	0.691	Download	Download
5	predict	1000	1	10000	0.000	0.000	0.532	0.0	[27]	0.001	0.000	0.155	0.160	Download	Download

Profiling traces can be visualized using Perfetto UI.

LinearRegression ¶

scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)

Speedup barplots ¶

All estimators share the following parameters:

Raw results ¶

fit

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	copy_X	fit_intercept	normalize	positive	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	fit	1000	1000	10000	1.956	0.018	0.041	0.002	True	True	deprecated	False	2.232	0.044	0.876	0.876	Download	Download
3	fit	1000000	1000000	100	11.412	0.694	0.070	0.000	True	True	deprecated	False	0.424	0.011	26.885	26.894	Download	Download

predict

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	copy_X	fit_intercept	normalize	positive	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	predict	1000	1000	10000	0.014	0.001	5.809	0.0	True	True	deprecated	False	0.023	0.001	0.605	0.606	Download	Download
2	predict	1000	10	10000	0.000	0.000	3.896	0.0	True	True	deprecated	False	0.000	0.000	0.525	0.545	Download	Download
4	predict	1000000	1000	100	0.000	0.000	4.295	0.0	True	True	deprecated	False	0.001	0.000	0.337	0.372	Download	Download
5	predict	1000000	10	100	0.000	0.000	0.077	0.0	True	True	deprecated	False	0.000	0.000	0.334	0.363	Download	Download

Profiling traces can be visualized using Perfetto UI.

Ridge ¶

scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)

Speedup barplots ¶

All estimators share the following parameters: alpha=1e-06.

Raw results ¶

fit

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	fit	1000	1000	10000	0.339	0.009	0.236	0.0	0.403	0.110	0.840	0.870	Download	Download
3	fit	1000000	1000000	100	1.472	0.111	0.544	0.0	0.429	0.011	3.433	3.434	Download	Download

predict

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
1	predict	1000	1000	10000	0.013	0.001	6.006	0.0	0.025	0.002	0.543	0.546	Download	Download
2	predict	1000	10	10000	0.000	0.000	4.763	0.0	0.000	0.000	0.412	0.436	Download	Download
4	predict	1000000	1000	100	0.001	0.001	1.269	0.0	0.000	0.000	1.744	1.804	Download	Download
5	predict	1000000	10	100	0.000	0.000	0.096	0.0	0.000	0.000	0.309	0.321	Download	Download

Profiling traces can be visualized using Perfetto UI.

TSNE ¶

scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)

Speedup barplots ¶

All estimators share the following parameters:

Raw results ¶

fit

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	n_iter	angle	early_exaggeration	init	learning_rate	method	metric	min_grad_norm	n_components	n_iter_without_progress	perplexity	square_distances	verbose	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	fit	1000	1000	3	4.315	0.175	0.0	0.004	1000	0.5	12.0	warn	warn	barnes_hut	euclidean	0.0	2	300	30.0	legacy	0	4.523	0.387	0.954	0.958	Download	Download

Profiling traces can be visualized using Perfetto UI.

PCA ¶

scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)

Speedup barplots ¶

All estimators share the following parameters: n_components=10.

Raw results ¶

fit

	function	n_samples_train	n_samples	n_features	mean_duration_sklearn	std_duration_sklearn	iteration_throughput	latency	mean_duration_sklearnex	std_duration_sklearnex	speedup	std_speedup	sklearn_profiling	sklearnex_profiling
0	fit	100000	100000	100	0.626	0.004	0.128	0.0	0.048	0.006	12.989	13.088	Download	Download
1	fit	10000	10000	1000	0.608	0.012	0.131	0.0	0.349	0.006	1.743	1.744	Download	Download

Profiling traces can be visualized using Perfetto UI.

Benchmark environment information

System

python	3.8.12 | packaged by conda-forge | (default, Jan 30 2022, 23:42:07) [GCC 9.4.0]
executable	/usr/share/miniconda/envs/sklbench/bin/python
machine	Linux-5.11.0-1028-azure-x86_64-with-glibc2.10

Dependencies

	version
pip	22.0.4
setuptools	60.9.3
sklearn	1.0.2
numpy	1.22.3
scipy	1.8.0
Cython	None
pandas	1.4.1
matplotlib	3.5.1
joblib	1.1.0
threadpoolctl	3.1.0

Threadpool

	user_api	internal_api	prefix	filepath	version	threading_layer	architecture	num_threads
0	blas	openblas	libopenblas	/usr/share/miniconda/envs/sklbench/lib/libopenblasp-r0.3.18.so	0.3.18	pthreads	Haswell	2
1	openmp	openmp	libgomp	/usr/share/miniconda/envs/sklbench/lib/libgomp.so.1.0.0	None	NaN	NaN	2

CPU count

cpu_count	2
physical_cpu_count	2