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)
results_dir = default_results_directory()
# Parameters
results_dir = "./results/local/20220315T181132/"
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.
scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)
All estimators share the following parameters: algorithm=brute.
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 | 1.530 | 0.026 | 0.052 | 0.0 | -1 | 1 | 0.056 | 0.007 | 27.390 | 27.616 | Download | Download |
| 3 | fit | 100000 | 100000 | 100 | 1.489 | 0.015 | 0.054 | 0.0 | -1 | 5 | 0.051 | 0.000 | 29.049 | 29.049 | Download | Download |
| 6 | fit | 100000 | 100000 | 100 | 1.495 | 0.018 | 0.054 | 0.0 | 1 | 100 | 0.051 | 0.000 | 29.274 | 29.274 | Download | Download |
| 9 | fit | 100000 | 100000 | 100 | 1.545 | 0.053 | 0.052 | 0.0 | -1 | 100 | 0.051 | 0.000 | 30.442 | 30.443 | Download | Download |
| 12 | fit | 100000 | 100000 | 100 | 1.504 | 0.031 | 0.053 | 0.0 | 1 | 5 | 0.051 | 0.000 | 29.395 | 29.395 | Download | Download |
| 15 | fit | 100000 | 100000 | 100 | 1.514 | 0.041 | 0.053 | 0.0 | 1 | 1 | 0.052 | 0.000 | 29.289 | 29.290 | Download | Download |
| 18 | fit | 100000 | 100000 | 2 | 0.059 | 0.001 | 0.027 | 0.0 | -1 | 1 | 0.010 | 0.000 | 5.707 | 5.709 | Download | Download |
| 21 | fit | 100000 | 100000 | 2 | 0.059 | 0.000 | 0.027 | 0.0 | -1 | 5 | 0.010 | 0.000 | 5.784 | 5.785 | Download | Download |
| 24 | fit | 100000 | 100000 | 2 | 0.058 | 0.000 | 0.027 | 0.0 | 1 | 100 | 0.010 | 0.000 | 5.567 | 5.567 | Download | Download |
| 27 | fit | 100000 | 100000 | 2 | 0.058 | 0.000 | 0.027 | 0.0 | -1 | 100 | 0.011 | 0.000 | 5.538 | 5.538 | Download | Download |
| 30 | fit | 100000 | 100000 | 2 | 0.059 | 0.000 | 0.027 | 0.0 | 1 | 5 | 0.010 | 0.000 | 5.736 | 5.737 | Download | Download |
| 33 | fit | 100000 | 100000 | 2 | 0.061 | 0.002 | 0.026 | 0.0 | 1 | 1 | 0.010 | 0.000 | 5.887 | 5.887 | 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 | 2.636 | 0.251 | 0.000 | 0.003 | -1 | 1 | 0.217 | 0.010 | 12.168 | 12.180 | Download | Download |
| 2 | predict | 100000 | 1 | 100 | 0.027 | 0.004 | 0.000 | 0.027 | -1 | 1 | 0.009 | 0.000 | 2.971 | 2.972 | Download | Download |
| 4 | predict | 100000 | 1000 | 100 | 3.210 | 0.071 | 0.000 | 0.003 | -1 | 5 | 0.216 | 0.003 | 14.843 | 14.844 | Download | Download |
| 5 | predict | 100000 | 1 | 100 | 0.026 | 0.003 | 0.000 | 0.026 | -1 | 5 | 0.009 | 0.000 | 2.872 | 2.873 | Download | Download |
| 7 | predict | 100000 | 1000 | 100 | 2.207 | 0.009 | 0.000 | 0.002 | 1 | 100 | 0.268 | 0.014 | 8.245 | 8.256 | Download | Download |
| 8 | predict | 100000 | 1 | 100 | 0.023 | 0.001 | 0.000 | 0.023 | 1 | 100 | 0.009 | 0.000 | 2.525 | 2.528 | Download | Download |
| 10 | predict | 100000 | 1000 | 100 | 3.128 | 0.046 | 0.000 | 0.003 | -1 | 100 | 0.267 | 0.002 | 11.698 | 11.698 | Download | Download |
| 11 | predict | 100000 | 1 | 100 | 0.025 | 0.003 | 0.000 | 0.025 | -1 | 100 | 0.009 | 0.000 | 2.756 | 2.757 | Download | Download |
| 13 | predict | 100000 | 1000 | 100 | 2.191 | 0.062 | 0.000 | 0.002 | 1 | 5 | 0.228 | 0.011 | 9.591 | 9.602 | Download | Download |
| 14 | predict | 100000 | 1 | 100 | 0.023 | 0.000 | 0.000 | 0.023 | 1 | 5 | 0.009 | 0.000 | 2.500 | 2.500 | Download | Download |
| 16 | predict | 100000 | 1000 | 100 | 1.330 | 0.006 | 0.001 | 0.001 | 1 | 1 | 0.220 | 0.007 | 6.043 | 6.046 | Download | Download |
| 17 | predict | 100000 | 1 | 100 | 0.021 | 0.000 | 0.000 | 0.021 | 1 | 1 | 0.009 | 0.000 | 2.400 | 2.401 | Download | Download |
| 19 | predict | 100000 | 1000 | 2 | 1.958 | 0.031 | 0.000 | 0.002 | -1 | 1 | 0.037 | 0.003 | 52.573 | 52.737 | Download | Download |
| 20 | predict | 100000 | 1 | 2 | 0.006 | 0.004 | 0.000 | 0.006 | -1 | 1 | 0.001 | 0.000 | 5.794 | 5.825 | Download | Download |
| 22 | predict | 100000 | 1000 | 2 | 2.899 | 0.085 | 0.000 | 0.003 | -1 | 5 | 0.042 | 0.003 | 69.003 | 69.163 | Download | Download |
| 23 | predict | 100000 | 1 | 2 | 0.006 | 0.002 | 0.000 | 0.006 | -1 | 5 | 0.001 | 0.000 | 5.955 | 5.982 | Download | Download |
| 25 | predict | 100000 | 1000 | 2 | 2.101 | 0.004 | 0.000 | 0.002 | 1 | 100 | 0.092 | 0.006 | 22.735 | 22.780 | Download | Download |
| 26 | predict | 100000 | 1 | 2 | 0.003 | 0.000 | 0.000 | 0.003 | 1 | 100 | 0.001 | 0.000 | 2.682 | 2.694 | Download | Download |
| 28 | predict | 100000 | 1000 | 2 | 2.928 | 0.053 | 0.000 | 0.003 | -1 | 100 | 0.092 | 0.005 | 31.783 | 31.838 | Download | Download |
| 29 | predict | 100000 | 1 | 2 | 0.007 | 0.002 | 0.000 | 0.007 | -1 | 100 | 0.001 | 0.000 | 6.252 | 6.302 | Download | Download |
| 31 | predict | 100000 | 1000 | 2 | 2.112 | 0.003 | 0.000 | 0.002 | 1 | 5 | 0.037 | 0.001 | 57.513 | 57.553 | Download | Download |
| 32 | predict | 100000 | 1 | 2 | 0.003 | 0.000 | 0.000 | 0.003 | 1 | 5 | 0.001 | 0.000 | 3.233 | 3.245 | Download | Download |
| 34 | predict | 100000 | 1000 | 2 | 1.194 | 0.004 | 0.000 | 0.001 | 1 | 1 | 0.035 | 0.001 | 34.220 | 34.234 | Download | Download |
| 35 | predict | 100000 | 1 | 2 | 0.002 | 0.000 | 0.000 | 0.002 | 1 | 1 | 0.001 | 0.000 | 2.518 | 2.528 | Download | Download |
Profiling traces can be visualized using Perfetto UI.
scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)
All estimators share the following parameters: algorithm=kd_tree.
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 | 3.464 | 0.036 | 0.023 | 0.0 | -1 | 1 | 0.874 | 0.023 | 3.964 | 3.965 | Download | Download |
| 3 | fit | 1000000 | 1000000 | 10 | 3.415 | 0.039 | 0.023 | 0.0 | -1 | 5 | 0.874 | 0.018 | 3.908 | 3.909 | Download | Download |
| 6 | fit | 1000000 | 1000000 | 10 | 3.445 | 0.025 | 0.023 | 0.0 | 1 | 100 | 0.895 | 0.032 | 3.848 | 3.851 | Download | Download |
| 9 | fit | 1000000 | 1000000 | 10 | 3.452 | 0.100 | 0.023 | 0.0 | -1 | 100 | 0.876 | 0.024 | 3.939 | 3.940 | Download | Download |
| 12 | fit | 1000000 | 1000000 | 10 | 3.584 | 0.014 | 0.022 | 0.0 | 1 | 5 | 0.890 | 0.027 | 4.029 | 4.031 | Download | Download |
| 15 | fit | 1000000 | 1000000 | 10 | 3.616 | 0.040 | 0.022 | 0.0 | 1 | 1 | 0.896 | 0.025 | 4.036 | 4.038 | Download | Download |
| 18 | fit | 1000 | 1000 | 2 | 0.001 | 0.000 | 0.026 | 0.0 | -1 | 1 | 0.001 | 0.000 | 0.546 | 0.546 | Download | Download |
| 21 | fit | 1000 | 1000 | 2 | 0.001 | 0.000 | 0.021 | 0.0 | -1 | 5 | 0.001 | 0.000 | 0.721 | 0.723 | Download | Download |
| 24 | fit | 1000 | 1000 | 2 | 0.001 | 0.000 | 0.024 | 0.0 | 1 | 100 | 0.001 | 0.000 | 0.487 | 0.502 | Download | Download |
| 27 | fit | 1000 | 1000 | 2 | 0.001 | 0.000 | 0.024 | 0.0 | -1 | 100 | 0.002 | 0.001 | 0.414 | 0.463 | Download | Download |
| 30 | fit | 1000 | 1000 | 2 | 0.001 | 0.000 | 0.026 | 0.0 | 1 | 5 | 0.001 | 0.000 | 0.471 | 0.476 | Download | Download |
| 33 | fit | 1000 | 1000 | 2 | 0.001 | 0.000 | 0.026 | 0.0 | 1 | 1 | 0.001 | 0.000 | 0.531 | 0.533 | 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 | 0.502 | 0.012 | 0.000 | 0.001 | -1 | 1 | 0.122 | 0.004 | 4.110 | 4.113 | Download | Download |
| 2 | predict | 1000000 | 1 | 10 | 0.004 | 0.001 | 0.000 | 0.004 | -1 | 1 | 0.000 | 0.000 | 11.481 | 11.826 | Download | Download |
| 4 | predict | 1000000 | 1000 | 10 | 0.910 | 0.024 | 0.000 | 0.001 | -1 | 5 | 0.217 | 0.003 | 4.201 | 4.201 | Download | Download |
| 5 | predict | 1000000 | 1 | 10 | 0.003 | 0.000 | 0.000 | 0.003 | -1 | 5 | 0.000 | 0.000 | 8.633 | 9.075 | Download | Download |
| 7 | predict | 1000000 | 1000 | 10 | 5.015 | 0.029 | 0.000 | 0.005 | 1 | 100 | 0.646 | 0.008 | 7.768 | 7.769 | Download | Download |
| 8 | predict | 1000000 | 1 | 10 | 0.003 | 0.001 | 0.000 | 0.003 | 1 | 100 | 0.001 | 0.000 | 4.045 | 4.158 | Download | Download |
| 10 | predict | 1000000 | 1000 | 10 | 2.904 | 0.022 | 0.000 | 0.003 | -1 | 100 | 0.645 | 0.016 | 4.503 | 4.505 | Download | Download |
| 11 | predict | 1000000 | 1 | 10 | 0.006 | 0.001 | 0.000 | 0.006 | -1 | 100 | 0.001 | 0.000 | 9.023 | 9.334 | Download | Download |
| 13 | predict | 1000000 | 1000 | 10 | 1.538 | 0.006 | 0.000 | 0.002 | 1 | 5 | 0.213 | 0.003 | 7.233 | 7.234 | Download | Download |
| 14 | predict | 1000000 | 1 | 10 | 0.001 | 0.000 | 0.000 | 0.001 | 1 | 5 | 0.000 | 0.000 | 3.523 | 3.650 | Download | Download |
| 16 | predict | 1000000 | 1000 | 10 | 0.830 | 0.004 | 0.000 | 0.001 | 1 | 1 | 0.123 | 0.004 | 6.736 | 6.739 | Download | Download |
| 17 | predict | 1000000 | 1 | 10 | 0.001 | 0.000 | 0.000 | 0.001 | 1 | 1 | 0.000 | 0.000 | 3.945 | 4.106 | Download | Download |
| 19 | predict | 1000 | 1000 | 2 | 0.030 | 0.003 | 0.001 | 0.000 | -1 | 1 | 0.001 | 0.000 | 52.505 | 52.778 | Download | Download |
| 20 | predict | 1000 | 1 | 2 | 0.003 | 0.000 | 0.000 | 0.003 | -1 | 1 | 0.000 | 0.000 | 20.373 | 20.981 | Download | Download |
| 22 | predict | 1000 | 1000 | 2 | 0.032 | 0.003 | 0.000 | 0.000 | -1 | 5 | 0.001 | 0.000 | 28.530 | 29.064 | Download | Download |
| 23 | predict | 1000 | 1 | 2 | 0.003 | 0.001 | 0.000 | 0.003 | -1 | 5 | 0.000 | 0.000 | 16.509 | 18.736 | Download | Download |
| 25 | predict | 1000 | 1000 | 2 | 0.044 | 0.002 | 0.000 | 0.000 | 1 | 100 | 0.006 | 0.001 | 7.137 | 7.174 | Download | Download |
| 26 | predict | 1000 | 1 | 2 | 0.001 | 0.000 | 0.000 | 0.001 | 1 | 100 | 0.000 | 0.000 | 4.210 | 4.462 | Download | Download |
| 28 | predict | 1000 | 1000 | 2 | 0.046 | 0.002 | 0.000 | 0.000 | -1 | 100 | 0.006 | 0.001 | 7.063 | 7.111 | Download | Download |
| 29 | predict | 1000 | 1 | 2 | 0.003 | 0.000 | 0.000 | 0.003 | -1 | 100 | 0.000 | 0.000 | 12.795 | 14.049 | Download | Download |
| 31 | predict | 1000 | 1000 | 2 | 0.025 | 0.000 | 0.001 | 0.000 | 1 | 5 | 0.001 | 0.000 | 24.431 | 24.734 | Download | Download |
| 32 | predict | 1000 | 1 | 2 | 0.001 | 0.000 | 0.000 | 0.001 | 1 | 5 | 0.000 | 0.000 | 3.105 | 3.289 | Download | Download |
| 34 | predict | 1000 | 1000 | 2 | 0.023 | 0.000 | 0.001 | 0.000 | 1 | 1 | 0.001 | 0.000 | 40.559 | 41.367 | Download | Download |
| 35 | predict | 1000 | 1 | 2 | 0.001 | 0.000 | 0.000 | 0.001 | 1 | 1 | 0.000 | 0.000 | 4.102 | 4.290 | Download | Download |
Profiling traces can be visualized using Perfetto UI.
scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)
All estimators share the following parameters: algorithm=full, n_clusters=3, max_iter=30, n_init=1, tol=1e-16.
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 | 0.617 | 0.015 | 0.026 | 0.0 | 30 | random | 0.524 | 0.024 | 1.176 | 1.178 | Download | Download |
| 3 | fit | 1000000 | 1000000 | 2 | 0.685 | 0.022 | 0.023 | 0.0 | 30 | k-means++ | 0.558 | 0.020 | 1.227 | 1.228 | Download | Download |
| 6 | fit | 1000000 | 1000000 | 100 | 5.896 | 0.488 | 0.136 | 0.0 | 30 | random | 3.069 | 0.054 | 1.921 | 1.921 | Download | Download |
| 9 | fit | 1000000 | 1000000 | 100 | 5.720 | 0.162 | 0.140 | 0.0 | 30 | k-means++ | 3.309 | 0.071 | 1.729 | 1.729 | 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 | 0.063 | 0.0 | 30 | random | 0.0 | 0.0 | 0.815 | 0.858 | Download | Download |
| 2 | predict | 1000000 | 1 | 2 | 0.000 | 0.0 | 0.000 | 0.0 | 30 | random | 0.0 | 0.0 | 1.243 | 1.316 | Download | Download |
| 4 | predict | 1000000 | 1000 | 2 | 0.000 | 0.0 | 0.061 | 0.0 | 30 | k-means++ | 0.0 | 0.0 | 1.042 | 1.097 | Download | Download |
| 5 | predict | 1000000 | 1 | 2 | 0.000 | 0.0 | 0.000 | 0.0 | 30 | k-means++ | 0.0 | 0.0 | 1.373 | 1.425 | Download | Download |
| 7 | predict | 1000000 | 1000 | 100 | 0.001 | 0.0 | 1.550 | 0.0 | 30 | random | 0.0 | 0.0 | 1.399 | 1.449 | Download | Download |
| 8 | predict | 1000000 | 1 | 100 | 0.000 | 0.0 | 0.004 | 0.0 | 30 | random | 0.0 | 0.0 | 1.299 | 1.330 | Download | Download |
| 10 | predict | 1000000 | 1000 | 100 | 0.001 | 0.0 | 1.551 | 0.0 | 30 | k-means++ | 0.0 | 0.0 | 1.113 | 1.195 | Download | Download |
| 11 | predict | 1000000 | 1 | 100 | 0.000 | 0.0 | 0.004 | 0.0 | 30 | k-means++ | 0.0 | 0.0 | 0.924 | 0.989 | Download | Download |
Profiling traces can be visualized using Perfetto UI.
scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)
All estimators share the following parameters: algorithm=full, n_clusters=300, max_iter=20, n_init=1, tol=1e-16.
| 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 | 0.001769 | 0.000097 | 0.452136 | 0.000002 | 20 | full | random | 20 | 300 | 1 | 1.000000e-16 | 0.293414 | 0.001389 | 0.000105 | 0.325483 | 1.273413 | 1.277036 |
| 10 | sklearn_KMeans_short | sklearn | 0.032656 | predict | 10000 | 1000 | 100 | 0.001918 | 0.000438 | 0.416995 | 0.000002 | 20 | full | k-means++ | 20 | 300 | 1 | 1.000000e-16 | 0.283247 | 0.001429 | 0.000088 | 0.315903 | 1.342707 | 1.345256 |
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 | 0.114 | 0.004 | 0.001 | 0.0 | 20 | random | 0.043 | 0.001 | 2.654 | 2.654 | Download | Download |
| 3 | fit | 10000 | 10000 | 2 | 0.285 | 0.011 | 0.001 | 0.0 | 20 | k-means++ | 0.114 | 0.003 | 2.492 | 2.493 | Download | Download |
| 6 | fit | 10000 | 10000 | 100 | 0.282 | 0.008 | 0.028 | 0.0 | 20 | random | 0.177 | 0.008 | 1.589 | 1.591 | Download | Download |
| 9 | fit | 10000 | 10000 | 100 | 0.730 | 0.024 | 0.011 | 0.0 | 20 | k-means++ | 0.419 | 0.012 | 1.740 | 1.741 | 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 | 0.018 | 0.0 | 20 | random | 0.001 | 0.0 | 1.130 | 1.132 | Download | Download |
| 2 | predict | 10000 | 1 | 2 | 0.000 | 0.0 | 0.000 | 0.0 | 20 | random | 0.000 | 0.0 | 1.340 | 1.369 | Download | Download |
| 4 | predict | 10000 | 1000 | 2 | 0.001 | 0.0 | 0.018 | 0.0 | 20 | k-means++ | 0.001 | 0.0 | 1.048 | 1.051 | Download | Download |
| 5 | predict | 10000 | 1 | 2 | 0.000 | 0.0 | 0.000 | 0.0 | 20 | k-means++ | 0.000 | 0.0 | 1.393 | 1.436 | Download | Download |
| 7 | predict | 10000 | 1000 | 100 | 0.002 | 0.0 | 0.452 | 0.0 | 20 | random | 0.001 | 0.0 | 1.273 | 1.277 | Download | Download |
| 8 | predict | 10000 | 1 | 100 | 0.000 | 0.0 | 0.003 | 0.0 | 20 | random | 0.000 | 0.0 | 1.222 | 1.243 | Download | Download |
| 10 | predict | 10000 | 1000 | 100 | 0.002 | 0.0 | 0.417 | 0.0 | 20 | k-means++ | 0.001 | 0.0 | 1.343 | 1.345 | Download | Download |
| 11 | predict | 10000 | 1 | 100 | 0.000 | 0.0 | 0.003 | 0.0 | 20 | k-means++ | 0.000 | 0.0 | 1.265 | 1.306 | Download | Download |
Profiling traces can be visualized using Perfetto UI.
scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)
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.
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 | 12.070 | 0.074 | 0.066 | 0.000 | [20] | 2.151 | 0.026 | 5.611 | 5.611 | Download | Download |
| 3 | fit | 1000 | 1000 | 10000 | 0.859 | 0.053 | 0.093 | 0.001 | [27] | 0.826 | 0.048 | 1.039 | 1.041 | 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 | 0.0 | 2.418 | 0.0 | [20] | 0.001 | 0.001 | 0.430 | 0.709 | Download | Download |
| 2 | predict | 1000000 | 1 | 100 | 0.000 | 0.0 | 0.011 | 0.0 | [20] | 0.000 | 0.000 | 0.302 | 0.312 | Download | Download |
| 4 | predict | 1000 | 100 | 10000 | 0.002 | 0.0 | 4.171 | 0.0 | [27] | 0.006 | 0.001 | 0.309 | 0.314 | Download | Download |
| 5 | predict | 1000 | 1 | 10000 | 0.000 | 0.0 | 0.841 | 0.0 | [27] | 0.002 | 0.000 | 0.055 | 0.056 | Download | Download |
Profiling traces can be visualized using Perfetto UI.
scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)
All estimators share the following parameters:
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 | 1.557 | 0.020 | 0.051 | 0.002 | True | True | deprecated | False | 2.004 | 0.149 | 0.777 | 0.779 | Download | Download |
| 3 | fit | 1000000 | 1000000 | 100 | 8.948 | 0.603 | 0.089 | 0.000 | True | True | deprecated | False | 0.240 | 0.012 | 37.274 | 37.321 | 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 | 0.011 | 0.0 | 7.241 | 0.0 | True | True | deprecated | False | 0.019 | 0.001 | 0.573 | 0.573 | Download | Download |
| 2 | predict | 1000 | 10 | 10000 | 0.000 | 0.0 | 4.869 | 0.0 | True | True | deprecated | False | 0.000 | 0.000 | 0.451 | 0.463 | Download | Download |
| 4 | predict | 1000000 | 1000 | 100 | 0.000 | 0.0 | 5.235 | 0.0 | True | True | deprecated | False | 0.001 | 0.000 | 0.274 | 0.298 | Download | Download |
| 5 | predict | 1000000 | 10 | 100 | 0.000 | 0.0 | 0.114 | 0.0 | True | True | deprecated | False | 0.000 | 0.000 | 0.392 | 0.402 | Download | Download |
Profiling traces can be visualized using Perfetto UI.
scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)
All estimators share the following parameters: alpha=1e-06.
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 | 0.203 | 0.003 | 0.394 | 0.0 | 0.210 | 0.001 | 0.967 | 0.967 | Download | Download |
| 3 | fit | 1000000 | 1000000 | 100 | 1.202 | 0.014 | 0.666 | 0.0 | 0.274 | 0.007 | 4.381 | 4.383 | 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 | 0.011 | 0.001 | 7.183 | 0.0 | 0.019 | 0.000 | 0.583 | 0.583 | Download | Download |
| 2 | predict | 1000 | 10 | 10000 | 0.000 | 0.000 | 4.515 | 0.0 | 0.001 | 0.001 | 0.241 | 0.414 | Download | Download |
| 4 | predict | 1000000 | 1000 | 100 | 0.000 | 0.000 | 4.902 | 0.0 | 0.000 | 0.000 | 0.475 | 0.499 | Download | Download |
| 5 | predict | 1000000 | 10 | 100 | 0.000 | 0.000 | 0.121 | 0.0 | 0.000 | 0.000 | 0.373 | 0.389 | Download | Download |
Profiling traces can be visualized using Perfetto UI.
scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)
All estimators share the following parameters:
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 | 4.214 | 0.222 | 0.0 | 0.004 | 1000 | 0.5 | 12.0 | warn | warn | barnes_hut | euclidean | 0.0 | 2 | 300 | 30.0 | legacy | 0 | 4.323 | 0.412 | 0.975 | 0.979 | Download | Download |
Profiling traces can be visualized using Perfetto UI.
scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)
All estimators share the following parameters: n_components=10.
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 | 0.518 | 0.014 | 0.154 | 0.0 | 0.034 | 0.006 | 15.253 | 15.498 | Download | Download |
| 1 | fit | 10000 | 10000 | 1000 | 0.492 | 0.088 | 0.163 | 0.0 | 0.242 | 0.007 | 2.030 | 2.031 | Download | Download |
Profiling traces can be visualized using Perfetto UI.
scikit-learn-intelex (2021.20220207.123530) vs. scikit-learn (1.0.2)
All estimators share the following parameters: eps=173, min_samples=5.
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 | 10000 | 10000 | 50 | 1.245 | 0.008 | 0.003 | 0.0 | 0.218 | 0.006 | 5.716 | 5.719 | Download | Download |
Profiling traces can be visualized using Perfetto UI.
| 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 |
| 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 |
| 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 | SkylakeX | 2 |
| 1 | openmp | openmp | libgomp | /usr/share/miniconda/envs/sklbench/lib/libgomp.so.1.0.0 | None | NaN | NaN | 2 |
| cpu_count | 2 |
|---|---|
| physical_cpu_count | 2 |