Skip to content

Commit 105d203

Browse files
ethanglaserethanglaser
committed
merge changes from root and add config updates
2 parents 8025719 + 595a7ee commit 105d203

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

52 files changed

+1129
-201
lines changed

‎configs/common/sklearn.json

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -12,6 +12,11 @@
1212
{ "library": "sklearnex", "device": ["cpu", "gpu"] }
1313
]
1414
},
15+
"sklearn-ex[gpu] implementations": {
16+
"algorithm": [
17+
{ "library": "sklearnex", "device": ["gpu"] }
18+
]
19+
},
1520
"sklearn-ex[preview] implementations": {
1621
"algorithm": [
1722
{ "library": "sklearn", "device": "cpu" },

‎configs/incremental.json

Lines changed: 96 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,96 @@
1+
{
2+
"PARAMETERS_SETS": {
3+
"common": {"bench": {"n_runs": 10, "time_limit": 60}},
4+
"covariance data": {
5+
"data": [
6+
{
7+
"source": "make_blobs",
8+
"generation_kwargs": {
9+
"centers": 1,
10+
"n_samples": 1000,
11+
"n_features": [16, 64]
12+
},
13+
"split_kwargs": {"ignore": true}
14+
}
15+
]
16+
},
17+
"basic_statistics data": {
18+
"data": {
19+
"source": "make_blobs",
20+
"generation_kwargs": {
21+
"centers": 1,
22+
"n_samples": 10000,
23+
"n_features": [16, 64]
24+
},
25+
"split_kwargs": {"ignore": true}
26+
}
27+
},
28+
"linear_regression data": {
29+
"data": {
30+
"source": "make_regression",
31+
"split_kwargs": {"train_size": 0.2, "test_size": 0.8},
32+
"generation_kwargs": {
33+
"n_samples": 5000,
34+
"n_features": [40, 100],
35+
"n_informative": 5,
36+
"noise": 2.0
37+
}
38+
}
39+
},
40+
"pca data": {
41+
"data": {
42+
"source": "make_blobs",
43+
"generation_kwargs": {
44+
"centers": 1,
45+
"n_samples": 1000,
46+
"n_features": [16, 64]
47+
},
48+
"split_kwargs": {"ignore": true}
49+
}
50+
},
51+
"covariance": {
52+
"algorithm": [
53+
{
54+
"estimator": "IncrementalEmpiricalCovariance",
55+
"library": "sklearnex.covariance",
56+
"estimator_methods": {"training": "partial_fit"},
57+
"num_batches": {"training": 2}
58+
}
59+
]
60+
},
61+
"basic_statistics": {
62+
"algorithm": [
63+
{
64+
"estimator": "IncrementalBasicStatistics",
65+
"library": "sklearnex.basic_statistics",
66+
"num_batches": {"training": 2}
67+
}
68+
]
69+
},
70+
"linear_regression": {
71+
"algorithm": [
72+
{
73+
"estimator": "IncrementalLinearRegression",
74+
"library": "sklearnex.linear_model",
75+
"num_batches": {"training": 2}
76+
}
77+
]
78+
},
79+
"pca": {
80+
"algorithm": [
81+
{
82+
"estimator": "IncrementalPCA",
83+
"library": "sklearnex.preview.decomposition",
84+
"num_batches": {"training": 2}
85+
}
86+
]
87+
}
88+
},
89+
"TEMPLATES": {
90+
"covariance": {"SETS": ["common", "covariance", "covariance data"]},
91+
"linear_regression": {
92+
"SETS": ["common", "linear_regression", "linear_regression data"]
93+
},
94+
"pca": {"SETS": ["common", "pca", "pca data"]}
95+
}
96+
}

‎configs/regular/batch_for_online.json

Lines changed: 84 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
1+
{
2+
"INCLUDE": ["../common/sklearn.json"],
3+
"PARAMETERS_SETS": {
4+
"common": {"bench": {"n_runs": 10}},
5+
"basic_statistics data": {
6+
"data": {
7+
"source": "make_blobs",
8+
"generation_kwargs": {
9+
"centers": 1,
10+
"n_samples": 12000000,
11+
"n_features": [10, 100]
12+
},
13+
"split_kwargs": {"ignore": true}
14+
}
15+
},
16+
"linear_regression data": {
17+
"data": {
18+
"source": "make_regression",
19+
"split_kwargs": {"train_size": 0.2, "test_size": 0.8},
20+
"generation_kwargs": {
21+
"n_samples": 12000000,
22+
"n_features": [10, 100],
23+
"n_informative": 5,
24+
"noise": 2.0
25+
}
26+
}
27+
},
28+
"pca data": {
29+
"data": {
30+
"source": "make_blobs",
31+
"generation_kwargs": {
32+
"centers": 1,
33+
"n_samples": 12000000,
34+
"n_features": [10, 100]
35+
},
36+
"split_kwargs": {"ignore": true}
37+
}
38+
},
39+
"basic_statistics": {
40+
"algorithm": [
41+
{
42+
"estimator": "BasicStatistics",
43+
"library": "sklearnex.basic_statistics",
44+
"estimator_methods": {"training": "fit"}
45+
}
46+
]
47+
},
48+
"covariance": {
49+
"algorithm": [
50+
{
51+
"estimator": "EmpiricalCovariance",
52+
"library": "sklearnex.preview.covariance",
53+
"estimator_methods": {"training": "fit"}
54+
}
55+
]
56+
},
57+
"linear_regression": {
58+
"algorithm": [
59+
{
60+
"estimator": "LinearRegression",
61+
"library": "sklearnex.linear_model",
62+
"estimator_methods": {"training": "fit"}
63+
}
64+
]
65+
},
66+
"pca": {
67+
"algorithm": [
68+
{
69+
"estimator": "PCA",
70+
"library": "sklearnex.decomposition",
71+
"estimator_methods": {"training": "fit"}
72+
}
73+
]
74+
}
75+
},
76+
"TEMPLATES": {
77+
"basic_statistics": {"SETS": ["common", "basic_statistics", "basic_statistics data", "sklearn-ex[gpu] implementations"]},
78+
"covariance": {"SETS": ["common", "basic_statistics data", "sklearn-ex[gpu] implementations", "covariance"]},
79+
"linear_regression": {
80+
"SETS": ["common", "linear_regression", "linear_regression data", "sklearn-ex[gpu] implementations"]
81+
},
82+
"pca": {"SETS": ["common", "pca", "pca data", "sklearn-ex[gpu] implementations"]}
83+
}
84+
}

‎configs/regular/bf16/dbscan.json

Lines changed: 41 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,41 @@
1+
{
2+
"INCLUDE": ["../../common/sklearn.json"],
3+
"PARAMETERS_SETS": {
4+
"common dbscan parameters": {
5+
"algorithm": {
6+
"estimator": "DBSCAN",
7+
"estimator_params": {
8+
"eps": "[SPECIAL_VALUE]distances_quantile:0.01",
9+
"min_samples": 5,
10+
"metric": "euclidean"
11+
}
12+
},
13+
"data": {
14+
"dtype": ["float32"]
15+
}
16+
},
17+
"sklearn dbscan parameters": {
18+
"algorithm": {
19+
"estimator_params": {
20+
"algorithm": "brute",
21+
"n_jobs": "[SPECIAL_VALUE]physical_cpus"
22+
}
23+
}
24+
},
25+
"synthetic dataset": {
26+
"data": [
27+
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 100000, "n_features": 10, "centers": 10 }, "algorithm": { "eps": 5, "min_samples": 5 } }
28+
]
29+
}
30+
},
31+
"TEMPLATES": {
32+
"sklearn dbscan": {
33+
"SETS": [
34+
"sklearn-ex[gpu] implementations",
35+
"common dbscan parameters",
36+
"sklearn dbscan parameters",
37+
"synthetic dataset"
38+
]
39+
}
40+
}
41+
}

‎configs/regular/bf16/ensemble.json

Lines changed: 48 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,48 @@
1+
{
2+
"INCLUDE": ["../../common/sklearn.json"],
3+
"PARAMETERS_SETS": {
4+
"common ensemble params": {
5+
"algorithm": {
6+
"estimator_params": {
7+
"n_estimators": 200,
8+
"max_depth": 16,
9+
"max_samples": 1.0,
10+
"min_samples_split": 5,
11+
"min_samples_leaf": 2,
12+
"min_impurity_decrease": 0.0,
13+
"bootstrap": true,
14+
"random_state": 42
15+
}
16+
},
17+
"data": {
18+
"dtype": ["float32"]
19+
}
20+
},
21+
"sklearn ensemble classifier params": {
22+
"algorithm": {
23+
"estimator": ["RandomForestClassifier", "ExtraTreesClassifier"],
24+
"estimator_params": {
25+
"criterion": "gini",
26+
"max_features": "sqrt",
27+
"max_leaf_nodes": null,
28+
"n_jobs": "[SPECIAL_VALUE]physical_cpus"
29+
}
30+
}
31+
},
32+
"synthetic data": {
33+
"data": [
34+
{ "source": "make_classification", "split_kwargs": { "train_size": 500000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 501000, "n_features": 10, "n_classes": 2 }, "algorithm": { "estimator_params": { "n_estimators": 20, "max_depth": 4 } } }
35+
]
36+
}
37+
},
38+
"TEMPLATES": {
39+
"sklearn ensemble classification": {
40+
"SETS": [
41+
"sklearn-ex[gpu] implementations",
42+
"common ensemble params",
43+
"sklearn ensemble classifier params",
44+
"synthetic data"
45+
]
46+
}
47+
}
48+
}

‎configs/regular/bf16/kmeans.json

Lines changed: 40 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,40 @@
1+
{
2+
"INCLUDE": ["../../common/sklearn.json"],
3+
"PARAMETERS_SETS": {
4+
"common kmeans parameters": {
5+
"algorithm": {
6+
"estimator": "KMeans",
7+
"estimator_params": {
8+
"n_clusters": "[SPECIAL_VALUE]auto",
9+
"n_init": 1,
10+
"max_iter": 30,
11+
"tol": 1e-3,
12+
"random_state": 42
13+
},
14+
"estimator_methods": { "inference": "predict" }
15+
},
16+
"data": {
17+
"dtype": ["float32"],
18+
"preprocessing_kwargs": { "normalize": true }
19+
}
20+
},
21+
"sklearn kmeans parameters": {
22+
"algorithm": { "estimator_params": { "init": "k-means++", "algorithm": "lloyd" } }
23+
},
24+
"synthetic data": {
25+
"data": [
26+
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 1000000, "n_features": 100, "centers": 100 }, "algorithm": { "n_clusters": 100, "max_iter": 100 } }
27+
]
28+
}
29+
},
30+
"TEMPLATES": {
31+
"sklearn kmeans": {
32+
"SETS": [
33+
"sklearn-ex[gpu] implementations",
34+
"common kmeans parameters",
35+
"sklearn kmeans parameters",
36+
"synthetic data"
37+
]
38+
}
39+
}
40+
}

‎configs/regular/bf16/knn.json

Lines changed: 41 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,41 @@
1+
{
2+
"INCLUDE": ["../../common/sklearn.json"],
3+
"PARAMETERS_SETS": {
4+
"common knn parameters": {
5+
"algorithm": {
6+
"estimator_params": {
7+
"n_neighbors": [10, 100],
8+
"weights": "uniform"
9+
}
10+
},
11+
"data": {
12+
"dtype": ["float32"],
13+
"preprocessing_kwargs": { "normalize": true }
14+
}
15+
},
16+
"sklearn knn parameters": {
17+
"algorithm": { "estimator_params": { "n_jobs": "[SPECIAL_VALUE]physical_cpus" } }
18+
},
19+
"synthetic classification data": {
20+
"data": [
21+
{ "source": "make_classification", "split_kwargs": { "train_size": 50000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 51000, "n_features": 100, "n_classes": 2, "n_informative": "[SPECIAL_VALUE]0.5" } }
22+
]
23+
},
24+
"synthetic regression data": {
25+
"data": [
26+
{ "source": "make_regression", "split_kwargs": { "train_size": 50000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 51000, "n_features": 100, "noise":1.5 } }
27+
]
28+
}
29+
},
30+
"TEMPLATES": {
31+
"sklearn brute knn clsf": {
32+
"SETS": [
33+
"sklearn-ex[gpu] implementations",
34+
"common knn parameters",
35+
"sklearn knn parameters",
36+
"synthetic classification data",
37+
"synthetic regression data"
38+
]
39+
}
40+
}
41+
}

0 commit comments

Comments
 (0)