Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .pre-commit-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -23,3 +23,9 @@ repos:
rev: 5.13.2
hooks:
- id: isort
- repo: https://github.com/pre-commit/mirrors-prettier
rev: v3.1.0
hooks:
- id: prettier
args: [--tab-width=4, --print-width=120]
files: ^configs/.*\.json$
6 changes: 3 additions & 3 deletions configs/common/svm.json
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
{
"algorithm": {
"library": "cuml",
"estimator_methods": {"inference": "predict"},
"estimator_methods": { "inference": "predict" },
"estimator_params": { "verbose": false, "multiclass_strategy": "ovr" }
},
"data": { "format": "cupy" }
Expand All @@ -27,7 +27,7 @@
{
"algorithm": {
"library": "cuml",
"estimator_methods": {"inference": "predict"},
"estimator_methods": { "inference": "predict" },
"estimator_params": { "multiclass_strategy": "ovr" }
},
"data": { "format": "cupy" }
Expand All @@ -43,7 +43,7 @@
{
"algorithm": {
"library": "cuml",
"estimator_methods": {"inference": "predict"}
"estimator_methods": { "inference": "predict" }
},
"data": { "format": "cupy" }
}
Expand Down
2 changes: 1 addition & 1 deletion configs/common/xgboost.json
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@
"algorithm": {
"library": "xgboost",
"estimator": "XGBRegressor",
"estimator_methods": {"inference": "predict"},
"estimator_methods": { "inference": "predict" },
"estimator_params": { "objective": "reg:squarederror" }
}
}
Expand Down
7 changes: 1 addition & 6 deletions configs/regular/dbscan.json
Original file line number Diff line number Diff line change
Expand Up @@ -35,12 +35,7 @@
]
},
"cuml dbscan": {
"SETS": [
"cuml implementation",
"common dbscan parameters",
"cuml dbscan parameters",
"dbscan datasets"
]
"SETS": ["cuml implementation", "common dbscan parameters", "cuml dbscan parameters", "dbscan datasets"]
}
}
}
8 changes: 1 addition & 7 deletions configs/regular/kmeans.json
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,6 @@
"split_kwargs": { "train_size": 0.2, "test_size": null }
}
}

]
},
"TEMPLATES": {
Expand All @@ -58,12 +57,7 @@
]
},
"cuml kmeans": {
"SETS": [
"cuml implementation",
"common kmeans parameters",
"cuml kmeans parameters",
"kmeans datasets"
]
"SETS": ["cuml implementation", "common kmeans parameters", "cuml kmeans parameters", "kmeans datasets"]
}
}
}
26 changes: 19 additions & 7 deletions configs/regular/knn.json
Original file line number Diff line number Diff line change
Expand Up @@ -18,16 +18,28 @@
"source": "make_classification",
"generation_kwargs": [
{
"n_classes": 5, "n_samples": 400000, "n_features": 4,
"n_redundant": 0, "n_repeated": 0, "n_informative": 4
"n_classes": 5,
"n_samples": 400000,
"n_features": 4,
"n_redundant": 0,
"n_repeated": 0,
"n_informative": 4
},
{
"n_classes": 5, "n_samples": 200000, "n_features": 8,
"n_redundant": 2, "n_repeated": 2, "n_informative": 4
"n_classes": 5,
"n_samples": 200000,
"n_features": 8,
"n_redundant": 2,
"n_repeated": 2,
"n_informative": 4
},
{
"n_classes": 5, "n_samples": 100000, "n_features": 16,
"n_redundant": 6, "n_repeated": 6, "n_informative": 4
"n_classes": 5,
"n_samples": 100000,
"n_features": 16,
"n_redundant": 6,
"n_repeated": 6,
"n_informative": 4
}
],
"split_kwargs": { "train_size": 0.5, "test_size": 0.5 }
Expand All @@ -48,7 +60,7 @@
},
{
"source": "make_regression",
"generation_kwargs":[
"generation_kwargs": [
{ "n_samples": 400000, "n_features": 4, "noise": 1.0 },
{ "n_samples": 200000, "n_features": 8, "noise": 1.5 },
{ "n_samples": 100000, "n_features": 16, "noise": 2.0 }
Expand Down
25 changes: 4 additions & 21 deletions configs/regular/lightgbm.json
Original file line number Diff line number Diff line change
@@ -1,32 +1,15 @@
{
"INCLUDE": [
"../common/lightgbm.json",
"xgboost_binary.json",
"xgboost_multi.json",
"xgboost_regression.json"
],
"INCLUDE": ["../common/lightgbm.json", "xgboost_binary.json", "xgboost_multi.json", "xgboost_regression.json"],
"PARAMETERS_SETS": {},
"TEMPLATES": {
"lightgbm binary classification": {
"SETS": [
"lightgbm binary classification",
"lightgbm implementations",
"gbt binary classification data"
]
"SETS": ["lightgbm binary classification", "lightgbm implementations", "gbt binary classification data"]
},
"lightgbm multi classification": {
"SETS": [
"lightgbm multi classification",
"lightgbm implementations",
"gbt multi classification data"
]
"SETS": ["lightgbm multi classification", "lightgbm implementations", "gbt multi classification data"]
},
"lightgbm regression": {
"SETS": [
"lightgbm regression",
"lightgbm implementations",
"gbt regression data"
]
"SETS": ["lightgbm regression", "lightgbm implementations", "gbt regression data"]
}
}
}
58 changes: 18 additions & 40 deletions configs/regular/linear_model.json
Original file line number Diff line number Diff line change
Expand Up @@ -8,16 +8,22 @@
"split_kwargs": { "train_size": 0.2, "test_size": 0.8 },
"generation_kwargs": [
{
"n_samples": 5000000, "n_features": 50,
"n_informative": 5, "noise": 20.0
"n_samples": 5000000,
"n_features": 50,
"n_informative": 5,
"noise": 20.0
},
{
"n_samples": 500000, "n_features": 400,
"n_informative": 5, "noise": 40.0
"n_samples": 500000,
"n_features": 400,
"n_informative": 5,
"noise": 40.0
},
{
"n_samples": 100000, "n_features": 2000,
"n_informative": 5, "noise": 60.0
"n_samples": 100000,
"n_features": 2000,
"n_informative": 5,
"noise": 60.0
}
]
}
Expand Down Expand Up @@ -55,50 +61,22 @@
]
},
"sklearn lasso": {
"SETS": [
"sklearn-ex[cpu] implementations",
"common lasso parameters",
"regression datasets"
]
"SETS": ["sklearn-ex[cpu] implementations", "common lasso parameters", "regression datasets"]
},
"sklearn elasticnet": {
"SETS": [
"sklearn-ex[cpu] implementations",
"common elasticnet parameters",
"regression datasets"
]
"SETS": ["sklearn-ex[cpu] implementations", "common elasticnet parameters", "regression datasets"]
},
"cuml linear": {
"SETS": [
"cuml implementation",
"common linear parameters",
"cuml L2 parameters",
"regression datasets"
]
"SETS": ["cuml implementation", "common linear parameters", "cuml L2 parameters", "regression datasets"]
},
"cuml ridge": {
"SETS": [
"cuml implementation",
"common ridge parameters",
"cuml L2 parameters",
"regression datasets"
]
"SETS": ["cuml implementation", "common ridge parameters", "cuml L2 parameters", "regression datasets"]
},
"cuml lasso": {
"SETS": [
"cuml implementation",
"common lasso parameters",
"cuml L1 parameters",
"regression datasets"
]
"SETS": ["cuml implementation", "common lasso parameters", "cuml L1 parameters", "regression datasets"]
},
"cuml elasticnet": {
"SETS": [
"cuml implementation",
"common elasticnet parameters",
"cuml L1 parameters",
"regression datasets"
]
"SETS": ["cuml implementation", "common elasticnet parameters", "cuml L1 parameters", "regression datasets"]
}
}
}
19 changes: 7 additions & 12 deletions configs/regular/logreg.json
Original file line number Diff line number Diff line change
Expand Up @@ -45,39 +45,39 @@
"test_size": 0.95
}
},
"algorithm": {"estimator_params": {"C": 1e-6}}
"algorithm": { "estimator_params": { "C": 1e-6 } }
},
{
"data": { "dataset": "mnist", "split_kwargs": { "train_size": 10000, "test_size": null } },
"algorithm": {"estimator_params": {"C": 1e-8}}
"algorithm": { "estimator_params": { "C": 1e-8 } }
},
{
"data": {
"dataset": "susy",
"split_kwargs": { "train_size": 0.1, "test_size": null }
},
"algorithm": { "estimator_params": {"C": 1e-2} }
"algorithm": { "estimator_params": { "C": 1e-2 } }
},
{
"data": {
"dataset": "hepmass",
"split_kwargs": { "train_size": 0.1, "test_size": null }
},
"algorithm": { "estimator_params": {"C": 1e-5} }
"algorithm": { "estimator_params": { "C": 1e-5 } }
},
{
"data": {
"dataset": "cifar",
"split_kwargs": { "train_size": 0.1, "test_size": null }
},
"algorithm": { "estimator_params": {"C": 1e-9} }
"algorithm": { "estimator_params": { "C": 1e-9 } }
},
{
"data": {
"dataset": "gisette",
"split_kwargs": { "train_size": 2000, "test_size": null }
},
"algorithm": { "estimator_params": {"C": 1e1} }
"algorithm": { "estimator_params": { "C": 1e1 } }
}
]
},
Expand All @@ -91,12 +91,7 @@
]
},
"cuml logreg": {
"SETS": [
"cuml implementation",
"common logreg parameters",
"cuml logreg parameters",
"logreg datasets"
]
"SETS": ["cuml implementation", "common logreg parameters", "cuml logreg parameters", "logreg datasets"]
}
}
}
13 changes: 2 additions & 11 deletions configs/regular/pca.json
Original file line number Diff line number Diff line change
Expand Up @@ -28,19 +28,10 @@
},
"TEMPLATES": {
"sklearn pca": {
"SETS": [
"sklearn-ex[cpu,gpu] implementations",
"pca parameters",
"pca datasets"
]
"SETS": ["sklearn-ex[cpu,gpu] implementations", "pca parameters", "pca datasets"]
},
"cuml pca": {
"SETS": [
"cuml implementation",
"pca parameters",
"cuml pca parameters",
"pca datasets"
]
"SETS": ["cuml implementation", "pca parameters", "cuml pca parameters", "pca datasets"]
}
}
}
20 changes: 5 additions & 15 deletions configs/regular/svm.json
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
"PARAMETERS_SETS": {
"svc binary datasets": [
{
"data": { "dataset": "a9a", "split_kwargs": { "train_size": 5000, "test_size": null } },
"data": { "dataset": "a9a", "split_kwargs": { "train_size": 5000, "test_size": null } },
"algorithm": { "estimator_params": { "C": 1.0, "kernel": "linear" } }
},
{
Expand Down Expand Up @@ -63,7 +63,7 @@
],
"nusvc datasets": [
{
"data": { "dataset": "a9a", "split_kwargs": { "train_size": 5000, "test_size": null } },
"data": { "dataset": "a9a", "split_kwargs": { "train_size": 5000, "test_size": null } },
"algorithm": { "estimator_params": { "nu": 0.1, "kernel": ["poly", "rbf"] } }
},
{
Expand Down Expand Up @@ -121,17 +121,12 @@
"multi svc implementations",
"common svm parameters",
"svm clsf parameters",
"svc parameters",
"svc parameters",
"svc multiclass datasets"
]
},
"svr": {
"SETS": [
"svr implementations",
"common svm parameters",
"svr parameters",
"svr datasets"
]
"SETS": ["svr implementations", "common svm parameters", "svr parameters", "svr datasets"]
},
"nusvc": {
"SETS": [
Expand All @@ -143,12 +138,7 @@
]
},
"nusvr": {
"SETS": [
"nusvm implementations",
"common svm parameters",
"nusvr parameters",
"nusvr datasets"
]
"SETS": ["nusvm implementations", "common svm parameters", "nusvr parameters", "nusvr datasets"]
}
}
}
Loading
Loading