Skip to content

feat(configs): add HDBSCAN benchmark configs #225

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Alexandr-Solovev wants to merge 3 commits into
base: main
Choose a base branch
from
Open

feat(configs): add HDBSCAN benchmark configs #225

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d812ff9
feat(configs): add HDBSCAN benchmark configs
Sep 18, 2026
f2a8edd
Shorten the regular HDBSCAN config and move the sweeps out of common
Alexandr-Solovev Sep 22, 2026
68ba517
Spread the regular HDBSCAN cases over distinct data situations
Alexandr-Solovev Sep 22, 2026
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
54 changes: 54 additions & 0 deletions configs/common/hdbscan.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,54 @@
{
"PARAMETERS_SETS": {
"hdbscan sklearn-ex[cpu] implementations": {
"algorithm": [
{ "library": "sklearn", "device": "cpu" },
{ "library": "sklearnex.preview.cluster", "device": "cpu" }
]
},
"common hdbscan parameters": {
"algorithm": {
"estimator": "HDBSCAN",
"estimator_params": {
"min_cluster_size": 5,
"min_samples": 5,
"metric": "euclidean",
"cluster_selection_method": "eom",
"allow_single_cluster": false,
"store_centers": null,
"copy": false
},
"estimator_methods": { "training": "fit" }
},
"data": { "format": "numpy", "order": "C", "dtype": "float64" },
"bench": { "n_runs": 3, "time_limit": 1200 }
},
"sklearn hdbscan parameters": {
"algorithm": {
"estimator_params": { "n_jobs": "[SPECIAL_VALUE]physical_cpus" }
}
},
"hdbscan brute method": {
"algorithm": { "estimator_params": { "algorithm": "brute" } }
},
"hdbscan kd_tree method": {
"algorithm": { "estimator_params": { "algorithm": "kd_tree", "leaf_size": 40 } }
},
"hdbscan ball_tree method": {
"algorithm": { "estimator_params": { "algorithm": "ball_tree", "leaf_size": 40 } }
},
"hdbscan tree methods": {
"algorithm": {
"estimator_params": { "algorithm": ["kd_tree", "ball_tree"], "leaf_size": 40 }
}
},
"hdbscan all methods": {
"algorithm": {
"estimator_params": {
"algorithm": ["brute", "kd_tree", "ball_tree"],
"leaf_size": 40
}
}
}
}
}
4 changes: 4 additions & 0 deletions configs/experiments/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,8 @@

`daal4py_svd`: tests performance scalability of `daal4py.svd` algorithm

`hdbscan_parameters`: sweeps the `HDBSCAN` parameter space (metrics, cluster selection, density thresholds, stored centers, dtypes and data formats) over the `sklearn` and `sklearnex` implementations.

`hdbscan_scaling`: tests thread, NUMA, `n_samples` and `n_features` scalability of `HDBSCAN`.

`nearest_neighbors`: tests performance of neighbors search implementations from `sklearnex`, `sklearn`, `raft`, `faiss` and `svs`.
169 changes: 169 additions & 0 deletions configs/experiments/hdbscan_parameters.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,169 @@
{
"INCLUDE": ["../common/hdbscan.json"],
"PARAMETERS_SETS": {
"hdbscan tree metrics": {
"algorithm": {
"estimator_params": { "metric": ["euclidean", "manhattan", "chebyshev"] }
}
},
"hdbscan minkowski metric": {
"algorithm": {
"estimator_params": { "metric": "minkowski", "metric_params": { "p": 3 } }
}
},
"hdbscan cosine metric": {
"algorithm": {
"estimator_params": { "metric": "cosine", "algorithm": "brute" }
}
},
"hdbscan cluster selection sweep": {
"algorithm": {
"estimator_params": { "cluster_selection_method": ["eom", "leaf"] }
}
},
"hdbscan density sweep": {
"algorithm": {
"estimator_params": { "min_cluster_size": [5, 25, 100], "min_samples": [5, 25] }
}
},
"hdbscan store centers sweep": {
"algorithm": {
"estimator_params": { "store_centers": [null, "centroid", "medoid", "both"] }
}
},
"hdbscan dtype sweep": {
"data": { "dtype": ["float32", "float64"] }
},
"hdbscan data format sweep": {
"data": [
{ "format": "numpy", "order": "C" },
{ "format": "numpy", "order": "F" },
{ "format": "pandas", "order": "F" }
]
},
"hdbscan parameters data [tree]": {
"data": {
"source": "make_blobs",
"generation_kwargs": {
"centers": 10,
"n_samples": 100000,
"n_features": 8,
"cluster_std": 2.0,
"random_state": 42
},
"split_kwargs": { "ignore": true }
}
},
"hdbscan parameters data [brute]": {
"data": {
"source": "make_blobs",
"generation_kwargs": {
"centers": 10,
"n_samples": 25000,
"n_features": 64,
"cluster_std": 4.0,
"random_state": 42
},
"split_kwargs": { "ignore": true }
}
},
"hdbscan parameters data [real]": {
"data": {
"dataset": "skin_segmentation",
"split_kwargs": { "train_size": 30000 },
"preprocessing_kwargs": { "normalize": "standard" }
}
}
},
"TEMPLATES": {
"hdbscan metrics [tree]": {
"SETS": [
"hdbscan sklearn-ex[cpu] implementations",
"common hdbscan parameters",
"sklearn hdbscan parameters",
"hdbscan tree methods",
"hdbscan tree metrics",
"hdbscan parameters data [tree]"
]
},
"hdbscan minkowski [tree]": {
"SETS": [
"hdbscan sklearn-ex[cpu] implementations",
"common hdbscan parameters",
"sklearn hdbscan parameters",
"hdbscan kd_tree method",
"hdbscan minkowski metric",
"hdbscan parameters data [tree]"
]
},
"hdbscan metrics [brute]": {
"SETS": [
"hdbscan sklearn-ex[cpu] implementations",
"common hdbscan parameters",
"sklearn hdbscan parameters",
"hdbscan brute method",
"hdbscan tree metrics",
"hdbscan parameters data [brute]"
]
},
"hdbscan cosine [brute]": {
"SETS": [
"hdbscan sklearn-ex[cpu] implementations",
"common hdbscan parameters",
"sklearn hdbscan parameters",
"hdbscan cosine metric",
"hdbscan parameters data [brute]"
]
},
"hdbscan cluster selection": {
"SETS": [
"hdbscan sklearn-ex[cpu] implementations",
"common hdbscan parameters",
"sklearn hdbscan parameters",
"hdbscan kd_tree method",
"hdbscan cluster selection sweep",
"hdbscan parameters data [tree]"
]
},
"hdbscan density": {
"SETS": [
"hdbscan sklearn-ex[cpu] implementations",
"common hdbscan parameters",
"sklearn hdbscan parameters",
"hdbscan kd_tree method",
"hdbscan density sweep",
"hdbscan parameters data [tree]"
]
},
"hdbscan store centers": {
"SETS": [
"hdbscan sklearn-ex[cpu] implementations",
"common hdbscan parameters",
"sklearn hdbscan parameters",
"hdbscan kd_tree method",
"hdbscan store centers sweep",
"hdbscan parameters data [tree]"
]
},
"hdbscan dtypes": {
"SETS": [
"hdbscan sklearn-ex[cpu] implementations",
"common hdbscan parameters",
"sklearn hdbscan parameters",
"hdbscan all methods",
"hdbscan dtype sweep",
"hdbscan parameters data [real]"
]
},
"hdbscan data formats": {
"SETS": [
"hdbscan sklearn-ex[cpu] implementations",
"common hdbscan parameters",
"sklearn hdbscan parameters",
"hdbscan kd_tree method",
"hdbscan data format sweep",
"hdbscan parameters data [tree]"
]
}
}
}
Loading
Loading