feat(configs): add HDBSCAN benchmark configs

configs/BENCH-CONFIG-SPEC.md

@@ -108,6 +108,7 @@ Configs have the three highest parameter keys:
 |:---------------|:--------------|:--------|:------------|
 | `algorithm`:`estimator` | None |  | Name of measured estimator. |
 | `algorithm`:`estimator_params` | Empty `dict` |  | Parameters for estimator constructor. |
+| `algorithm`:`method_params`:`{method}` | None |  | Parameters for a measured method of estimator. A method listed here is called with these parameters only, without data, which fits methods working off the fitted model such as `HDBSCAN.dbscan_clustering`. |
 | `algorithm`:`batch_size`:`{stage}` | None | Any positive integer | Enables online mode for `{stage}` methods of estimator (sequential calls for each batch). |
 | `algorithm`:`sklearn_context` | None |  | Parameters for sklearn `config_context` used over estimator. `array_api_dispatch` requires `SCIPY_ARRAY_API=1`, which scikit-learn_bench sets by default if it is unset in the environment. |
 | `algorithm`:`sklearnex_context` | None |  | Parameters for sklearnex `config_context` used over estimator. Updated by `sklearn_context` if set. |
@@ -140,6 +141,7 @@ List of available special values:
 | `algorithm`:`estimator_params`:`scale_pos_weight` | sklearn_estimator | `auto` | Sets `scale_pos_weight` parameter to `sum(negative instances) / sum(positive instances)` value for estimator. |
 | `algorithm`:`estimator_params`:`n_clusters` | sklearn_estimator | `auto` | Sets `n_clusters` parameter to number of clusters or classes from dataset description for estimator. |
 | `algorithm`:`estimator_params`:`eps` | sklearn_estimator | `distances_quantile:{quantile}` format where quantile is *float* value in [0, 1] range | Computes `eps` parameter as quantile value of distances in `x_train` matrix for estimator. |
+| `algorithm`:`method_params`:`dbscan_clustering`:`cut_distance` | sklearn_estimator | `distances_quantile:{quantile}` format where quantile is *float* value in [0, 1] range | Computes `cut_distance` the same way as `eps` above, so that an HDBSCAN hierarchy can be re-cut at the distance DBSCAN is measured at. |
 
 ## Range of Values
 

configs/common/hdbscan.json

@@ -0,0 +1,48 @@
+{
+    "PARAMETERS_SETS": {
+        "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
+                }
+            }
+        }
+    }
+}

configs/experiments/README.md

@@ -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`.

configs/experiments/hdbscan_parameters.json

@@ -0,0 +1,169 @@
+{
+    "INCLUDE": ["../common/sklearn.json", "../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": [
+                "sklearn-ex[cpu] implementations",
+                "common hdbscan parameters",
+                "sklearn hdbscan parameters",
+                "hdbscan tree methods",
+                "hdbscan tree metrics",
+                "hdbscan parameters data [tree]"
+            ]
+        },
+        "hdbscan minkowski [tree]": {
+            "SETS": [
+                "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": [
+                "sklearn-ex[cpu] implementations",
+                "common hdbscan parameters",
+                "sklearn hdbscan parameters",
+                "hdbscan brute method",
+                "hdbscan tree metrics",
+                "hdbscan parameters data [brute]"
+            ]
+        },
+        "hdbscan cosine [brute]": {
+            "SETS": [
+                "sklearn-ex[cpu] implementations",
+                "common hdbscan parameters",
+                "sklearn hdbscan parameters",
+                "hdbscan cosine metric",
+                "hdbscan parameters data [brute]"
+            ]
+        },
+        "hdbscan cluster selection": {
+            "SETS": [
+                "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": [
+                "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": [
+                "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": [
+                "sklearn-ex[cpu] implementations",
+                "common hdbscan parameters",
+                "sklearn hdbscan parameters",
+                "hdbscan all methods",
+                "hdbscan dtype sweep",
+                "hdbscan parameters data [real]"
+            ]
+        },
+        "hdbscan data formats": {
+            "SETS": [
+                "sklearn-ex[cpu] implementations",
+                "common hdbscan parameters",
+                "sklearn hdbscan parameters",
+                "hdbscan kd_tree method",
+                "hdbscan data format sweep",
+                "hdbscan parameters data [tree]"
+            ]
+        }
+    }
+}