Skip to content
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

initial alignment of configs to final results #176

Merged
merged 12 commits into from
Mar 21, 2025
+273 −490
Merged

initial alignment of configs to final results #176

Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
fc29011
initial alignment of configs to final results
ethanglaser Mar 19, 2025
fca41a9
logic updates
ethanglaser Mar 20, 2025
3e94f60
fix large scale CI
ethanglaser Mar 20, 2025
3af87d7
black
ethanglaser Mar 21, 2025
66b6834
minimize incremental
ethanglaser Mar 21, 2025
3f25ddb
Merge branch 'dev/eglaser-large-scale-ci-fix' into dev/eglaser-large-…
ethanglaser Mar 21, 2025
d3f0b85
black
ethanglaser Mar 21, 2025
7796f95
align custom function with skl estimator
ethanglaser Mar 21, 2025
f6c6967
Update sklbench/utils/measurement.py
ethanglaser Mar 21, 2025
646f7a5
Update sklbench/utils/measurement.py
ethanglaser Mar 21, 2025
e684c8d
Update sklbench/utils/measurement.py
ethanglaser Mar 21, 2025
878d31d
Update sklbench/utils/measurement.py
ethanglaser Mar 21, 2025
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
100 changes: 0 additions & 100 deletions configs/incremental.json
View file

This file was deleted.

15 changes: 8 additions & 7 deletions configs/spmd/large_scale/basic_stats.json
View file
Original file line number Diff line number Diff line change
@@ -4,16 +4,17 @@
"spmd basicstats parameters": {
"algorithm": {
"estimator": "BasicStatistics",
"estimator_methods": { "training": "fit" }
"estimator_methods": { "training": "fit" },
"sklearnex_context": { "use_raw_input": true }
},
"data": {
"split_kwargs": { "test_size": 0.0001 }
}
"data": {
"split_kwargs": { "test_size": 0.0001 }
}
},
"synthetic data": {
"data": [
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 10000000, "n_features": 10, "centers": 1 } },
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 100000, "n_features": 1000, "centers": 1 } }
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 100000000, "n_features": 10, "centers": 1 } },
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 1000000, "n_features": 1000, "centers": 1 } }
]
}
},
@@ -22,7 +23,7 @@
"SETS": [
"sklearnex spmd implementation",
"large scale 2k parameters",
"synthetic data",
"synthetic data",
"spmd basicstats parameters"
]
}
13 changes: 7 additions & 6 deletions configs/spmd/large_scale/basic_stats_strong.json
View file
Original file line number Diff line number Diff line change
@@ -4,11 +4,12 @@
"spmd basicstats parameters": {
"algorithm": {
"estimator": "BasicStatistics",
"estimator_methods": { "training": "fit" }
"estimator_methods": { "training": "fit" },
"sklearnex_context": { "use_raw_input": true }
},
"data": {
"split_kwargs": { "test_size": 0.0001 }
}
"data": {
"split_kwargs": { "test_size": 0.0001 }
}
},
"synthetic data": {
"data": [
@@ -20,8 +21,8 @@
"basicstats": {
"SETS": [
"sklearnex spmd implementation",
"large scale strong 2k parameters",
"synthetic data",
"large scale strong <=64 parameters",
"synthetic data",
"spmd basicstats parameters"
]
}
9 changes: 5 additions & 4 deletions configs/spmd/large_scale/covariance.json
View file
Original file line number Diff line number Diff line change
@@ -4,16 +4,17 @@
"spmd basicstats parameters": {
"algorithm": {
"estimator": "EmpiricalCovariance",
"estimator_methods": { "training": "fit" }
"estimator_methods": { "training": "fit" },
"sklearnex_context": { "use_raw_input": true }
},
"data": {
"split_kwargs": { "test_size": 0.0001 }
}
},
"synthetic data": {
"data": [
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 10000000, "n_features": 10, "centers": 1 } },
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 100000, "n_features": 1000, "centers": 1 } }
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 100000000, "n_features": 10, "centers": 1 } },
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 1000000, "n_features": 1000, "centers": 1 } }
]
}
},
@@ -22,7 +23,7 @@
"SETS": [
"sklearnex spmd implementation",
"large scale 2k parameters",
"synthetic data",
"synthetic data",
"spmd basicstats parameters"
]
}
7 changes: 4 additions & 3 deletions configs/spmd/large_scale/covariance_strong.json
View file
Original file line number Diff line number Diff line change
@@ -4,7 +4,8 @@
"spmd basicstats parameters": {
"algorithm": {
"estimator": "EmpiricalCovariance",
"estimator_methods": { "training": "fit" }
"estimator_methods": { "training": "fit" },
"sklearnex_context": { "use_raw_input": true }
},
"data": {
"split_kwargs": { "test_size": 0.0001 }
@@ -20,8 +21,8 @@
"covariance": {
"SETS": [
"sklearnex spmd implementation",
"large scale strong 2k parameters",
"synthetic data",
"large scale strong <=64 parameters",
"synthetic data",
"spmd basicstats parameters"
]
}
5 changes: 3 additions & 2 deletions configs/spmd/large_scale/dbscan.json
View file
Original file line number Diff line number Diff line change
@@ -9,15 +9,16 @@
},
"estimator_params" : {
"eps": 10, "min_samples": 5
}
},
"sklearnex_context": { "use_raw_input": true }
},
"data": {
"dtype": "float64"
}
},
"synthetic dataset": {
"data": [
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 100000, "n_features": 100, "centers": 10 } }
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 40000, "n_features": 100, "centers": 10 } }
]
}
},
15 changes: 8 additions & 7 deletions configs/spmd/large_scale/dbscan_strong.json
View file
Original file line number Diff line number Diff line change
@@ -3,21 +3,22 @@
"PARAMETERS_SETS": {
"spmd dbscan parameters": {
"algorithm": {
"estimator": "DBSCAN",
"estimator_methods": {
"training": "fit"
"estimator": "DBSCAN",
"estimator_methods": {
"training": "fit"
},
"estimator_params" : {
"eps": 10, "min_samples": 5
}
"eps": 15, "min_samples": 50
},
"sklearnex_context": { "use_raw_input": true }
},
"data": {
"dtype": "float64"
}
},
"synthetic dataset": {
"data": [
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 500000, "n_features": 100, "centers": 10 } }
{ "source": "make_blobs", "generation_kwargs": { "n_samples": 4000000, "n_features": 100, "centers": 10 } }
]
}
},
@@ -27,7 +28,7 @@
"common dbscan parameters",
"synthetic dataset",
"sklearnex spmd implementation",
"large scale strong <=64 parameters",
"large scale strong <=64 parameters",
"spmd dbscan parameters"
]
}
28 changes: 28 additions & 0 deletions configs/spmd/large_scale/forest_max_samples.json
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
{
"INCLUDE": ["../../common/sklearn.json", "large_scale.json"],
"PARAMETERS_SETS": {
"spmd forest classification parameters": {
"algorithm": {
"estimator": "RandomForestClassifier",
"estimator_methods": { "training": "fit" },
"estimator_params": { "n_estimators": 20, "max_depth": 10 },
"sklearnex_context": { "use_raw_input": true }
}
},
"synthetic data": {
"data": [
{ "source": "make_classification", "split_kwargs": { "train_size": 1000000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 1001000, "n_features": 100, "n_classes": 2 } }
]
}
},
"TEMPLATES": {
"forestCls": {
"SETS": [
"sklearnex spmd implementation",
"large scale 32 parameters",
"synthetic data",
"spmd forest classification parameters"
]
}
}
}
9 changes: 4 additions & 5 deletions configs/spmd/large_scale/forest.json → ...md/large_scale/forest_no_max_samples.json
View file
Original file line number Diff line number Diff line change
@@ -4,14 +4,13 @@
"spmd forest classification parameters": {
"algorithm": {
"estimator": "RandomForestClassifier",
"estimator_methods": { "training": "fit" },
"estimator_params": { "n_estimators": 20, "max_depth": 4 }
"estimator_params": { "n_estimators": 100, "max_depth": 7 },
"sklearnex_context": { "use_raw_input": true }
}
},
"synthetic data": {
"data": [
{ "source": "make_classification", "split_kwargs": { "train_size": 500000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 501000, "n_features": 10, "n_classes": 2 } },
{ "source": "make_classification", "split_kwargs": { "train_size": 10000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 11000, "n_features": 1000, "n_classes": 2 } }
{ "source": "make_classification", "split_kwargs": { "train_size": 1000000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 1001000, "n_features": 100, "n_classes": 2 }, "n_informative": "[SPECIAL_VALUE]0.5" }
]
}
},
@@ -20,7 +19,7 @@
"SETS": [
"sklearnex spmd implementation",
"large scale 2k parameters",
"synthetic data",
"synthetic data",
"spmd forest classification parameters"
]
}
11 changes: 6 additions & 5 deletions configs/spmd/large_scale/forest_strong.json
View file
Original file line number Diff line number Diff line change
@@ -4,22 +4,23 @@
"spmd forest classification parameters": {
"algorithm": {
"estimator": "RandomForestClassifier",
"estimator_methods": { "training": "fit" },
"estimator_params": { "n_estimators": 20, "max_depth": 4 }
"estimator_methods": { "training": "fit" },
"estimator_params": { "n_estimators": 100, "max_depth": 8 },
"sklearnex_context": {"use_raw_input": true}
}
},
"synthetic data": {
"data": [
{ "source": "make_classification", "split_kwargs": { "train_size": 10000000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 10001000, "n_features": 100, "n_classes": 2 } }
{ "source": "make_classification", "split_kwargs": { "train_size": 20000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 21000, "n_features": 200, "n_classes": 2 } }
]
}
},
"TEMPLATES": {
"forestCls": {
"SETS": [
"sklearnex spmd implementation",
"large scale strong 2k parameters",
"synthetic data",
"large scale strong <=64 parameters",
"synthetic data",
"spmd forest classification parameters"
]
}
Loading