OpenML

JavaScript is required to properly view the contents of this page!

Explore
- Data
- Task
- Flow
- Run
- Study
- Task type
- Measure
- People
Help
Blog
Contact
Please cite us

guillermo_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True

active ARFF Publicly available Visibility: public Uploaded 17-11-2022 by David Wilson
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes

Issue	#Downvotes for this reason	By

Loading wiki

Help us complete this description Edit

Subsampling of the dataset guillermo (41159) with seed=3 args.nrows=2000 args.ncols=100 args.nclasses=10 args.no_stratify=True Generated with the following source code: ```python def subsample( self, seed: int, nrows_max: int = 2_000, ncols_max: int = 100, nclasses_max: int = 10, stratified: bool = True, ) -> Dataset: rng = np.random.default_rng(seed) x = self.x y = self.y # Uniformly sample classes = y.unique() if len(classes) > nclasses_max: vcs = y.value_counts() selected_classes = rng.choice( classes, size=nclasses_max, replace=False, p=vcs / sum(vcs), ) # Select the indices where one of these classes is present idxs = y.index[y.isin(classes)] x = x.iloc[idxs] y = y.iloc[idxs] # Uniformly sample columns if required if len(x.columns) > ncols_max: columns_idxs = rng.choice( list(range(len(x.columns))), size=ncols_max, replace=False ) sorted_column_idxs = sorted(columns_idxs) selected_columns = list(x.columns[sorted_column_idxs]) x = x[selected_columns] else: sorted_column_idxs = list(range(len(x.columns))) if len(x) > nrows_max: # Stratify accordingly target_name = y.name data = pd.concat((x, y), axis="columns") _, subset = train_test_split( data, test_size=nrows_max, stratify=data[target_name], shuffle=True, random_state=seed, ) x = subset.drop(target_name, axis="columns") y = subset[target_name] # We need to convert categorical columns to string for openml categorical_mask = [self.categorical_mask[i] for i in sorted_column_idxs] columns = list(x.columns) return Dataset( # Technically this is not the same but it's where it was derived from dataset=self.dataset, x=x, y=y, categorical_mask=categorical_mask, columns=columns, ) ```

101 features

class (target)	nominal	2 unique values 0 missing
V7	numeric	614 unique values 0 missing
V21	numeric	1021 unique values 0 missing
V130	numeric	464 unique values 0 missing
V138	numeric	735 unique values 0 missing
V166	numeric	862 unique values 0 missing
V183	numeric	236 unique values 0 missing
V327	numeric	511 unique values 0 missing
V360	numeric	903 unique values 0 missing
V388	numeric	412 unique values 0 missing
V396	numeric	472 unique values 0 missing
V440	numeric	792 unique values 0 missing
V480	numeric	716 unique values 0 missing
V591	numeric	679 unique values 0 missing
V673	numeric	521 unique values 0 missing
V731	numeric	732 unique values 0 missing
V754	numeric	291 unique values 0 missing
V762	numeric	646 unique values 0 missing
V810	numeric	419 unique values 0 missing
V884	numeric	737 unique values 0 missing
V936	numeric	748 unique values 0 missing
V965	numeric	780 unique values 0 missing
V995	numeric	749 unique values 0 missing
V1040	numeric	983 unique values 0 missing
V1059	numeric	459 unique values 0 missing
V1081	numeric	445 unique values 0 missing
V1083	numeric	428 unique values 0 missing
V1116	numeric	649 unique values 0 missing
V1203	numeric	666 unique values 0 missing
V1240	numeric	320 unique values 0 missing
V1250	numeric	852 unique values 0 missing
V1266	numeric	237 unique values 0 missing
V1274	numeric	261 unique values 0 missing
V1333	numeric	619 unique values 0 missing
V1354	numeric	708 unique values 0 missing
V1397	numeric	709 unique values 0 missing
V1398	numeric	870 unique values 0 missing
V1594	numeric	726 unique values 0 missing
V1651	numeric	905 unique values 0 missing
V1659	numeric	854 unique values 0 missing
V1693	numeric	778 unique values 0 missing
V1774	numeric	687 unique values 0 missing
V1819	numeric	221 unique values 0 missing
V1823	numeric	143 unique values 0 missing
V1837	numeric	87 unique values 0 missing
V1907	numeric	614 unique values 0 missing
V2004	numeric	717 unique values 0 missing
V2017	numeric	770 unique values 0 missing
V2018	numeric	384 unique values 0 missing
V2082	numeric	645 unique values 0 missing
V2181	numeric	323 unique values 0 missing
V2213	numeric	585 unique values 0 missing
V2218	numeric	377 unique values 0 missing
V2448	numeric	573 unique values 0 missing
V2479	numeric	445 unique values 0 missing
V2486	numeric	724 unique values 0 missing
V2548	numeric	368 unique values 0 missing
V2594	numeric	406 unique values 0 missing
V2595	numeric	571 unique values 0 missing
V2615	numeric	170 unique values 0 missing
V2690	numeric	639 unique values 0 missing
V2745	numeric	667 unique values 0 missing
V2753	numeric	878 unique values 0 missing
V2795	numeric	478 unique values 0 missing
V2814	numeric	494 unique values 0 missing
V2815	numeric	974 unique values 0 missing
V2816	numeric	836 unique values 0 missing
V2820	numeric	667 unique values 0 missing
V2913	numeric	248 unique values 0 missing
V2924	numeric	204 unique values 0 missing
V2948	numeric	679 unique values 0 missing
V3009	numeric	794 unique values 0 missing
V3087	numeric	761 unique values 0 missing
V3096	numeric	924 unique values 0 missing
V3119	numeric	344 unique values 0 missing
V3169	numeric	471 unique values 0 missing
V3199	numeric	514 unique values 0 missing
V3254	numeric	781 unique values 0 missing
V3288	numeric	540 unique values 0 missing
V3325	numeric	640 unique values 0 missing
V3367	numeric	880 unique values 0 missing
V3406	numeric	563 unique values 0 missing
V3514	numeric	524 unique values 0 missing
V3551	numeric	950 unique values 0 missing
V3606	numeric	941 unique values 0 missing
V3649	numeric	548 unique values 0 missing
V3654	numeric	708 unique values 0 missing
V3682	numeric	512 unique values 0 missing
V3746	numeric	817 unique values 0 missing
V3769	numeric	420 unique values 0 missing
V3787	numeric	707 unique values 0 missing
V3915	numeric	632 unique values 0 missing
V3958	numeric	782 unique values 0 missing
V3972	numeric	846 unique values 0 missing
V3978	numeric	912 unique values 0 missing
V4004	numeric	577 unique values 0 missing
V4044	numeric	918 unique values 0 missing
V4103	numeric	1220 unique values 0 missing
V4128	numeric	1221 unique values 0 missing
V4280	numeric	1223 unique values 0 missing
V4291	numeric	1218 unique values 0 missing