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

robert_seed_2_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 robert (41165) with seed=2 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	10 unique values 0 missing
V278	numeric	633 unique values 0 missing
V284	numeric	552 unique values 0 missing
V393	numeric	699 unique values 0 missing
V410	numeric	702 unique values 0 missing
V550	numeric	585 unique values 0 missing
V654	numeric	604 unique values 0 missing
V696	numeric	556 unique values 0 missing
V725	numeric	563 unique values 0 missing
V749	numeric	542 unique values 0 missing
V768	numeric	506 unique values 0 missing
V777	numeric	479 unique values 0 missing
V1070	numeric	553 unique values 0 missing
V1337	numeric	563 unique values 0 missing
V1434	numeric	583 unique values 0 missing
V1447	numeric	546 unique values 0 missing
V1530	numeric	628 unique values 0 missing
V1556	numeric	561 unique values 0 missing
V1567	numeric	253 unique values 0 missing
V1601	numeric	623 unique values 0 missing
V1854	numeric	643 unique values 0 missing
V1858	numeric	510 unique values 0 missing
V1863	numeric	523 unique values 0 missing
V1958	numeric	743 unique values 0 missing
V2121	numeric	588 unique values 0 missing
V2177	numeric	578 unique values 0 missing
V2275	numeric	632 unique values 0 missing
V2378	numeric	611 unique values 0 missing
V2381	numeric	525 unique values 0 missing
V2439	numeric	615 unique values 0 missing
V2471	numeric	588 unique values 0 missing
V2714	numeric	571 unique values 0 missing
V2796	numeric	536 unique values 0 missing
V2916	numeric	634 unique values 0 missing
V2941	numeric	566 unique values 0 missing
V3015	numeric	661 unique values 0 missing
V3083	numeric	644 unique values 0 missing
V3147	numeric	617 unique values 0 missing
V3164	numeric	622 unique values 0 missing
V3194	numeric	549 unique values 0 missing
V3208	numeric	621 unique values 0 missing
V3217	numeric	607 unique values 0 missing
V3255	numeric	558 unique values 0 missing
V3369	numeric	551 unique values 0 missing
V3386	numeric	611 unique values 0 missing
V3415	numeric	543 unique values 0 missing
V3492	numeric	625 unique values 0 missing
V3579	numeric	482 unique values 0 missing
V3581	numeric	587 unique values 0 missing
V3608	numeric	504 unique values 0 missing
V3652	numeric	599 unique values 0 missing
V3706	numeric	710 unique values 0 missing
V3742	numeric	608 unique values 0 missing
V3762	numeric	543 unique values 0 missing
V3973	numeric	622 unique values 0 missing
V4005	numeric	613 unique values 0 missing
V4075	numeric	512 unique values 0 missing
V4142	numeric	553 unique values 0 missing
V4258	numeric	602 unique values 0 missing
V4259	numeric	537 unique values 0 missing
V4267	numeric	253 unique values 0 missing
V4409	numeric	580 unique values 0 missing
V4516	numeric	254 unique values 0 missing
V4552	numeric	548 unique values 0 missing
V4621	numeric	689 unique values 0 missing
V4681	numeric	533 unique values 0 missing
V4771	numeric	454 unique values 0 missing
V4838	numeric	553 unique values 0 missing
V4872	numeric	610 unique values 0 missing
V4875	numeric	491 unique values 0 missing
V4948	numeric	613 unique values 0 missing
V4965	numeric	619 unique values 0 missing
V4980	numeric	575 unique values 0 missing
V5013	numeric	650 unique values 0 missing
V5182	numeric	616 unique values 0 missing
V5338	numeric	548 unique values 0 missing
V5533	numeric	730 unique values 0 missing
V5544	numeric	254 unique values 0 missing
V5632	numeric	255 unique values 0 missing
V5783	numeric	678 unique values 0 missing
V5786	numeric	530 unique values 0 missing
V5948	numeric	251 unique values 0 missing
V5960	numeric	620 unique values 0 missing
V6088	numeric	510 unique values 0 missing
V6189	numeric	558 unique values 0 missing
V6193	numeric	599 unique values 0 missing
V6263	numeric	462 unique values 0 missing
V6269	numeric	631 unique values 0 missing
V6337	numeric	597 unique values 0 missing
V6369	numeric	494 unique values 0 missing
V6409	numeric	605 unique values 0 missing
V6490	numeric	545 unique values 0 missing
V6610	numeric	597 unique values 0 missing
V6670	numeric	602 unique values 0 missing
V6739	numeric	614 unique values 0 missing
V6859	numeric	614 unique values 0 missing
V6902	numeric	527 unique values 0 missing
V6982	numeric	555 unique values 0 missing
V7063	numeric	539 unique values 0 missing
V7140	numeric	580 unique values 0 missing
V7176	numeric	552 unique values 0 missing