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_4_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=4 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
V193	numeric	253 unique values 0 missing
V250	numeric	540 unique values 0 missing
V432	numeric	621 unique values 0 missing
V568	numeric	545 unique values 0 missing
V575	numeric	619 unique values 0 missing
V645	numeric	254 unique values 0 missing
V828	numeric	557 unique values 0 missing
V920	numeric	250 unique values 0 missing
V954	numeric	618 unique values 0 missing
V994	numeric	553 unique values 0 missing
V1181	numeric	530 unique values 0 missing
V1228	numeric	669 unique values 0 missing
V1242	numeric	658 unique values 0 missing
V1269	numeric	533 unique values 0 missing
V1291	numeric	587 unique values 0 missing
V1372	numeric	540 unique values 0 missing
V1438	numeric	253 unique values 0 missing
V1485	numeric	684 unique values 0 missing
V1558	numeric	636 unique values 0 missing
V1564	numeric	701 unique values 0 missing
V1593	numeric	654 unique values 0 missing
V1603	numeric	249 unique values 0 missing
V1921	numeric	703 unique values 0 missing
V2014	numeric	667 unique values 0 missing
V2171	numeric	621 unique values 0 missing
V2409	numeric	530 unique values 0 missing
V2505	numeric	539 unique values 0 missing
V2602	numeric	654 unique values 0 missing
V2606	numeric	558 unique values 0 missing
V2637	numeric	581 unique values 0 missing
V2640	numeric	468 unique values 0 missing
V2678	numeric	254 unique values 0 missing
V2753	numeric	677 unique values 0 missing
V2917	numeric	623 unique values 0 missing
V3068	numeric	633 unique values 0 missing
V3225	numeric	705 unique values 0 missing
V3306	numeric	742 unique values 0 missing
V3313	numeric	514 unique values 0 missing
V3400	numeric	251 unique values 0 missing
V3418	numeric	536 unique values 0 missing
V3444	numeric	553 unique values 0 missing
V3528	numeric	544 unique values 0 missing
V3531	numeric	712 unique values 0 missing
V3560	numeric	598 unique values 0 missing
V3565	numeric	256 unique values 0 missing
V3574	numeric	677 unique values 0 missing
V3579	numeric	465 unique values 0 missing
V3633	numeric	576 unique values 0 missing
V3727	numeric	555 unique values 0 missing
V3740	numeric	253 unique values 0 missing
V3830	numeric	528 unique values 0 missing
V3867	numeric	665 unique values 0 missing
V3873	numeric	470 unique values 0 missing
V4092	numeric	652 unique values 0 missing
V4126	numeric	528 unique values 0 missing
V4134	numeric	651 unique values 0 missing
V4172	numeric	565 unique values 0 missing
V4207	numeric	552 unique values 0 missing
V4319	numeric	651 unique values 0 missing
V4348	numeric	545 unique values 0 missing
V4460	numeric	451 unique values 0 missing
V4594	numeric	590 unique values 0 missing
V4754	numeric	671 unique values 0 missing
V4757	numeric	615 unique values 0 missing
V4811	numeric	558 unique values 0 missing
V4850	numeric	575 unique values 0 missing
V4974	numeric	634 unique values 0 missing
V5035	numeric	253 unique values 0 missing
V5159	numeric	730 unique values 0 missing
V5227	numeric	673 unique values 0 missing
V5537	numeric	663 unique values 0 missing
V5624	numeric	639 unique values 0 missing
V5705	numeric	565 unique values 0 missing
V5788	numeric	663 unique values 0 missing
V5816	numeric	612 unique values 0 missing
V6120	numeric	664 unique values 0 missing
V6205	numeric	683 unique values 0 missing
V6261	numeric	542 unique values 0 missing
V6326	numeric	519 unique values 0 missing
V6365	numeric	606 unique values 0 missing
V6396	numeric	532 unique values 0 missing
V6426	numeric	607 unique values 0 missing
V6442	numeric	596 unique values 0 missing
V6630	numeric	689 unique values 0 missing
V6631	numeric	648 unique values 0 missing
V6669	numeric	629 unique values 0 missing
V6682	numeric	660 unique values 0 missing
V6698	numeric	563 unique values 0 missing
V6730	numeric	595 unique values 0 missing
V6736	numeric	574 unique values 0 missing
V6860	numeric	582 unique values 0 missing
V6876	numeric	653 unique values 0 missing
V6896	numeric	523 unique values 0 missing
V6913	numeric	608 unique values 0 missing
V6927	numeric	552 unique values 0 missing
V6938	numeric	523 unique values 0 missing
V7003	numeric	630 unique values 0 missing
V7018	numeric	694 unique values 0 missing
V7146	numeric	254 unique values 0 missing
V7164	numeric	627 unique values 0 missing