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_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 robert (41165) 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	10 unique values 0 missing
V11	numeric	629 unique values 0 missing
V34	numeric	473 unique values 0 missing
V218	numeric	590 unique values 0 missing
V233	numeric	573 unique values 0 missing
V281	numeric	519 unique values 0 missing
V309	numeric	549 unique values 0 missing
V550	numeric	610 unique values 0 missing
V609	numeric	552 unique values 0 missing
V651	numeric	757 unique values 0 missing
V670	numeric	599 unique values 0 missing
V737	numeric	574 unique values 0 missing
V810	numeric	570 unique values 0 missing
V996	numeric	634 unique values 0 missing
V1137	numeric	731 unique values 0 missing
V1233	numeric	610 unique values 0 missing
V1275	numeric	252 unique values 0 missing
V1289	numeric	598 unique values 0 missing
V1362	numeric	630 unique values 0 missing
V1486	numeric	540 unique values 0 missing
V1571	numeric	652 unique values 0 missing
V1618	numeric	246 unique values 0 missing
V1683	numeric	634 unique values 0 missing
V1751	numeric	538 unique values 0 missing
V1779	numeric	718 unique values 0 missing
V1817	numeric	254 unique values 0 missing
V1822	numeric	626 unique values 0 missing
V1884	numeric	479 unique values 0 missing
V2028	numeric	662 unique values 0 missing
V2091	numeric	552 unique values 0 missing
V2100	numeric	520 unique values 0 missing
V2133	numeric	614 unique values 0 missing
V2140	numeric	616 unique values 0 missing
V2245	numeric	650 unique values 0 missing
V2284	numeric	597 unique values 0 missing
V2343	numeric	522 unique values 0 missing
V2363	numeric	557 unique values 0 missing
V2681	numeric	622 unique values 0 missing
V2768	numeric	559 unique values 0 missing
V2786	numeric	604 unique values 0 missing
V2787	numeric	553 unique values 0 missing
V2837	numeric	662 unique values 0 missing
V2994	numeric	550 unique values 0 missing
V3069	numeric	720 unique values 0 missing
V3081	numeric	611 unique values 0 missing
V3082	numeric	610 unique values 0 missing
V3220	numeric	608 unique values 0 missing
V3372	numeric	637 unique values 0 missing
V3396	numeric	574 unique values 0 missing
V3408	numeric	529 unique values 0 missing
V3497	numeric	718 unique values 0 missing
V3682	numeric	600 unique values 0 missing
V3722	numeric	583 unique values 0 missing
V3729	numeric	548 unique values 0 missing
V4139	numeric	623 unique values 0 missing
V4183	numeric	255 unique values 0 missing
V4186	numeric	485 unique values 0 missing
V4271	numeric	553 unique values 0 missing
V4361	numeric	562 unique values 0 missing
V4362	numeric	249 unique values 0 missing
V4419	numeric	253 unique values 0 missing
V4520	numeric	617 unique values 0 missing
V4629	numeric	537 unique values 0 missing
V4642	numeric	253 unique values 0 missing
V4694	numeric	254 unique values 0 missing
V4725	numeric	549 unique values 0 missing
V4726	numeric	541 unique values 0 missing
V4734	numeric	643 unique values 0 missing
V4739	numeric	543 unique values 0 missing
V4749	numeric	667 unique values 0 missing
V4907	numeric	577 unique values 0 missing
V4921	numeric	641 unique values 0 missing
V4970	numeric	611 unique values 0 missing
V5062	numeric	639 unique values 0 missing
V5184	numeric	625 unique values 0 missing
V5229	numeric	702 unique values 0 missing
V5261	numeric	517 unique values 0 missing
V5323	numeric	575 unique values 0 missing
V5397	numeric	567 unique values 0 missing
V5457	numeric	551 unique values 0 missing
V5534	numeric	476 unique values 0 missing
V5608	numeric	624 unique values 0 missing
V5694	numeric	733 unique values 0 missing
V5763	numeric	647 unique values 0 missing
V5895	numeric	506 unique values 0 missing
V5961	numeric	612 unique values 0 missing
V6053	numeric	646 unique values 0 missing
V6117	numeric	550 unique values 0 missing
V6178	numeric	682 unique values 0 missing
V6206	numeric	622 unique values 0 missing
V6320	numeric	558 unique values 0 missing
V6324	numeric	721 unique values 0 missing
V6376	numeric	722 unique values 0 missing
V6569	numeric	622 unique values 0 missing
V6653	numeric	653 unique values 0 missing
V6677	numeric	249 unique values 0 missing
V6704	numeric	618 unique values 0 missing
V6745	numeric	618 unique values 0 missing
V6821	numeric	665 unique values 0 missing
V6882	numeric	611 unique values 0 missing
V6955	numeric	668 unique values 0 missing