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_1_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=1 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
V142	numeric	621 unique values 0 missing
V197	numeric	254 unique values 0 missing
V248	numeric	255 unique values 0 missing
V285	numeric	543 unique values 0 missing
V390	numeric	615 unique values 0 missing
V444	numeric	579 unique values 0 missing
V448	numeric	652 unique values 0 missing
V611	numeric	568 unique values 0 missing
V659	numeric	683 unique values 0 missing
V831	numeric	579 unique values 0 missing
V836	numeric	254 unique values 0 missing
V884	numeric	254 unique values 0 missing
V888	numeric	617 unique values 0 missing
V957	numeric	641 unique values 0 missing
V1025	numeric	515 unique values 0 missing
V1065	numeric	649 unique values 0 missing
V1150	numeric	550 unique values 0 missing
V1453	numeric	634 unique values 0 missing
V1544	numeric	566 unique values 0 missing
V1772	numeric	552 unique values 0 missing
V1829	numeric	627 unique values 0 missing
V1870	numeric	554 unique values 0 missing
V1873	numeric	255 unique values 0 missing
V1944	numeric	693 unique values 0 missing
V1982	numeric	627 unique values 0 missing
V2004	numeric	521 unique values 0 missing
V2097	numeric	252 unique values 0 missing
V2099	numeric	700 unique values 0 missing
V2162	numeric	649 unique values 0 missing
V2218	numeric	560 unique values 0 missing
V2310	numeric	736 unique values 0 missing
V2350	numeric	549 unique values 0 missing
V2478	numeric	626 unique values 0 missing
V2602	numeric	649 unique values 0 missing
V2643	numeric	253 unique values 0 missing
V2735	numeric	534 unique values 0 missing
V2877	numeric	255 unique values 0 missing
V2912	numeric	252 unique values 0 missing
V3011	numeric	661 unique values 0 missing
V3016	numeric	513 unique values 0 missing
V3043	numeric	711 unique values 0 missing
V3066	numeric	256 unique values 0 missing
V3227	numeric	566 unique values 0 missing
V3235	numeric	586 unique values 0 missing
V3266	numeric	625 unique values 0 missing
V3283	numeric	692 unique values 0 missing
V3298	numeric	578 unique values 0 missing
V3361	numeric	724 unique values 0 missing
V3468	numeric	534 unique values 0 missing
V3560	numeric	604 unique values 0 missing
V3586	numeric	622 unique values 0 missing
V3635	numeric	550 unique values 0 missing
V3665	numeric	538 unique values 0 missing
V3676	numeric	504 unique values 0 missing
V3697	numeric	254 unique values 0 missing
V3794	numeric	614 unique values 0 missing
V3834	numeric	557 unique values 0 missing
V3872	numeric	489 unique values 0 missing
V3913	numeric	631 unique values 0 missing
V3924	numeric	497 unique values 0 missing
V4183	numeric	254 unique values 0 missing
V4261	numeric	519 unique values 0 missing
V4396	numeric	513 unique values 0 missing
V4468	numeric	650 unique values 0 missing
V4583	numeric	736 unique values 0 missing
V4607	numeric	523 unique values 0 missing
V4846	numeric	674 unique values 0 missing
V5156	numeric	632 unique values 0 missing
V5184	numeric	644 unique values 0 missing
V5196	numeric	554 unique values 0 missing
V5356	numeric	556 unique values 0 missing
V5360	numeric	600 unique values 0 missing
V5364	numeric	252 unique values 0 missing
V5367	numeric	553 unique values 0 missing
V5419	numeric	657 unique values 0 missing
V5532	numeric	585 unique values 0 missing
V5542	numeric	615 unique values 0 missing
V5568	numeric	625 unique values 0 missing
V5620	numeric	251 unique values 0 missing
V5782	numeric	675 unique values 0 missing
V5826	numeric	462 unique values 0 missing
V5849	numeric	642 unique values 0 missing
V5889	numeric	553 unique values 0 missing
V5902	numeric	568 unique values 0 missing
V5969	numeric	750 unique values 0 missing
V6039	numeric	613 unique values 0 missing
V6126	numeric	559 unique values 0 missing
V6164	numeric	640 unique values 0 missing
V6180	numeric	249 unique values 0 missing
V6260	numeric	548 unique values 0 missing
V6451	numeric	618 unique values 0 missing
V6579	numeric	256 unique values 0 missing
V6618	numeric	662 unique values 0 missing
V6744	numeric	501 unique values 0 missing
V6753	numeric	251 unique values 0 missing
V6876	numeric	662 unique values 0 missing
V6945	numeric	520 unique values 0 missing
V6969	numeric	724 unique values 0 missing
V7011	numeric	485 unique values 0 missing
V7058	numeric	687 unique values 0 missing