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

riccardo_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 riccardo (41161) 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	699 unique values 0 missing
V21	numeric	1197 unique values 0 missing
V130	numeric	545 unique values 0 missing
V138	numeric	1039 unique values 0 missing
V166	numeric	1006 unique values 0 missing
V183	numeric	658 unique values 0 missing
V327	numeric	931 unique values 0 missing
V360	numeric	951 unique values 0 missing
V388	numeric	901 unique values 0 missing
V396	numeric	788 unique values 0 missing
V440	numeric	1089 unique values 0 missing
V480	numeric	970 unique values 0 missing
V591	numeric	916 unique values 0 missing
V673	numeric	820 unique values 0 missing
V731	numeric	920 unique values 0 missing
V754	numeric	763 unique values 0 missing
V762	numeric	993 unique values 0 missing
V810	numeric	936 unique values 0 missing
V884	numeric	988 unique values 0 missing
V936	numeric	1021 unique values 0 missing
V965	numeric	1017 unique values 0 missing
V995	numeric	581 unique values 0 missing
V1040	numeric	1137 unique values 0 missing
V1059	numeric	743 unique values 0 missing
V1081	numeric	568 unique values 0 missing
V1083	numeric	687 unique values 0 missing
V1116	numeric	701 unique values 0 missing
V1203	numeric	1047 unique values 0 missing
V1240	numeric	677 unique values 0 missing
V1250	numeric	1145 unique values 0 missing
V1266	numeric	383 unique values 0 missing
V1274	numeric	525 unique values 0 missing
V1333	numeric	1132 unique values 0 missing
V1354	numeric	751 unique values 0 missing
V1397	numeric	815 unique values 0 missing
V1398	numeric	974 unique values 0 missing
V1594	numeric	741 unique values 0 missing
V1651	numeric	1083 unique values 0 missing
V1659	numeric	886 unique values 0 missing
V1693	numeric	998 unique values 0 missing
V1774	numeric	542 unique values 0 missing
V1819	numeric	127 unique values 0 missing
V1823	numeric	311 unique values 0 missing
V1837	numeric	224 unique values 0 missing
V1907	numeric	684 unique values 0 missing
V2004	numeric	665 unique values 0 missing
V2017	numeric	642 unique values 0 missing
V2018	numeric	630 unique values 0 missing
V2082	numeric	910 unique values 0 missing
V2181	numeric	706 unique values 0 missing
V2213	numeric	875 unique values 0 missing
V2218	numeric	420 unique values 0 missing
V2448	numeric	897 unique values 0 missing
V2479	numeric	885 unique values 0 missing
V2486	numeric	819 unique values 0 missing
V2548	numeric	720 unique values 0 missing
V2594	numeric	867 unique values 0 missing
V2595	numeric	778 unique values 0 missing
V2615	numeric	405 unique values 0 missing
V2690	numeric	654 unique values 0 missing
V2745	numeric	674 unique values 0 missing
V2753	numeric	859 unique values 0 missing
V2795	numeric	665 unique values 0 missing
V2814	numeric	757 unique values 0 missing
V2815	numeric	1124 unique values 0 missing
V2816	numeric	898 unique values 0 missing
V2820	numeric	807 unique values 0 missing
V2913	numeric	206 unique values 0 missing
V2924	numeric	348 unique values 0 missing
V2948	numeric	978 unique values 0 missing
V3009	numeric	798 unique values 0 missing
V3087	numeric	918 unique values 0 missing
V3096	numeric	1104 unique values 0 missing
V3119	numeric	479 unique values 0 missing
V3169	numeric	855 unique values 0 missing
V3199	numeric	780 unique values 0 missing
V3254	numeric	1029 unique values 0 missing
V3288	numeric	675 unique values 0 missing
V3325	numeric	1071 unique values 0 missing
V3367	numeric	938 unique values 0 missing
V3406	numeric	994 unique values 0 missing
V3514	numeric	916 unique values 0 missing
V3551	numeric	1088 unique values 0 missing
V3606	numeric	1206 unique values 0 missing
V3649	numeric	892 unique values 0 missing
V3654	numeric	836 unique values 0 missing
V3682	numeric	739 unique values 0 missing
V3746	numeric	1105 unique values 0 missing
V3769	numeric	768 unique values 0 missing
V3787	numeric	693 unique values 0 missing
V3915	numeric	570 unique values 0 missing
V3958	numeric	1030 unique values 0 missing
V3972	numeric	1143 unique values 0 missing
V3978	numeric	1027 unique values 0 missing
V4004	numeric	1090 unique values 0 missing
V4044	numeric	1056 unique values 0 missing
V4103	numeric	1784 unique values 0 missing
V4128	numeric	1799 unique values 0 missing
V4280	numeric	1786 unique values 0 missing
V4291	numeric	1783 unique values 0 missing