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

dilbert_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 dilbert (41163) 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	5 unique values 0 missing
V54	numeric	1998 unique values 0 missing
V70	numeric	1998 unique values 0 missing
V117	numeric	1999 unique values 0 missing
V155	numeric	1997 unique values 0 missing
V156	numeric	1999 unique values 0 missing
V176	numeric	1998 unique values 0 missing
V228	numeric	1999 unique values 0 missing
V256	numeric	1997 unique values 0 missing
V260	numeric	1994 unique values 0 missing
V269	numeric	1999 unique values 0 missing
V324	numeric	1997 unique values 0 missing
V335	numeric	1999 unique values 0 missing
V341	numeric	1998 unique values 0 missing
V345	numeric	1994 unique values 0 missing
V357	numeric	1998 unique values 0 missing
V379	numeric	2000 unique values 0 missing
V394	numeric	1999 unique values 0 missing
V405	numeric	1999 unique values 0 missing
V422	numeric	1997 unique values 0 missing
V430	numeric	1998 unique values 0 missing
V439	numeric	1997 unique values 0 missing
V442	numeric	1999 unique values 0 missing
V528	numeric	1998 unique values 0 missing
V542	numeric	1998 unique values 0 missing
V590	numeric	2000 unique values 0 missing
V650	numeric	1999 unique values 0 missing
V686	numeric	1998 unique values 0 missing
V712	numeric	1998 unique values 0 missing
V715	numeric	1998 unique values 0 missing
V720	numeric	1998 unique values 0 missing
V721	numeric	1997 unique values 0 missing
V728	numeric	1997 unique values 0 missing
V765	numeric	2000 unique values 0 missing
V794	numeric	1996 unique values 0 missing
V830	numeric	1998 unique values 0 missing
V866	numeric	1988 unique values 0 missing
V900	numeric	1994 unique values 0 missing
V915	numeric	1993 unique values 0 missing
V919	numeric	1991 unique values 0 missing
V942	numeric	1994 unique values 0 missing
V953	numeric	1998 unique values 0 missing
V964	numeric	1988 unique values 0 missing
V971	numeric	1993 unique values 0 missing
V973	numeric	1992 unique values 0 missing
V974	numeric	1996 unique values 0 missing
V978	numeric	1994 unique values 0 missing
V984	numeric	1991 unique values 0 missing
V1016	numeric	1987 unique values 0 missing
V1025	numeric	1994 unique values 0 missing
V1045	numeric	1991 unique values 0 missing
V1052	numeric	1996 unique values 0 missing
V1069	numeric	1996 unique values 0 missing
V1110	numeric	1996 unique values 0 missing
V1113	numeric	1994 unique values 0 missing
V1131	numeric	1992 unique values 0 missing
V1142	numeric	1998 unique values 0 missing
V1146	numeric	1997 unique values 0 missing
V1161	numeric	1993 unique values 0 missing
V1182	numeric	1998 unique values 0 missing
V1200	numeric	1993 unique values 0 missing
V1260	numeric	1997 unique values 0 missing
V1296	numeric	1997 unique values 0 missing
V1315	numeric	1997 unique values 0 missing
V1336	numeric	1996 unique values 0 missing
V1369	numeric	1997 unique values 0 missing
V1373	numeric	1996 unique values 0 missing
V1381	numeric	1996 unique values 0 missing
V1417	numeric	1996 unique values 0 missing
V1522	numeric	1998 unique values 0 missing
V1529	numeric	1999 unique values 0 missing
V1535	numeric	1989 unique values 0 missing
V1605	numeric	1993 unique values 0 missing
V1671	numeric	1990 unique values 0 missing
V1672	numeric	1992 unique values 0 missing
V1678	numeric	1990 unique values 0 missing
V1728	numeric	1996 unique values 0 missing
V1730	numeric	1993 unique values 0 missing
V1735	numeric	1998 unique values 0 missing
V1767	numeric	1992 unique values 0 missing
V1792	numeric	1997 unique values 0 missing
V1794	numeric	1992 unique values 0 missing
V1796	numeric	1999 unique values 0 missing
V1799	numeric	1994 unique values 0 missing
V1833	numeric	2000 unique values 0 missing
V1834	numeric	1993 unique values 0 missing
V1847	numeric	1999 unique values 0 missing
V1851	numeric	1993 unique values 0 missing
V1861	numeric	1998 unique values 0 missing
V1874	numeric	1988 unique values 0 missing
V1875	numeric	1989 unique values 0 missing
V1900	numeric	1999 unique values 0 missing
V1922	numeric	1989 unique values 0 missing
V1929	numeric	1992 unique values 0 missing
V1939	numeric	1998 unique values 0 missing
V1946	numeric	1997 unique values 0 missing
V1965	numeric	1992 unique values 0 missing
V1974	numeric	1996 unique values 0 missing
V1985	numeric	1998 unique values 0 missing
V1995	numeric	1997 unique values 0 missing
V1998	numeric	1994 unique values 0 missing