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

arcene_seed_2_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 arcene (41157) with seed=2 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
V387	numeric	42 unique values 0 missing
V396	numeric	43 unique values 0 missing
V547	numeric	4 unique values 0 missing
V569	numeric	23 unique values 0 missing
V765	numeric	60 unique values 0 missing
V911	numeric	86 unique values 0 missing
V967	numeric	12 unique values 0 missing
V1007	numeric	21 unique values 0 missing
V1042	numeric	20 unique values 0 missing
V1068	numeric	30 unique values 0 missing
V1083	numeric	69 unique values 0 missing
V1490	numeric	5 unique values 0 missing
V1862	numeric	69 unique values 0 missing
V1863	numeric	63 unique values 0 missing
V1998	numeric	56 unique values 0 missing
V2012	numeric	28 unique values 0 missing
V2127	numeric	66 unique values 0 missing
V2162	numeric	45 unique values 0 missing
V2183	numeric	2 unique values 0 missing
V2228	numeric	48 unique values 0 missing
V2582	numeric	23 unique values 0 missing
V2587	numeric	5 unique values 0 missing
V2591	numeric	69 unique values 0 missing
V2728	numeric	33 unique values 0 missing
V2957	numeric	81 unique values 0 missing
V3033	numeric	37 unique values 0 missing
V3166	numeric	69 unique values 0 missing
V3311	numeric	27 unique values 0 missing
V3319	numeric	63 unique values 0 missing
V3388	numeric	91 unique values 0 missing
V3440	numeric	88 unique values 0 missing
V3778	numeric	24 unique values 0 missing
V3892	numeric	38 unique values 0 missing
V4055	numeric	49 unique values 0 missing
V4099	numeric	59 unique values 0 missing
V4199	numeric	65 unique values 0 missing
V4295	numeric	64 unique values 0 missing
V4374	numeric	86 unique values 0 missing
V4397	numeric	49 unique values 0 missing
V4438	numeric	71 unique values 0 missing
V4471	numeric	47 unique values 0 missing
V4475	numeric	51 unique values 0 missing
V4526	numeric	48 unique values 0 missing
V4688	numeric	55 unique values 0 missing
V4707	numeric	28 unique values 0 missing
V4750	numeric	43 unique values 0 missing
V4853	numeric	47 unique values 0 missing
V4975	numeric	23 unique values 0 missing
V4977	numeric	65 unique values 0 missing
V5011	numeric	59 unique values 0 missing
V5083	numeric	67 unique values 0 missing
V5153	numeric	50 unique values 0 missing
V5205	numeric	45 unique values 0 missing
V5226	numeric	61 unique values 0 missing
V5536	numeric	38 unique values 0 missing
V5579	numeric	46 unique values 0 missing
V5669	numeric	27 unique values 0 missing
V5765	numeric	8 unique values 0 missing
V5920	numeric	67 unique values 0 missing
V5921	numeric	27 unique values 0 missing
V5922	numeric	90 unique values 0 missing
V5947	numeric	66 unique values 0 missing
V6128	numeric	24 unique values 0 missing
V6289	numeric	25 unique values 0 missing
V6324	numeric	77 unique values 0 missing
V6426	numeric	23 unique values 0 missing
V6522	numeric	54 unique values 0 missing
V6645	numeric	30 unique values 0 missing
V6738	numeric	9 unique values 0 missing
V6776	numeric	59 unique values 0 missing
V6787	numeric	11 unique values 0 missing
V6887	numeric	71 unique values 0 missing
V6908	numeric	83 unique values 0 missing
V6919	numeric	77 unique values 0 missing
V6974	numeric	66 unique values 0 missing
V7222	numeric	35 unique values 0 missing
V7436	numeric	23 unique values 0 missing
V7687	numeric	66 unique values 0 missing
V7716	numeric	55 unique values 0 missing
V7829	numeric	72 unique values 0 missing
V8060	numeric	40 unique values 0 missing
V8066	numeric	59 unique values 0 missing
V8282	numeric	27 unique values 0 missing
V8293	numeric	35 unique values 0 missing
V8466	numeric	25 unique values 0 missing
V8603	numeric	83 unique values 0 missing
V8623	numeric	10 unique values 0 missing
V8724	numeric	55 unique values 0 missing
V8728	numeric	59 unique values 0 missing
V8813	numeric	31 unique values 0 missing
V8864	numeric	20 unique values 0 missing
V8907	numeric	32 unique values 0 missing
V9030	numeric	47 unique values 0 missing
V9198	numeric	87 unique values 0 missing
V9287	numeric	61 unique values 0 missing
V9386	numeric	70 unique values 0 missing
V9541	numeric	46 unique values 0 missing
V9611	numeric	50 unique values 0 missing
V9717	numeric	24 unique values 0 missing
V9843	numeric	66 unique values 0 missing