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_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 arcene (41157) 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	2 unique values 0 missing
V198	numeric	71 unique values 0 missing
V274	numeric	42 unique values 0 missing
V346	numeric	92 unique values 0 missing
V395	numeric	60 unique values 0 missing
V542	numeric	23 unique values 0 missing
V617	numeric	21 unique values 0 missing
V623	numeric	88 unique values 0 missing
V851	numeric	40 unique values 0 missing
V917	numeric	69 unique values 0 missing
V1155	numeric	17 unique values 0 missing
V1164	numeric	58 unique values 0 missing
V1231	numeric	58 unique values 0 missing
V1236	numeric	76 unique values 0 missing
V1332	numeric	26 unique values 0 missing
V1429	numeric	42 unique values 0 missing
V1479	numeric	22 unique values 0 missing
V1600	numeric	7 unique values 0 missing
V2022	numeric	61 unique values 0 missing
V2146	numeric	87 unique values 0 missing
V2470	numeric	23 unique values 0 missing
V2549	numeric	33 unique values 0 missing
V2598	numeric	83 unique values 0 missing
V2608	numeric	86 unique values 0 missing
V2708	numeric	4 unique values 0 missing
V2757	numeric	13 unique values 0 missing
V2789	numeric	63 unique values 0 missing
V2918	numeric	40 unique values 0 missing
V2919	numeric	52 unique values 0 missing
V3011	numeric	31 unique values 0 missing
V3091	numeric	89 unique values 0 missing
V3213	numeric	48 unique values 0 missing
V3273	numeric	25 unique values 0 missing
V3443	numeric	81 unique values 0 missing
V3618	numeric	57 unique values 0 missing
V3674	numeric	31 unique values 0 missing
V3809	numeric	88 unique values 0 missing
V4006	numeric	80 unique values 0 missing
V4058	numeric	86 unique values 0 missing
V4195	numeric	29 unique values 0 missing
V4197	numeric	13 unique values 0 missing
V4232	numeric	34 unique values 0 missing
V4262	numeric	14 unique values 0 missing
V4494	numeric	58 unique values 0 missing
V4505	numeric	51 unique values 0 missing
V4541	numeric	4 unique values 0 missing
V4564	numeric	36 unique values 0 missing
V4584	numeric	58 unique values 0 missing
V4686	numeric	5 unique values 0 missing
V4826	numeric	61 unique values 0 missing
V4956	numeric	86 unique values 0 missing
V4992	numeric	47 unique values 0 missing
V5069	numeric	28 unique values 0 missing
V5091	numeric	51 unique values 0 missing
V5106	numeric	40 unique values 0 missing
V5142	numeric	50 unique values 0 missing
V5274	numeric	31 unique values 0 missing
V5341	numeric	25 unique values 0 missing
V5388	numeric	61 unique values 0 missing
V5451	numeric	84 unique values 0 missing
V5811	numeric	60 unique values 0 missing
V5922	numeric	90 unique values 0 missing
V6112	numeric	32 unique values 0 missing
V6214	numeric	40 unique values 0 missing
V6385	numeric	60 unique values 0 missing
V6402	numeric	39 unique values 0 missing
V6733	numeric	8 unique values 0 missing
V7168	numeric	26 unique values 0 missing
V7214	numeric	42 unique values 0 missing
V7228	numeric	26 unique values 0 missing
V7453	numeric	80 unique values 0 missing
V7461	numeric	3 unique values 0 missing
V7477	numeric	62 unique values 0 missing
V7479	numeric	60 unique values 0 missing
V7528	numeric	30 unique values 0 missing
V7688	numeric	29 unique values 0 missing
V7706	numeric	26 unique values 0 missing
V7742	numeric	81 unique values 0 missing
V7828	numeric	25 unique values 0 missing
V8034	numeric	85 unique values 0 missing
V8115	numeric	46 unique values 0 missing
V8153	numeric	26 unique values 0 missing
V8197	numeric	21 unique values 0 missing
V8206	numeric	59 unique values 0 missing
V8315	numeric	18 unique values 0 missing
V8391	numeric	4 unique values 0 missing
V8513	numeric	37 unique values 0 missing
V8588	numeric	39 unique values 0 missing
V8613	numeric	24 unique values 0 missing
V8701	numeric	85 unique values 0 missing
V8982	numeric	8 unique values 0 missing
V9148	numeric	62 unique values 0 missing
V9208	numeric	54 unique values 0 missing
V9400	numeric	42 unique values 0 missing
V9414	numeric	15 unique values 0 missing
V9569	numeric	38 unique values 0 missing
V9661	numeric	57 unique values 0 missing
V9704	numeric	32 unique values 0 missing
V9757	numeric	49 unique values 0 missing
V9805	numeric	89 unique values 0 missing
V9999	numeric	60 unique values 0 missing