{ "data_id": "44763", "name": "Click_prediction_small_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "Click_prediction_small_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "2e53ca33-f93d-47fb-9fc8-39463fef0607", "description": "Subsampling of the dataset Click_prediction_small (42733) with\n\nseed=0\nargs.nrows=2000\nargs.ncols=100\nargs.nclasses=10\nargs.no_stratify=True\nGenerated with the following source code:\n\n\n```python\n def subsample(\n self,\n seed: int,\n nrows_max: int = 2_000,\n ncols_max: int = 100,\n nclasses_max: int = 10,\n stratified: bool = True,\n ) -> Dataset:\n rng = np.random.default_rng(seed)\n\n x = self.x\n y = self.y\n\n # Uniformly sample\n classes = y.unique()\n if len(classes) > nclasses_max:\n vcs = y.value_counts()\n selected_classes = rng.choice(\n classes,\n size=nclasses_max,\n replace=False,\n p=vcs \/ sum(vcs),\n )\n\n # Select the indices where one of these classes is present\n idxs = y.index[y.isin(classes)]\n x = x.iloc[idxs]\n y = y.iloc[idxs]\n\n # Uniformly sample columns if required\n if len(x.columns) > ncols_max:\n columns_idxs = rng.choice(\n list(range(len(x.columns))), size=ncols_max, replace=False\n )\n sorted_column_idxs = sorted(columns_idxs)\n selected_columns = list(x.columns[sorted_column_idxs])\n x = x[selected_columns]\n else:\n sorted_column_idxs = list(range(len(x.columns)))\n\n if len(x) > nrows_max:\n # Stratify accordingly\n target_name = y.name\n data = pd.concat((x, y), axis=\"columns\")\n _, subset = train_test_split(\n data,\n test_size=nrows_max,\n stratify=data[target_name],\n shuffle=True,\n random_state=seed,\n )\n x = subset.drop(target_name, axis=\"columns\")\n y = subset[target_name]\n\n # We need to convert categorical columns to string for openml\n categorical_mask = [self.categorical_mask[i] for i in sorted_column_idxs]\n columns = list(x.columns)\n\n return Dataset(\n # Technically this is not the same but it's where it was derived from\n dataset=self.dataset,\n x=x,\n y=y,\n categorical_mask=categorical_mask,\n columns=columns,\n )\n```", "format": "arff", "uploader": "Eddie Bergman", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:49:13", "update_comment": null, "last_update": "2022-11-17 18:49:13", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111525\/dataset", "default_target_attribute": "click", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Click_prediction_small_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset Click_prediction_small (42733) with seed=0 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 " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 12, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 5, "NumberOfSymbolicFeatures": 7, "PercentageOfBinaryFeatures": 8.333333333333332, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.7153576788394197, "PercentageOfNumericFeatures": 41.66666666666667, "Dimensionality": 0.006, "PercentageOfSymbolicFeatures": 58.333333333333336, "MajorityClassPercentage": 83.15, "MajorityClassSize": 1663, "MinorityClassPercentage": 16.85, "MinorityClassSize": 337, "NumberOfBinaryFeatures": 1 }, "tags": [ { "uploader": "38960", "tag": "Health" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "click", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1663", "0" ], [ "0", "337" ] ] ] }, { "name": "impression", "index": "0", "type": "numeric", "distinct": "26", "missing": "0", "min": "1", "max": "584", "mean": "2", "stdev": "17" }, { "name": "url_hash", "index": "1", "type": "numeric", "distinct": "942", "missing": "0", "min": "2147483647", "max": "2147483647", "mean": "2147483647", "stdev": "2147483647" }, { "name": "ad_id", "index": "2", "type": "nominal", "distinct": "1658", "missing": "0", "distr": [] }, { "name": "advertiser_id", "index": "3", "type": "nominal", "distinct": "918", "missing": "0", "distr": [] }, { "name": "depth", "index": "4", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "position", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "query_id", "index": "6", "type": "numeric", "distinct": "1826", "missing": "0", "min": "0", "max": "26240100", "mean": "3054725", "stdev": "5776398" }, { "name": "keyword_id", "index": "7", "type": "nominal", "distinct": "1655", "missing": "0", "distr": [] }, { "name": "title_id", "index": "8", "type": "nominal", "distinct": "1754", "missing": "0", "distr": [] }, { "name": "description_id", "index": "9", "type": "nominal", "distinct": "1687", "missing": "0", "distr": [] }, { "name": "user_id", "index": "10", "type": "nominal", "distinct": "1511", "missing": "0", "distr": [] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }