{ "data_id": "44671", "name": "GesturePhaseSegmentationProcessed_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "GesturePhaseSegmentationProcessed_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "55c9a95e-6255-4b58-bb22-0fb4e2858c62", "description": "Subsampling of the dataset GesturePhaseSegmentationProcessed (4538) with\n\nseed=3\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 18:41:44", "update_comment": null, "last_update": "2022-11-17 18:41:44", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111433\/dataset", "default_target_attribute": "Phase", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "GesturePhaseSegmentationProcessed_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset GesturePhaseSegmentationProcessed (4538) 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() select " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 33, "NumberOfClasses": 5, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 32, "NumberOfSymbolicFeatures": 1, "MinorityClassPercentage": 10.100000000000001, "MinorityClassSize": 202, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.22811405702851426, "PercentageOfMissingValues": 0, "Dimensionality": 0.0165, "PercentageOfNumericFeatures": 96.96969696969697, "MajorityClassPercentage": 29.9, "PercentageOfSymbolicFeatures": 3.0303030303030303, "MajorityClassSize": 598 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Mathematics" } ], "features": [ { "name": "Phase", "index": "32", "type": "nominal", "distinct": "5", "missing": "0", "target": "1", "distr": [ [ "D", "H", "P", "R", "S" ], [ [ "555", "0", "0", "0", "0" ], [ "0", "202", "0", "0", "0" ], [ "0", "0", "425", "0", "0" ], [ "0", "0", "0", "220", "0" ], [ "0", "0", "0", "0", "598" ] ] ] }, { "name": "X1", "index": "0", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X2", "index": "1", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X3", "index": "2", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X4", "index": "3", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X5", "index": "4", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X6", "index": "5", "type": "numeric", "distinct": "1993", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X7", "index": "6", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X8", "index": "7", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X9", "index": "8", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X10", "index": "9", "type": "numeric", "distinct": "1999", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X11", "index": "10", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X12", "index": "11", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X13", "index": "12", "type": "numeric", "distinct": "1986", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X14", "index": "13", "type": "numeric", "distinct": "1986", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X15", "index": "14", "type": "numeric", "distinct": "1921", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X16", "index": "15", "type": "numeric", "distinct": "1990", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X17", "index": "16", "type": "numeric", "distinct": "1984", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X18", "index": "17", "type": "numeric", "distinct": "1934", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X19", "index": "18", "type": "numeric", "distinct": "1970", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X20", "index": "19", "type": "numeric", "distinct": "1973", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X21", "index": "20", "type": "numeric", "distinct": "1915", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X22", "index": "21", "type": "numeric", "distinct": "1976", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X23", "index": "22", "type": "numeric", "distinct": "1984", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X24", "index": "23", "type": "numeric", "distinct": "1939", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X25", "index": "24", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X26", "index": "25", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X27", "index": "26", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X28", "index": "27", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X29", "index": "28", "type": "numeric", "distinct": "1979", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X30", "index": "29", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X31", "index": "30", "type": "numeric", "distinct": "1981", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X32", "index": "31", "type": "numeric", "distinct": "1985", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" } ], "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 }