{ "data_id": "44439", "name": "eye_movements_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "eye_movements_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 2, "version_label": "f4965cea-77c0-4a2e-b583-8bdcd7aa700f", "description": "Subsampling of the dataset eye_movements (44157) with\n\nseed=1\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 18:01:29", "update_comment": null, "last_update": "2022-11-17 18:01:29", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111201\/dataset", "default_target_attribute": "label", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "eye_movements_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset eye_movements (44157) 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.ch " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 24, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 20, "NumberOfSymbolicFeatures": 4, "PercentageOfBinaryFeatures": 16.666666666666664, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.4762381190595298, "PercentageOfMissingValues": 0, "Dimensionality": 0.012, "PercentageOfNumericFeatures": 83.33333333333334, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 16.666666666666664, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 4 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Mathematics" } ], "features": [ { "name": "label", "index": "23", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "lineNo", "index": "0", "type": "numeric", "distinct": "2000", "missing": "0", "min": "1", "max": "10927", "mean": "5406", "stdev": "3194" }, { "name": "assgNo", "index": "1", "type": "numeric", "distinct": "320", "missing": "0", "min": "1", "max": "336", "mean": "166", "stdev": "98" }, { "name": "P1stFixation", "index": "2", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "209", "182" ], [ "791", "818" ] ] ] }, { "name": "P2stFixation", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "616", "678" ], [ "384", "322" ] ] ] }, { "name": "prevFixDur", "index": "4", "type": "numeric", "distinct": "48", "missing": "0", "min": "0", "max": "1036", "mean": "156", "stdev": "83" }, { "name": "firstfixDur", "index": "5", "type": "numeric", "distinct": "41", "missing": "0", "min": "20", "max": "777", "mean": "164", "stdev": "71" }, { "name": "firstPassFixDur", "index": "6", "type": "numeric", "distinct": "72", "missing": "0", "min": "20", "max": "1392", "mean": "191", "stdev": "100" }, { "name": "nextFixDur", "index": "7", "type": "numeric", "distinct": "47", "missing": "0", "min": "0", "max": "616", "mean": "167", "stdev": "74" }, { "name": "firstSaccLen", "index": "8", "type": "numeric", "distinct": "1875", "missing": "0", "min": "0", "max": "1686", "mean": "232", "stdev": "202" }, { "name": "lastSaccLen", "index": "9", "type": "numeric", "distinct": "1950", "missing": "0", "min": "0", "max": "1641", "mean": "239", "stdev": "201" }, { "name": "prevFixPos", "index": "10", "type": "numeric", "distinct": "1810", "missing": "0", "min": "0", "max": "1070", "mean": "216", "stdev": "197" }, { "name": "landingPos", "index": "11", "type": "numeric", "distinct": "1808", "missing": "0", "min": "1", "max": "1270", "mean": "74", "stdev": "86" }, { "name": "leavingPos", "index": "12", "type": "numeric", "distinct": "1841", "missing": "0", "min": "1", "max": "1279", "mean": "76", "stdev": "83" }, { "name": "totalFixDur", "index": "13", "type": "numeric", "distinct": "72", "missing": "0", "min": "20", "max": "1351", "mean": "192", "stdev": "99" }, { "name": "meanFixDur", "index": "14", "type": "numeric", "distinct": "98", "missing": "0", "min": "20", "max": "638", "mean": "164", "stdev": "69" }, { "name": "regressLen", "index": "15", "type": "numeric", "distinct": "224", "missing": "0", "min": "0", "max": "24987", "mean": "426", "stdev": "1772" }, { "name": "nextWordRegress", "index": "16", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "799", "901" ], [ "201", "99" ] ] ] }, { "name": "regressDur", "index": "17", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "5838", "mean": "193", "stdev": "539" }, { "name": "pupilDiamMax", "index": "18", "type": "numeric", "distinct": "1420", "missing": "0", "min": "-4", "max": "3", "mean": "0", "stdev": "0" }, { "name": "pupilDiamLag", "index": "19", "type": "numeric", "distinct": "1186", "missing": "0", "min": "-1", "max": "3", "mean": "0", "stdev": "0" }, { "name": "timePrtctg", "index": "20", "type": "numeric", "distinct": "554", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "titleNo", "index": "21", "type": "numeric", "distinct": "10", "missing": "0", "min": "1", "max": "10", "mean": "5", "stdev": "3" }, { "name": "wordNo", "index": "22", "type": "numeric", "distinct": "9", "missing": "0", "min": "1", "max": "9", "mean": "3", "stdev": "2" } ], "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 }