{ "data_id": "44741", "name": "robert_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "robert_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "68420531-06fa-4a0d-b6ca-ccc8c4b33561", "description": "Subsampling of the dataset robert (41165) 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 18:47:18", "update_comment": null, "last_update": "2022-11-17 18:47:18", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111503\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "robert_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset robert (41165) 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() selected_classes = rng.choice( c " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 10, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.09804902451225612, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 99.00990099009901, "MajorityClassPercentage": 10.4, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassSize": 208, "MinorityClassPercentage": 9.6, "MinorityClassSize": 192, "NumberOfBinaryFeatures": 0 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "10", "missing": "0", "target": "1", "distr": [ [ "0", "1", "2", "3", "4", "5", "6", "7", "8", "9" ], [ [ "198", "0", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "192", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "196", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "199", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "208", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "206", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "197", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "201", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "196", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "0", "207" ] ] ] }, { "name": "V11", "index": "0", "type": "numeric", "distinct": "629", "missing": "0", "min": "0", "max": "900", "mean": "251", "stdev": "196" }, { "name": "V34", "index": "1", "type": "numeric", "distinct": "473", "missing": "0", "min": "137", "max": "900", "mean": "321", "stdev": "181" }, { "name": "V218", "index": "2", "type": "numeric", "distinct": "590", "missing": "0", "min": "136", "max": "900", "mean": "397", "stdev": "220" }, { "name": "V233", "index": "3", "type": "numeric", "distinct": "573", "missing": "0", "min": "68", "max": "864", "mean": "405", "stdev": "139" }, { "name": "V281", "index": "4", "type": "numeric", "distinct": "519", "missing": "0", "min": "94", "max": "825", "mean": "480", "stdev": "119" }, { "name": "V309", "index": "5", "type": "numeric", "distinct": "549", "missing": "0", "min": "98", "max": "810", "mean": "488", "stdev": "134" }, { "name": "V550", "index": "6", "type": "numeric", "distinct": "610", "missing": "0", "min": "62", "max": "825", "mean": "416", "stdev": "143" }, { "name": "V609", "index": "7", "type": "numeric", "distinct": "552", "missing": "0", "min": "0", "max": "896", "mean": "306", "stdev": "235" }, { "name": "V651", "index": "8", "type": "numeric", "distinct": "757", "missing": "0", "min": "12", "max": "876", "mean": "478", "stdev": "227" }, { "name": "V670", "index": "9", "type": "numeric", "distinct": "599", "missing": "0", "min": "0", "max": "900", "mean": "241", "stdev": "192" }, { "name": "V737", "index": "10", "type": "numeric", "distinct": "574", "missing": "0", "min": "79", "max": "875", "mean": "486", "stdev": "134" }, { "name": "V810", "index": "11", "type": "numeric", "distinct": "570", "missing": "0", "min": "140", "max": "900", "mean": "393", "stdev": "221" }, { "name": "V996", "index": "12", "type": "numeric", "distinct": "634", "missing": "0", "min": "62", "max": "837", "mean": "471", "stdev": "167" }, { "name": "V1137", "index": "13", "type": "numeric", "distinct": "731", "missing": "0", "min": "35", "max": "871", "mean": "482", "stdev": "215" }, { "name": "V1233", "index": "14", "type": "numeric", "distinct": "610", "missing": "0", "min": "57", "max": "820", "mean": "354", "stdev": "165" }, { "name": "V1275", "index": "15", "type": "numeric", "distinct": "252", "missing": "0", "min": "0", "max": "900", "mean": "489", "stdev": "224" }, { "name": "V1289", "index": "16", "type": "numeric", "distinct": "598", "missing": "0", "min": "0", "max": "900", "mean": "244", "stdev": "193" }, { "name": "V1362", "index": "17", "type": "numeric", "distinct": "630", "missing": "0", "min": "63", "max": "882", "mean": "547", "stdev": "164" }, { "name": "V1486", "index": "18", "type": "numeric", "distinct": "540", "missing": "0", "min": "0", "max": "897", "mean": "297", "stdev": "252" }, { "name": "V1571", "index": "19", "type": "numeric", "distinct": "652", "missing": "0", "min": "66", "max": "840", "mean": "493", "stdev": "179" }, { "name": "V1618", "index": "20", "type": "numeric", "distinct": "246", "missing": "0", "min": "4", "max": "900", "mean": "495", "stdev": "208" }, { "name": "V1683", "index": "21", "type": "numeric", "distinct": "634", "missing": "0", "min": "45", "max": "861", "mean": "463", "stdev": "162" }, { "name": "V1751", "index": "22", "type": "numeric", "distinct": "538", "missing": "0", "min": "0", "max": "897", "mean": "275", "stdev": "256" }, { "name": "V1779", "index": "23", "type": "numeric", "distinct": "718", "missing": "0", "min": "32", "max": "881", "mean": "424", "stdev": "194" }, { "name": "V1817", "index": "24", "type": "numeric", "distinct": "254", "missing": "0", "min": "0", "max": "900", "mean": "509", "stdev": "230" }, { "name": "V1822", "index": "25", "type": "numeric", "distinct": "626", "missing": "0", "min": "0", "max": "900", "mean": "251", "stdev": "194" }, { "name": "V1884", "index": "26", "type": "numeric", "distinct": "479", "missing": "0", "min": "138", "max": "727", "mean": "450", "stdev": "113" }, { "name": "V2028", "index": "27", "type": "numeric", "distinct": "662", "missing": "0", "min": "43", "max": "891", "mean": "497", "stdev": "169" }, { "name": "V2091", "index": "28", "type": "numeric", "distinct": "552", "missing": "0", "min": "0", "max": "898", "mean": "271", "stdev": "238" }, { "name": "V2100", "index": "29", "type": "numeric", "distinct": "520", "missing": "0", "min": "143", "max": "784", "mean": "403", "stdev": "132" }, { "name": "V2133", "index": "30", "type": "numeric", "distinct": "614", "missing": "0", "min": "0", "max": "900", "mean": "251", "stdev": "193" }, { "name": "V2140", "index": "31", "type": "numeric", "distinct": "616", "missing": "0", "min": "87", "max": "860", "mean": "474", "stdev": "147" }, { "name": "V2245", "index": "32", "type": "numeric", "distinct": "650", "missing": "0", "min": "44", "max": "870", "mean": "593", "stdev": "194" }, { "name": "V2284", "index": "33", "type": "numeric", "distinct": "597", "missing": "0", "min": "139", "max": "900", "mean": "431", "stdev": "238" }, { "name": "V2343", "index": "34", "type": "numeric", "distinct": "522", "missing": "0", "min": "129", "max": "870", "mean": "430", "stdev": "120" }, { "name": "V2363", "index": "35", "type": "numeric", "distinct": "557", "missing": "0", "min": "0", "max": "897", "mean": "315", "stdev": "243" }, { "name": "V2681", "index": "36", "type": "numeric", "distinct": "622", "missing": "0", "min": "90", "max": "862", "mean": "562", "stdev": "167" }, { "name": "V2768", "index": "37", "type": "numeric", "distinct": "559", "missing": "0", "min": "0", "max": "899", "mean": "300", "stdev": "251" }, { "name": "V2786", "index": "38", "type": "numeric", "distinct": "604", "missing": "0", "min": "0", "max": "900", "mean": "251", "stdev": "194" }, { "name": "V2787", "index": "39", "type": "numeric", "distinct": "553", "missing": "0", "min": "153", "max": "900", "mean": "388", "stdev": "222" }, { "name": "V2837", "index": "40", "type": "numeric", "distinct": "662", "missing": "0", "min": "39", "max": "877", "mean": "406", "stdev": "173" }, { "name": "V2994", "index": "41", "type": "numeric", "distinct": "550", "missing": "0", "min": "140", "max": "900", "mean": "385", "stdev": "223" }, { "name": "V3069", "index": "42", "type": "numeric", "distinct": "720", "missing": "0", "min": "29", "max": "889", "mean": "476", "stdev": "202" }, { "name": "V3081", "index": "43", "type": "numeric", "distinct": "611", "missing": "0", "min": "0", "max": "900", "mean": "237", "stdev": "197" }, { "name": "V3082", "index": "44", "type": "numeric", "distinct": "610", "missing": "0", "min": "0", "max": "900", "mean": "244", "stdev": "189" }, { "name": "V3220", "index": "45", "type": "numeric", "distinct": "608", "missing": "0", "min": "0", "max": "900", "mean": "251", "stdev": "193" }, { "name": "V3372", "index": "46", "type": "numeric", "distinct": "637", "missing": "0", "min": "75", "max": "854", "mean": "408", "stdev": "162" }, { "name": "V3396", "index": "47", "type": "numeric", "distinct": "574", "missing": "0", "min": "149", "max": "900", "mean": "404", "stdev": "226" }, { "name": "V3408", "index": "48", "type": "numeric", "distinct": "529", "missing": "0", "min": "79", "max": "818", "mean": "329", "stdev": "140" }, { "name": "V3497", "index": "49", "type": "numeric", "distinct": "718", "missing": "0", "min": "18", "max": "863", "mean": "392", "stdev": "203" }, { "name": "V3682", "index": "50", "type": "numeric", "distinct": "600", "missing": "0", "min": "0", "max": "900", "mean": "243", "stdev": "190" }, { "name": "V3722", "index": "51", "type": "numeric", "distinct": "583", "missing": "0", "min": "85", "max": "812", "mean": "369", "stdev": "158" }, { "name": "V3729", "index": "52", "type": "numeric", "distinct": "548", "missing": "0", "min": "138", "max": "900", "mean": "369", "stdev": "212" }, { "name": "V4139", "index": "53", "type": "numeric", "distinct": "623", "missing": "0", "min": "0", "max": "900", "mean": "250", "stdev": "189" }, { "name": "V4183", "index": "54", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "900", "mean": "517", "stdev": "240" }, { "name": "V4186", "index": "55", "type": "numeric", "distinct": "485", "missing": "0", "min": "109", "max": "858", "mean": "481", "stdev": "106" }, { "name": "V4271", "index": "56", "type": "numeric", "distinct": "553", "missing": "0", "min": "0", "max": "897", "mean": "307", "stdev": "241" }, { "name": "V4361", "index": "57", "type": "numeric", "distinct": "562", "missing": "0", "min": "70", "max": "819", "mean": "385", "stdev": "142" }, { "name": "V4362", "index": "58", "type": "numeric", "distinct": "249", "missing": "0", "min": "18", "max": "900", "mean": "494", "stdev": "204" }, { "name": "V4419", "index": "59", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "900", "mean": "515", "stdev": "234" }, { "name": "V4520", "index": "60", "type": "numeric", "distinct": "617", "missing": "0", "min": "0", "max": "900", "mean": "248", "stdev": "195" }, { "name": "V4629", "index": "61", "type": "numeric", "distinct": "537", "missing": "0", "min": "0", "max": "898", "mean": "275", "stdev": "244" }, { "name": "V4642", "index": "62", "type": "numeric", "distinct": "253", "missing": "0", "min": "0", "max": "900", "mean": "506", "stdev": "239" }, { "name": "V4694", "index": "63", "type": "numeric", "distinct": "254", "missing": "0", "min": "4", "max": "900", "mean": "443", "stdev": "213" }, { "name": "V4725", "index": "64", "type": "numeric", "distinct": "549", "missing": "0", "min": "0", "max": "895", "mean": "313", "stdev": "239" }, { "name": "V4726", "index": "65", "type": "numeric", "distinct": "541", "missing": "0", "min": "0", "max": "896", "mean": "271", "stdev": "243" }, { "name": "V4734", "index": "66", "type": "numeric", "distinct": "643", "missing": "0", "min": "35", "max": "853", "mean": "520", "stdev": "184" }, { "name": "V4739", "index": "67", "type": "numeric", "distinct": "543", "missing": "0", "min": "0", "max": "896", "mean": "275", "stdev": "245" }, { "name": "V4749", "index": "68", "type": "numeric", "distinct": "667", "missing": "0", "min": "61", "max": "875", "mean": "561", "stdev": "190" }, { "name": "V4907", "index": "69", "type": "numeric", "distinct": "577", "missing": "0", "min": "0", "max": "899", "mean": "315", "stdev": "240" }, { "name": "V4921", "index": "70", "type": "numeric", "distinct": "641", "missing": "0", "min": "0", "max": "900", "mean": "258", "stdev": "201" }, { "name": "V4970", "index": "71", "type": "numeric", "distinct": "611", "missing": "0", "min": "0", "max": "900", "mean": "247", "stdev": "192" }, { "name": "V5062", "index": "72", "type": "numeric", "distinct": "639", "missing": "0", "min": "44", "max": "873", "mean": "435", "stdev": "155" }, { "name": "V5184", "index": "73", "type": "numeric", "distinct": "625", "missing": "0", "min": "81", "max": "849", "mean": "508", "stdev": "163" }, { "name": "V5229", "index": "74", "type": "numeric", "distinct": "702", "missing": "0", "min": "29", "max": "869", "mean": "420", "stdev": "188" }, { "name": "V5261", "index": "75", "type": "numeric", "distinct": "517", "missing": "0", "min": "140", "max": "900", "mean": "359", "stdev": "209" }, { "name": "V5323", "index": "76", "type": "numeric", "distinct": "575", "missing": "0", "min": "86", "max": "866", "mean": "483", "stdev": "139" }, { "name": "V5397", "index": "77", "type": "numeric", "distinct": "567", "missing": "0", "min": "135", "max": "900", "mean": "402", "stdev": "226" }, { "name": "V5457", "index": "78", "type": "numeric", "distinct": "551", "missing": "0", "min": "0", "max": "898", "mean": "274", "stdev": "241" }, { "name": "V5534", "index": "79", "type": "numeric", "distinct": "476", "missing": "0", "min": "156", "max": "769", "mean": "506", "stdev": "114" }, { "name": "V5608", "index": "80", "type": "numeric", "distinct": "624", "missing": "0", "min": "75", "max": "884", "mean": "593", "stdev": "172" }, { "name": "V5694", "index": "81", "type": "numeric", "distinct": "733", "missing": "0", "min": "33", "max": "895", "mean": "511", "stdev": "206" }, { "name": "V5763", "index": "82", "type": "numeric", "distinct": "647", "missing": "0", "min": "0", "max": "900", "mean": "264", "stdev": "203" }, { "name": "V5895", "index": "83", "type": "numeric", "distinct": "506", "missing": "0", "min": "96", "max": "793", "mean": "355", "stdev": "120" }, { "name": "V5961", "index": "84", "type": "numeric", "distinct": "612", "missing": "0", "min": "0", "max": "900", "mean": "248", "stdev": "192" }, { "name": "V6053", "index": "85", "type": "numeric", "distinct": "646", "missing": "0", "min": "35", "max": "886", "mean": "452", "stdev": "168" }, { "name": "V6117", "index": "86", "type": "numeric", "distinct": "550", "missing": "0", "min": "157", "max": "900", "mean": "372", "stdev": "207" }, { "name": "V6178", "index": "87", "type": "numeric", "distinct": "682", "missing": "0", "min": "36", "max": "856", "mean": "535", "stdev": "203" }, { "name": "V6206", "index": "88", "type": "numeric", "distinct": "622", "missing": "0", "min": "58", "max": "860", "mean": "411", "stdev": "155" }, { "name": "V6320", "index": "89", "type": "numeric", "distinct": "558", "missing": "0", "min": "0", "max": "899", "mean": "312", "stdev": "240" }, { "name": "V6324", "index": "90", "type": "numeric", "distinct": "721", "missing": "0", "min": "16", "max": "879", "mean": "496", "stdev": "216" }, { "name": "V6376", "index": "91", "type": "numeric", "distinct": "722", "missing": "0", "min": "25", "max": "873", "mean": "478", "stdev": "205" }, { "name": "V6569", "index": "92", "type": "numeric", "distinct": "622", "missing": "0", "min": "0", "max": "900", "mean": "248", "stdev": "196" }, { "name": "V6653", "index": "93", "type": "numeric", "distinct": "653", "missing": "0", "min": "0", "max": "900", "mean": "261", "stdev": "202" }, { "name": "V6677", "index": "94", "type": "numeric", "distinct": "249", "missing": "0", "min": "4", "max": "900", "mean": "518", "stdev": "221" }, { "name": "V6704", "index": "95", "type": "numeric", "distinct": "618", "missing": "0", "min": "75", "max": "871", "mean": "357", "stdev": "167" }, { "name": "V6745", "index": "96", "type": "numeric", "distinct": "618", "missing": "0", "min": "74", "max": "854", "mean": "485", "stdev": "158" }, { "name": "V6821", "index": "97", "type": "numeric", "distinct": "665", "missing": "0", "min": "12", "max": "878", "mean": "280", "stdev": "214" }, { "name": "V6882", "index": "98", "type": "numeric", "distinct": "611", "missing": "0", "min": "80", "max": "836", "mean": "566", "stdev": "168" }, { "name": "V6955", "index": "99", "type": "numeric", "distinct": "668", "missing": "0", "min": "17", "max": "864", "mean": "550", "stdev": "189" } ], "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 }