DEVELOPMENT... { "data_id": "44706", "name": "connect-4_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "connect-4_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "216e93c9-1ab0-4f21-b816-e5d24504cffa", "description": "Subsampling of the dataset connect-4 (40668) 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": "David Wilson", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:44:31", "update_comment": null, "last_update": "2022-11-17 18:44:31", "licence": "public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111468\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "connect-4_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset connect-4 (40668) 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 " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 43, "NumberOfClasses": 3, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 0, "NumberOfSymbolicFeatures": 43, "PercentageOfSymbolicFeatures": 100, "AutoCorrelation": 0.49974987493746875, "PercentageOfNumericFeatures": 0, "PercentageOfMissingValues": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfBinaryFeatures": 0, "NumberOfBinaryFeatures": 0, "MinorityClassSize": 191, "MinorityClassPercentage": 9.55, "MajorityClassSize": 1317, "MajorityClassPercentage": 65.85, "Dimensionality": 0.0215 }, "tags": [], "features": [ { "name": "class", "index": "42", "type": "nominal", "distinct": "3", "missing": "0", "target": "1", "distr": [ [ "0", "1", "2" ], [ [ "191", "0", "0" ], [ "0", "492", "0" ], [ "0", "0", "1317" ] ] ] }, { "name": "d5", "index": "22", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "188", "477", "1286" ], [ "2", "7", "25" ], [ "1", "8", "6" ] ] ] }, { "name": "d4", "index": "21", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "185", "447", "1226" ], [ "1", "29", "51" ], [ "5", "16", "40" ] ] ] }, { "name": "d6", "index": "23", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "190", "491", "1311" ], [ "0", "1", "5" ], [ "1", "0", "1" ] ] ] }, { "name": "e1", "index": "24", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "122", "307", "797" ], [ "45", "133", "374" ], [ "24", "52", "146" ] ] ] }, { "name": "e2", "index": "25", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "157", "404", "1062" ], [ "19", "58", "95" ], [ "15", "30", "160" ] ] ] }, { "name": "e3", "index": "26", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "176", "461", "1206" ], [ "10", "21", "35" ], [ "5", "10", "76" ] ] ] }, { "name": "e4", "index": "27", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "186", "478", "1268" ], [ "3", "7", "20" ], [ "2", "7", "29" ] ] ] }, { "name": "e5", "index": "28", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "190", "487", "1303" ], [ "1", "1", "11" ], [ "0", "4", "3" ] ] ] }, { "name": "e6", "index": "29", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "190", "491", "1316" ], [ "0", "1", "0" ], [ "1", "0", "1" ] ] ] }, { "name": "f1", "index": "30", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "102", "257", "670" ], [ "51", "122", "370" ], [ "38", "113", "277" ] ] ] }, { "name": "f2", "index": "31", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "156", "377", "1005" ], [ "20", "63", "144" ], [ "15", "52", "168" ] ] ] }, { "name": "f3", "index": "32", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "180", "429", "1176" ], [ "3", "39", "66" ], [ "8", "24", "75" ] ] ] }, { "name": "f4", "index": "33", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "185", "472", "1263" ], [ "4", "7", "31" ], [ "2", "13", "23" ] ] ] }, { "name": "f5", "index": "34", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "190", "486", "1306" ], [ "0", "3", "8" ], [ "1", "3", "3" ] ] ] }, { "name": "f6", "index": "35", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "191", "491", "1317" ], [ "0", "0", "0" ], [ "0", "1", "0" ] ] ] }, { "name": "g1", "index": "36", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "72", "243", "603" ], [ "55", "87", "434" ], [ "64", "162", "280" ] ] ] }, { "name": "g2", "index": "37", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "127", "370", "950" ], [ "31", "37", "206" ], [ "33", "85", "161" ] ] ] }, { "name": "g3", "index": "38", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "156", "436", "1164" ], [ "12", "21", "95" ], [ "23", "35", "58" ] ] ] }, { "name": "g4", "index": "39", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "180", "470", "1262" ], [ "6", "15", "22" ], [ "5", "7", "33" ] ] ] }, { "name": "g5", "index": "40", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "185", "488", "1298" ], [ "0", "1", "16" ], [ "6", "3", "3" ] ] ] }, { "name": "g6", "index": "41", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "190", "492", "1316" ], [ "1", "0", "1" ], [ "0", "0", "0" ] ] ] }, { "name": "b6", "index": "11", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "189", "489", "1297" ], [ "2", "2", "14" ], [ "0", "1", "6" ] ] ] }, { "name": "a2", "index": "1", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "106", "322", "828" ], [ "43", "58", "283" ], [ "42", "112", "206" ] ] ] }, { "name": "a3", "index": "2", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "150", "407", "1061" ], [ "13", "41", "128" ], [ "28", "44", "128" ] ] ] }, { "name": "a4", "index": "3", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "176", "444", "1187" ], [ "8", "27", "67" ], [ "7", "21", "63" ] ] ] }, { "name": "a5", "index": "4", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "186", "475", "1262" ], [ "4", "3", "28" ], [ "1", "14", "27" ] ] ] }, { "name": "a6", "index": "5", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "190", "486", "1304" ], [ "1", "4", "10" ], [ "0", "2", "3" ] ] ] }, { "name": "b1", "index": "6", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "71", "162", "415" ], [ "46", "108", "438" ], [ "74", "222", "464" ] ] ] }, { "name": "b2", "index": "7", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "125", "300", "786" ], [ "43", "115", "242" ], [ "23", "77", "289" ] ] ] }, { "name": "b3", "index": "8", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "160", "388", "1035" ], [ "17", "70", "139" ], [ "14", "34", "143" ] ] ] }, { "name": "b4", "index": "9", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "176", "444", "1166" ], [ "7", "31", "68" ], [ "8", "17", "83" ] ] ] }, { "name": "b5", "index": "10", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "185", "472", "1241" ], [ "3", "7", "51" ], [ "3", "13", "25" ] ] ] }, { "name": "a1", "index": "0", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "55", "184", "469" ], [ "52", "62", "474" ], [ "84", "246", "374" ] ] ] }, { "name": "c1", "index": "12", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "29", "110", "345" ], [ "70", "131", "371" ], [ "92", "251", "601" ] ] ] }, { "name": "c2", "index": "13", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "108", "255", "775" ], [ "49", "163", "245" ], [ "34", "74", "297" ] ] ] }, { "name": "c3", "index": "14", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "141", "379", "1092" ], [ "33", "85", "94" ], [ "17", "28", "131" ] ] ] }, { "name": "c4", "index": "15", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "168", "444", "1213" ], [ "10", "27", "50" ], [ "13", "21", "54" ] ] ] }, { "name": "c5", "index": "16", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "180", "477", "1280" ], [ "6", "5", "24" ], [ "5", "10", "13" ] ] ] }, { "name": "c6", "index": "17", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "189", "488", "1307" ], [ "0", "2", "9" ], [ "2", "2", "1" ] ] ] }, { "name": "d1", "index": "18", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "88", "210", "558" ], [ "62", "194", "307" ], [ "41", "88", "452" ] ] ] }, { "name": "d2", "index": "19", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "155", "330", "916" ], [ "12", "117", "157" ], [ "24", "45", "244" ] ] ] }, { "name": "d3", "index": "20", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "169", "408", "1136" ], [ "19", "63", "60" ], [ "3", "21", "121" ] ] ] } ], "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 }