DEVELOPMENT... { "data_id": "44707", "name": "connect-4_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "connect-4_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "5dea137e-2296-48dd-ac4f-04b296fa9e1d", "description": "Subsampling of the dataset connect-4 (40668) with\n\nseed=4\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 18:44:35", "update_comment": null, "last_update": "2022-11-17 18:44:35", "licence": "public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111469\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "connect-4_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset connect-4 (40668) with seed=4 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": 0.5177588794397199, "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" ], [ [ "187", "480", "1284" ], [ "2", "5", "23" ], [ "2", "7", "10" ] ] ] }, { "name": "d4", "index": "21", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "183", "441", "1221" ], [ "2", "38", "51" ], [ "6", "13", "45" ] ] ] }, { "name": "d6", "index": "23", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "189", "491", "1312" ], [ "1", "0", "5" ], [ "1", "1", "0" ] ] ] }, { "name": "e1", "index": "24", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "118", "316", "760" ], [ "47", "124", "376" ], [ "26", "52", "181" ] ] ] }, { "name": "e2", "index": "25", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "166", "415", "1067" ], [ "11", "48", "97" ], [ "14", "29", "153" ] ] ] }, { "name": "e3", "index": "26", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "180", "458", "1222" ], [ "8", "23", "32" ], [ "3", "11", "63" ] ] ] }, { "name": "e4", "index": "27", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "187", "476", "1272" ], [ "2", "11", "24" ], [ "2", "5", "21" ] ] ] }, { "name": "e5", "index": "28", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "191", "492", "1306" ], [ "0", "0", "7" ], [ "0", "0", "4" ] ] ] }, { "name": "e6", "index": "29", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "191", "492", "1316" ], [ "0", "0", "1" ], [ "0", "0", "0" ] ] ] }, { "name": "f1", "index": "30", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "97", "273", "685" ], [ "53", "107", "368" ], [ "41", "112", "264" ] ] ] }, { "name": "f2", "index": "31", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "150", "389", "1033" ], [ "22", "70", "141" ], [ "19", "33", "143" ] ] ] }, { "name": "f3", "index": "32", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "171", "440", "1194" ], [ "4", "35", "57" ], [ "16", "17", "66" ] ] ] }, { "name": "f4", "index": "33", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "182", "472", "1274" ], [ "7", "9", "17" ], [ "2", "11", "26" ] ] ] }, { "name": "f5", "index": "34", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "189", "487", "1300" ], [ "1", "3", "12" ], [ "1", "2", "5" ] ] ] }, { "name": "f6", "index": "35", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "191", "491", "1314" ], [ "0", "0", "3" ], [ "0", "1", "0" ] ] ] }, { "name": "g1", "index": "36", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "86", "215", "603" ], [ "52", "82", "423" ], [ "53", "195", "291" ] ] ] }, { "name": "g2", "index": "37", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "123", "372", "957" ], [ "32", "45", "207" ], [ "36", "75", "153" ] ] ] }, { "name": "g3", "index": "38", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "160", "436", "1153" ], [ "12", "25", "88" ], [ "19", "31", "76" ] ] ] }, { "name": "g4", "index": "39", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "182", "468", "1254" ], [ "6", "12", "33" ], [ "3", "12", "30" ] ] ] }, { "name": "g5", "index": "40", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "188", "489", "1303" ], [ "3", "2", "13" ], [ "0", "1", "1" ] ] ] }, { "name": "g6", "index": "41", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "191", "492", "1316" ], [ "0", "0", "1" ], [ "0", "0", "0" ] ] ] }, { "name": "b6", "index": "11", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "190", "489", "1301" ], [ "0", "1", "14" ], [ "1", "2", "2" ] ] ] }, { "name": "a2", "index": "1", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "123", "322", "838" ], [ "31", "68", "270" ], [ "37", "102", "209" ] ] ] }, { "name": "a3", "index": "2", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "157", "404", "1087" ], [ "12", "36", "120" ], [ "22", "52", "110" ] ] ] }, { "name": "a4", "index": "3", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "175", "447", "1200" ], [ "9", "18", "64" ], [ "7", "27", "53" ] ] ] }, { "name": "a5", "index": "4", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "185", "476", "1274" ], [ "5", "7", "28" ], [ "1", "9", "15" ] ] ] }, { "name": "a6", "index": "5", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "188", "489", "1302" ], [ "1", "0", "9" ], [ "2", "3", "6" ] ] ] }, { "name": "b1", "index": "6", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "47", "148", "408" ], [ "56", "116", "437" ], [ "88", "228", "472" ] ] ] }, { "name": "b2", "index": "7", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "109", "313", "783" ], [ "54", "105", "227" ], [ "28", "74", "307" ] ] ] }, { "name": "b3", "index": "8", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "145", "399", "1045" ], [ "17", "65", "130" ], [ "29", "28", "142" ] ] ] }, { "name": "b4", "index": "9", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "172", "459", "1174" ], [ "12", "17", "65" ], [ "7", "16", "78" ] ] ] }, { "name": "b5", "index": "10", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "183", "481", "1270" ], [ "4", "3", "29" ], [ "4", "8", "18" ] ] ] }, { "name": "a1", "index": "0", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "64", "194", "466" ], [ "57", "76", "465" ], [ "70", "222", "386" ] ] ] }, { "name": "c1", "index": "12", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "43", "114", "340" ], [ "54", "145", "402" ], [ "94", "233", "575" ] ] ] }, { "name": "c2", "index": "13", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "114", "265", "734" ], [ "48", "154", "267" ], [ "29", "73", "316" ] ] ] }, { "name": "c3", "index": "14", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "152", "362", "1061" ], [ "27", "90", "100" ], [ "12", "40", "156" ] ] ] }, { "name": "c4", "index": "15", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "170", "435", "1191" ], [ "11", "36", "68" ], [ "10", "21", "58" ] ] ] }, { "name": "c5", "index": "16", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "183", "466", "1267" ], [ "1", "8", "29" ], [ "7", "18", "21" ] ] ] }, { "name": "c6", "index": "17", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "190", "487", "1303" ], [ "1", "3", "13" ], [ "0", "2", "1" ] ] ] }, { "name": "d1", "index": "18", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "92", "186", "554" ], [ "62", "192", "310" ], [ "37", "114", "453" ] ] ] }, { "name": "d2", "index": "19", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "147", "313", "907" ], [ "11", "123", "181" ], [ "33", "56", "229" ] ] ] }, { "name": "d3", "index": "20", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "163", "394", "1127" ], [ "26", "66", "61" ], [ "2", "32", "129" ] ] ] } ], "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 }