DEVELOPMENT... { "data_id": "44704", "name": "connect-4_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "connect-4_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "4b78db11-75c0-4d7c-bda9-0d0f676ea755", "description": "Subsampling of the dataset connect-4 (40668) 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": "David Wilson", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:44:22", "update_comment": null, "last_update": "2022-11-17 18:44:22", "licence": "public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111466\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "connect-4_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset connect-4 (40668) 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.choice " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 43, "NumberOfClasses": 3, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 0, "NumberOfSymbolicFeatures": 43, "PercentageOfSymbolicFeatures": 100, "AutoCorrelation": 0.5117558779389695, "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" ], [ [ "186", "479", "1289" ], [ "4", "6", "19" ], [ "1", "7", "9" ] ] ] }, { "name": "d4", "index": "21", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "179", "455", "1236" ], [ "2", "21", "37" ], [ "10", "16", "44" ] ] ] }, { "name": "d6", "index": "23", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "191", "491", "1310" ], [ "0", "1", "5" ], [ "0", "0", "2" ] ] ] }, { "name": "e1", "index": "24", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "124", "321", "747" ], [ "44", "122", "386" ], [ "23", "49", "184" ] ] ] }, { "name": "e2", "index": "25", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "158", "416", "1063" ], [ "11", "45", "92" ], [ "22", "31", "162" ] ] ] }, { "name": "e3", "index": "26", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "174", "459", "1217" ], [ "14", "23", "41" ], [ "3", "10", "59" ] ] ] }, { "name": "e4", "index": "27", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "182", "480", "1270" ], [ "4", "7", "27" ], [ "5", "5", "20" ] ] ] }, { "name": "e5", "index": "28", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "190", "488", "1300" ], [ "0", "0", "12" ], [ "1", "4", "5" ] ] ] }, { "name": "e6", "index": "29", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "191", "492", "1315" ], [ "0", "0", "1" ], [ "0", "0", "1" ] ] ] }, { "name": "f1", "index": "30", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "91", "242", "648" ], [ "54", "131", "402" ], [ "46", "119", "267" ] ] ] }, { "name": "f2", "index": "31", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "148", "369", "1009" ], [ "25", "78", "130" ], [ "18", "45", "178" ] ] ] }, { "name": "f3", "index": "32", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "176", "444", "1192" ], [ "7", "27", "61" ], [ "8", "21", "64" ] ] ] }, { "name": "f4", "index": "33", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "181", "477", "1263" ], [ "7", "5", "28" ], [ "3", "10", "26" ] ] ] }, { "name": "f5", "index": "34", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "187", "489", "1300" ], [ "2", "2", "13" ], [ "2", "1", "4" ] ] ] }, { "name": "f6", "index": "35", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "189", "492", "1317" ], [ "1", "0", "0" ], [ "1", "0", "0" ] ] ] }, { "name": "g1", "index": "36", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "71", "243", "545" ], [ "58", "64", "445" ], [ "62", "185", "327" ] ] ] }, { "name": "g2", "index": "37", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "134", "368", "920" ], [ "24", "43", "249" ], [ "33", "81", "148" ] ] ] }, { "name": "g3", "index": "38", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "164", "431", "1145" ], [ "10", "30", "82" ], [ "17", "31", "90" ] ] ] }, { "name": "g4", "index": "39", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "179", "470", "1247" ], [ "7", "11", "37" ], [ "5", "11", "33" ] ] ] }, { "name": "g5", "index": "40", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "185", "489", "1294" ], [ "0", "1", "20" ], [ "6", "2", "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" ], [ [ "190", "487", "1310" ], [ "1", "0", "6" ], [ "0", "5", "1" ] ] ] }, { "name": "a2", "index": "1", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "106", "335", "860" ], [ "45", "55", "255" ], [ "40", "102", "202" ] ] ] }, { "name": "a3", "index": "2", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "144", "409", "1096" ], [ "20", "41", "121" ], [ "27", "42", "100" ] ] ] }, { "name": "a4", "index": "3", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "164", "448", "1226" ], [ "14", "21", "51" ], [ "13", "23", "40" ] ] ] }, { "name": "a5", "index": "4", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "177", "477", "1281" ], [ "4", "7", "15" ], [ "10", "8", "21" ] ] ] }, { "name": "a6", "index": "5", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "188", "490", "1310" ], [ "2", "0", "4" ], [ "1", "2", "3" ] ] ] }, { "name": "b1", "index": "6", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "70", "153", "444" ], [ "44", "117", "430" ], [ "77", "222", "443" ] ] ] }, { "name": "b2", "index": "7", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "133", "285", "805" ], [ "35", "136", "216" ], [ "23", "71", "296" ] ] ] }, { "name": "b3", "index": "8", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "163", "369", "1091" ], [ "15", "81", "114" ], [ "13", "42", "112" ] ] ] }, { "name": "b4", "index": "9", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "178", "438", "1210" ], [ "6", "28", "45" ], [ "7", "26", "62" ] ] ] }, { "name": "b5", "index": "10", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "188", "472", "1278" ], [ "1", "9", "23" ], [ "2", "11", "16" ] ] ] }, { "name": "a1", "index": "0", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "52", "179", "504" ], [ "77", "72", "483" ], [ "62", "241", "330" ] ] ] }, { "name": "c1", "index": "12", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "43", "145", "298" ], [ "49", "108", "400" ], [ "99", "239", "619" ] ] ] }, { "name": "c2", "index": "13", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "116", "279", "723" ], [ "45", "144", "262" ], [ "30", "69", "332" ] ] ] }, { "name": "c3", "index": "14", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "152", "368", "1039" ], [ "26", "91", "120" ], [ "13", "33", "158" ] ] ] }, { "name": "c4", "index": "15", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "174", "429", "1188" ], [ "11", "37", "59" ], [ "6", "26", "70" ] ] ] }, { "name": "c5", "index": "16", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "184", "472", "1265" ], [ "1", "5", "28" ], [ "6", "15", "24" ] ] ] }, { "name": "c6", "index": "17", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "190", "490", "1303" ], [ "0", "0", "12" ], [ "1", "2", "2" ] ] ] }, { "name": "d1", "index": "18", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "92", "187", "556" ], [ "57", "217", "302" ], [ "42", "88", "459" ] ] ] }, { "name": "d2", "index": "19", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "154", "320", "904" ], [ "13", "122", "188" ], [ "24", "50", "225" ] ] ] }, { "name": "d3", "index": "20", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "166", "409", "1144" ], [ "23", "60", "46" ], [ "2", "23", "127" ] ] ] } ], "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 }