{ "data_id": "44627", "name": "mfeat-factors_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "mfeat-factors_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "a1efad71-44f1-48f5-90d9-737975ace450", "description": "Subsampling of the dataset mfeat-factors (12) 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": "Eddie Bergman", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:38:16", "update_comment": null, "last_update": "2022-11-17 18:38:16", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111389\/dataset", "kaggle_url": null, "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "mfeat-factors_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset mfeat-factors (12) 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.choic " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 10, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": 0.9954977488744372, "PercentageOfNumericFeatures": 99.00990099009901, "Dimensionality": 0.0505, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassPercentage": 10, "MajorityClassSize": 200, "MinorityClassPercentage": 10, "MinorityClassSize": 200, "NumberOfBinaryFeatures": 0 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "10", "missing": "0", "target": "1", "distr": [ [ "1", "2", "3", "4", "5", "6", "7", "8", "9", "10" ], [ [ "200", "0", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "200", "0", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "200", "0", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "200", "0", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "200", "0", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "200", "0", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "200", "0", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "200", "0", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "200", "0" ], [ "0", "0", "0", "0", "0", "0", "0", "0", "0", "200" ] ] ] }, { "name": "att6", "index": "0", "type": "numeric", "distinct": "419", "missing": "0", "min": "439", "max": "1047", "mean": "684", "stdev": "85" }, { "name": "att8", "index": "1", "type": "numeric", "distinct": "39", "missing": "0", "min": "1", "max": "39", "mean": "18", "stdev": "7" }, { "name": "att9", "index": "2", "type": "numeric", "distinct": "40", "missing": "0", "min": "0", "max": "39", "mean": "15", "stdev": "9" }, { "name": "att11", "index": "3", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "18", "mean": "9", "stdev": "4" }, { "name": "att15", "index": "4", "type": "numeric", "distinct": "421", "missing": "0", "min": "422", "max": "1060", "mean": "654", "stdev": "96" }, { "name": "att20", "index": "5", "type": "numeric", "distinct": "41", "missing": "0", "min": "1", "max": "43", "mean": "24", "stdev": "7" }, { "name": "att22", "index": "6", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "24", "mean": "10", "stdev": "5" }, { "name": "att23", "index": "7", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "18", "mean": "10", "stdev": "4" }, { "name": "att24", "index": "8", "type": "numeric", "distinct": "21", "missing": "0", "min": "0", "max": "20", "mean": "12", "stdev": "4" }, { "name": "att28", "index": "9", "type": "numeric", "distinct": "323", "missing": "0", "min": "436", "max": "992", "mean": "649", "stdev": "72" }, { "name": "att30", "index": "10", "type": "numeric", "distinct": "377", "missing": "0", "min": "474", "max": "1003", "mean": "730", "stdev": "77" }, { "name": "att34", "index": "11", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "20", "mean": "9", "stdev": "5" }, { "name": "att36", "index": "12", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "22", "mean": "8", "stdev": "6" }, { "name": "att39", "index": "13", "type": "numeric", "distinct": "468", "missing": "0", "min": "581", "max": "1226", "mean": "821", "stdev": "114" }, { "name": "att40", "index": "14", "type": "numeric", "distinct": "411", "missing": "0", "min": "607", "max": "1193", "mean": "805", "stdev": "102" }, { "name": "att43", "index": "15", "type": "numeric", "distinct": "34", "missing": "0", "min": "2", "max": "35", "mean": "21", "stdev": "7" }, { "name": "att47", "index": "16", "type": "numeric", "distinct": "22", "missing": "0", "min": "0", "max": "21", "mean": "9", "stdev": "6" }, { "name": "att48", "index": "17", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "22", "mean": "9", "stdev": "5" }, { "name": "att49", "index": "18", "type": "numeric", "distinct": "300", "missing": "0", "min": "123", "max": "514", "mean": "307", "stdev": "64" }, { "name": "att50", "index": "19", "type": "numeric", "distinct": "484", "missing": "0", "min": "71", "max": "650", "mean": "312", "stdev": "118" }, { "name": "att55", "index": "20", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "41", "mean": "22", "stdev": "11" }, { "name": "att57", "index": "21", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "43", "mean": "20", "stdev": "11" }, { "name": "att61", "index": "22", "type": "numeric", "distinct": "302", "missing": "0", "min": "106", "max": "501", "mean": "269", "stdev": "64" }, { "name": "att62", "index": "23", "type": "numeric", "distinct": "348", "missing": "0", "min": "125", "max": "580", "mean": "309", "stdev": "79" }, { "name": "att63", "index": "24", "type": "numeric", "distinct": "464", "missing": "0", "min": "442", "max": "1093", "mean": "656", "stdev": "115" }, { "name": "att65", "index": "25", "type": "numeric", "distinct": "449", "missing": "0", "min": "647", "max": "1179", "mean": "1000", "stdev": "121" }, { "name": "att67", "index": "26", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "40", "mean": "21", "stdev": "11" }, { "name": "att72", "index": "27", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "24", "mean": "9", "stdev": "6" }, { "name": "att74", "index": "28", "type": "numeric", "distinct": "361", "missing": "0", "min": "125", "max": "613", "mean": "327", "stdev": "82" }, { "name": "att75", "index": "29", "type": "numeric", "distinct": "435", "missing": "0", "min": "511", "max": "1164", "mean": "766", "stdev": "97" }, { "name": "att77", "index": "30", "type": "numeric", "distinct": "313", "missing": "0", "min": "432", "max": "937", "mean": "717", "stdev": "63" }, { "name": "att81", "index": "31", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "40", "mean": "23", "stdev": "10" }, { "name": "att83", "index": "32", "type": "numeric", "distinct": "20", "missing": "0", "min": "1", "max": "20", "mean": "10", "stdev": "4" }, { "name": "att84", "index": "33", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "19", "mean": "9", "stdev": "5" }, { "name": "att85", "index": "34", "type": "numeric", "distinct": "301", "missing": "0", "min": "131", "max": "503", "mean": "324", "stdev": "63" }, { "name": "att86", "index": "35", "type": "numeric", "distinct": "460", "missing": "0", "min": "98", "max": "725", "mean": "341", "stdev": "108" }, { "name": "att87", "index": "36", "type": "numeric", "distinct": "427", "missing": "0", "min": "476", "max": "1101", "mean": "716", "stdev": "96" }, { "name": "att90", "index": "37", "type": "numeric", "distinct": "405", "missing": "0", "min": "527", "max": "1084", "mean": "861", "stdev": "96" }, { "name": "att91", "index": "38", "type": "numeric", "distinct": "42", "missing": "0", "min": "0", "max": "41", "mean": "18", "stdev": "9" }, { "name": "att93", "index": "39", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "44", "mean": "22", "stdev": "11" }, { "name": "att94", "index": "40", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "24", "mean": "11", "stdev": "5" }, { "name": "att95", "index": "41", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "18", "mean": "10", "stdev": "3" }, { "name": "att96", "index": "42", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "22", "mean": "13", "stdev": "4" }, { "name": "att98", "index": "43", "type": "numeric", "distinct": "390", "missing": "0", "min": "99", "max": "623", "mean": "306", "stdev": "89" }, { "name": "att99", "index": "44", "type": "numeric", "distinct": "352", "missing": "0", "min": "522", "max": "1047", "mean": "769", "stdev": "77" }, { "name": "att104", "index": "45", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "43", "mean": "21", "stdev": "9" }, { "name": "att105", "index": "46", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "45", "mean": "22", "stdev": "11" }, { "name": "att108", "index": "47", "type": "numeric", "distinct": "20", "missing": "0", "min": "2", "max": "21", "mean": "13", "stdev": "4" }, { "name": "att109", "index": "48", "type": "numeric", "distinct": "450", "missing": "0", "min": "128", "max": "643", "mean": "355", "stdev": "107" }, { "name": "att110", "index": "49", "type": "numeric", "distinct": "342", "missing": "0", "min": "110", "max": "549", "mean": "273", "stdev": "77" }, { "name": "att112", "index": "50", "type": "numeric", "distinct": "297", "missing": "0", "min": "574", "max": "1043", "mean": "804", "stdev": "63" }, { "name": "att114", "index": "51", "type": "numeric", "distinct": "401", "missing": "0", "min": "536", "max": "1099", "mean": "770", "stdev": "82" }, { "name": "att116", "index": "52", "type": "numeric", "distinct": "30", "missing": "0", "min": "2", "max": "32", "mean": "20", "stdev": "5" }, { "name": "att117", "index": "53", "type": "numeric", "distinct": "41", "missing": "0", "min": "0", "max": "40", "mean": "20", "stdev": "10" }, { "name": "att120", "index": "54", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "23", "mean": "7", "stdev": "5" }, { "name": "att123", "index": "55", "type": "numeric", "distinct": "548", "missing": "0", "min": "362", "max": "1114", "mean": "620", "stdev": "141" }, { "name": "att125", "index": "56", "type": "numeric", "distinct": "411", "missing": "0", "min": "523", "max": "1045", "mean": "869", "stdev": "102" }, { "name": "att127", "index": "57", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "42", "mean": "19", "stdev": "10" }, { "name": "att130", "index": "58", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "24", "mean": "12", "stdev": "5" }, { "name": "att131", "index": "59", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "18", "mean": "10", "stdev": "3" }, { "name": "att135", "index": "60", "type": "numeric", "distinct": "590", "missing": "0", "min": "523", "max": "1353", "mean": "842", "stdev": "154" }, { "name": "att137", "index": "61", "type": "numeric", "distinct": "335", "missing": "0", "min": "460", "max": "917", "mean": "680", "stdev": "72" }, { "name": "att138", "index": "62", "type": "numeric", "distinct": "326", "missing": "0", "min": "538", "max": "961", "mean": "733", "stdev": "71" }, { "name": "att140", "index": "63", "type": "numeric", "distinct": "35", "missing": "0", "min": "2", "max": "36", "mean": "20", "stdev": "7" }, { "name": "att142", "index": "64", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "23", "mean": "11", "stdev": "5" }, { "name": "att144", "index": "65", "type": "numeric", "distinct": "23", "missing": "0", "min": "0", "max": "22", "mean": "7", "stdev": "5" }, { "name": "att145", "index": "66", "type": "numeric", "distinct": "278", "missing": "0", "min": "156", "max": "519", "mean": "328", "stdev": "60" }, { "name": "att146", "index": "67", "type": "numeric", "distinct": "434", "missing": "0", "min": "80", "max": "621", "mean": "292", "stdev": "106" }, { "name": "att150", "index": "68", "type": "numeric", "distinct": "355", "missing": "0", "min": "498", "max": "977", "mean": "685", "stdev": "79" }, { "name": "att151", "index": "69", "type": "numeric", "distinct": "37", "missing": "0", "min": "1", "max": "37", "mean": "18", "stdev": "8" }, { "name": "att152", "index": "70", "type": "numeric", "distinct": "32", "missing": "0", "min": "5", "max": "36", "mean": "20", "stdev": "7" }, { "name": "att153", "index": "71", "type": "numeric", "distinct": "35", "missing": "0", "min": "0", "max": "35", "mean": "17", "stdev": "8" }, { "name": "att155", "index": "72", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "17", "mean": "9", "stdev": "4" }, { "name": "att158", "index": "73", "type": "numeric", "distinct": "398", "missing": "0", "min": "95", "max": "614", "mean": "312", "stdev": "86" }, { "name": "att160", "index": "74", "type": "numeric", "distinct": "403", "missing": "0", "min": "470", "max": "1029", "mean": "675", "stdev": "94" }, { "name": "att163", "index": "75", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "43", "mean": "17", "stdev": "8" }, { "name": "att165", "index": "76", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "45", "mean": "19", "stdev": "12" }, { "name": "att168", "index": "77", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "18", "mean": "10", "stdev": "3" }, { "name": "att170", "index": "78", "type": "numeric", "distinct": "394", "missing": "0", "min": "93", "max": "604", "mean": "308", "stdev": "83" }, { "name": "att171", "index": "79", "type": "numeric", "distinct": "435", "missing": "0", "min": "477", "max": "1088", "mean": "687", "stdev": "105" }, { "name": "att172", "index": "80", "type": "numeric", "distinct": "314", "missing": "0", "min": "387", "max": "948", "mean": "632", "stdev": "69" }, { "name": "att175", "index": "81", "type": "numeric", "distinct": "44", "missing": "0", "min": "0", "max": "44", "mean": "17", "stdev": "9" }, { "name": "att177", "index": "82", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "44", "mean": "18", "stdev": "12" }, { "name": "att184", "index": "83", "type": "numeric", "distinct": "416", "missing": "0", "min": "588", "max": "1235", "mean": "886", "stdev": "96" }, { "name": "att185", "index": "84", "type": "numeric", "distinct": "460", "missing": "0", "min": "700", "max": "1314", "mean": "1142", "stdev": "123" }, { "name": "att187", "index": "85", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "42", "mean": "19", "stdev": "10" }, { "name": "att188", "index": "86", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "43", "mean": "21", "stdev": "9" }, { "name": "att190", "index": "87", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "17", "mean": "9", "stdev": "4" }, { "name": "att192", "index": "88", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "24", "mean": "9", "stdev": "6" }, { "name": "att194", "index": "89", "type": "numeric", "distinct": "517", "missing": "0", "min": "121", "max": "793", "mean": "436", "stdev": "119" }, { "name": "att195", "index": "90", "type": "numeric", "distinct": "474", "missing": "0", "min": "505", "max": "1234", "mean": "850", "stdev": "111" }, { "name": "att199", "index": "91", "type": "numeric", "distinct": "46", "missing": "0", "min": "2", "max": "48", "mean": "24", "stdev": "12" }, { "name": "att202", "index": "92", "type": "numeric", "distinct": "25", "missing": "0", "min": "0", "max": "25", "mean": "10", "stdev": "5" }, { "name": "att204", "index": "93", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "18", "mean": "9", "stdev": "4" }, { "name": "att205", "index": "94", "type": "numeric", "distinct": "303", "missing": "0", "min": "144", "max": "534", "mean": "345", "stdev": "65" }, { "name": "att208", "index": "95", "type": "numeric", "distinct": "472", "missing": "0", "min": "425", "max": "1012", "mean": "642", "stdev": "119" }, { "name": "att209", "index": "96", "type": "numeric", "distinct": "292", "missing": "0", "min": "427", "max": "853", "mean": "641", "stdev": "57" }, { "name": "att210", "index": "97", "type": "numeric", "distinct": "391", "missing": "0", "min": "461", "max": "1049", "mean": "687", "stdev": "83" }, { "name": "att213", "index": "98", "type": "numeric", "distinct": "36", "missing": "0", "min": "1", "max": "36", "mean": "18", "stdev": "6" }, { "name": "att216", "index": "99", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "23", "mean": "13", "stdev": "5" } ], "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 }