{ "data_id": "44527", "name": "jasmine_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "jasmine_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "2f0926f5-844f-4c9a-9672-7373364f42f2", "description": "Subsampling of the dataset jasmine (41143) 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 18:25:32", "update_comment": null, "last_update": "2022-11-17 18:25:32", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111289\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "jasmine_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset jasmine (41143) 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": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 6, "NumberOfSymbolicFeatures": 95, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 5.9405940594059405, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 94.05940594059405, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 95, "PercentageOfBinaryFeatures": 94.05940594059405, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.4977488744372186, "PercentageOfMissingValues": 0 }, "tags": [ { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "V4", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "962", "972" ], [ "38", "28" ] ] ] }, { "name": "V5", "index": "1", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "963", "961" ], [ "37", "39" ] ] ] }, { "name": "V9", "index": "2", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "738", "790" ], [ "262", "210" ] ] ] }, { "name": "V10", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "921", "931" ], [ "79", "69" ] ] ] }, { "name": "V11", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "852", "446" ], [ "148", "554" ] ] ] }, { "name": "V13", "index": "5", "type": "numeric", "distinct": "106", "missing": "0", "min": "-1", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V14", "index": "6", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "942", "824" ], [ "58", "176" ] ] ] }, { "name": "V15", "index": "7", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "936", "907" ], [ "64", "93" ] ] ] }, { "name": "V16", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "985", "982" ], [ "15", "18" ] ] ] }, { "name": "V18", "index": "9", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "922", "915" ], [ "78", "85" ] ] ] }, { "name": "V19", "index": "10", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "838", "752" ], [ "162", "248" ] ] ] }, { "name": "V21", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "752", "352" ], [ "248", "648" ] ] ] }, { "name": "V22", "index": "12", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "419", "448" ], [ "581", "552" ] ] ] }, { "name": "V23", "index": "13", "type": "numeric", "distinct": "101", "missing": "0", "min": "-1", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V24", "index": "14", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "929", "945" ], [ "71", "55" ] ] ] }, { "name": "V25", "index": "15", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "893", "914" ], [ "107", "86" ] ] ] }, { "name": "V26", "index": "16", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "554", "543" ], [ "446", "457" ] ] ] }, { "name": "V27", "index": "17", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "498", "555" ], [ "502", "445" ] ] ] }, { "name": "V29", "index": "18", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "993", "993" ], [ "7", "7" ] ] ] }, { "name": "V31", "index": "19", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "971", "946" ], [ "29", "54" ] ] ] }, { "name": "V33", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "933", "758" ], [ "67", "242" ] ] ] }, { "name": "V35", "index": "21", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "909", "892" ], [ "91", "108" ] ] ] }, { "name": "V36", "index": "22", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "891", "889" ], [ "109", "111" ] ] ] }, { "name": "V37", "index": "23", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "936", "917" ], [ "64", "83" ] ] ] }, { "name": "V39", "index": "24", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "693", "181" ], [ "307", "819" ] ] ] }, { "name": "V42", "index": "25", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "970", "865" ], [ "30", "135" ] ] ] }, { "name": "V44", "index": "26", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "982", "990" ], [ "18", "10" ] ] ] }, { "name": "V46", "index": "27", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "939", "910" ], [ "61", "90" ] ] ] }, { "name": "V47", "index": "28", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "935", "878" ], [ "65", "122" ] ] ] }, { "name": "V48", "index": "29", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "746", "761" ], [ "254", "239" ] ] ] }, { "name": "V49", "index": "30", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "956", "951" ], [ "44", "49" ] ] ] }, { "name": "V50", "index": "31", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "969", "972" ], [ "31", "28" ] ] ] }, { "name": "V52", "index": "32", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "962", "958" ], [ "38", "42" ] ] ] }, { "name": "V53", "index": "33", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "609", "629" ], [ "391", "371" ] ] ] }, { "name": "V54", "index": "34", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "841", "855" ], [ "159", "145" ] ] ] }, { "name": "V55", "index": "35", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "971", "899" ], [ "29", "101" ] ] ] }, { "name": "V56", "index": "36", "type": "numeric", "distinct": "1158", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "V57", "index": "37", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "815", "456" ], [ "185", "544" ] ] ] }, { "name": "V58", "index": "38", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "950", "804" ], [ "50", "196" ] ] ] }, { "name": "V59", "index": "39", "type": "numeric", "distinct": "119", "missing": "0", "min": "-1", "max": "9", "mean": "-1", "stdev": "1" }, { "name": "V60", "index": "40", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "880", "678" ], [ "120", "322" ] ] ] }, { "name": "V61", "index": "41", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "983", "917" ], [ "17", "83" ] ] ] }, { "name": "V62", "index": "42", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "983", "928" ], [ "17", "72" ] ] ] }, { "name": "V64", "index": "43", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "1000" ], [ "0", "0" ] ] ] }, { "name": "V65", "index": "44", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "999", "1000" ], [ "1", "0" ] ] ] }, { "name": "V66", "index": "45", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "992", "988" ], [ "8", "12" ] ] ] }, { "name": "V67", "index": "46", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "924", "846" ], [ "76", "154" ] ] ] }, { "name": "V68", "index": "47", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "989", "976" ], [ "11", "24" ] ] ] }, { "name": "V70", "index": "48", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "954", "847" ], [ "46", "153" ] ] ] }, { "name": "V71", "index": "49", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "992", "953" ], [ "8", "47" ] ] ] }, { "name": "V73", "index": "50", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "994", "985" ], [ "6", "15" ] ] ] }, { "name": "V75", "index": "51", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "927", "905" ], [ "73", "95" ] ] ] }, { "name": "V76", "index": "52", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "961", "887" ], [ "39", "113" ] ] ] }, { "name": "V77", "index": "53", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "906", "904" ], [ "94", "96" ] ] ] }, { "name": "V82", "index": "54", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "836", "603" ], [ "164", "397" ] ] ] }, { "name": "V83", "index": "55", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "852", "856" ], [ "148", "144" ] ] ] }, { "name": "V86", "index": "56", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "896", "631" ], [ "104", "369" ] ] ] }, { "name": "V87", "index": "57", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "954", "953" ], [ "46", "47" ] ] ] }, { "name": "V88", "index": "58", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "935", "917" ], [ "65", "83" ] ] ] }, { "name": "V90", "index": "59", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "981", "940" ], [ "19", "60" ] ] ] }, { "name": "V93", "index": "60", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "683", "681" ], [ "317", "319" ] ] ] }, { "name": "V94", "index": "61", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "998", "995" ], [ "2", "5" ] ] ] }, { "name": "V95", "index": "62", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "609", "645" ], [ "391", "355" ] ] ] }, { "name": "V96", "index": "63", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "972", "978" ], [ "28", "22" ] ] ] }, { "name": "V97", "index": "64", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "527", "535" ], [ "473", "465" ] ] ] }, { "name": "V98", "index": "65", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "954", "948" ], [ "46", "52" ] ] ] }, { "name": "V99", "index": "66", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "799", "777" ], [ "201", "223" ] ] ] }, { "name": "V100", "index": "67", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "470", "932" ], [ "530", "68" ] ] ] }, { "name": "V101", "index": "68", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "968", "972" ], [ "32", "28" ] ] ] }, { "name": "V102", "index": "69", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "660", "259" ], [ "340", "741" ] ] ] }, { "name": "V104", "index": "70", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "994", "972" ], [ "6", "28" ] ] ] }, { "name": "V107", "index": "71", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "634", "628" ], [ "366", "372" ] ] ] }, { "name": "V108", "index": "72", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "744", "470" ], [ "256", "530" ] ] ] }, { "name": "V109", "index": "73", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "519", "36" ], [ "481", "964" ] ] ] }, { "name": "V111", "index": "74", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "897", "685" ], [ "103", "315" ] ] ] }, { "name": "V112", "index": "75", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "792", "454" ], [ "208", "546" ] ] ] }, { "name": "V113", "index": "76", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "940", "922" ], [ "60", "78" ] ] ] }, { "name": "V114", "index": "77", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "899", "913" ], [ "101", "87" ] ] ] }, { "name": "V115", "index": "78", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "993", "984" ], [ "7", "16" ] ] ] }, { "name": "V116", "index": "79", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "976", "962" ], [ "24", "38" ] ] ] }, { "name": "V119", "index": "80", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "944", "942" ], [ "56", "58" ] ] ] }, { "name": "V121", "index": "81", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "979", "971" ], [ "21", "29" ] ] ] }, { "name": "V122", "index": "82", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "949", "954" ], [ "51", "46" ] ] ] }, { "name": "V123", "index": "83", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "786", "562" ], [ "214", "438" ] ] ] }, { "name": "V125", "index": "84", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "942", "819" ], [ "58", "181" ] ] ] }, { "name": "V126", "index": "85", "type": "numeric", "distinct": "110", "missing": "0", "min": "-1", "max": "9", "mean": "-1", "stdev": "1" }, { "name": "V129", "index": "86", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "980", "908" ], [ "20", "92" ] ] ] }, { "name": "V130", "index": "87", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "918", "918" ], [ "82", "82" ] ] ] }, { "name": "V131", "index": "88", "type": "numeric", "distinct": "101", "missing": "0", "min": "-1", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V132", "index": "89", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "593", "77" ], [ "407", "923" ] ] ] }, { "name": "V133", "index": "90", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "940", "935" ], [ "60", "65" ] ] ] }, { "name": "V134", "index": "91", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "693", "182" ], [ "307", "818" ] ] ] }, { "name": "V135", "index": "92", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "920", "835" ], [ "80", "165" ] ] ] }, { "name": "V136", "index": "93", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "991", "996" ], [ "9", "4" ] ] ] }, { "name": "V137", "index": "94", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "914", "905" ], [ "86", "95" ] ] ] }, { "name": "V138", "index": "95", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "696", "714" ], [ "304", "286" ] ] ] }, { "name": "V140", "index": "96", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "683", "722" ], [ "317", "278" ] ] ] }, { "name": "V141", "index": "97", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "623", "630" ], [ "377", "370" ] ] ] }, { "name": "V143", "index": "98", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "987", "983" ], [ "13", "17" ] ] ] }, { "name": "V144", "index": "99", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "973", "971" ], [ "27", "29" ] ] ] } ], "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 }