{ "data_id": "44525", "name": "jasmine_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "jasmine_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "bf42b5f2-087d-49e2-814d-7aba8d388745", "description": "Subsampling of the dataset jasmine (41143) with\n\nseed=2\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 18:25:23", "update_comment": null, "last_update": "2022-11-17 18:25:23", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111287\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "jasmine_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset jasmine (41143) with seed=2 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, "PercentageOfBinaryFeatures": 94.05940594059405, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.49674837418709356, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 5.9405940594059405, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 94.05940594059405, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 95 }, "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" ], [ [ "963", "971" ], [ "37", "29" ] ] ] }, { "name": "V5", "index": "1", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "965", "958" ], [ "35", "42" ] ] ] }, { "name": "V6", "index": "2", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "477", "959" ], [ "523", "41" ] ] ] }, { "name": "V8", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "999", "987" ], [ "1", "13" ] ] ] }, { "name": "V10", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "915", "934" ], [ "85", "66" ] ] ] }, { "name": "V11", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "853", "444" ], [ "147", "556" ] ] ] }, { "name": "V13", "index": "6", "type": "numeric", "distinct": "105", "missing": "0", "min": "-1", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V15", "index": "7", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "918", "915" ], [ "82", "85" ] ] ] }, { "name": "V16", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "987", "978" ], [ "13", "22" ] ] ] }, { "name": "V17", "index": "9", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "870", "728" ], [ "130", "272" ] ] ] }, { "name": "V18", "index": "10", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "915", "916" ], [ "85", "84" ] ] ] }, { "name": "V20", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "892", "816" ], [ "108", "184" ] ] ] }, { "name": "V21", "index": "12", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "751", "349" ], [ "249", "651" ] ] ] }, { "name": "V22", "index": "13", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "406", "446" ], [ "594", "554" ] ] ] }, { "name": "V24", "index": "14", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "925", "949" ], [ "75", "51" ] ] ] }, { "name": "V27", "index": "15", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "518", "523" ], [ "482", "477" ] ] ] }, { "name": "V29", "index": "16", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "994", "993" ], [ "6", "7" ] ] ] }, { "name": "V30", "index": "17", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "919", "901" ], [ "81", "99" ] ] ] }, { "name": "V31", "index": "18", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "967", "942" ], [ "33", "58" ] ] ] }, { "name": "V32", "index": "19", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "991", "968" ], [ "9", "32" ] ] ] }, { "name": "V33", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "937", "762" ], [ "63", "238" ] ] ] }, { "name": "V35", "index": "21", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "915", "888" ], [ "85", "112" ] ] ] }, { "name": "V37", "index": "22", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "934", "928" ], [ "66", "72" ] ] ] }, { "name": "V38", "index": "23", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "532", "47" ], [ "468", "953" ] ] ] }, { "name": "V41", "index": "24", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "692", "661" ], [ "308", "339" ] ] ] }, { "name": "V43", "index": "25", "type": "numeric", "distinct": "74", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "0" }, { "name": "V45", "index": "26", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "16", "mean": "2", "stdev": "2" }, { "name": "V47", "index": "27", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "940", "879" ], [ "60", "121" ] ] ] }, { "name": "V48", "index": "28", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "750", "758" ], [ "250", "242" ] ] ] }, { "name": "V49", "index": "29", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "955", "947" ], [ "45", "53" ] ] ] }, { "name": "V50", "index": "30", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "972", "970" ], [ "28", "30" ] ] ] }, { "name": "V51", "index": "31", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "989", "981" ], [ "11", "19" ] ] ] }, { "name": "V52", "index": "32", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "960", "941" ], [ "40", "59" ] ] ] }, { "name": "V53", "index": "33", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "602", "660" ], [ "398", "340" ] ] ] }, { "name": "V55", "index": "34", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "971", "890" ], [ "29", "110" ] ] ] }, { "name": "V56", "index": "35", "type": "numeric", "distinct": "1148", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "V57", "index": "36", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "811", "452" ], [ "189", "548" ] ] ] }, { "name": "V58", "index": "37", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "948", "799" ], [ "52", "201" ] ] ] }, { "name": "V59", "index": "38", "type": "numeric", "distinct": "110", "missing": "0", "min": "-1", "max": "9", "mean": "-1", "stdev": "1" }, { "name": "V61", "index": "39", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "981", "920" ], [ "19", "80" ] ] ] }, { "name": "V62", "index": "40", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "985", "923" ], [ "15", "77" ] ] ] }, { "name": "V63", "index": "41", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "810", "810" ], [ "190", "190" ] ] ] }, { "name": "V66", "index": "42", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "991", "987" ], [ "9", "13" ] ] ] }, { "name": "V67", "index": "43", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "939", "849" ], [ "61", "151" ] ] ] }, { "name": "V68", "index": "44", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "988", "971" ], [ "12", "29" ] ] ] }, { "name": "V69", "index": "45", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "988", "988" ], [ "12", "12" ] ] ] }, { "name": "V70", "index": "46", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "952", "846" ], [ "48", "154" ] ] ] }, { "name": "V71", "index": "47", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "988", "954" ], [ "12", "46" ] ] ] }, { "name": "V72", "index": "48", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "927", "819" ], [ "73", "181" ] ] ] }, { "name": "V73", "index": "49", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "995", "986" ], [ "5", "14" ] ] ] }, { "name": "V74", "index": "50", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "953", "837" ], [ "47", "163" ] ] ] }, { "name": "V75", "index": "51", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "920", "902" ], [ "80", "98" ] ] ] }, { "name": "V76", "index": "52", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "969", "880" ], [ "31", "120" ] ] ] }, { "name": "V77", "index": "53", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "900", "917" ], [ "100", "83" ] ] ] }, { "name": "V78", "index": "54", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "884", "564" ], [ "116", "436" ] ] ] }, { "name": "V79", "index": "55", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "629", "599" ], [ "371", "401" ] ] ] }, { "name": "V80", "index": "56", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "435", "453" ], [ "565", "547" ] ] ] }, { "name": "V81", "index": "57", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "951", "958" ], [ "49", "42" ] ] ] }, { "name": "V82", "index": "58", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "825", "597" ], [ "175", "403" ] ] ] }, { "name": "V83", "index": "59", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "845", "849" ], [ "155", "151" ] ] ] }, { "name": "V86", "index": "60", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "891", "627" ], [ "109", "373" ] ] ] }, { "name": "V87", "index": "61", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "959", "954" ], [ "41", "46" ] ] ] }, { "name": "V88", "index": "62", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "939", "920" ], [ "61", "80" ] ] ] }, { "name": "V89", "index": "63", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "998" ], [ "0", "2" ] ] ] }, { "name": "V90", "index": "64", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "979", "930" ], [ "21", "70" ] ] ] }, { "name": "V91", "index": "65", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "910", "917" ], [ "90", "83" ] ] ] }, { "name": "V92", "index": "66", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "747", "464" ], [ "253", "536" ] ] ] }, { "name": "V93", "index": "67", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "690", "668" ], [ "310", "332" ] ] ] }, { "name": "V94", "index": "68", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "998", "996" ], [ "2", "4" ] ] ] }, { "name": "V96", "index": "69", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "975", "979" ], [ "25", "21" ] ] ] }, { "name": "V99", "index": "70", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "813", "781" ], [ "187", "219" ] ] ] }, { "name": "V100", "index": "71", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "470", "926" ], [ "530", "74" ] ] ] }, { "name": "V101", "index": "72", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "965", "968" ], [ "35", "32" ] ] ] }, { "name": "V102", "index": "73", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "671", "263" ], [ "329", "737" ] ] ] }, { "name": "V104", "index": "74", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "994", "975" ], [ "6", "25" ] ] ] }, { "name": "V106", "index": "75", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "939", "740" ], [ "61", "260" ] ] ] }, { "name": "V107", "index": "76", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "628", "626" ], [ "372", "374" ] ] ] }, { "name": "V108", "index": "77", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "716", "474" ], [ "284", "526" ] ] ] }, { "name": "V109", "index": "78", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "524", "35" ], [ "476", "965" ] ] ] }, { "name": "V111", "index": "79", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "897", "688" ], [ "103", "312" ] ] ] }, { "name": "V112", "index": "80", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "789", "453" ], [ "211", "547" ] ] ] }, { "name": "V113", "index": "81", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "937", "941" ], [ "63", "59" ] ] ] }, { "name": "V117", "index": "82", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "969", "846" ], [ "31", "154" ] ] ] }, { "name": "V119", "index": "83", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "942", "944" ], [ "58", "56" ] ] ] }, { "name": "V120", "index": "84", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "709", "680" ], [ "291", "320" ] ] ] }, { "name": "V122", "index": "85", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "943", "962" ], [ "57", "38" ] ] ] }, { "name": "V124", "index": "86", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "978", "957" ], [ "22", "43" ] ] ] }, { "name": "V125", "index": "87", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "954", "817" ], [ "46", "183" ] ] ] }, { "name": "V126", "index": "88", "type": "numeric", "distinct": "102", "missing": "0", "min": "-1", "max": "9", "mean": "-1", "stdev": "1" }, { "name": "V127", "index": "89", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "990", "985" ], [ "10", "15" ] ] ] }, { "name": "V128", "index": "90", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "997", "996" ], [ "3", "4" ] ] ] }, { "name": "V130", "index": "91", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "920", "928" ], [ "80", "72" ] ] ] }, { "name": "V132", "index": "92", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "598", "82" ], [ "402", "918" ] ] ] }, { "name": "V133", "index": "93", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "940", "944" ], [ "60", "56" ] ] ] }, { "name": "V136", "index": "94", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "989", "996" ], [ "11", "4" ] ] ] }, { "name": "V137", "index": "95", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "915", "902" ], [ "85", "98" ] ] ] }, { "name": "V140", "index": "96", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "681", "708" ], [ "319", "292" ] ] ] }, { "name": "V142", "index": "97", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "521", "555" ], [ "479", "445" ] ] ] }, { "name": "V143", "index": "98", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "991", "986" ], [ "9", "14" ] ] ] }, { "name": "V144", "index": "99", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "965", "973" ], [ "35", "27" ] ] ] } ], "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 }