{ "data_id": "44524", "name": "jasmine_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "jasmine_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "8465f5b6-da4c-4c73-8611-54ccae714d32", "description": "Subsampling of the dataset jasmine (41143) 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": "Eddie Bergman", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:25:19", "update_comment": null, "last_update": "2022-11-17 18:25:19", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111286\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "jasmine_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset jasmine (41143) 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": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 6, "NumberOfSymbolicFeatures": 95, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 94.05940594059405, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 95, "PercentageOfBinaryFeatures": 94.05940594059405, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.48574287143571787, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 5.9405940594059405 }, "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": "V2", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "958", "952" ], [ "42", "48" ] ] ] }, { "name": "V5", "index": "1", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "966", "968" ], [ "34", "32" ] ] ] }, { "name": "V6", "index": "2", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "504", "967" ], [ "496", "33" ] ] ] }, { "name": "V8", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "998", "983" ], [ "2", "17" ] ] ] }, { "name": "V9", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "736", "766" ], [ "264", "234" ] ] ] }, { "name": "V10", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "931", "926" ], [ "69", "74" ] ] ] }, { "name": "V11", "index": "6", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "849", "433" ], [ "151", "567" ] ] ] }, { "name": "V13", "index": "7", "type": "numeric", "distinct": "108", "missing": "0", "min": "-1", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V14", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "931", "826" ], [ "69", "174" ] ] ] }, { "name": "V16", "index": "9", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "981", "982" ], [ "19", "18" ] ] ] }, { "name": "V17", "index": "10", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "863", "724" ], [ "137", "276" ] ] ] }, { "name": "V22", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "423", "454" ], [ "577", "546" ] ] ] }, { "name": "V23", "index": "12", "type": "numeric", "distinct": "98", "missing": "0", "min": "-1", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V24", "index": "13", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "921", "942" ], [ "79", "58" ] ] ] }, { "name": "V25", "index": "14", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "899", "914" ], [ "101", "86" ] ] ] }, { "name": "V28", "index": "15", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "973", "970" ], [ "27", "30" ] ] ] }, { "name": "V29", "index": "16", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "993", "993" ], [ "7", "7" ] ] ] }, { "name": "V31", "index": "17", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "957", "943" ], [ "43", "57" ] ] ] }, { "name": "V32", "index": "18", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "992", "963" ], [ "8", "37" ] ] ] }, { "name": "V33", "index": "19", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "932", "767" ], [ "68", "233" ] ] ] }, { "name": "V34", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "796", "711" ], [ "204", "289" ] ] ] }, { "name": "V35", "index": "21", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "910", "880" ], [ "90", "120" ] ] ] }, { "name": "V36", "index": "22", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "886", "872" ], [ "114", "128" ] ] ] }, { "name": "V37", "index": "23", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "938", "911" ], [ "62", "89" ] ] ] }, { "name": "V40", "index": "24", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "671", "196" ], [ "329", "804" ] ] ] }, { "name": "V42", "index": "25", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "963", "861" ], [ "37", "139" ] ] ] }, { "name": "V44", "index": "26", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "983", "989" ], [ "17", "11" ] ] ] }, { "name": "V45", "index": "27", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "16", "mean": "2", "stdev": "2" }, { "name": "V46", "index": "28", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "940", "900" ], [ "60", "100" ] ] ] }, { "name": "V47", "index": "29", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "932", "868" ], [ "68", "132" ] ] ] }, { "name": "V48", "index": "30", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "765", "773" ], [ "235", "227" ] ] ] }, { "name": "V49", "index": "31", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "960", "951" ], [ "40", "49" ] ] ] }, { "name": "V50", "index": "32", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "966", "972" ], [ "34", "28" ] ] ] }, { "name": "V51", "index": "33", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "993", "977" ], [ "7", "23" ] ] ] }, { "name": "V54", "index": "34", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "846", "845" ], [ "154", "155" ] ] ] }, { "name": "V55", "index": "35", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "973", "876" ], [ "27", "124" ] ] ] }, { "name": "V56", "index": "36", "type": "numeric", "distinct": "1149", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "V57", "index": "37", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "797", "451" ], [ "203", "549" ] ] ] }, { "name": "V58", "index": "38", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "939", "793" ], [ "61", "207" ] ] ] }, { "name": "V59", "index": "39", "type": "numeric", "distinct": "119", "missing": "0", "min": "-1", "max": "9", "mean": "-1", "stdev": "1" }, { "name": "V64", "index": "40", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "999" ], [ "0", "1" ] ] ] }, { "name": "V65", "index": "41", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "999", "999" ], [ "1", "1" ] ] ] }, { "name": "V66", "index": "42", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "989", "989" ], [ "11", "11" ] ] ] }, { "name": "V67", "index": "43", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "931", "838" ], [ "69", "162" ] ] ] }, { "name": "V69", "index": "44", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "989", "985" ], [ "11", "15" ] ] ] }, { "name": "V70", "index": "45", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "948", "856" ], [ "52", "144" ] ] ] }, { "name": "V71", "index": "46", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "992", "951" ], [ "8", "49" ] ] ] }, { "name": "V72", "index": "47", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "924", "820" ], [ "76", "180" ] ] ] }, { "name": "V74", "index": "48", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "950", "838" ], [ "50", "162" ] ] ] }, { "name": "V75", "index": "49", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "913", "907" ], [ "87", "93" ] ] ] }, { "name": "V76", "index": "50", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "966", "886" ], [ "34", "114" ] ] ] }, { "name": "V77", "index": "51", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "890", "911" ], [ "110", "89" ] ] ] }, { "name": "V78", "index": "52", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "883", "547" ], [ "117", "453" ] ] ] }, { "name": "V79", "index": "53", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "606", "606" ], [ "394", "394" ] ] ] }, { "name": "V80", "index": "54", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "453", "445" ], [ "547", "555" ] ] ] }, { "name": "V81", "index": "55", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "944", "957" ], [ "56", "43" ] ] ] }, { "name": "V82", "index": "56", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "816", "613" ], [ "184", "387" ] ] ] }, { "name": "V83", "index": "57", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "856", "854" ], [ "144", "146" ] ] ] }, { "name": "V84", "index": "58", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "728", "533" ], [ "272", "467" ] ] ] }, { "name": "V85", "index": "59", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "998", "999" ], [ "2", "1" ] ] ] }, { "name": "V86", "index": "60", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "890", "629" ], [ "110", "371" ] ] ] }, { "name": "V87", "index": "61", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "950", "947" ], [ "50", "53" ] ] ] }, { "name": "V88", "index": "62", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "936", "918" ], [ "64", "82" ] ] ] }, { "name": "V89", "index": "63", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "998" ], [ "0", "2" ] ] ] }, { "name": "V91", "index": "64", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "914", "924" ], [ "86", "76" ] ] ] }, { "name": "V92", "index": "65", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "721", "486" ], [ "279", "514" ] ] ] }, { "name": "V93", "index": "66", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "692", "677" ], [ "308", "323" ] ] ] }, { "name": "V94", "index": "67", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "999", "997" ], [ "1", "3" ] ] ] }, { "name": "V96", "index": "68", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "971", "981" ], [ "29", "19" ] ] ] }, { "name": "V98", "index": "69", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "952", "949" ], [ "48", "51" ] ] ] }, { "name": "V99", "index": "70", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "808", "780" ], [ "192", "220" ] ] ] }, { "name": "V101", "index": "71", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "963", "973" ], [ "37", "27" ] ] ] }, { "name": "V102", "index": "72", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "644", "273" ], [ "356", "727" ] ] ] }, { "name": "V104", "index": "73", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "995", "971" ], [ "5", "29" ] ] ] }, { "name": "V105", "index": "74", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "554", "563" ], [ "446", "437" ] ] ] }, { "name": "V106", "index": "75", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "927", "732" ], [ "73", "268" ] ] ] }, { "name": "V107", "index": "76", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "611", "626" ], [ "389", "374" ] ] ] }, { "name": "V110", "index": "77", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "953", "931" ], [ "47", "69" ] ] ] }, { "name": "V112", "index": "78", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "790", "442" ], [ "210", "558" ] ] ] }, { "name": "V113", "index": "79", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "939", "930" ], [ "61", "70" ] ] ] }, { "name": "V114", "index": "80", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "899", "909" ], [ "101", "91" ] ] ] }, { "name": "V117", "index": "81", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "965", "857" ], [ "35", "143" ] ] ] }, { "name": "V119", "index": "82", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "931", "939" ], [ "69", "61" ] ] ] }, { "name": "V120", "index": "83", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "694", "682" ], [ "306", "318" ] ] ] }, { "name": "V122", "index": "84", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "949", "956" ], [ "51", "44" ] ] ] }, { "name": "V123", "index": "85", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "776", "545" ], [ "224", "455" ] ] ] }, { "name": "V124", "index": "86", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "979", "956" ], [ "21", "44" ] ] ] }, { "name": "V128", "index": "87", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "995", "995" ], [ "5", "5" ] ] ] }, { "name": "V129", "index": "88", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "972", "901" ], [ "28", "99" ] ] ] }, { "name": "V131", "index": "89", "type": "numeric", "distinct": "105", "missing": "0", "min": "-1", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V132", "index": "90", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "568", "93" ], [ "432", "907" ] ] ] }, { "name": "V133", "index": "91", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "937", "932" ], [ "63", "68" ] ] ] }, { "name": "V134", "index": "92", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "675", "182" ], [ "325", "818" ] ] ] }, { "name": "V136", "index": "93", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "988", "996" ], [ "12", "4" ] ] ] }, { "name": "V137", "index": "94", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "911", "909" ], [ "89", "91" ] ] ] }, { "name": "V139", "index": "95", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "919", "749" ], [ "81", "251" ] ] ] }, { "name": "V140", "index": "96", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "671", "727" ], [ "329", "273" ] ] ] }, { "name": "V141", "index": "97", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "616", "639" ], [ "384", "361" ] ] ] }, { "name": "V142", "index": "98", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "511", "559" ], [ "489", "441" ] ] ] }, { "name": "V143", "index": "99", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "989", "983" ], [ "11", "17" ] ] ] } ], "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 }