{ "data_id": "44526", "name": "jasmine_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "jasmine_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "bae4109c-c24e-40e2-9d8f-acdebdd00ff2", "description": "Subsampling of the dataset jasmine (41143) with\n\nseed=3\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 18:25:27", "update_comment": null, "last_update": "2022-11-17 18:25:27", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111288\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "jasmine_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset jasmine (41143) with seed=3 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": 0.5107553776888444, "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": "V1", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "977", "913" ], [ "23", "87" ] ] ] }, { "name": "V3", "index": "1", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "983", "985" ], [ "17", "15" ] ] ] }, { "name": "V4", "index": "2", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "971", "969" ], [ "29", "31" ] ] ] }, { "name": "V5", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "965", "961" ], [ "35", "39" ] ] ] }, { "name": "V6", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "499", "956" ], [ "501", "44" ] ] ] }, { "name": "V7", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "789", "623" ], [ "211", "377" ] ] ] }, { "name": "V8", "index": "6", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "997", "987" ], [ "3", "13" ] ] ] }, { "name": "V9", "index": "7", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "754", "773" ], [ "246", "227" ] ] ] }, { "name": "V10", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "925", "927" ], [ "75", "73" ] ] ] }, { "name": "V12", "index": "9", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "853", "789" ], [ "147", "211" ] ] ] }, { "name": "V13", "index": "10", "type": "numeric", "distinct": "106", "missing": "0", "min": "-1", "max": "9", "mean": "-1", "stdev": "1" }, { "name": "V15", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "929", "914" ], [ "71", "86" ] ] ] }, { "name": "V16", "index": "12", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "984", "982" ], [ "16", "18" ] ] ] }, { "name": "V19", "index": "13", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "819", "753" ], [ "181", "247" ] ] ] }, { "name": "V23", "index": "14", "type": "numeric", "distinct": "101", "missing": "0", "min": "-1", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V24", "index": "15", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "926", "946" ], [ "74", "54" ] ] ] }, { "name": "V25", "index": "16", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "902", "918" ], [ "98", "82" ] ] ] }, { "name": "V26", "index": "17", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "535", "553" ], [ "465", "447" ] ] ] }, { "name": "V27", "index": "18", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "493", "541" ], [ "507", "459" ] ] ] }, { "name": "V28", "index": "19", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "972", "970" ], [ "28", "30" ] ] ] }, { "name": "V29", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "994", "993" ], [ "6", "7" ] ] ] }, { "name": "V30", "index": "21", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "904", "902" ], [ "96", "98" ] ] ] }, { "name": "V31", "index": "22", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "967", "944" ], [ "33", "56" ] ] ] }, { "name": "V36", "index": "23", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "895", "881" ], [ "105", "119" ] ] ] }, { "name": "V37", "index": "24", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "932", "917" ], [ "68", "83" ] ] ] }, { "name": "V40", "index": "25", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "681", "196" ], [ "319", "804" ] ] ] }, { "name": "V41", "index": "26", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "692", "682" ], [ "308", "318" ] ] ] }, { "name": "V43", "index": "27", "type": "numeric", "distinct": "77", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "0" }, { "name": "V45", "index": "28", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "16", "mean": "2", "stdev": "2" }, { "name": "V46", "index": "29", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "938", "890" ], [ "62", "110" ] ] ] }, { "name": "V47", "index": "30", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "943", "875" ], [ "57", "125" ] ] ] }, { "name": "V48", "index": "31", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "752", "756" ], [ "248", "244" ] ] ] }, { "name": "V49", "index": "32", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "962", "948" ], [ "38", "52" ] ] ] }, { "name": "V52", "index": "33", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "963", "951" ], [ "37", "49" ] ] ] }, { "name": "V53", "index": "34", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "622", "637" ], [ "378", "363" ] ] ] }, { "name": "V54", "index": "35", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "842", "852" ], [ "158", "148" ] ] ] }, { "name": "V55", "index": "36", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "968", "883" ], [ "32", "117" ] ] ] }, { "name": "V57", "index": "37", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "808", "450" ], [ "192", "550" ] ] ] }, { "name": "V58", "index": "38", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "946", "805" ], [ "54", "195" ] ] ] }, { "name": "V60", "index": "39", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "884", "675" ], [ "116", "325" ] ] ] }, { "name": "V61", "index": "40", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "976", "923" ], [ "24", "77" ] ] ] }, { "name": "V63", "index": "41", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "809", "818" ], [ "191", "182" ] ] ] }, { "name": "V67", "index": "42", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "930", "835" ], [ "70", "165" ] ] ] }, { "name": "V68", "index": "43", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "987", "972" ], [ "13", "28" ] ] ] }, { "name": "V70", "index": "44", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "945", "848" ], [ "55", "152" ] ] ] }, { "name": "V72", "index": "45", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "924", "831" ], [ "76", "169" ] ] ] }, { "name": "V73", "index": "46", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "994", "986" ], [ "6", "14" ] ] ] }, { "name": "V74", "index": "47", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "949", "829" ], [ "51", "171" ] ] ] }, { "name": "V78", "index": "48", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "882", "572" ], [ "118", "428" ] ] ] }, { "name": "V79", "index": "49", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "623", "606" ], [ "377", "394" ] ] ] }, { "name": "V80", "index": "50", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "432", "453" ], [ "568", "547" ] ] ] }, { "name": "V81", "index": "51", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "944", "955" ], [ "56", "45" ] ] ] }, { "name": "V83", "index": "52", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "852", "844" ], [ "148", "156" ] ] ] }, { "name": "V84", "index": "53", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "730", "526" ], [ "270", "474" ] ] ] }, { "name": "V85", "index": "54", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "998", "998" ], [ "2", "2" ] ] ] }, { "name": "V86", "index": "55", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "888", "641" ], [ "112", "359" ] ] ] }, { "name": "V89", "index": "56", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "998" ], [ "0", "2" ] ] ] }, { "name": "V90", "index": "57", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "979", "921" ], [ "21", "79" ] ] ] }, { "name": "V91", "index": "58", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "907", "922" ], [ "93", "78" ] ] ] }, { "name": "V92", "index": "59", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "730", "482" ], [ "270", "518" ] ] ] }, { "name": "V94", "index": "60", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "997", "996" ], [ "3", "4" ] ] ] }, { "name": "V95", "index": "61", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "615", "645" ], [ "385", "355" ] ] ] }, { "name": "V96", "index": "62", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "973", "976" ], [ "27", "24" ] ] ] }, { "name": "V99", "index": "63", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "808", "762" ], [ "192", "238" ] ] ] }, { "name": "V101", "index": "64", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "967", "966" ], [ "33", "34" ] ] ] }, { "name": "V102", "index": "65", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "655", "269" ], [ "345", "731" ] ] ] }, { "name": "V103", "index": "66", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "858", "812" ], [ "142", "188" ] ] ] }, { "name": "V104", "index": "67", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "995", "973" ], [ "5", "27" ] ] ] }, { "name": "V105", "index": "68", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "557", "551" ], [ "443", "449" ] ] ] }, { "name": "V107", "index": "69", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "634", "607" ], [ "366", "393" ] ] ] }, { "name": "V108", "index": "70", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "724", "467" ], [ "276", "533" ] ] ] }, { "name": "V109", "index": "71", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "502", "36" ], [ "498", "964" ] ] ] }, { "name": "V110", "index": "72", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "947", "943" ], [ "53", "57" ] ] ] }, { "name": "V111", "index": "73", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "888", "679" ], [ "112", "321" ] ] ] }, { "name": "V112", "index": "74", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "798", "465" ], [ "202", "535" ] ] ] }, { "name": "V113", "index": "75", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "939", "917" ], [ "61", "83" ] ] ] }, { "name": "V114", "index": "76", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "904", "912" ], [ "96", "88" ] ] ] }, { "name": "V115", "index": "77", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "990", "982" ], [ "10", "18" ] ] ] }, { "name": "V116", "index": "78", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "976", "959" ], [ "24", "41" ] ] ] }, { "name": "V117", "index": "79", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "962", "849" ], [ "38", "151" ] ] ] }, { "name": "V118", "index": "80", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "807", "821" ], [ "193", "179" ] ] ] }, { "name": "V119", "index": "81", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "936", "948" ], [ "64", "52" ] ] ] }, { "name": "V121", "index": "82", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "983", "964" ], [ "17", "36" ] ] ] }, { "name": "V122", "index": "83", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "940", "951" ], [ "60", "49" ] ] ] }, { "name": "V124", "index": "84", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "978", "958" ], [ "22", "42" ] ] ] }, { "name": "V125", "index": "85", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "944", "807" ], [ "56", "193" ] ] ] }, { "name": "V126", "index": "86", "type": "numeric", "distinct": "109", "missing": "0", "min": "-1", "max": "9", "mean": "-1", "stdev": "1" }, { "name": "V127", "index": "87", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "984", "986" ], [ "16", "14" ] ] ] }, { "name": "V128", "index": "88", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "994", "995" ], [ "6", "5" ] ] ] }, { "name": "V129", "index": "89", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "969", "904" ], [ "31", "96" ] ] ] }, { "name": "V130", "index": "90", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "917", "921" ], [ "83", "79" ] ] ] }, { "name": "V131", "index": "91", "type": "numeric", "distinct": "100", "missing": "0", "min": "-1", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V134", "index": "92", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "683", "186" ], [ "317", "814" ] ] ] }, { "name": "V135", "index": "93", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "913", "828" ], [ "87", "172" ] ] ] }, { "name": "V137", "index": "94", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "913", "899" ], [ "87", "101" ] ] ] }, { "name": "V138", "index": "95", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "709", "717" ], [ "291", "283" ] ] ] }, { "name": "V141", "index": "96", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "616", "632" ], [ "384", "368" ] ] ] }, { "name": "V142", "index": "97", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "530", "552" ], [ "470", "448" ] ] ] }, { "name": "V143", "index": "98", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "990", "986" ], [ "10", "14" ] ] ] }, { "name": "V144", "index": "99", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "971", "966" ], [ "29", "34" ] ] ] } ], "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 }