{ "data_id": "44566", "name": "philippine_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "philippine_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "cd68d81b-d71c-4b77-8847-4095ebec3947", "description": "Subsampling of the dataset philippine (41145) 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 18:33:40", "update_comment": null, "last_update": "2022-11-17 18:33:40", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111328\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "philippine_seed_3_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset philippine (41145) 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.choic " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 1, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.5032516258129065, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 99.00990099009901 }, "tags": [ { "uploader": "38960", "tag": "Life Science" }, { "uploader": "38960", "tag": "Medicine" } ], "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": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "V2", "index": "1", "type": "numeric", "distinct": "555", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V8", "index": "2", "type": "numeric", "distinct": "1952", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V9", "index": "3", "type": "numeric", "distinct": "1909", "missing": "0", "min": "-3", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V12", "index": "4", "type": "numeric", "distinct": "1960", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V18", "index": "5", "type": "numeric", "distinct": "1994", "missing": "0", "min": "29", "max": "211", "mean": "124", "stdev": "44" }, { "name": "V20", "index": "6", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V21", "index": "7", "type": "numeric", "distinct": "1983", "missing": "0", "min": "3", "max": "40", "mean": "16", "stdev": "4" }, { "name": "V25", "index": "8", "type": "numeric", "distinct": "1912", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V26", "index": "9", "type": "numeric", "distinct": "150", "missing": "0", "min": "75", "max": "255", "mean": "237", "stdev": "33" }, { "name": "V32", "index": "10", "type": "numeric", "distinct": "1998", "missing": "0", "min": "77", "max": "12134", "mean": "1605", "stdev": "1141" }, { "name": "V36", "index": "11", "type": "numeric", "distinct": "1905", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V38", "index": "12", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V39", "index": "13", "type": "numeric", "distinct": "1455", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V41", "index": "14", "type": "numeric", "distinct": "1713", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "V51", "index": "15", "type": "numeric", "distinct": "1944", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V58", "index": "16", "type": "numeric", "distinct": "1992", "missing": "0", "min": "28", "max": "211", "mean": "110", "stdev": "49" }, { "name": "V60", "index": "17", "type": "numeric", "distinct": "1993", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V63", "index": "18", "type": "numeric", "distinct": "1994", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V64", "index": "19", "type": "numeric", "distinct": "1964", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V67", "index": "20", "type": "numeric", "distinct": "1992", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "V68", "index": "21", "type": "numeric", "distinct": "106", "missing": "0", "min": "0", "max": "114", "mean": "29", "stdev": "24" }, { "name": "V69", "index": "22", "type": "numeric", "distinct": "1832", "missing": "0", "min": "0", "max": "1271360", "mean": "838", "stdev": "29827" }, { "name": "V70", "index": "23", "type": "numeric", "distinct": "1994", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V73", "index": "24", "type": "numeric", "distinct": "1956", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V76", "index": "25", "type": "numeric", "distinct": "1995", "missing": "0", "min": "11", "max": "99", "mean": "49", "stdev": "17" }, { "name": "V78", "index": "26", "type": "numeric", "distinct": "1708", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "V81", "index": "27", "type": "numeric", "distinct": "1989", "missing": "0", "min": "4071", "max": "45715", "mean": "13514", "stdev": "4785" }, { "name": "V84", "index": "28", "type": "numeric", "distinct": "1997", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V85", "index": "29", "type": "numeric", "distinct": "1982", "missing": "0", "min": "2", "max": "19", "mean": "9", "stdev": "3" }, { "name": "V90", "index": "30", "type": "numeric", "distinct": "447", "missing": "0", "min": "2", "max": "479", "mean": "212", "stdev": "130" }, { "name": "V96", "index": "31", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V98", "index": "32", "type": "numeric", "distinct": "1993", "missing": "0", "min": "1", "max": "112", "mean": "3", "stdev": "4" }, { "name": "V99", "index": "33", "type": "numeric", "distinct": "1996", "missing": "0", "min": "1", "max": "87", "mean": "4", "stdev": "3" }, { "name": "V101", "index": "34", "type": "numeric", "distinct": "1896", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V102", "index": "35", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "16", "mean": "2", "stdev": "1" }, { "name": "V104", "index": "36", "type": "numeric", "distinct": "102", "missing": "0", "min": "0", "max": "122", "mean": "25", "stdev": "24" }, { "name": "V107", "index": "37", "type": "numeric", "distinct": "1953", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V113", "index": "38", "type": "numeric", "distinct": "1933", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V117", "index": "39", "type": "numeric", "distinct": "537", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V120", "index": "40", "type": "numeric", "distinct": "1989", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V122", "index": "41", "type": "numeric", "distinct": "1992", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "V124", "index": "42", "type": "numeric", "distinct": "1950", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V126", "index": "43", "type": "numeric", "distinct": "2000", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V128", "index": "44", "type": "numeric", "distinct": "1996", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V138", "index": "45", "type": "numeric", "distinct": "1995", "missing": "0", "min": "2548", "max": "33688", "mean": "9294", "stdev": "3551" }, { "name": "V139", "index": "46", "type": "numeric", "distinct": "1979", "missing": "0", "min": "2", "max": "37", "mean": "15", "stdev": "4" }, { "name": "V140", "index": "47", "type": "numeric", "distinct": "1918", "missing": "0", "min": "-1", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V144", "index": "48", "type": "numeric", "distinct": "1985", "missing": "0", "min": "2864", "max": "783560", "mean": "132451", "stdev": "70587" }, { "name": "V153", "index": "49", "type": "numeric", "distinct": "1996", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "V156", "index": "50", "type": "numeric", "distinct": "451", "missing": "0", "min": "2", "max": "479", "mean": "261", "stdev": "120" }, { "name": "V157", "index": "51", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V159", "index": "52", "type": "numeric", "distinct": "418", "missing": "0", "min": "64", "max": "656", "mean": "391", "stdev": "123" }, { "name": "V160", "index": "53", "type": "numeric", "distinct": "1390", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V167", "index": "54", "type": "numeric", "distinct": "1997", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V170", "index": "55", "type": "numeric", "distinct": "1985", "missing": "0", "min": "23", "max": "214", "mean": "122", "stdev": "44" }, { "name": "V172", "index": "56", "type": "numeric", "distinct": "1994", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "V176", "index": "57", "type": "numeric", "distinct": "1953", "missing": "0", "min": "-13", "max": "8", "mean": "-1", "stdev": "1" }, { "name": "V177", "index": "58", "type": "numeric", "distinct": "1991", "missing": "0", "min": "4150", "max": "707109", "mean": "133424", "stdev": "67289" }, { "name": "V181", "index": "59", "type": "numeric", "distinct": "1800", "missing": "0", "min": "2", "max": "24", "mean": "13", "stdev": "3" }, { "name": "V187", "index": "60", "type": "numeric", "distinct": "1995", "missing": "0", "min": "144", "max": "10741", "mean": "1609", "stdev": "1115" }, { "name": "V188", "index": "61", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V190", "index": "62", "type": "numeric", "distinct": "336", "missing": "0", "min": "53", "max": "606", "mean": "322", "stdev": "85" }, { "name": "V193", "index": "63", "type": "numeric", "distinct": "1995", "missing": "0", "min": "11", "max": "100", "mean": "50", "stdev": "18" }, { "name": "V201", "index": "64", "type": "numeric", "distinct": "1990", "missing": "0", "min": "631", "max": "6289", "mean": "2586", "stdev": "793" }, { "name": "V202", "index": "65", "type": "numeric", "distinct": "169", "missing": "0", "min": "81", "max": "255", "mean": "222", "stdev": "45" }, { "name": "V205", "index": "66", "type": "numeric", "distinct": "1985", "missing": "0", "min": "31", "max": "730", "mean": "139", "stdev": "75" }, { "name": "V206", "index": "67", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V207", "index": "68", "type": "numeric", "distinct": "1907", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V211", "index": "69", "type": "numeric", "distinct": "1997", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V215", "index": "70", "type": "numeric", "distinct": "1994", "missing": "0", "min": "1", "max": "15", "mean": "3", "stdev": "1" }, { "name": "V228", "index": "71", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V230", "index": "72", "type": "numeric", "distinct": "1676", "missing": "0", "min": "6", "max": "86", "mean": "16", "stdev": "4" }, { "name": "V231", "index": "73", "type": "numeric", "distinct": "27", "missing": "0", "min": "8", "max": "35", "mean": "14", "stdev": "3" }, { "name": "V234", "index": "74", "type": "numeric", "distinct": "1984", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "0" }, { "name": "V239", "index": "75", "type": "numeric", "distinct": "1949", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V241", "index": "76", "type": "numeric", "distinct": "1906", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V243", "index": "77", "type": "numeric", "distinct": "1996", "missing": "0", "min": "11", "max": "99", "mean": "49", "stdev": "18" }, { "name": "V246", "index": "78", "type": "numeric", "distinct": "1981", "missing": "0", "min": "5", "max": "53", "mean": "17", "stdev": "5" }, { "name": "V248", "index": "79", "type": "numeric", "distinct": "1992", "missing": "0", "min": "7506", "max": "563943", "mean": "178581", "stdev": "67883" }, { "name": "V252", "index": "80", "type": "numeric", "distinct": "88", "missing": "0", "min": "21", "max": "140", "mean": "68", "stdev": "25" }, { "name": "V255", "index": "81", "type": "numeric", "distinct": "1988", "missing": "0", "min": "4", "max": "436", "mean": "18", "stdev": "12" }, { "name": "V258", "index": "82", "type": "numeric", "distinct": "1977", "missing": "0", "min": "4", "max": "37", "mean": "15", "stdev": "4" }, { "name": "V259", "index": "83", "type": "numeric", "distinct": "1998", "missing": "0", "min": "0", "max": "19", "mean": "2", "stdev": "1" }, { "name": "V261", "index": "84", "type": "numeric", "distinct": "2000", "missing": "0", "min": "2", "max": "9644", "mean": "1658", "stdev": "1085" }, { "name": "V263", "index": "85", "type": "numeric", "distinct": "1986", "missing": "0", "min": "5", "max": "39", "mean": "17", "stdev": "5" }, { "name": "V265", "index": "86", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V266", "index": "87", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V268", "index": "88", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "108", "mean": "19", "stdev": "21" }, { "name": "V271", "index": "89", "type": "numeric", "distinct": "1994", "missing": "0", "min": "11", "max": "99", "mean": "50", "stdev": "17" }, { "name": "V272", "index": "90", "type": "numeric", "distinct": "1626", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "V273", "index": "91", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V274", "index": "92", "type": "numeric", "distinct": "1982", "missing": "0", "min": "277", "max": "4121", "mean": "1567", "stdev": "489" }, { "name": "V277", "index": "93", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "V279", "index": "94", "type": "numeric", "distinct": "1992", "missing": "0", "min": "2548", "max": "37170", "mean": "9951", "stdev": "3964" }, { "name": "V283", "index": "95", "type": "numeric", "distinct": "1995", "missing": "0", "min": "3", "max": "53", "mean": "21", "stdev": "7" }, { "name": "V287", "index": "96", "type": "numeric", "distinct": "1987", "missing": "0", "min": "7179", "max": "658938", "mean": "133866", "stdev": "67003" }, { "name": "V291", "index": "97", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V302", "index": "98", "type": "numeric", "distinct": "1926", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V305", "index": "99", "type": "numeric", "distinct": "1957", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" } ], "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 }