{ "data_id": "44567", "name": "philippine_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "philippine_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "6750ee51-763b-491a-8395-7aa9b075069c", "description": "Subsampling of the dataset philippine (41145) 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 18:33:45", "update_comment": null, "last_update": "2022-11-17 18:33:45", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111329\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "philippine_seed_4_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset philippine (41145) 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.choic " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 0.9900990099009901, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.5017508754377189, "PercentageOfMissingValues": 0, "Dimensionality": 0.0505, "PercentageOfNumericFeatures": 99.00990099009901, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 0.9900990099009901, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 1 }, "tags": [ { "uploader": "38960", "tag": "Life Science" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "V8", "index": "0", "type": "numeric", "distinct": "1961", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V11", "index": "1", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "709", "mean": "143", "stdev": "76" }, { "name": "V14", "index": "2", "type": "numeric", "distinct": "1993", "missing": "0", "min": "3", "max": "59", "mean": "20", "stdev": "7" }, { "name": "V18", "index": "3", "type": "numeric", "distinct": "1988", "missing": "0", "min": "28", "max": "218", "mean": "123", "stdev": "44" }, { "name": "V22", "index": "4", "type": "numeric", "distinct": "1993", "missing": "0", "min": "1", "max": "10", "mean": "3", "stdev": "1" }, { "name": "V24", "index": "5", "type": "numeric", "distinct": "1993", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V33", "index": "6", "type": "numeric", "distinct": "1997", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V35", "index": "7", "type": "numeric", "distinct": "1994", "missing": "0", "min": "28", "max": "213", "mean": "122", "stdev": "44" }, { "name": "V39", "index": "8", "type": "numeric", "distinct": "1464", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V40", "index": "9", "type": "numeric", "distinct": "2000", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V44", "index": "10", "type": "numeric", "distinct": "1670", "missing": "0", "min": "0", "max": "33", "mean": "16", "stdev": "4" }, { "name": "V45", "index": "11", "type": "numeric", "distinct": "1998", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V50", "index": "12", "type": "numeric", "distinct": "1995", "missing": "0", "min": "63", "max": "4160", "mean": "723", "stdev": "376" }, { "name": "V52", "index": "13", "type": "numeric", "distinct": "1937", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V53", "index": "14", "type": "numeric", "distinct": "853", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "1" }, { "name": "V54", "index": "15", "type": "numeric", "distinct": "1986", "missing": "0", "min": "223", "max": "4121", "mean": "1534", "stdev": "477" }, { "name": "V57", "index": "16", "type": "numeric", "distinct": "979", "missing": "0", "min": "36", "max": "11764", "mean": "1630", "stdev": "1247" }, { "name": "V60", "index": "17", "type": "numeric", "distinct": "1995", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V63", "index": "18", "type": "numeric", "distinct": "1997", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V67", "index": "19", "type": "numeric", "distinct": "1991", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "V75", "index": "20", "type": "numeric", "distinct": "1999", "missing": "0", "min": "9", "max": "4324", "mean": "769", "stdev": "369" }, { "name": "V76", "index": "21", "type": "numeric", "distinct": "1995", "missing": "0", "min": "14", "max": "101", "mean": "49", "stdev": "18" }, { "name": "V78", "index": "22", "type": "numeric", "distinct": "1710", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "1" }, { "name": "V83", "index": "23", "type": "numeric", "distinct": "1985", "missing": "0", "min": "673", "max": "673622", "mean": "121262", "stdev": "64874" }, { "name": "V89", "index": "24", "type": "numeric", "distinct": "1998", "missing": "0", "min": "1", "max": "12", "mean": "5", "stdev": "1" }, { "name": "V94", "index": "25", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "19", "mean": "8", "stdev": "3" }, { "name": "V96", "index": "26", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V99", "index": "27", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "20", "mean": "4", "stdev": "2" }, { "name": "V101", "index": "28", "type": "numeric", "distinct": "1918", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V103", "index": "29", "type": "numeric", "distinct": "2000", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V106", "index": "30", "type": "numeric", "distinct": "1959", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V108", "index": "31", "type": "numeric", "distinct": "1896", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V109", "index": "32", "type": "numeric", "distinct": "1945", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V111", "index": "33", "type": "numeric", "distinct": "1909", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V115", "index": "34", "type": "numeric", "distinct": "1951", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V118", "index": "35", "type": "numeric", "distinct": "1993", "missing": "0", "min": "0", "max": "19", "mean": "2", "stdev": "1" }, { "name": "V125", "index": "36", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "1" }, { "name": "V129", "index": "37", "type": "numeric", "distinct": "172", "missing": "0", "min": "70", "max": "255", "mean": "220", "stdev": "46" }, { "name": "V130", "index": "38", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "130", "mean": "31", "stdev": "25" }, { "name": "V132", "index": "39", "type": "numeric", "distinct": "180", "missing": "0", "min": "57", "max": "255", "mean": "214", "stdev": "48" }, { "name": "V133", "index": "40", "type": "numeric", "distinct": "1993", "missing": "0", "min": "0", "max": "11", "mean": "2", "stdev": "1" }, { "name": "V134", "index": "41", "type": "numeric", "distinct": "1944", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V137", "index": "42", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "4", "mean": "2", "stdev": "1" }, { "name": "V139", "index": "43", "type": "numeric", "distinct": "1986", "missing": "0", "min": "2", "max": "46", "mean": "15", "stdev": "4" }, { "name": "V140", "index": "44", "type": "numeric", "distinct": "1936", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V141", "index": "45", "type": "numeric", "distinct": "1997", "missing": "0", "min": "12", "max": "101", "mean": "51", "stdev": "18" }, { "name": "V143", "index": "46", "type": "numeric", "distinct": "1992", "missing": "0", "min": "5345", "max": "756994", "mean": "132266", "stdev": "67765" }, { "name": "V145", "index": "47", "type": "numeric", "distinct": "1994", "missing": "0", "min": "14", "max": "66", "mean": "40", "stdev": "9" }, { "name": "V147", "index": "48", "type": "numeric", "distinct": "88", "missing": "0", "min": "0", "max": "97", "mean": "22", "stdev": "21" }, { "name": "V151", "index": "49", "type": "numeric", "distinct": "1992", "missing": "0", "min": "48", "max": "482", "mean": "279", "stdev": "88" }, { "name": "V152", "index": "50", "type": "numeric", "distinct": "103", "missing": "0", "min": "0", "max": "119", "mean": "29", "stdev": "24" }, { "name": "V153", "index": "51", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "V157", "index": "52", "type": "numeric", "distinct": "1997", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V158", "index": "53", "type": "numeric", "distinct": "1997", "missing": "0", "min": "27", "max": "213", "mean": "107", "stdev": "49" }, { "name": "V161", "index": "54", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V170", "index": "55", "type": "numeric", "distinct": "1992", "missing": "0", "min": "23", "max": "214", "mean": "122", "stdev": "44" }, { "name": "V175", "index": "56", "type": "numeric", "distinct": "90", "missing": "0", "min": "18", "max": "140", "mean": "70", "stdev": "26" }, { "name": "V177", "index": "57", "type": "numeric", "distinct": "1986", "missing": "0", "min": "3061", "max": "627932", "mean": "133757", "stdev": "68373" }, { "name": "V179", "index": "58", "type": "numeric", "distinct": "1988", "missing": "0", "min": "39", "max": "448", "mean": "238", "stdev": "64" }, { "name": "V186", "index": "59", "type": "numeric", "distinct": "1988", "missing": "0", "min": "0", "max": "4", "mean": "0", "stdev": "1" }, { "name": "V187", "index": "60", "type": "numeric", "distinct": "1993", "missing": "0", "min": "55", "max": "10741", "mean": "1580", "stdev": "1129" }, { "name": "V192", "index": "61", "type": "numeric", "distinct": "1986", "missing": "0", "min": "233", "max": "4481", "mean": "1506", "stdev": "469" }, { "name": "V196", "index": "62", "type": "numeric", "distinct": "1941", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V197", "index": "63", "type": "numeric", "distinct": "1989", "missing": "0", "min": "3", "max": "40", "mean": "15", "stdev": "4" }, { "name": "V199", "index": "64", "type": "numeric", "distinct": "404", "missing": "0", "min": "73", "max": "658", "mean": "386", "stdev": "121" }, { "name": "V201", "index": "65", "type": "numeric", "distinct": "1996", "missing": "0", "min": "573", "max": "7727", "mean": "2586", "stdev": "786" }, { "name": "V208", "index": "66", "type": "numeric", "distinct": "1983", "missing": "0", "min": "3144", "max": "833839", "mean": "131465", "stdev": "69486" }, { "name": "V209", "index": "67", "type": "numeric", "distinct": "1980", "missing": "0", "min": "71", "max": "441", "mean": "236", "stdev": "53" }, { "name": "V210", "index": "68", "type": "numeric", "distinct": "1519", "missing": "0", "min": "0", "max": "34", "mean": "16", "stdev": "4" }, { "name": "V215", "index": "69", "type": "numeric", "distinct": "1991", "missing": "0", "min": "0", "max": "6", "mean": "3", "stdev": "1" }, { "name": "V223", "index": "70", "type": "numeric", "distinct": "1992", "missing": "0", "min": "6792", "max": "673622", "mean": "131296", "stdev": "66408" }, { "name": "V224", "index": "71", "type": "numeric", "distinct": "1267", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "1" }, { "name": "V226", "index": "72", "type": "numeric", "distinct": "1841", "missing": "0", "min": "3", "max": "81", "mean": "21", "stdev": "7" }, { "name": "V227", "index": "73", "type": "numeric", "distinct": "1948", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V229", "index": "74", "type": "numeric", "distinct": "1993", "missing": "0", "min": "1", "max": "11", "mean": "4", "stdev": "1" }, { "name": "V235", "index": "75", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V238", "index": "76", "type": "numeric", "distinct": "1958", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V242", "index": "77", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V244", "index": "78", "type": "numeric", "distinct": "1740", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V246", "index": "79", "type": "numeric", "distinct": "1978", "missing": "0", "min": "6", "max": "48", "mean": "17", "stdev": "5" }, { "name": "V250", "index": "80", "type": "numeric", "distinct": "1913", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V254", "index": "81", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V258", "index": "82", "type": "numeric", "distinct": "1992", "missing": "0", "min": "3", "max": "38", "mean": "15", "stdev": "4" }, { "name": "V259", "index": "83", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "19", "mean": "2", "stdev": "1" }, { "name": "V260", "index": "84", "type": "numeric", "distinct": "1997", "missing": "0", "min": "17", "max": "225", "mean": "54", "stdev": "22" }, { "name": "V261", "index": "85", "type": "numeric", "distinct": "1998", "missing": "0", "min": "2", "max": "9644", "mean": "1743", "stdev": "1156" }, { "name": "V265", "index": "86", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V271", "index": "87", "type": "numeric", "distinct": "1999", "missing": "0", "min": "11", "max": "99", "mean": "49", "stdev": "17" }, { "name": "V279", "index": "88", "type": "numeric", "distinct": "1997", "missing": "0", "min": "3561", "max": "49041", "mean": "9832", "stdev": "3921" }, { "name": "V282", "index": "89", "type": "numeric", "distinct": "499", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V283", "index": "90", "type": "numeric", "distinct": "1991", "missing": "0", "min": "3", "max": "53", "mean": "21", "stdev": "7" }, { "name": "V285", "index": "91", "type": "numeric", "distinct": "1912", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V288", "index": "92", "type": "numeric", "distinct": "1958", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V289", "index": "93", "type": "numeric", "distinct": "1987", "missing": "0", "min": "325", "max": "4015", "mean": "1518", "stdev": "464" }, { "name": "V290", "index": "94", "type": "numeric", "distinct": "1994", "missing": "0", "min": "2", "max": "20", "mean": "9", "stdev": "3" }, { "name": "V291", "index": "95", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V292", "index": "96", "type": "numeric", "distinct": "1995", "missing": "0", "min": "1", "max": "12", "mean": "3", "stdev": "1" }, { "name": "V293", "index": "97", "type": "numeric", "distinct": "180", "missing": "0", "min": "57", "max": "255", "mean": "214", "stdev": "48" }, { "name": "V296", "index": "98", "type": "numeric", "distinct": "1988", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V300", "index": "99", "type": "numeric", "distinct": "1994", "missing": "0", "min": "1", "max": "1", "mean": "1", "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 }