DEVELOPMENT... { "data_id": "44564", "name": "philippine_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "philippine_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "2c35e60e-b85b-497b-8bda-3b9c1eca3abd", "description": "Subsampling of the dataset philippine (41145) 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": "David Wilson", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:33:31", "update_comment": null, "last_update": "2022-11-17 18:33:31", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111326\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "philippine_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset philippine (41145) 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.choic " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 101, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 100, "NumberOfSymbolicFeatures": 1, "PercentageOfSymbolicFeatures": 0.9900990099009901, "AutoCorrelation": 0.5237618809404703, "PercentageOfNumericFeatures": 99.00990099009901, "PercentageOfMissingValues": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfBinaryFeatures": 0.9900990099009901, "NumberOfBinaryFeatures": 1, "MinorityClassSize": 1000, "MinorityClassPercentage": 50, "MajorityClassSize": 1000, "MajorityClassPercentage": 50, "Dimensionality": 0.0505 }, "tags": [], "features": [ { "name": "class", "index": "100", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "V5", "index": "0", "type": "numeric", "distinct": "1937", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V7", "index": "1", "type": "numeric", "distinct": "1982", "missing": "0", "min": "2892", "max": "636162", "mean": "122029", "stdev": "62379" }, { "name": "V8", "index": "2", "type": "numeric", "distinct": "1952", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V12", "index": "3", "type": "numeric", "distinct": "1954", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V16", "index": "4", "type": "numeric", "distinct": "1812", "missing": "0", "min": "0", "max": "1942400", "mean": "3473", "stdev": "71137" }, { "name": "V17", "index": "5", "type": "numeric", "distinct": "412", "missing": "0", "min": "70", "max": "651", "mean": "381", "stdev": "121" }, { "name": "V18", "index": "6", "type": "numeric", "distinct": "1988", "missing": "0", "min": "28", "max": "218", "mean": "125", "stdev": "43" }, { "name": "V20", "index": "7", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V24", "index": "8", "type": "numeric", "distinct": "1997", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V30", "index": "9", "type": "numeric", "distinct": "1952", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V31", "index": "10", "type": "numeric", "distinct": "1943", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V32", "index": "11", "type": "numeric", "distinct": "1992", "missing": "0", "min": "77", "max": "12134", "mean": "1640", "stdev": "1230" }, { "name": "V33", "index": "12", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V43", "index": "13", "type": "numeric", "distinct": "1994", "missing": "0", "min": "47", "max": "483", "mean": "277", "stdev": "87" }, { "name": "V46", "index": "14", "type": "numeric", "distinct": "1991", "missing": "0", "min": "52", "max": "478", "mean": "282", "stdev": "89" }, { "name": "V51", "index": "15", "type": "numeric", "distinct": "1964", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V55", "index": "16", "type": "numeric", "distinct": "1972", "missing": "0", "min": "31", "max": "984", "mean": "126", "stdev": "67" }, { "name": "V58", "index": "17", "type": "numeric", "distinct": "1992", "missing": "0", "min": "28", "max": "209", "mean": "110", "stdev": "49" }, { "name": "V61", "index": "18", "type": "numeric", "distinct": "1989", "missing": "0", "min": "2", "max": "610", "mean": "20", "stdev": "21" }, { "name": "V63", "index": "19", "type": "numeric", "distinct": "1995", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V66", "index": "20", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V68", "index": "21", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "125", "mean": "30", "stdev": "24" }, { "name": "V71", "index": "22", "type": "numeric", "distinct": "1829", "missing": "0", "min": "3", "max": "28", "mean": "13", "stdev": "3" }, { "name": "V73", "index": "23", "type": "numeric", "distinct": "1950", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V74", "index": "24", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V77", "index": "25", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V78", "index": "26", "type": "numeric", "distinct": "1707", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "1" }, { "name": "V80", "index": "27", "type": "numeric", "distinct": "1993", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "V87", "index": "28", "type": "numeric", "distinct": "1898", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V92", "index": "29", "type": "numeric", "distinct": "1994", "missing": "0", "min": "26646", "max": "582278", "mean": "203041", "stdev": "71864" }, { "name": "V94", "index": "30", "type": "numeric", "distinct": "1992", "missing": "0", "min": "2", "max": "20", "mean": "8", "stdev": "3" }, { "name": "V99", "index": "31", "type": "numeric", "distinct": "1999", "missing": "0", "min": "1", "max": "28", "mean": "4", "stdev": "2" }, { "name": "V101", "index": "32", "type": "numeric", "distinct": "1908", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V103", "index": "33", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V106", "index": "34", "type": "numeric", "distinct": "1938", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V107", "index": "35", "type": "numeric", "distinct": "1952", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V108", "index": "36", "type": "numeric", "distinct": "1910", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V109", "index": "37", "type": "numeric", "distinct": "1957", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V114", "index": "38", "type": "numeric", "distinct": "1291", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V116", "index": "39", "type": "numeric", "distinct": "1837", "missing": "0", "min": "3", "max": "27", "mean": "12", "stdev": "3" }, { "name": "V121", "index": "40", "type": "numeric", "distinct": "1982", "missing": "0", "min": "2892", "max": "636162", "mean": "122029", "stdev": "62379" }, { "name": "V124", "index": "41", "type": "numeric", "distinct": "1943", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V125", "index": "42", "type": "numeric", "distinct": "1996", "missing": "0", "min": "1", "max": "7", "mean": "3", "stdev": "1" }, { "name": "V126", "index": "43", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V127", "index": "44", "type": "numeric", "distinct": "1985", "missing": "0", "min": "31", "max": "1595", "mean": "124", "stdev": "71" }, { "name": "V132", "index": "45", "type": "numeric", "distinct": "175", "missing": "0", "min": "69", "max": "255", "mean": "217", "stdev": "47" }, { "name": "V133", "index": "46", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "7", "mean": "2", "stdev": "1" }, { "name": "V140", "index": "47", "type": "numeric", "distinct": "1944", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V142", "index": "48", "type": "numeric", "distinct": "985", "missing": "0", "min": "138", "max": "10146", "mean": "1632", "stdev": "1210" }, { "name": "V145", "index": "49", "type": "numeric", "distinct": "1994", "missing": "0", "min": "14", "max": "66", "mean": "40", "stdev": "9" }, { "name": "V151", "index": "50", "type": "numeric", "distinct": "1989", "missing": "0", "min": "48", "max": "482", "mean": "282", "stdev": "89" }, { "name": "V153", "index": "51", "type": "numeric", "distinct": "1993", "missing": "0", "min": "1", "max": "6", "mean": "3", "stdev": "1" }, { "name": "V155", "index": "52", "type": "numeric", "distinct": "1993", "missing": "0", "min": "13297", "max": "563943", "mean": "181383", "stdev": "70763" }, { "name": "V160", "index": "53", "type": "numeric", "distinct": "1378", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V168", "index": "54", "type": "numeric", "distinct": "89", "missing": "0", "min": "19", "max": "140", "mean": "68", "stdev": "25" }, { "name": "V171", "index": "55", "type": "numeric", "distinct": "1952", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V174", "index": "56", "type": "numeric", "distinct": "1997", "missing": "0", "min": "1", "max": "46", "mean": "4", "stdev": "2" }, { "name": "V175", "index": "57", "type": "numeric", "distinct": "90", "missing": "0", "min": "18", "max": "140", "mean": "70", "stdev": "26" }, { "name": "V177", "index": "58", "type": "numeric", "distinct": "1988", "missing": "0", "min": "4150", "max": "651464", "mean": "135348", "stdev": "74519" }, { "name": "V184", "index": "59", "type": "numeric", "distinct": "1994", "missing": "0", "min": "12", "max": "66", "mean": "40", "stdev": "10" }, { "name": "V186", "index": "60", "type": "numeric", "distinct": "1991", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V187", "index": "61", "type": "numeric", "distinct": "1996", "missing": "0", "min": "101", "max": "10092", "mean": "1595", "stdev": "1122" }, { "name": "V188", "index": "62", "type": "numeric", "distinct": "1997", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V189", "index": "63", "type": "numeric", "distinct": "1992", "missing": "0", "min": "47", "max": "482", "mean": "276", "stdev": "89" }, { "name": "V191", "index": "64", "type": "numeric", "distinct": "1949", "missing": "0", "min": "-14", "max": "7", "mean": "-1", "stdev": "1" }, { "name": "V193", "index": "65", "type": "numeric", "distinct": "1993", "missing": "0", "min": "12", "max": "100", "mean": "49", "stdev": "18" }, { "name": "V194", "index": "66", "type": "numeric", "distinct": "538", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V199", "index": "67", "type": "numeric", "distinct": "404", "missing": "0", "min": "73", "max": "659", "mean": "383", "stdev": "121" }, { "name": "V202", "index": "68", "type": "numeric", "distinct": "169", "missing": "0", "min": "77", "max": "255", "mean": "222", "stdev": "45" }, { "name": "V203", "index": "69", "type": "numeric", "distinct": "1992", "missing": "0", "min": "2", "max": "20", "mean": "8", "stdev": "3" }, { "name": "V204", "index": "70", "type": "numeric", "distinct": "1996", "missing": "0", "min": "1", "max": "14", "mean": "3", "stdev": "1" }, { "name": "V205", "index": "71", "type": "numeric", "distinct": "1975", "missing": "0", "min": "31", "max": "717", "mean": "140", "stdev": "78" }, { "name": "V215", "index": "72", "type": "numeric", "distinct": "1994", "missing": "0", "min": "1", "max": "7", "mean": "3", "stdev": "1" }, { "name": "V216", "index": "73", "type": "numeric", "distinct": "1997", "missing": "0", "min": "12", "max": "68", "mean": "37", "stdev": "10" }, { "name": "V222", "index": "74", "type": "numeric", "distinct": "1989", "missing": "0", "min": "673", "max": "698652", "mean": "132725", "stdev": "70111" }, { "name": "V225", "index": "75", "type": "numeric", "distinct": "1634", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "V229", "index": "76", "type": "numeric", "distinct": "1990", "missing": "0", "min": "1", "max": "12", "mean": "3", "stdev": "1" }, { "name": "V232", "index": "77", "type": "numeric", "distinct": "1251", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "1" }, { "name": "V233", "index": "78", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "103", "mean": "19", "stdev": "20" }, { "name": "V236", "index": "79", "type": "numeric", "distinct": "1998", "missing": "0", "min": "1", "max": "12", "mean": "4", "stdev": "1" }, { "name": "V238", "index": "80", "type": "numeric", "distinct": "1955", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V239", "index": "81", "type": "numeric", "distinct": "1948", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V243", "index": "82", "type": "numeric", "distinct": "1995", "missing": "0", "min": "12", "max": "100", "mean": "49", "stdev": "18" }, { "name": "V244", "index": "83", "type": "numeric", "distinct": "1741", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V247", "index": "84", "type": "numeric", "distinct": "1993", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V249", "index": "85", "type": "numeric", "distinct": "1992", "missing": "0", "min": "49", "max": "479", "mean": "288", "stdev": "91" }, { "name": "V251", "index": "86", "type": "numeric", "distinct": "1799", "missing": "0", "min": "3", "max": "24", "mean": "13", "stdev": "3" }, { "name": "V252", "index": "87", "type": "numeric", "distinct": "89", "missing": "0", "min": "16", "max": "140", "mean": "67", "stdev": "25" }, { "name": "V253", "index": "88", "type": "numeric", "distinct": "1997", "missing": "0", "min": "12", "max": "68", "mean": "37", "stdev": "10" }, { "name": "V255", "index": "89", "type": "numeric", "distinct": "1987", "missing": "0", "min": "4", "max": "135", "mean": "18", "stdev": "7" }, { "name": "V257", "index": "90", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "19", "mean": "2", "stdev": "1" }, { "name": "V260", "index": "91", "type": "numeric", "distinct": "1999", "missing": "0", "min": "17", "max": "248", "mean": "54", "stdev": "22" }, { "name": "V263", "index": "92", "type": "numeric", "distinct": "1996", "missing": "0", "min": "5", "max": "39", "mean": "17", "stdev": "5" }, { "name": "V265", "index": "93", "type": "numeric", "distinct": "1994", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V278", "index": "94", "type": "numeric", "distinct": "1996", "missing": "0", "min": "3", "max": "77", "mean": "21", "stdev": "9" }, { "name": "V285", "index": "95", "type": "numeric", "distinct": "1916", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V292", "index": "96", "type": "numeric", "distinct": "1997", "missing": "0", "min": "1", "max": "12", "mean": "3", "stdev": "1" }, { "name": "V296", "index": "97", "type": "numeric", "distinct": "1989", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V298", "index": "98", "type": "numeric", "distinct": "1952", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V299", "index": "99", "type": "numeric", "distinct": "1999", "missing": "0", "min": "11", "max": "99", "mean": "49", "stdev": "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 }