DEVELOPMENT... { "data_id": "44565", "name": "philippine_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "philippine_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "80f7d898-1e9b-42a7-b995-2b8db1b3d97b", "description": "Subsampling of the dataset philippine (41145) with\n\nseed=2\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 18:33:35", "update_comment": null, "last_update": "2022-11-17 18:33:35", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111327\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "philippine_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset philippine (41145) with seed=2 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": 0.49374687343671836, "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": "V10", "index": "0", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "122", "mean": "24", "stdev": "25" }, { "name": "V12", "index": "1", "type": "numeric", "distinct": "1949", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V13", "index": "2", "type": "numeric", "distinct": "1991", "missing": "0", "min": "23", "max": "218", "mean": "104", "stdev": "49" }, { "name": "V18", "index": "3", "type": "numeric", "distinct": "1985", "missing": "0", "min": "28", "max": "218", "mean": "123", "stdev": "44" }, { "name": "V20", "index": "4", "type": "numeric", "distinct": "1997", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V23", "index": "5", "type": "numeric", "distinct": "1999", "missing": "0", "min": "12", "max": "100", "mean": "52", "stdev": "19" }, { "name": "V24", "index": "6", "type": "numeric", "distinct": "1995", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V29", "index": "7", "type": "numeric", "distinct": "1987", "missing": "0", "min": "23", "max": "217", "mean": "120", "stdev": "44" }, { "name": "V31", "index": "8", "type": "numeric", "distinct": "1926", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V35", "index": "9", "type": "numeric", "distinct": "1986", "missing": "0", "min": "28", "max": "213", "mean": "122", "stdev": "44" }, { "name": "V42", "index": "10", "type": "numeric", "distinct": "1990", "missing": "0", "min": "1", "max": "102", "mean": "3", "stdev": "3" }, { "name": "V46", "index": "11", "type": "numeric", "distinct": "1993", "missing": "0", "min": "50", "max": "479", "mean": "281", "stdev": "89" }, { "name": "V47", "index": "12", "type": "numeric", "distinct": "1293", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V53", "index": "13", "type": "numeric", "distinct": "835", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "1" }, { "name": "V55", "index": "14", "type": "numeric", "distinct": "1985", "missing": "0", "min": "28", "max": "639", "mean": "123", "stdev": "63" }, { "name": "V59", "index": "15", "type": "numeric", "distinct": "1552", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "V61", "index": "16", "type": "numeric", "distinct": "1993", "missing": "0", "min": "4", "max": "702", "mean": "20", "stdev": "23" }, { "name": "V62", "index": "17", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "122", "mean": "24", "stdev": "25" }, { "name": "V63", "index": "18", "type": "numeric", "distinct": "1997", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V64", "index": "19", "type": "numeric", "distinct": "1954", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V66", "index": "20", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V71", "index": "21", "type": "numeric", "distinct": "1833", "missing": "0", "min": "2", "max": "28", "mean": "13", "stdev": "3" }, { "name": "V73", "index": "22", "type": "numeric", "distinct": "1961", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V79", "index": "23", "type": "numeric", "distinct": "1965", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V83", "index": "24", "type": "numeric", "distinct": "1988", "missing": "0", "min": "4150", "max": "933558", "mean": "120277", "stdev": "63093" }, { "name": "V87", "index": "25", "type": "numeric", "distinct": "1920", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V89", "index": "26", "type": "numeric", "distinct": "1997", "missing": "0", "min": "1", "max": "12", "mean": "5", "stdev": "1" }, { "name": "V94", "index": "27", "type": "numeric", "distinct": "1997", "missing": "0", "min": "2", "max": "31", "mean": "8", "stdev": "4" }, { "name": "V97", "index": "28", "type": "numeric", "distinct": "1937", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V98", "index": "29", "type": "numeric", "distinct": "1995", "missing": "0", "min": "1", "max": "113", "mean": "3", "stdev": "4" }, { "name": "V101", "index": "30", "type": "numeric", "distinct": "1909", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V102", "index": "31", "type": "numeric", "distinct": "1991", "missing": "0", "min": "0", "max": "15", "mean": "2", "stdev": "1" }, { "name": "V114", "index": "32", "type": "numeric", "distinct": "1316", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V122", "index": "33", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "7", "mean": "3", "stdev": "1" }, { "name": "V124", "index": "34", "type": "numeric", "distinct": "1942", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V126", "index": "35", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V127", "index": "36", "type": "numeric", "distinct": "1984", "missing": "0", "min": "32", "max": "627", "mean": "124", "stdev": "63" }, { "name": "V128", "index": "37", "type": "numeric", "distinct": "1990", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V129", "index": "38", "type": "numeric", "distinct": "171", "missing": "0", "min": "76", "max": "255", "mean": "220", "stdev": "46" }, { "name": "V130", "index": "39", "type": "numeric", "distinct": "104", "missing": "0", "min": "0", "max": "112", "mean": "29", "stdev": "24" }, { "name": "V131", "index": "40", "type": "numeric", "distinct": "1996", "missing": "0", "min": "2", "max": "20", "mean": "9", "stdev": "3" }, { "name": "V132", "index": "41", "type": "numeric", "distinct": "176", "missing": "0", "min": "63", "max": "255", "mean": "214", "stdev": "48" }, { "name": "V135", "index": "42", "type": "numeric", "distinct": "1947", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V138", "index": "43", "type": "numeric", "distinct": "1996", "missing": "0", "min": "2865", "max": "40094", "mean": "9374", "stdev": "3834" }, { "name": "V141", "index": "44", "type": "numeric", "distinct": "1999", "missing": "0", "min": "12", "max": "100", "mean": "52", "stdev": "19" }, { "name": "V143", "index": "45", "type": "numeric", "distinct": "1988", "missing": "0", "min": "3179", "max": "774874", "mean": "132363", "stdev": "69055" }, { "name": "V146", "index": "46", "type": "numeric", "distinct": "1997", "missing": "0", "min": "13", "max": "67", "mean": "36", "stdev": "11" }, { "name": "V148", "index": "47", "type": "numeric", "distinct": "1997", "missing": "0", "min": "11", "max": "99", "mean": "49", "stdev": "17" }, { "name": "V150", "index": "48", "type": "numeric", "distinct": "1895", "missing": "0", "min": "-3", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V152", "index": "49", "type": "numeric", "distinct": "107", "missing": "0", "min": "0", "max": "112", "mean": "30", "stdev": "24" }, { "name": "V154", "index": "50", "type": "numeric", "distinct": "1990", "missing": "0", "min": "28", "max": "205", "mean": "122", "stdev": "45" }, { "name": "V158", "index": "51", "type": "numeric", "distinct": "1991", "missing": "0", "min": "28", "max": "213", "mean": "108", "stdev": "49" }, { "name": "V160", "index": "52", "type": "numeric", "distinct": "1388", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V161", "index": "53", "type": "numeric", "distinct": "1999", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V165", "index": "54", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V167", "index": "55", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V169", "index": "56", "type": "numeric", "distinct": "1993", "missing": "0", "min": "45", "max": "477", "mean": "291", "stdev": "91" }, { "name": "V175", "index": "57", "type": "numeric", "distinct": "90", "missing": "0", "min": "18", "max": "140", "mean": "71", "stdev": "26" }, { "name": "V176", "index": "58", "type": "numeric", "distinct": "1949", "missing": "0", "min": "-12", "max": "10", "mean": "-1", "stdev": "1" }, { "name": "V179", "index": "59", "type": "numeric", "distinct": "1987", "missing": "0", "min": "39", "max": "453", "mean": "235", "stdev": "62" }, { "name": "V180", "index": "60", "type": "numeric", "distinct": "1982", "missing": "0", "min": "31", "max": "510", "mean": "123", "stdev": "64" }, { "name": "V184", "index": "61", "type": "numeric", "distinct": "1993", "missing": "0", "min": "12", "max": "66", "mean": "40", "stdev": "10" }, { "name": "V186", "index": "62", "type": "numeric", "distinct": "1992", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "V187", "index": "63", "type": "numeric", "distinct": "1995", "missing": "0", "min": "55", "max": "10741", "mean": "1580", "stdev": "1153" }, { "name": "V190", "index": "64", "type": "numeric", "distinct": "334", "missing": "0", "min": "53", "max": "621", "mean": "321", "stdev": "85" }, { "name": "V197", "index": "65", "type": "numeric", "distinct": "1979", "missing": "0", "min": "4", "max": "37", "mean": "15", "stdev": "4" }, { "name": "V199", "index": "66", "type": "numeric", "distinct": "406", "missing": "0", "min": "89", "max": "664", "mean": "382", "stdev": "124" }, { "name": "V207", "index": "67", "type": "numeric", "distinct": "1905", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V211", "index": "68", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V220", "index": "69", "type": "numeric", "distinct": "1994", "missing": "0", "min": "2", "max": "22", "mean": "9", "stdev": "3" }, { "name": "V223", "index": "70", "type": "numeric", "distinct": "1994", "missing": "0", "min": "6792", "max": "783560", "mean": "132380", "stdev": "65068" }, { "name": "V224", "index": "71", "type": "numeric", "distinct": "1280", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "V225", "index": "72", "type": "numeric", "distinct": "1644", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "V226", "index": "73", "type": "numeric", "distinct": "1834", "missing": "0", "min": "3", "max": "81", "mean": "21", "stdev": "8" }, { "name": "V227", "index": "74", "type": "numeric", "distinct": "1949", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V232", "index": "75", "type": "numeric", "distinct": "1251", "missing": "0", "min": "0", "max": "13", "mean": "1", "stdev": "1" }, { "name": "V233", "index": "76", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "94", "mean": "18", "stdev": "20" }, { "name": "V235", "index": "77", "type": "numeric", "distinct": "1998", "missing": "0", "min": "-1", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V236", "index": "78", "type": "numeric", "distinct": "1999", "missing": "0", "min": "1", "max": "12", "mean": "4", "stdev": "2" }, { "name": "V241", "index": "79", "type": "numeric", "distinct": "1912", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V244", "index": "80", "type": "numeric", "distinct": "1728", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V247", "index": "81", "type": "numeric", "distinct": "1996", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V251", "index": "82", "type": "numeric", "distinct": "1800", "missing": "0", "min": "3", "max": "25", "mean": "13", "stdev": "3" }, { "name": "V253", "index": "83", "type": "numeric", "distinct": "1997", "missing": "0", "min": "13", "max": "67", "mean": "36", "stdev": "11" }, { "name": "V258", "index": "84", "type": "numeric", "distinct": "1989", "missing": "0", "min": "4", "max": "38", "mean": "15", "stdev": "4" }, { "name": "V259", "index": "85", "type": "numeric", "distinct": "1993", "missing": "0", "min": "0", "max": "19", "mean": "2", "stdev": "1" }, { "name": "V263", "index": "86", "type": "numeric", "distinct": "1987", "missing": "0", "min": "4", "max": "37", "mean": "17", "stdev": "5" }, { "name": "V268", "index": "87", "type": "numeric", "distinct": "90", "missing": "0", "min": "0", "max": "94", "mean": "18", "stdev": "20" }, { "name": "V269", "index": "88", "type": "numeric", "distinct": "1996", "missing": "0", "min": "2865", "max": "40094", "mean": "9374", "stdev": "3834" }, { "name": "V270", "index": "89", "type": "numeric", "distinct": "1987", "missing": "0", "min": "39", "max": "453", "mean": "235", "stdev": "62" }, { "name": "V272", "index": "90", "type": "numeric", "distinct": "1644", "missing": "0", "min": "0", "max": "8", "mean": "2", "stdev": "1" }, { "name": "V276", "index": "91", "type": "numeric", "distinct": "292", "missing": "0", "min": "60", "max": "586", "mean": "318", "stdev": "71" }, { "name": "V281", "index": "92", "type": "numeric", "distinct": "1995", "missing": "0", "min": "44", "max": "12196", "mean": "1735", "stdev": "1178" }, { "name": "V282", "index": "93", "type": "numeric", "distinct": "500", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V288", "index": "94", "type": "numeric", "distinct": "1946", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V291", "index": "95", "type": "numeric", "distinct": "1996", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V292", "index": "96", "type": "numeric", "distinct": "1998", "missing": "0", "min": "1", "max": "12", "mean": "3", "stdev": "1" }, { "name": "V297", "index": "97", "type": "numeric", "distinct": "1280", "missing": "0", "min": "6", "max": "48", "mean": "17", "stdev": "4" }, { "name": "V300", "index": "98", "type": "numeric", "distinct": "1996", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V302", "index": "99", "type": "numeric", "distinct": "1921", "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 }

A PHP Error was encountered

Severity: Core Warning

Message: Module 'mysqli' already loaded

Filename: Unknown

Line Number: 0

Backtrace: