{ "data_id": "44588", "name": "eucalyptus_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "eucalyptus_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "78769429-bf05-49bb-9a80-df2775d0df09", "description": "Subsampling of the dataset eucalyptus (188) with\n\nseed=0\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 18:35:19", "update_comment": null, "last_update": "2022-11-17 18:35:19", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111350\/dataset", "default_target_attribute": "Utility", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "eucalyptus_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset eucalyptus (188) with seed=0 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": 736, "NumberOfFeatures": 20, "NumberOfClasses": 5, "NumberOfMissingValues": 448, "NumberOfInstancesWithMissingValues": 95, "NumberOfNumericFeatures": 14, "NumberOfSymbolicFeatures": 6, "MajorityClassSize": 214, "MinorityClassPercentage": 14.266304347826086, "MinorityClassSize": 105, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 12.907608695652172, "AutoCorrelation": 0.39319727891156464, "PercentageOfMissingValues": 3.0434782608695654, "Dimensionality": 0.02717391304347826, "PercentageOfNumericFeatures": 70, "MajorityClassPercentage": 29.076086956521742, "PercentageOfSymbolicFeatures": 30 }, "tags": [ { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "Utility", "index": "19", "type": "nominal", "distinct": "5", "missing": "0", "target": "1", "distr": [ [ "none", "low", "average", "good", "best" ], [ [ "180", "0", "0", "0", "0" ], [ "0", "107", "0", "0", "0" ], [ "0", "0", "130", "0", "0" ], [ "0", "0", "0", "214", "0" ], [ "0", "0", "0", "0", "105" ] ] ] }, { "name": "Abbrev", "index": "0", "type": "nominal", "distinct": "16", "missing": "0", "distr": [ [ "Cra", "Cly", "Nga", "Wai", "K81", "Wak", "K82", "WSp", "K83", "Lon", "Puk", "Paw", "K81a", "Mor", "Wen", "WSh" ], [ [ "0", "4", "7", "13", "6" ], [ "0", "5", "1", "11", "7" ], [ "4", "1", "3", "13", "1" ], [ "14", "14", "5", "14", "23" ], [ "7", "17", "9", "16", "16" ], [ "29", "12", "10", "14", "8" ], [ "10", "14", "11", "4", "6" ], [ "4", "1", "17", "31", "6" ], [ "10", "12", "14", "10", "3" ], [ "4", "8", "8", "30", "3" ], [ "22", "10", "24", "23", "5" ], [ "3", "4", "6", "27", "15" ], [ "4", "5", "13", "5", "6" ], [ "63", "0", "0", "0", "0" ], [ "6", "0", "0", "0", "0" ], [ "0", "0", "2", "3", "0" ] ] ] }, { "name": "Rep", "index": "1", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "22", "mean": "2", "stdev": "1" }, { "name": "Locality", "index": "2", "type": "nominal", "distinct": "8", "missing": "0", "distr": [ [ "Central_Hawkes_Bay", "Northern_Hawkes_Bay", "Southern_Hawkes_Bay", "Central_Hawkes_Bay_(coastal)", "Central_Wairarapa", "South_Wairarapa", "Southern_Hawkes_Bay_(coastal)", "Central_Poverty_Bay" ], [ [ "63", "4", "7", "13", "6" ], [ "0", "5", "1", "11", "7" ], [ "8", "2", "22", "47", "7" ], [ "14", "14", "5", "14", "23" ], [ "31", "48", "47", "35", "31" ], [ "55", "30", "42", "67", "16" ], [ "3", "4", "6", "27", "15" ], [ "6", "0", "0", "0", "0" ] ] ] }, { "name": "Map_Ref", "index": "3", "type": "nominal", "distinct": "14", "missing": "0", "distr": [ [ "N135_382\/137", "N116_848\/985", "N145_874\/586", "N142_377\/957", "N158_344\/626", "N162_081\/300", "N158_343\/625", "N151_912\/221", "N162_097\/424", "N166_063\/197", "N146_273\/737", "N141_295\/063", "N98_539\/567", "N151_922\/226" ], [ [ "0", "4", "7", "13", "6" ], [ "0", "5", "1", "11", "7" ], [ "4", "1", "3", "13", "1" ], [ "14", "14", "5", "14", "23" ], [ "21", "34", "36", "31", "25" ], [ "29", "12", "10", "14", "8" ], [ "10", "14", "11", "4", "6" ], [ "4", "1", "17", "31", "6" ], [ "4", "8", "8", "30", "3" ], [ "22", "10", "24", "23", "5" ], [ "3", "4", "6", "27", "15" ], [ "63", "0", "0", "0", "0" ], [ "6", "0", "0", "0", "0" ], [ "0", "0", "2", "3", "0" ] ] ] }, { "name": "Latitude", "index": "4", "type": "nominal", "distinct": "12", "missing": "0", "distr": [ [ "39__38", "39__00", "40__11", "39__50", "40__57", "41__12", "40__36", "41__08", "41__16", "40__00", "39__43", "82__32" ], [ [ "0", "4", "7", "13", "6" ], [ "0", "5", "1", "11", "7" ], [ "4", "1", "3", "13", "1" ], [ "14", "14", "5", "14", "23" ], [ "31", "48", "47", "35", "31" ], [ "29", "12", "10", "14", "8" ], [ "4", "1", "19", "34", "6" ], [ "4", "8", "8", "30", "3" ], [ "22", "10", "24", "23", "5" ], [ "3", "4", "6", "27", "15" ], [ "63", "0", "0", "0", "0" ], [ "6", "0", "0", "0", "0" ] ] ] }, { "name": "Altitude", "index": "5", "type": "numeric", "distinct": "9", "missing": "0", "min": "70", "max": "300", "mean": "172", "stdev": "59" }, { "name": "Rainfall", "index": "6", "type": "numeric", "distinct": "10", "missing": "0", "min": "850", "max": "1750", "mean": "1096", "stdev": "145" }, { "name": "Frosts", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "-3", "max": "0", "mean": "-3", "stdev": "0" }, { "name": "Year", "index": "8", "type": "numeric", "distinct": "5", "missing": "0", "min": "1980", "max": "1986", "mean": "1982", "stdev": "2" }, { "name": "Sp", "index": "9", "type": "nominal", "distinct": "27", "missing": "0", "distr": [ [ "co", "fr", "ma", "nd", "ni", "ob", "ov", "pu", "rd", "si", "mn", "ag", "bxs", "br", "el", "fa", "jo", "ka", "re", "sm", "ro", "nc", "am", "cr", "pa", "ra", "te" ], [ [ "4", "4", "7", "10", "2" ], [ "5", "5", "9", "24", "9" ], [ "0", "2", "1", "0", "0" ], [ "20", "2", "14", "36", "14" ], [ "0", "3", "5", "20", "3" ], [ "6", "2", "6", "19", "17" ], [ "11", "12", "16", "15", "8" ], [ "16", "0", "6", "9", "8" ], [ "15", "14", "6", "2", "0" ], [ "1", "1", "1", "5", "1" ], [ "1", "1", "0", "1", "0" ], [ "7", "2", "0", "0", "0" ], [ "3", "3", "7", "4", "0" ], [ "6", "14", "5", "1", "2" ], [ "4", "5", "2", "1", "0" ], [ "6", "5", "13", "20", "8" ], [ "4", "4", "1", "0", "0" ], [ "11", "8", "0", "0", "0" ], [ "7", "4", "17", "29", "25" ], [ "8", "6", "0", "0", "0" ], [ "1", "1", "0", "0", "0" ], [ "2", "3", "1", "0", "0" ], [ "19", "0", "7", "16", "6" ], [ "0", "5", "5", "1", "0" ], [ "3", "1", "1", "1", "2" ], [ "7", "0", "0", "0", "0" ], [ "13", "0", "0", "0", "0" ] ] ] }, { "name": "PMCno", "index": "10", "type": "numeric", "distinct": "85", "missing": "7", "min": "1", "max": "3275", "mean": "2055", "stdev": "618" }, { "name": "DBH", "index": "11", "type": "numeric", "distinct": "603", "missing": "1", "min": "1", "max": "42085", "mean": "73", "stdev": "1552" }, { "name": "Ht", "index": "12", "type": "numeric", "distinct": "531", "missing": "1", "min": "1", "max": "22", "mean": "9", "stdev": "4" }, { "name": "Surv", "index": "13", "type": "numeric", "distinct": "47", "missing": "94", "min": "2", "max": "100", "mean": "60", "stdev": "31" }, { "name": "Vig", "index": "14", "type": "numeric", "distinct": "33", "missing": "69", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Ins_res", "index": "15", "type": "numeric", "distinct": "28", "missing": "69", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Stem_Fm", "index": "16", "type": "numeric", "distinct": "26", "missing": "69", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Crown_Fm", "index": "17", "type": "numeric", "distinct": "29", "missing": "69", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Brnch_Fm", "index": "18", "type": "numeric", "distinct": "28", "missing": "69", "min": "0", "max": "5", "mean": "3", "stdev": "1" } ], "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 }