{ "data_id": "44445", "name": "covertype_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "covertype_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 2, "version_label": "3040efed-cc3f-42ac-a645-63b71b802312", "description": "Subsampling of the dataset covertype (44159) 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": "Eddie Bergman", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:02:01", "update_comment": null, "last_update": "2022-11-17 18:02:01", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111207\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "covertype_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset covertype (44159) 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.choice " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 55, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 10, "NumberOfSymbolicFeatures": 45, "PercentageOfBinaryFeatures": 72.72727272727273, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.49974987493746875, "PercentageOfMissingValues": 0, "Dimensionality": 0.0275, "PercentageOfNumericFeatures": 18.181818181818183, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 81.81818181818183, "MajorityClassSize": 1000, "MinorityClassPercentage": 50, "MinorityClassSize": 1000, "NumberOfBinaryFeatures": 40 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Mathematics" } ], "features": [ { "name": "class", "index": "54", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "1", "2" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "Elevation", "index": "0", "type": "numeric", "distinct": "738", "missing": "0", "min": "2190", "max": "3594", "mean": "3029", "stdev": "201" }, { "name": "Aspect", "index": "1", "type": "numeric", "distinct": "353", "missing": "0", "min": "0", "max": "359", "mean": "154", "stdev": "113" }, { "name": "Slope", "index": "2", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "44", "mean": "13", "stdev": "7" }, { "name": "Horizontal_Distance_To_Hydrology", "index": "3", "type": "numeric", "distinct": "239", "missing": "0", "min": "0", "max": "1224", "mean": "273", "stdev": "213" }, { "name": "Vertical_Distance_To_Hydrology", "index": "4", "type": "numeric", "distinct": "275", "missing": "0", "min": "-111", "max": "394", "mean": "43", "stdev": "57" }, { "name": "Horizontal_Distance_To_Roadways", "index": "5", "type": "numeric", "distinct": "1469", "missing": "0", "min": "30", "max": "6915", "mean": "2528", "stdev": "1563" }, { "name": "Hillshade_9am", "index": "6", "type": "numeric", "distinct": "124", "missing": "0", "min": "89", "max": "254", "mean": "213", "stdev": "24" }, { "name": "Hillshade_Noon", "index": "7", "type": "numeric", "distinct": "97", "missing": "0", "min": "129", "max": "254", "mean": "225", "stdev": "18" }, { "name": "Hillshade_3pm", "index": "8", "type": "numeric", "distinct": "188", "missing": "0", "min": "0", "max": "240", "mean": "144", "stdev": "35" }, { "name": "Horizontal_Distance_To_Fire_Points", "index": "9", "type": "numeric", "distinct": "1324", "missing": "0", "min": "42", "max": "6925", "mean": "2095", "stdev": "1339" }, { "name": "Wilderness_Area1", "index": "10", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "493", "494" ], [ "507", "506" ] ] ] }, { "name": "Wilderness_Area2", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "972", "912" ], [ "28", "88" ] ] ] }, { "name": "Wilderness_Area3", "index": "12", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "545", "594" ], [ "455", "406" ] ] ] }, { "name": "Wilderness_Area4", "index": "13", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "990", "1000" ], [ "10", "0" ] ] ] }, { "name": "Soil_Type1", "index": "14", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "Soil_Type2", "index": "15", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "996", "1000" ], [ "4", "0" ] ] ] }, { "name": "Soil_Type3", "index": "16", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "993", "1000" ], [ "7", "0" ] ] ] }, { "name": "Soil_Type4", "index": "17", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "988", "997" ], [ "12", "3" ] ] ] }, { "name": "Soil_Type5", "index": "18", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "Soil_Type6", "index": "19", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "995", "1000" ], [ "5", "0" ] ] ] }, { "name": "Soil_Type7", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "998", "1000" ], [ "2", "0" ] ] ] }, { "name": "Soil_Type8", "index": "21", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "1000" ], [ "0", "0" ] ] ] }, { "name": "Soil_Type9", "index": "22", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "993", "997" ], [ "7", "3" ] ] ] }, { "name": "Soil_Type10", "index": "23", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "963", "998" ], [ "37", "2" ] ] ] }, { "name": "Soil_Type11", "index": "24", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "968", "996" ], [ "32", "4" ] ] ] }, { "name": "Soil_Type12", "index": "25", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "897", "987" ], [ "103", "13" ] ] ] }, { "name": "Soil_Type13", "index": "26", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "953", "991" ], [ "47", "9" ] ] ] }, { "name": "Soil_Type14", "index": "27", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "Soil_Type15", "index": "28", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "Soil_Type16", "index": "29", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "995", "997" ], [ "5", "3" ] ] ] }, { "name": "Soil_Type17", "index": "30", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "995", "1000" ], [ "5", "0" ] ] ] }, { "name": "Soil_Type18", "index": "31", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "997", "1000" ], [ "3", "0" ] ] ] }, { "name": "Soil_Type19", "index": "32", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "997", "991" ], [ "3", "9" ] ] ] }, { "name": "Soil_Type20", "index": "33", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "987", "983" ], [ "13", "17" ] ] ] }, { "name": "Soil_Type21", "index": "34", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "996" ], [ "0", "4" ] ] ] }, { "name": "Soil_Type22", "index": "35", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "976", "872" ], [ "24", "128" ] ] ] }, { "name": "Soil_Type23", "index": "36", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "920", "840" ], [ "80", "160" ] ] ] }, { "name": "Soil_Type24", "index": "37", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "964", "947" ], [ "36", "53" ] ] ] }, { "name": "Soil_Type25", "index": "38", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "1000" ], [ "0", "0" ] ] ] }, { "name": "Soil_Type26", "index": "39", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "991", "1000" ], [ "9", "0" ] ] ] }, { "name": "Soil_Type27", "index": "40", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "997", "998" ], [ "3", "2" ] ] ] }, { "name": "Soil_Type28", "index": "41", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "995", "999" ], [ "5", "1" ] ] ] }, { "name": "Soil_Type29", "index": "42", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "762", "804" ], [ "238", "196" ] ] ] }, { "name": "Soil_Type30", "index": "43", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "927", "962" ], [ "73", "38" ] ] ] }, { "name": "Soil_Type31", "index": "44", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "960", "937" ], [ "40", "63" ] ] ] }, { "name": "Soil_Type32", "index": "45", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "885", "912" ], [ "115", "88" ] ] ] }, { "name": "Soil_Type33", "index": "46", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "920", "914" ], [ "80", "86" ] ] ] }, { "name": "Soil_Type34", "index": "47", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "995", "1000" ], [ "5", "0" ] ] ] }, { "name": "Soil_Type35", "index": "48", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "993" ], [ "0", "7" ] ] ] }, { "name": "Soil_Type36", "index": "49", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "999" ], [ "0", "1" ] ] ] }, { "name": "Soil_Type37", "index": "50", "type": "nominal", "distinct": "1", "missing": "0", "distr": [ [ "0" ], [ [ "1000", "1000" ] ] ] }, { "name": "Soil_Type38", "index": "51", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "997", "961" ], [ "3", "39" ] ] ] }, { "name": "Soil_Type39", "index": "52", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1000", "950" ], [ "0", "50" ] ] ] }, { "name": "Soil_Type40", "index": "53", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "996", "979" ], [ "4", "21" ] ] ] } ], "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 }