DEVELOPMENT... { "data_id": "44455", "name": "road-safety_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "road-safety_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "522236d0-e48f-4631-9cc5-ee250fbeaa06", "description": "Subsampling of the dataset road-safety (44161) 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 18:02:54", "update_comment": null, "last_update": "2022-11-17 18:02:54", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111217\/dataset", "default_target_attribute": "Sex_of_Driver", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "road-safety_seed_2_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset road-safety (44161) 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.choi " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 33, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 29, "NumberOfSymbolicFeatures": 4, "PercentageOfSymbolicFeatures": 12.121212121212121, "AutoCorrelation": 0.5062531265632816, "PercentageOfNumericFeatures": 87.87878787878788, "PercentageOfMissingValues": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfBinaryFeatures": 12.121212121212121, "NumberOfBinaryFeatures": 4, "MinorityClassSize": 1000, "MinorityClassPercentage": 50, "MajorityClassSize": 1000, "MajorityClassPercentage": 50, "Dimensionality": 0.0165 }, "tags": [], "features": [ { "name": "Sex_of_Driver", "index": "32", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "1.0", "2.0" ], [ [ "1000", "0" ], [ "0", "1000" ] ] ] }, { "name": "Number_of_Vehicles", "index": "17", "type": "numeric", "distinct": "10", "missing": "0", "min": "1", "max": "37", "mean": "2", "stdev": "3" }, { "name": "Police_Force", "index": "16", "type": "numeric", "distinct": "39", "missing": "0", "min": "1", "max": "98", "mean": "23", "stdev": "18" }, { "name": "Number_of_Casualties", "index": "18", "type": "numeric", "distinct": "13", "missing": "0", "min": "1", "max": "36", "mean": "2", "stdev": "3" }, { "name": "Local_Authority_(District)", "index": "19", "type": "numeric", "distinct": "276", "missing": "0", "min": "1", "max": "921", "mean": "276", "stdev": "189" }, { "name": "1st_Road_Number", "index": "20", "type": "numeric", "distinct": "720", "missing": "0", "min": "0", "max": "9704", "mean": "947", "stdev": "1756" }, { "name": "2nd_Road_Number", "index": "21", "type": "numeric", "distinct": "346", "missing": "0", "min": "0", "max": "9500", "mean": "393", "stdev": "1314" }, { "name": "Urban_or_Rural_Area", "index": "22", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1.0", "2.0" ], [ [ "639", "602" ], [ "361", "398" ] ] ] }, { "name": "Vehicle_Reference_df", "index": "23", "type": "numeric", "distinct": "10", "missing": "0", "min": "1", "max": "27", "mean": "2", "stdev": "1" }, { "name": "Casualty_Reference", "index": "24", "type": "numeric", "distinct": "15", "missing": "0", "min": "1", "max": "36", "mean": "2", "stdev": "2" }, { "name": "Sex_of_Casualty", "index": "25", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1.0", "2.0" ], [ [ "703", "339" ], [ "297", "661" ] ] ] }, { "name": "Age_of_Casualty", "index": "26", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "93", "mean": "37", "stdev": "18" }, { "name": "Age_Band_of_Casualty", "index": "27", "type": "numeric", "distinct": "11", "missing": "0", "min": "1", "max": "11", "mean": "6", "stdev": "2" }, { "name": "Pedestrian_Location", "index": "28", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "10", "mean": "0", "stdev": "1" }, { "name": "Pedestrian_Movement", "index": "29", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Casualty_Type", "index": "30", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "98", "mean": "8", "stdev": "7" }, { "name": "Casualty_IMD_Decile", "index": "31", "type": "numeric", "distinct": "10", "missing": "0", "min": "1", "max": "10", "mean": "5", "stdev": "3" }, { "name": "Vehicle_Reference_df_res", "index": "0", "type": "numeric", "distinct": "13", "missing": "0", "min": "1", "max": "37", "mean": "2", "stdev": "2" }, { "name": "Latitude", "index": "15", "type": "numeric", "distinct": "1946", "missing": "0", "min": "50", "max": "56", "mean": "53", "stdev": "1" }, { "name": "Longitude", "index": "14", "type": "numeric", "distinct": "1948", "missing": "0", "min": "-6", "max": "2", "mean": "-1", "stdev": "1" }, { "name": "Location_Northing_OSGR", "index": "13", "type": "numeric", "distinct": "1922", "missing": "0", "min": "19648", "max": "670541", "mean": "295842", "stdev": "123758" }, { "name": "Location_Easting_OSGR", "index": "12", "type": "numeric", "distinct": "1921", "missing": "0", "min": "147682", "max": "652670", "mean": "447565", "stdev": "81721" }, { "name": "Age_of_Vehicle", "index": "11", "type": "numeric", "distinct": "30", "missing": "0", "min": "1", "max": "45", "mean": "8", "stdev": "5" }, { "name": "Propulsion_Code", "index": "10", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "8", "mean": "1", "stdev": "1" }, { "name": "Engine_Capacity_(CC)", "index": "9", "type": "numeric", "distinct": "275", "missing": "0", "min": "49", "max": "18000", "mean": "1827", "stdev": "1448" }, { "name": "Age_Band_of_Driver", "index": "8", "type": "numeric", "distinct": "9", "missing": "0", "min": "3", "max": "11", "mean": "7", "stdev": "2" }, { "name": "Age_of_Driver", "index": "7", "type": "numeric", "distinct": "77", "missing": "0", "min": "15", "max": "91", "mean": "40", "stdev": "16" }, { "name": "Was_Vehicle_Left_Hand_Drive?", "index": "6", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1.0", "2.0" ], [ [ "998", "996" ], [ "2", "4" ] ] ] }, { "name": "Hit_Object_off_Carriageway", "index": "5", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "11", "mean": "1", "stdev": "2" }, { "name": "Hit_Object_in_Carriageway", "index": "4", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "12", "mean": "0", "stdev": "2" }, { "name": "Vehicle_Location-Restricted_Lane", "index": "3", "type": "numeric", "distinct": "7", "missing": "0", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Vehicle_Manoeuvre", "index": "2", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "18", "mean": "12", "stdev": "6" }, { "name": "Vehicle_Type", "index": "1", "type": "numeric", "distinct": "13", "missing": "0", "min": "2", "max": "98", "mean": "10", "stdev": "7" } ], "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 }