{ "data_id": "44659", "name": "churn_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "churn_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "131deadc-59e0-4232-83b6-7fcba513d195", "description": "Subsampling of the dataset churn (40701) 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": "Eddie Bergman", "uploader_id": 32840, "visibility": "public", "creator": "\"Eddie Bergman\"", "contributor": null, "date": "2022-11-17 18:40:48", "update_comment": null, "last_update": "2022-11-17 18:40:48", "licence": "public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111421\/dataset", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "churn_seed_1_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset churn (40701) 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.choice( cl " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 21, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 16, "NumberOfSymbolicFeatures": 5, "PercentageOfBinaryFeatures": 14.285714285714285, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.7603801900950475, "PercentageOfMissingValues": 0, "Dimensionality": 0.0105, "PercentageOfNumericFeatures": 76.19047619047619, "MajorityClassPercentage": 85.85000000000001, "PercentageOfSymbolicFeatures": 23.809523809523807, "MajorityClassSize": 1717, "MinorityClassPercentage": 14.149999999999999, "MinorityClassSize": 283, "NumberOfBinaryFeatures": 3 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Mathematics" } ], "features": [ { "name": "class", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "1717", "0" ], [ "0", "283" ] ] ] }, { "name": "state", "index": "0", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "50", "mean": "26", "stdev": "15" }, { "name": "account_length", "index": "1", "type": "numeric", "distinct": "199", "missing": "0", "min": "1", "max": "224", "mean": "100", "stdev": "40" }, { "name": "area_code", "index": "2", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "408", "415", "510" ], [ [ "463", "64" ], [ "835", "130" ], [ "419", "89" ] ] ] }, { "name": "phone_number", "index": "3", "type": "numeric", "distinct": "2000", "missing": "0", "min": "0", "max": "4999", "mean": "2458", "stdev": "1438" }, { "name": "international_plan", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1599", "207" ], [ "118", "76" ] ] ] }, { "name": "voice_mail_plan", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "1232", "236" ], [ "485", "47" ] ] ] }, { "name": "number_vmail_messages", "index": "6", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "50", "mean": "8", "stdev": "13" }, { "name": "total_day_minutes", "index": "7", "type": "numeric", "distinct": "1283", "missing": "0", "min": "7", "max": "352", "mean": "181", "stdev": "54" }, { "name": "total_day_calls", "index": "8", "type": "numeric", "distinct": "112", "missing": "0", "min": "34", "max": "163", "mean": "100", "stdev": "20" }, { "name": "total_day_charge", "index": "9", "type": "numeric", "distinct": "1283", "missing": "0", "min": "1", "max": "60", "mean": "31", "stdev": "9" }, { "name": "total_eve_minutes", "index": "10", "type": "numeric", "distinct": "1187", "missing": "0", "min": "31", "max": "359", "mean": "201", "stdev": "50" }, { "name": "total_eve_calls", "index": "11", "type": "numeric", "distinct": "116", "missing": "0", "min": "12", "max": "157", "mean": "99", "stdev": "20" }, { "name": "total_eve_charge", "index": "12", "type": "numeric", "distinct": "1085", "missing": "0", "min": "3", "max": "31", "mean": "17", "stdev": "4" }, { "name": "total_night_minutes", "index": "13", "type": "numeric", "distinct": "1231", "missing": "0", "min": "0", "max": "382", "mean": "201", "stdev": "51" }, { "name": "total_night_calls", "index": "14", "type": "numeric", "distinct": "119", "missing": "0", "min": "0", "max": "175", "mean": "100", "stdev": "20" }, { "name": "total_night_charge", "index": "15", "type": "numeric", "distinct": "798", "missing": "0", "min": "0", "max": "17", "mean": "9", "stdev": "2" }, { "name": "total_intl_minutes", "index": "16", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "20", "mean": "10", "stdev": "3" }, { "name": "total_intl_calls", "index": "17", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "19", "mean": "4", "stdev": "2" }, { "name": "total_intl_charge", "index": "18", "type": "numeric", "distinct": "160", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "number_customer_service_calls", "index": "19", "type": "nominal", "distinct": "10", "missing": "0", "distr": [ [ "0", "1", "2", "3", "4", "5", "6", "7", "8", "9" ], [ [ "346", "46" ], [ "640", "78" ], [ "410", "44" ], [ "243", "31" ], [ "54", "47" ], [ "14", "25" ], [ "7", "8" ], [ "2", "3" ], [ "1", "0" ], [ "0", "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 }