{ "data_id": "44673", "name": "PhishingWebsites_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "exact_name": "PhishingWebsites_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "version": 1, "version_label": "f9944590-15d4-4f60-a185-81677b2fe553", "description": "Subsampling of the dataset PhishingWebsites (4534) 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 18:41:53", "update_comment": null, "last_update": "2022-11-17 18:41:53", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111435\/dataset", "default_target_attribute": "Result", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "PhishingWebsites_seed_0_nrows_2000_nclasses_10_ncols_100_stratify_True", "Subsampling of the dataset PhishingWebsites (4534) 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. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 2000, "NumberOfFeatures": 31, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 0, "NumberOfSymbolicFeatures": 31, "PercentageOfBinaryFeatures": 74.19354838709677, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.5022511255627814, "PercentageOfMissingValues": 0, "Dimensionality": 0.0155, "PercentageOfNumericFeatures": 0, "MajorityClassPercentage": 55.7, "PercentageOfSymbolicFeatures": 100, "MajorityClassSize": 1114, "MinorityClassPercentage": 44.3, "MinorityClassSize": 886, "NumberOfBinaryFeatures": 23 }, "tags": [ { "uploader": "38960", "tag": "Chemistry" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "Result", "index": "30", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "-1", "1" ], [ [ "886", "0" ], [ "0", "1114" ] ] ] }, { "name": "having_IP_Address", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "362", "323" ], [ "524", "791" ] ] ] }, { "name": "URL_Length", "index": "1", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "0", "-1" ], [ [ "119", "214" ], [ "16", "13" ], [ "751", "887" ] ] ] }, { "name": "Shortining_Service", "index": "2", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "-1" ], [ [ "796", "963" ], [ "90", "151" ] ] ] }, { "name": "having_At_Symbol", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "-1" ], [ [ "724", "986" ], [ "162", "128" ] ] ] }, { "name": "double_slash_redirecting", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "93", "145" ], [ "793", "969" ] ] ] }, { "name": "Prefix_Suffix", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "886", "865" ], [ "0", "249" ] ] ] }, { "name": "having_Sub_Domain", "index": "6", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "-1", "0", "1" ], [ [ "295", "275" ], [ "423", "260" ], [ "168", "579" ] ] ] }, { "name": "SSLfinal_State", "index": "7", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "-1", "1", "0" ], [ [ "567", "74" ], [ "106", "1035" ], [ "213", "5" ] ] ] }, { "name": "Domain_registeration_length", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "462", "859" ], [ "424", "255" ] ] ] }, { "name": "Favicon", "index": "9", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "-1" ], [ [ "721", "912" ], [ "165", "202" ] ] ] }, { "name": "port", "index": "10", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "-1" ], [ [ "759", "963" ], [ "127", "151" ] ] ] }, { "name": "HTTPS_token", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "128", "174" ], [ "758", "940" ] ] ] }, { "name": "Request_URL", "index": "12", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "-1" ], [ [ "375", "795" ], [ "511", "319" ] ] ] }, { "name": "URL_of_Anchor", "index": "13", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "-1", "0", "1" ], [ [ "590", "9" ], [ "268", "692" ], [ "28", "413" ] ] ] }, { "name": "Links_in_tags", "index": "14", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "-1", "0" ], [ [ "141", "343" ], [ "421", "320" ], [ "324", "451" ] ] ] }, { "name": "SFH", "index": "15", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "-1", "1", "0" ], [ [ "780", "782" ], [ "58", "246" ], [ "48", "86" ] ] ] }, { "name": "Submitting_to_email", "index": "16", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "169", "201" ], [ "717", "913" ] ] ] }, { "name": "Abnormal_URL", "index": "17", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "117", "174" ], [ "769", "940" ] ] ] }, { "name": "Redirect", "index": "18", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "774", "996" ], [ "112", "118" ] ] ] }, { "name": "on_mouseover", "index": "19", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "-1" ], [ [ "770", "996" ], [ "116", "118" ] ] ] }, { "name": "RightClick", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "-1" ], [ [ "848", "1068" ], [ "38", "46" ] ] ] }, { "name": "popUpWidnow", "index": "21", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "-1" ], [ [ "711", "906" ], [ "175", "208" ] ] ] }, { "name": "Iframe", "index": "22", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "-1" ], [ [ "809", "1023" ], [ "77", "91" ] ] ] }, { "name": "age_of_domain", "index": "23", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "470", "479" ], [ "416", "635" ] ] ] }, { "name": "DNSRecord", "index": "24", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "304", "321" ], [ "582", "793" ] ] ] }, { "name": "web_traffic", "index": "25", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "-1", "0", "1" ], [ [ "315", "204" ], [ "307", "167" ], [ "264", "743" ] ] ] }, { "name": "Page_Rank", "index": "26", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "689", "780" ], [ "197", "334" ] ] ] }, { "name": "Google_Index", "index": "27", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "-1" ], [ [ "732", "1007" ], [ "154", "107" ] ] ] }, { "name": "Links_pointing_to_page", "index": "28", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "0", "-1" ], [ [ "319", "457" ], [ "541", "596" ], [ "26", "61" ] ] ] }, { "name": "Statistical_report", "index": "29", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "-1", "1" ], [ [ "156", "140" ], [ "730", "974" ] ] ] } ], "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 }