add system wise datasets

Former-commit-id: e1bf8c0e30 [formerly 9386448d17] [formerly 17c1ae5bd3 [formerly 78ee2cffef]] [formerly 459a703f1b [formerly 9126884a53] [formerly 74ee83089e [formerly 8b9742d9f1]]] [formerly 797aba0ba4 [formerly 38ad206c4d] [formerly d128882536 [formerly d30ea801db]] [formerly e0123572d2 [formerly 3cfe65ed4c] [formerly 157285e255 [formerly a45a5bb647]]]] [formerly 36cca8a1e3 [formerly 8f8d4d8b17] [formerly 9fe36cc4eb [formerly f59aba98c1]] [formerly 771721df00 [formerly 2ae7aeefd5] [formerly bfb21c9242 [formerly 25e2655f8f]]] [formerly 548d352c8e [formerly 708bec7e6b] [formerly 6c6c9d5cee [formerly 2526236028]] [formerly fb6696cdde [formerly 242c28d5be] [formerly 74be87e1ca [formerly 888e32e522]]]]] [formerly 4e8d3b08b1 [formerly bdcd927d00] [formerly 797632a3aa [formerly 5e99b61d0f]] [formerly 556e0094f9 [formerly 6b3e4bf814] [formerly a178cbe64a [formerly 414507f19b]]] [formerly f700544f5b [formerly 7219cb0c49] [formerly d9cfd00316 [formerly 36cf918db5]] [formerly f44ee9f8fa [formerly 775a39010e] [formerly 669e4be3a5 [formerly 4aeed1de94]]]] [formerly a01eab2239 [formerly 30b99549b1] [formerly 98f5a2b268 [formerly 5e171c968c]] [formerly e92331bbc5 [formerly 3062bbaf1e] [formerly 2ad768c57f [formerly 3c7cab92bb]]] [formerly 5251f5eaa1 [formerly d41594d6cf] [formerly 337ed90f39 [formerly a869a0da0b]] [formerly c7892d7b93 [formerly 743930398e] [formerly 9df64f76bb [formerly 3d026595c5]]]]]]
Former-commit-id: 56d7594018 [formerly 57fe5ebddb] [formerly 9634e332d5 [formerly 139bb4d769]] [formerly 698d33fcc2 [formerly ca034df97e] [formerly 1c11166990 [formerly f25bc66ade]]] [formerly 3a1fb43afd [formerly 956d67eba6] [formerly bb93922e72 [formerly 6a92a7b182]] [formerly b53dc2efc4 [formerly 26c42afb71] [formerly abfe82131c [formerly aa7f9d3dbc]]]] [formerly d8c015d646 [formerly 9d1f8fc076] [formerly b33024c2f5 [formerly dc18f076ce]] [formerly 9f4bd97ffd [formerly 801e22e53a] [formerly aa995f4256 [formerly d92bf22f2a]]] [formerly a015d7de32 [formerly c11f641bb7] [formerly d4644de408 [formerly 818e998069]] [formerly 8d6e0b5f80 [formerly 91619ff57b] [formerly 9df64f76bb]]]]
Former-commit-id: 0c182064c1 [formerly 088250998b] [formerly 85c8591dc4 [formerly 62f275f8c3]] [formerly eff442ebfe [formerly 53fdbb1ae6] [formerly a3ed102fcb [formerly 79d253fb53]]] [formerly 4cda58d913 [formerly 67ee5d4bd3] [formerly f2a3730052 [formerly 85b4ff9a27]] [formerly 79759673b5 [formerly dbcd059d16] [formerly 0ceacff851 [formerly 9e2fa43118]]]]
Former-commit-id: ad4014557d [formerly aaa89fbc0e] [formerly 344f971c75 [formerly f1eca02881]] [formerly 326ba02646 [formerly 2dbbd64bc3] [formerly 33410592f3 [formerly c3717a27c9]]]
Former-commit-id: 2d95b9a6a6 [formerly 04a561ef26] [formerly 8bb647760f [formerly 2e0ca90d2e]]
Former-commit-id: 08aa419524 [formerly 06c7e0433f]
Former-commit-id: 54496b2adb

datasets/anomaly/yahoo_system_sub_5/SCORE/dataset_TEST/datasetDoc.json

@@ -0,0 +1,71 @@
+{
+    "about": {
+        "datasetID": "yahoo_system_sub_5_dataset_TEST",
+        "datasetName": "NULL",
+        "description": "Database of baseball players and play statistics, including 'Games_played', 'At_bats', 'Runs', 'Hits', 'Doubles', 'Triples', 'Home_runs', 'RBIs', 'Walks', 'Strikeouts', 'Batting_average', 'On_base_pct', 'Slugging_pct' and 'Fielding_ave'",
+        "citation": " @book{simonoff2003analyzing,title={Analyzing Categorical Data},author={Simonoff, J.S.},isbn={9780387007496},lccn={2003044946},series={Springer Texts in Statistics},url={https://books.google.com/books?id=G8wrifweAoC},year={2003},publisher={Springer New York}} ",
+        "license": " CC Public Domain Mark 1.0 ",
+        "source": "OpenML",
+        "sourceURI": "http://www.openml.org/d/185",
+        "approximateSize": "",
+        "datasetSchemaVersion": "4.0.0",
+        "redacted": false,
+        "datasetVersion": "4.0.0"
+    },
+    "dataResources": [
+        {
+            "resID": "learningData",
+            "resPath": "tables/learningData.csv",
+            "resType": "table",
+            "resFormat": {
+                "text/csv": [
+                    "csv"
+                ]
+            },
+            "isCollection": false,
+            "columns": [
+                {
+                    "colIndex": 0,
+                    "colName": "d3mIndex",
+                    "colType": "integer",
+                    "role": [
+                        "index"
+                    ]
+                },
+                {
+                    "colIndex": 1,
+                    "colName": "timestamp",
+                    "colType": "integer",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 2,
+                    "colName": "value_0",
+                    "colType": "real",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 3,
+                    "colName": "system_id",
+                    "colType": "real",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 4,
+                    "colName": "ground_truth",
+                    "colType": "integer",
+                    "role": [
+                        "suggestedTarget"
+                    ]
+                }
+            ],
+            "columnsCount": 5
+        }
+    ]
+}

datasets/anomaly/yahoo_system_sub_5/SCORE/problem_TEST/problemDoc.json

@@ -0,0 +1,65 @@
+{
+    "about": {
+        "problemID": "yahoo_system_sub_5_problem",
+        "problemName": "yahoo_system_sub_5_problem",
+        "problemDescription": "Anomaly detection",
+        "problemVersion": "4.0.0",
+        "problemSchemaVersion": "4.0.0",
+        "taskKeywords": [
+            "classification",
+            "binary",
+            "tabular"
+        ]
+    },
+    "inputs": {
+        "data": [
+            {
+                "datasetID": "yahoo_system_sub_5_dataset",
+                "targets": [
+                    {
+                        "targetIndex": 0,
+                        "resID": "learningData",
+                        "colIndex": 4,
+                        "colName": "ground_truth"
+                    }
+                ]
+            }
+        ],
+        "dataSplits": {
+            "method": "holdOut",
+            "testSize": 0.2,
+            "stratified": true,
+            "numRepeats": 0,
+            "randomSeed": 42,
+            "splitsFile": "dataSplits.csv",
+            "datasetViewMaps": {
+                "train": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_TRAIN"
+                    }
+                ],
+                "test": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_TEST"
+                    }
+                ],
+                "score": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_SCORE"
+                    }
+                ]
+            }
+        },
+        "performanceMetrics": [
+            {
+                "metric": "f1Macro"
+            }
+        ]
+    },
+    "expectedOutputs": {
+        "predictionsFile": "predictions.csv"
+    }
+}

datasets/anomaly/yahoo_system_sub_5/TEST/dataset_TEST/datasetDoc.json

@@ -0,0 +1,71 @@
+{
+    "about": {
+        "datasetID": "yahoo_system_sub_5_dataset_TEST",
+        "datasetName": "NULL",
+        "description": "Database of baseball players and play statistics, including 'Games_played', 'At_bats', 'Runs', 'Hits', 'Doubles', 'Triples', 'Home_runs', 'RBIs', 'Walks', 'Strikeouts', 'Batting_average', 'On_base_pct', 'Slugging_pct' and 'Fielding_ave'",
+        "citation": " @book{simonoff2003analyzing,title={Analyzing Categorical Data},author={Simonoff, J.S.},isbn={9780387007496},lccn={2003044946},series={Springer Texts in Statistics},url={https://books.google.com/books?id=G8wrifweAoC},year={2003},publisher={Springer New York}} ",
+        "license": " CC Public Domain Mark 1.0 ",
+        "source": "OpenML",
+        "sourceURI": "http://www.openml.org/d/185",
+        "approximateSize": "",
+        "datasetSchemaVersion": "4.0.0",
+        "redacted": false,
+        "datasetVersion": "4.0.0"
+    },
+    "dataResources": [
+        {
+            "resID": "learningData",
+            "resPath": "tables/learningData.csv",
+            "resType": "table",
+            "resFormat": {
+                "text/csv": [
+                    "csv"
+                ]
+            },
+            "isCollection": false,
+            "columns": [
+                {
+                    "colIndex": 0,
+                    "colName": "d3mIndex",
+                    "colType": "integer",
+                    "role": [
+                        "index"
+                    ]
+                },
+                {
+                    "colIndex": 1,
+                    "colName": "timestamp",
+                    "colType": "integer",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 2,
+                    "colName": "value_0",
+                    "colType": "real",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 3,
+                    "colName": "system_id",
+                    "colType": "real",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 4,
+                    "colName": "ground_truth",
+                    "colType": "integer",
+                    "role": [
+                        "suggestedTarget"
+                    ]
+                }
+            ],
+            "columnsCount": 5
+        }
+    ]
+}

datasets/anomaly/yahoo_system_sub_5/TEST/problem_TEST/problemDoc.json

@@ -0,0 +1,65 @@
+{
+    "about": {
+        "problemID": "yahoo_system_sub_5_problem",
+        "problemName": "yahoo_system_sub_5_problem",
+        "problemDescription": "Anomaly detection",
+        "problemVersion": "4.0.0",
+        "problemSchemaVersion": "4.0.0",
+        "taskKeywords": [
+            "classification",
+            "binary",
+            "tabular"
+        ]
+    },
+    "inputs": {
+        "data": [
+            {
+                "datasetID": "yahoo_system_sub_5_dataset",
+                "targets": [
+                    {
+                        "targetIndex": 0,
+                        "resID": "learningData",
+                        "colIndex": 4,
+                        "colName": "ground_truth"
+                    }
+                ]
+            }
+        ],
+        "dataSplits": {
+            "method": "holdOut",
+            "testSize": 0.2,
+            "stratified": true,
+            "numRepeats": 0,
+            "randomSeed": 42,
+            "splitsFile": "dataSplits.csv",
+            "datasetViewMaps": {
+                "train": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_TRAIN"
+                    }
+                ],
+                "test": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_TEST"
+                    }
+                ],
+                "score": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_SCORE"
+                    }
+                ]
+            }
+        },
+        "performanceMetrics": [
+            {
+                "metric": "f1Macro"
+            }
+        ]
+    },
+    "expectedOutputs": {
+        "predictionsFile": "predictions.csv"
+    }
+}

datasets/anomaly/yahoo_system_sub_5/TRAIN/dataset_TRAIN/datasetDoc.json

@@ -0,0 +1,71 @@
+{
+    "about": {
+        "datasetID": "yahoo_system_sub_5_dataset_TRAIN",
+        "datasetName": "NULL",
+        "description": "Database of baseball players and play statistics, including 'Games_played', 'At_bats', 'Runs', 'Hits', 'Doubles', 'Triples', 'Home_runs', 'RBIs', 'Walks', 'Strikeouts', 'Batting_average', 'On_base_pct', 'Slugging_pct' and 'Fielding_ave'",
+        "citation": " @book{simonoff2003analyzing,title={Analyzing Categorical Data},author={Simonoff, J.S.},isbn={9780387007496},lccn={2003044946},series={Springer Texts in Statistics},url={https://books.google.com/books?id=G8wrifweAoC},year={2003},publisher={Springer New York}} ",
+        "license": " CC Public Domain Mark 1.0 ",
+        "source": "OpenML",
+        "sourceURI": "http://www.openml.org/d/185",
+        "approximateSize": "",
+        "datasetSchemaVersion": "4.0.0",
+        "redacted": false,
+        "datasetVersion": "4.0.0"
+    },
+    "dataResources": [
+        {
+            "resID": "learningData",
+            "resPath": "tables/learningData.csv",
+            "resType": "table",
+            "resFormat": {
+                "text/csv": [
+                    "csv"
+                ]
+            },
+            "isCollection": false,
+            "columns": [
+                {
+                    "colIndex": 0,
+                    "colName": "d3mIndex",
+                    "colType": "integer",
+                    "role": [
+                        "index"
+                    ]
+                },
+                {
+                    "colIndex": 1,
+                    "colName": "timestamp",
+                    "colType": "integer",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 2,
+                    "colName": "value_0",
+                    "colType": "real",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 3,
+                    "colName": "system_id",
+                    "colType": "real",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 4,
+                    "colName": "ground_truth",
+                    "colType": "integer",
+                    "role": [
+                        "suggestedTarget"
+                    ]
+                }
+            ],
+            "columnsCount": 5
+        }
+    ]
+}

datasets/anomaly/yahoo_system_sub_5/TRAIN/problem_TRAIN/problemDoc.json

@@ -0,0 +1,65 @@
+{
+    "about": {
+        "problemID": "yahoo_system_sub_5_problem",
+        "problemName": "yahoo_system_sub_5_problem",
+        "problemDescription": "Anomaly detection",
+        "problemVersion": "4.0.0",
+        "problemSchemaVersion": "4.0.0",
+        "taskKeywords": [
+            "classification",
+            "binary",
+            "tabular"
+        ]
+    },
+    "inputs": {
+        "data": [
+            {
+                "datasetID": "yahoo_system_sub_5_dataset",
+                "targets": [
+                    {
+                        "targetIndex": 0,
+                        "resID": "learningData",
+                        "colIndex": 4,
+                        "colName": "ground_truth"
+                    }
+                ]
+            }
+        ],
+        "dataSplits": {
+            "method": "holdOut",
+            "testSize": 0.2,
+            "stratified": true,
+            "numRepeats": 0,
+            "randomSeed": 42,
+            "splitsFile": "dataSplits.csv",
+            "datasetViewMaps": {
+                "train": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_TRAIN"
+                    }
+                ],
+                "test": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_TEST"
+                    }
+                ],
+                "score": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_SCORE"
+                    }
+                ]
+            }
+        },
+        "performanceMetrics": [
+            {
+                "metric": "f1Macro"
+            }
+        ]
+    },
+    "expectedOutputs": {
+        "predictionsFile": "predictions.csv"
+    }
+}

datasets/anomaly/yahoo_system_sub_5/yahoo_system_sub_5_dataset/datasetDoc.json

@@ -0,0 +1,71 @@
+{
+    "about": {
+        "datasetID": "yahoo_system_sub_5_dataset",
+        "datasetName": "yahoo_system_sub_5",
+        "description": "Database of baseball players and play statistics, including 'Games_played', 'At_bats', 'Runs', 'Hits', 'Doubles', 'Triples', 'Home_runs', 'RBIs', 'Walks', 'Strikeouts', 'Batting_average', 'On_base_pct', 'Slugging_pct' and 'Fielding_ave'",
+        "citation": " @book{simonoff2003analyzing,title={Analyzing Categorical Data},author={Simonoff, J.S.},isbn={9780387007496},lccn={2003044946},series={Springer Texts in Statistics},url={https://books.google.com/books?id=G8wrifweAoC},year={2003},publisher={Springer New York}} ",
+        "license": " CC Public Domain Mark 1.0 ",
+        "source": "OpenML",
+        "sourceURI": "http://www.openml.org/d/185",
+        "approximateSize": "",
+        "datasetSchemaVersion": "4.0.0",
+        "redacted": false,
+        "datasetVersion": "4.0.0"
+    },
+    "dataResources": [
+        {
+            "resID": "learningData",
+            "resPath": "tables/learningData.csv",
+            "resType": "table",
+            "resFormat": {
+                "text/csv": [
+                    "csv"
+                ]
+            },
+            "isCollection": false,
+            "columns": [
+                {
+                    "colIndex": 0,
+                    "colName": "d3mIndex",
+                    "colType": "integer",
+                    "role": [
+                        "index"
+                    ]
+                },
+                {
+                    "colIndex": 1,
+                    "colName": "timestamp",
+                    "colType": "integer",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 2,
+                    "colName": "value_0",
+                    "colType": "real",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 3,
+                    "colName": "system_id",
+                    "colType": "real",
+                    "role": [
+                        "attribute"
+                    ]
+                },
+                {
+                    "colIndex": 4,
+                    "colName": "ground_truth",
+                    "colType": "integer",
+                    "role": [
+                        "suggestedTarget"
+                    ]
+                }
+            ],
+            "columnsCount": 5
+        }
+    ]
+}

datasets/anomaly/yahoo_system_sub_5/yahoo_system_sub_5_problem/problemDoc.json

@@ -0,0 +1,65 @@
+{
+    "about": {
+        "problemID": "yahoo_system_sub_5_problem",
+        "problemName": "yahoo_system_sub_5_problem",
+        "problemDescription": "Anomaly detection",
+        "problemVersion": "4.0.0",
+        "problemSchemaVersion": "4.0.0",
+        "taskKeywords": [
+            "classification",
+            "binary",
+            "tabular"
+        ]
+    },
+    "inputs": {
+        "data": [
+            {
+                "datasetID": "yahoo_system_sub_5_dataset",
+                "targets": [
+                    {
+                        "targetIndex": 0,
+                        "resID": "learningData",
+                        "colIndex": 4,
+                        "colName": "ground_truth"
+                    }
+                ]
+            }
+        ],
+        "dataSplits": {
+            "method": "holdOut",
+            "testSize": 0.2,
+            "stratified": true,
+            "numRepeats": 0,
+            "randomSeed": 42,
+            "splitsFile": "dataSplits.csv",
+            "datasetViewMaps": {
+                "train": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_TRAIN"
+                    }
+                ],
+                "test": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_TEST"
+                    }
+                ],
+                "score": [
+                    {
+                        "from": "yahoo_system_sub_5_dataset",
+                        "to": "yahoo_system_sub_5_dataset_SCORE"
+                    }
+                ]
+            }
+        },
+        "performanceMetrics": [
+            {
+                "metric": "f1Macro"
+            }
+        ]
+    },
+    "expectedOutputs": {
+        "predictionsFile": "predictions.csv"
+    }
+}