recover KPI example dataset

datasets/NAB/README.md

@@ -1,68 +0,0 @@
-NAB Data Corpus
----
-
-Data are ordered, timestamped, single-valued metrics. All data files contain anomalies, unless otherwise noted.
-
-
-### Real data
-- realAWSCloudwatch/
-
-	AWS server metrics as collected by the AmazonCloudwatch service. Example metrics include CPU Utilization, Network Bytes In, and Disk Read Bytes.
-
-- realAdExchange/
-	
-	Online advertisement clicking rates, where the metrics are cost-per-click (CPC) and cost per thousand impressions (CPM). One of the files is normal, without anomalies.
-	
-- realKnownCause/
-
-	This is data for which we know the anomaly causes; no hand labeling.
-	
-	- ambient_temperature_system_failure.csv: The ambient temperature in an office
-	setting.
-	- cpu_utilization_asg_misconfiguration.csv: From Amazon Web Services (AWS)
-	monitoring CPU usage – i.e. average CPU usage across a given cluster. When
-	usage is high, AWS spins up a new machine, and uses fewer machines when usage
-	is low.
-	- ec2_request_latency_system_failure.csv: CPU usage data from a server in
-	Amazon's East Coast datacenter. The dataset ends with complete system failure
-	resulting from a documented failure of AWS API servers. There's an interesting
-	story behind this data in the [Numenta
-	blog](http://numenta.com/blog/anomaly-of-the-week.html).
-	- machine_temperature_system_failure.csv: Temperature sensor data of an
-	internal component of a large, industrial mahcine. The first anomaly is a
-	planned shutdown of the machine. The second anomaly is difficult to detect and
-	directly led to the third anomaly, a catastrophic failure of the machine.
-	- nyc_taxi.csv: Number of NYC taxi passengers, where the five anomalies occur
-	during the NYC marathon, Thanksgiving, Christmas, New Years day, and a snow
-	storm. The raw data is from the [NYC Taxi and Limousine Commission](http://www.nyc.gov/html/tlc/html/about/trip_record_data.shtml).
-	The data file included here consists of aggregating the total number of
-	taxi passengers into 30 minute buckets.
-	- rogue_agent_key_hold.csv: Timing the key holds for several users of a
-	computer, where the anomalies represent a change in the user.
-	- rogue_agent_key_updown.csv: Timing the key strokes for several users of a
-	computer, where the anomalies represent a change in the user.
-
-- realTraffic/
-
-	Real time traffic data from the Twin Cities Metro area in Minnesota, collected
-	by the
-	[Minnesota Department of Transportation](http://www.dot.state.mn.us/tmc/trafficinfo/developers.html).
-	Included metrics include occupancy, speed, and travel time from specific
-	sensors.
-
-- realTweets/
-
-	A collection of Twitter mentions of large publicly-traded companies
-	such as Google and IBM. The metric value represents the number of mentions
-	for a given ticker symbol every 5 minutes.
-
-
-### Artificial data
-
-- artificialNoAnomaly/
-
-	Artificially-generated data without any anomalies.
-
-- artificialWithAnomaly/
-
-	Artificially-generated data with varying types of anomalies.

datasets/NAB/combined_labels.json

@@ -1,232 +0,0 @@
-{
-    "artificialNoAnomaly/art_daily_no_noise.csv": [],
-    "artificialNoAnomaly/art_daily_perfect_square_wave.csv": [],
-    "artificialNoAnomaly/art_daily_small_noise.csv": [],
-    "artificialNoAnomaly/art_flatline.csv": [],
-    "artificialNoAnomaly/art_noisy.csv": [],
-    "artificialWithAnomaly/art_daily_flatmiddle.csv": [
-        "2014-04-11 00:00:00"
-    ],
-    "artificialWithAnomaly/art_daily_jumpsdown.csv": [
-        "2014-04-11 09:00:00"
-    ],
-    "artificialWithAnomaly/art_daily_jumpsup.csv": [
-        "2014-04-11 09:00:00"
-    ],
-    "artificialWithAnomaly/art_daily_nojump.csv": [
-        "2014-04-11 09:00:00"
-    ],
-    "artificialWithAnomaly/art_increase_spike_density.csv": [
-        "2014-04-07 23:10:00"
-    ],
-    "artificialWithAnomaly/art_load_balancer_spikes.csv": [
-        "2014-04-11 04:35:00"
-    ],
-    "realAWSCloudwatch/ec2_cpu_utilization_24ae8d.csv": [
-        "2014-02-26 22:05:00",
-        "2014-02-27 17:15:00"
-    ],
-    "realAWSCloudwatch/ec2_cpu_utilization_53ea38.csv": [
-        "2014-02-19 19:10:00",
-        "2014-02-23 20:05:00"
-    ],
-    "realAWSCloudwatch/ec2_cpu_utilization_5f5533.csv": [
-        "2014-02-19 00:22:00",
-        "2014-02-24 18:37:00"
-    ],
-    "realAWSCloudwatch/ec2_cpu_utilization_77c1ca.csv": [
-        "2014-04-09 10:15:00"
-    ],
-    "realAWSCloudwatch/ec2_cpu_utilization_825cc2.csv": [
-        "2014-04-15 15:44:00",
-        "2014-04-16 03:34:00"
-    ],
-    "realAWSCloudwatch/ec2_cpu_utilization_ac20cd.csv": [
-        "2014-04-15 00:49:00"
-    ],
-    "realAWSCloudwatch/ec2_cpu_utilization_c6585a.csv": [],
-    "realAWSCloudwatch/ec2_cpu_utilization_fe7f93.csv": [
-        "2014-02-17 06:12:00",
-        "2014-02-22 00:02:00",
-        "2014-02-23 15:17:00"
-    ],
-    "realAWSCloudwatch/ec2_disk_write_bytes_1ef3de.csv": [
-        "2014-03-10 21:09:00"
-    ],
-    "realAWSCloudwatch/ec2_disk_write_bytes_c0d644.csv": [
-        "2014-04-09 01:30:00",
-        "2014-04-10 14:35:00",
-        "2014-04-13 03:00:00"
-    ],
-    "realAWSCloudwatch/ec2_network_in_257a54.csv": [
-        "2014-04-15 16:44:00"
-    ],
-    "realAWSCloudwatch/ec2_network_in_5abac7.csv": [
-        "2014-03-10 18:56:00",
-        "2014-03-12 21:01:00"
-    ],
-    "realAWSCloudwatch/elb_request_count_8c0756.csv": [
-        "2014-04-12 17:24:00",
-        "2014-04-22 19:34:00"
-    ],
-    "realAWSCloudwatch/grok_asg_anomaly.csv": [
-        "2014-01-20 08:30:00",
-        "2014-01-21 10:45:00",
-        "2014-01-29 00:45:00"
-    ],
-    "realAWSCloudwatch/iio_us-east-1_i-a2eb1cd9_NetworkIn.csv": [
-        "2013-10-10 09:35:00",
-        "2013-10-10 20:40:00"
-    ],
-    "realAWSCloudwatch/rds_cpu_utilization_cc0c53.csv": [
-        "2014-02-25 07:15:00",
-        "2014-02-27 00:50:00"
-    ],
-    "realAWSCloudwatch/rds_cpu_utilization_e47b3b.csv": [
-        "2014-04-13 06:52:00",
-        "2014-04-18 23:27:00"
-    ],
-    "realAdExchange/exchange-2_cpc_results.csv": [
-        "2011-07-14 13:00:01"
-    ],
-    "realAdExchange/exchange-2_cpm_results.csv": [
-        "2011-07-26 06:00:01",
-        "2011-08-10 17:00:01"
-    ],
-    "realAdExchange/exchange-3_cpc_results.csv": [
-        "2011-07-14 10:15:01",
-        "2011-07-20 10:15:01",
-        "2011-08-13 10:15:01"
-    ],
-    "realAdExchange/exchange-3_cpm_results.csv": [
-        "2011-08-19 18:15:01"
-    ],
-    "realAdExchange/exchange-4_cpc_results.csv": [
-        "2011-07-16 09:15:01",
-        "2011-08-02 12:15:01",
-        "2011-08-23 08:15:01"
-    ],
-    "realAdExchange/exchange-4_cpm_results.csv": [
-        "2011-07-16 09:15:01",
-        "2011-08-01 07:15:01",
-        "2011-08-23 08:15:01",
-        "2011-08-28 13:15:01"
-    ],
-    "realKnownCause/ambient_temperature_system_failure.csv": [
-        "2013-12-22 20:00:00",
-        "2014-04-13 09:00:00"
-    ],
-    "realKnownCause/cpu_utilization_asg_misconfiguration.csv": [
-        "2014-07-12 02:04:00",
-        "2014-07-14 21:44:00"
-    ],
-    "realKnownCause/ec2_request_latency_system_failure.csv": [
-        "2014-03-14 09:06:00",
-        "2014-03-18 22:41:00",
-        "2014-03-21 03:01:00"
-    ],
-    "realKnownCause/machine_temperature_system_failure.csv": [
-        "2013-12-11 06:00:00",
-        "2013-12-16 17:25:00",
-        "2014-01-28 13:55:00",
-        "2014-02-08 14:30:00"
-    ],
-    "realKnownCause/nyc_taxi.csv": [
-        "2014-11-01 19:00:00",
-        "2014-11-27 15:30:00",
-        "2014-12-25 15:00:00",
-        "2015-01-01 01:00:00",
-        "2015-01-27 00:00:00"
-    ],
-    "realKnownCause/rogue_agent_key_hold.csv": [
-        "2014-07-15 08:30:00",
-        "2014-07-17 09:50:00"
-    ],
-    "realKnownCause/rogue_agent_key_updown.csv": [
-        "2014-07-15 04:00:00",
-        "2014-07-17 08:50:00"
-    ],
-    "realTraffic/TravelTime_387.csv": [
-        "2015-07-30 12:29:00",
-        "2015-08-18 16:26:00",
-        "2015-09-01 05:34:00"
-    ],
-    "realTraffic/TravelTime_451.csv": [
-        "2015-08-11 12:07:00"
-    ],
-    "realTraffic/occupancy_6005.csv": [
-        "2015-09-15 06:55:00"
-    ],
-    "realTraffic/occupancy_t4013.csv": [
-        "2015-09-16 08:09:00",
-        "2015-09-17 07:55:00"
-    ],
-    "realTraffic/speed_6005.csv": [
-        "2015-09-17 07:00:00"
-    ],
-    "realTraffic/speed_7578.csv": [
-        "2015-09-11 16:44:00",
-        "2015-09-15 14:34:00",
-        "2015-09-16 14:14:00",
-        "2015-09-16 17:10:00"
-    ],
-    "realTraffic/speed_t4013.csv": [
-        "2015-09-16 08:04:00",
-        "2015-09-17 08:15:00"
-    ],
-    "realTweets/Twitter_volume_AAPL.csv": [
-        "2015-03-03 21:07:53",
-        "2015-03-09 17:32:53",
-        "2015-03-16 02:57:53",
-        "2015-03-31 03:27:53"
-    ],
-    "realTweets/Twitter_volume_AMZN.csv": [
-        "2015-03-05 19:47:53",
-        "2015-03-11 20:57:53",
-        "2015-04-01 21:57:53",
-        "2015-04-08 04:52:53"
-    ],
-    "realTweets/Twitter_volume_CRM.csv": [
-        "2015-03-09 19:07:53",
-        "2015-03-19 23:07:53",
-        "2015-03-26 19:07:53"
-    ],
-    "realTweets/Twitter_volume_CVS.csv": [
-        "2015-03-04 16:02:53",
-        "2015-03-05 19:57:53",
-        "2015-03-26 14:07:53",
-        "2015-04-14 22:37:53"
-    ],
-    "realTweets/Twitter_volume_FB.csv": [
-        "2015-03-16 07:07:53",
-        "2015-04-03 17:47:53"
-    ],
-    "realTweets/Twitter_volume_GOOG.csv": [
-        "2015-03-13 20:22:53",
-        "2015-03-14 16:27:53",
-        "2015-03-22 22:52:53",
-        "2015-04-01 05:27:53"
-    ],
-    "realTweets/Twitter_volume_IBM.csv": [
-        "2015-03-23 22:27:53",
-        "2015-04-20 20:07:53"
-    ],
-    "realTweets/Twitter_volume_KO.csv": [
-        "2015-03-20 13:12:53",
-        "2015-04-08 23:42:53",
-        "2015-04-14 14:52:53"
-    ],
-    "realTweets/Twitter_volume_PFE.csv": [
-        "2015-03-02 21:22:53",
-        "2015-03-04 10:32:53",
-        "2015-03-13 19:57:53",
-        "2015-04-07 23:42:53"
-    ],
-    "realTweets/Twitter_volume_UPS.csv": [
-        "2015-03-03 00:27:53",
-        "2015-03-04 11:07:53",
-        "2015-03-05 15:22:53",
-        "2015-03-24 18:17:53",
-        "2015-03-29 16:27:53"
-    ]
-}

datasets/NAB/realKnownCause/labeled_cpu_utilization_asg_misconfiguration.csv.REMOVED.git-id

@@ -1 +0,0 @@
-948611b07519538ef036e0ec1c948f6bf97009cf

datasets/NAB/realKnownCause/labeled_machine_temperature_system_failure.csv.REMOVED.git-id

@@ -1 +0,0 @@
-428229640a5466e68014f74649a24f00abb1150b

datasets/NAB/realTweets/labeled_Twitter_volume_AAPL.csv.REMOVED.git-id

@@ -1 +0,0 @@
-68dd1084ed091fb9affe45b4e0894250c6c62c07

datasets/NAB/realTweets/labeled_Twitter_volume_AMZN.csv.REMOVED.git-id

@@ -1 +0,0 @@
-7bebf0fe077dda56f789d644090faf1d2484913c

datasets/NAB/realTweets/labeled_Twitter_volume_CRM.csv.REMOVED.git-id

@@ -1 +0,0 @@
-59fdf3c2b8d171704e3de1e10d8ccfca72c8ab9a

datasets/NAB/realTweets/labeled_Twitter_volume_CVS.csv.REMOVED.git-id

@@ -1 +0,0 @@
-d20453833fc13c681f0b5f5a830f3aba52b774cd

datasets/NAB/realTweets/labeled_Twitter_volume_FB.csv.REMOVED.git-id

@@ -1 +0,0 @@
-ed60bba6f53c779335874c39966b7d5e4309e2c3

datasets/NAB/realTweets/labeled_Twitter_volume_GOOG.csv.REMOVED.git-id

@@ -1 +0,0 @@
-f01b654d9a6a6ebc7efc65da240f83680de2131d

datasets/NAB/realTweets/labeled_Twitter_volume_IBM.csv.REMOVED.git-id

@@ -1 +0,0 @@
-8e0088d97641d6ab39b808fe03ac0a7ec9ea99b9

datasets/NAB/realTweets/labeled_Twitter_volume_KO.csv.REMOVED.git-id

@@ -1 +0,0 @@
-d72fffb08da82bb70ecc379bb1fa56316efda557

datasets/NAB/realTweets/labeled_Twitter_volume_PFE.csv.REMOVED.git-id

@@ -1 +0,0 @@
-4c2f8543201c0a66e44815dee128d9044a41c382

datasets/NAB/realTweets/labeled_Twitter_volume_UPS.csv.REMOVED.git-id

@@ -1 +0,0 @@
-25a0dd3110986418d379a887cc575f9fdc45a6da

datasets/anomaly/kpi/TRAIN/dataset_TRAIN/tables/learningData.csv.REMOVED.git-id

@@ -1 +0,0 @@
-44db328c252a8156434142a37ef65765869e7548

datasets/anomaly/raw_data/kpi.csv.REMOVED.git-id

@@ -1 +0,0 @@
-bea5d1c052730eaba76b84ff5df854477cdfa80b

datasets/anomaly_reserve/kpi/SCORE/dataset_TEST/datasetDoc.json

@@ -1,63 +0,0 @@
-{
-    "about": {
-        "datasetID": "kpi_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",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 3,
-                    "colName": "ground_truth",
-                    "colType": "integer",
-                    "role": [
-                        "suggestedTarget"
-                    ]
-                }
-            ],
-            "columnsCount": 4
-        }
-    ]
-}

datasets/anomaly_reserve/kpi/SCORE/problem_TEST/problemDoc.json

@@ -1,65 +0,0 @@
-{
-    "about": {
-        "problemID": "kpi_problem",
-        "problemName": "kpi_problem",
-        "problemDescription": "Anomaly detection",
-        "problemVersion": "4.0.0",
-        "problemSchemaVersion": "4.0.0",
-        "taskKeywords": [
-            "classification",
-            "binary",
-            "tabular"
-        ]
-    },
-    "inputs": {
-        "data": [
-            {
-                "datasetID": "kpi_dataset",
-                "targets": [
-                    {
-                        "targetIndex": 0,
-                        "resID": "learningData",
-                        "colIndex": 3,
-                        "colName": "ground_truth"
-                    }
-                ]
-            }
-        ],
-        "dataSplits": {
-            "method": "holdOut",
-            "testSize": 0.2,
-            "stratified": true,
-            "numRepeats": 0,
-            "randomSeed": 42,
-            "splitsFile": "dataSplits.csv",
-            "datasetViewMaps": {
-                "train": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_TRAIN"
-                    }
-                ],
-                "test": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_TEST"
-                    }
-                ],
-                "score": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_SCORE"
-                    }
-                ]
-            }
-        },
-        "performanceMetrics": [
-            {
-                "metric": "f1Macro"
-            }
-        ]
-    },
-    "expectedOutputs": {
-        "predictionsFile": "predictions.csv"
-    }
-}

datasets/anomaly_reserve/kpi/TEST/dataset_TEST/datasetDoc.json

@@ -1,63 +0,0 @@
-{
-    "about": {
-        "datasetID": "kpi_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",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 3,
-                    "colName": "ground_truth",
-                    "colType": "integer",
-                    "role": [
-                        "suggestedTarget"
-                    ]
-                }
-            ],
-            "columnsCount": 4
-        }
-    ]
-}

datasets/anomaly_reserve/kpi/TEST/problem_TEST/problemDoc.json

@@ -1,65 +0,0 @@
-{
-    "about": {
-        "problemID": "kpi_problem",
-        "problemName": "kpi_problem",
-        "problemDescription": "Anomaly detection",
-        "problemVersion": "4.0.0",
-        "problemSchemaVersion": "4.0.0",
-        "taskKeywords": [
-            "classification",
-            "binary",
-            "tabular"
-        ]
-    },
-    "inputs": {
-        "data": [
-            {
-                "datasetID": "kpi_dataset",
-                "targets": [
-                    {
-                        "targetIndex": 0,
-                        "resID": "learningData",
-                        "colIndex": 3,
-                        "colName": "ground_truth"
-                    }
-                ]
-            }
-        ],
-        "dataSplits": {
-            "method": "holdOut",
-            "testSize": 0.2,
-            "stratified": true,
-            "numRepeats": 0,
-            "randomSeed": 42,
-            "splitsFile": "dataSplits.csv",
-            "datasetViewMaps": {
-                "train": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_TRAIN"
-                    }
-                ],
-                "test": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_TEST"
-                    }
-                ],
-                "score": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_SCORE"
-                    }
-                ]
-            }
-        },
-        "performanceMetrics": [
-            {
-                "metric": "f1Macro"
-            }
-        ]
-    },
-    "expectedOutputs": {
-        "predictionsFile": "predictions.csv"
-    }
-}

datasets/anomaly_reserve/kpi/TRAIN/dataset_TRAIN/datasetDoc.json

@@ -1,63 +0,0 @@
-{
-    "about": {
-        "datasetID": "kpi_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",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 3,
-                    "colName": "ground_truth",
-                    "colType": "integer",
-                    "role": [
-                        "suggestedTarget"
-                    ]
-                }
-            ],
-            "columnsCount": 4
-        }
-    ]
-}

datasets/anomaly_reserve/kpi/TRAIN/dataset_TRAIN/tables/learningData.csv.REMOVED.git-id

@@ -1 +0,0 @@
-44db328c252a8156434142a37ef65765869e7548

datasets/anomaly_reserve/kpi/TRAIN/problem_TRAIN/problemDoc.json

@@ -1,65 +0,0 @@
-{
-    "about": {
-        "problemID": "kpi_problem",
-        "problemName": "kpi_problem",
-        "problemDescription": "Anomaly detection",
-        "problemVersion": "4.0.0",
-        "problemSchemaVersion": "4.0.0",
-        "taskKeywords": [
-            "classification",
-            "binary",
-            "tabular"
-        ]
-    },
-    "inputs": {
-        "data": [
-            {
-                "datasetID": "kpi_dataset",
-                "targets": [
-                    {
-                        "targetIndex": 0,
-                        "resID": "learningData",
-                        "colIndex": 3,
-                        "colName": "ground_truth"
-                    }
-                ]
-            }
-        ],
-        "dataSplits": {
-            "method": "holdOut",
-            "testSize": 0.2,
-            "stratified": true,
-            "numRepeats": 0,
-            "randomSeed": 42,
-            "splitsFile": "dataSplits.csv",
-            "datasetViewMaps": {
-                "train": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_TRAIN"
-                    }
-                ],
-                "test": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_TEST"
-                    }
-                ],
-                "score": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_SCORE"
-                    }
-                ]
-            }
-        },
-        "performanceMetrics": [
-            {
-                "metric": "f1Macro"
-            }
-        ]
-    },
-    "expectedOutputs": {
-        "predictionsFile": "predictions.csv"
-    }
-}

datasets/anomaly_reserve/kpi/kpi_dataset/datasetDoc.json

@@ -1,63 +0,0 @@
-{
-    "about": {
-        "datasetID": "kpi_dataset",
-        "datasetName": "kpi",
-        "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",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 3,
-                    "colName": "ground_truth",
-                    "colType": "integer",
-                    "role": [
-                        "suggestedTarget"
-                    ]
-                }
-            ],
-            "columnsCount": 4
-        }
-    ]
-}

datasets/anomaly_reserve/kpi/kpi_dataset/tables/learningData.csv.REMOVED.git-id

@@ -1 +0,0 @@
-d80846dc46c173472f646a52005a1fb3670ccd09

datasets/anomaly_reserve/kpi/kpi_problem/dataSplits.csv.REMOVED.git-id

@@ -1 +0,0 @@
-44db328c252a8156434142a37ef65765869e7548

datasets/anomaly_reserve/kpi/kpi_problem/problemDoc.json

@@ -1,65 +0,0 @@
-{
-    "about": {
-        "problemID": "kpi_problem",
-        "problemName": "kpi_problem",
-        "problemDescription": "Anomaly detection",
-        "problemVersion": "4.0.0",
-        "problemSchemaVersion": "4.0.0",
-        "taskKeywords": [
-            "classification",
-            "binary",
-            "tabular"
-        ]
-    },
-    "inputs": {
-        "data": [
-            {
-                "datasetID": "kpi_dataset",
-                "targets": [
-                    {
-                        "targetIndex": 0,
-                        "resID": "learningData",
-                        "colIndex": 3,
-                        "colName": "ground_truth"
-                    }
-                ]
-            }
-        ],
-        "dataSplits": {
-            "method": "holdOut",
-            "testSize": 0.2,
-            "stratified": true,
-            "numRepeats": 0,
-            "randomSeed": 42,
-            "splitsFile": "dataSplits.csv",
-            "datasetViewMaps": {
-                "train": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_TRAIN"
-                    }
-                ],
-                "test": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_TEST"
-                    }
-                ],
-                "score": [
-                    {
-                        "from": "kpi_dataset",
-                        "to": "kpi_dataset_SCORE"
-                    }
-                ]
-            }
-        },
-        "performanceMetrics": [
-            {
-                "metric": "f1Macro"
-            }
-        ]
-    },
-    "expectedOutputs": {
-        "predictionsFile": "predictions.csv"
-    }
-}

datasets/anomaly_reserve/raw_data/kpi.csv.REMOVED.git-id

@@ -1 +0,0 @@
-bea5d1c052730eaba76b84ff5df854477cdfa80b

datasets/anomaly_reserve/template/datasetDoc.json

@@ -1,183 +0,0 @@
-{
-  "about": {
-    "datasetID": "template",
-    "datasetName": "baseball",
-    "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": "Player",
-          "colType": "categorical",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 2,
-          "colName": "Number_seasons",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 3,
-          "colName": "Games_played",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 4,
-          "colName": "At_bats",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 5,
-          "colName": "Runs",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 6,
-          "colName": "Hits",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 7,
-          "colName": "Doubles",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 8,
-          "colName": "Triples",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 9,
-          "colName": "Home_runs",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 10,
-          "colName": "RBIs",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 11,
-          "colName": "Walks",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 12,
-          "colName": "Strikeouts",
-          "colType": "integer",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 13,
-          "colName": "Batting_average",
-          "colType": "real",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 14,
-          "colName": "On_base_pct",
-          "colType": "real",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 15,
-          "colName": "Slugging_pct",
-          "colType": "real",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 16,
-          "colName": "Fielding_ave",
-          "colType": "real",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 17,
-          "colName": "Position",
-          "colType": "categorical",
-          "role": [
-            "attribute"
-          ]
-        },
-        {
-          "colIndex": 18,
-          "colName": "Hall_of_Fame",
-          "colType": "categorical",
-          "role": [
-            "suggestedTarget"
-          ]
-        }
-      ],
-      "columnsCount": 19
-    }
-  ]
-}

datasets/anomaly_reserve/template/problemDoc.json

@@ -1,65 +0,0 @@
-{
-  "about": {
-    "problemID": "template",
-    "problemName": "baseball_problem",
-    "problemDescription": "**Author**: Jeffrey S. Simonoff  \n**Source**: [AnalCatData](http://www.stern.nyu.edu/~jsimonof/AnalCatData) - 2003  \n**Please cite**: Jeffrey S. Simonoff, Analyzing Categorical Data, Springer-Verlag, New York, 2003  \n \nDatabase 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' \n\nNotes:  \n* Quotes, Single-Quotes and Backslashes were removed, Blanks replaced with Underscores\n* Player is an identifier that should be ignored when modelling the data",
-    "problemVersion": "4.0.0",
-    "problemSchemaVersion": "4.0.0",
-    "taskKeywords": [
-      "classification",
-      "multiClass",
-      "tabular"
-    ]
-  },
-  "inputs": {
-    "data": [
-      {
-        "datasetID": "185_baseball_dataset",
-        "targets": [
-          {
-            "targetIndex": 0,
-            "resID": "learningData",
-            "colIndex": 18,
-            "colName": "Hall_of_Fame"
-          }
-        ]
-      }
-    ],
-    "dataSplits": {
-      "method": "holdOut",
-      "testSize": 0.2,
-      "stratified": true,
-      "numRepeats": 0,
-      "randomSeed": 42,
-      "splitsFile": "dataSplits.csv",
-      "datasetViewMaps": {
-        "train": [
-          {
-            "from": "185_baseball_dataset",
-            "to": "185_baseball_dataset_TRAIN"
-          }
-        ],
-        "test": [
-          {
-            "from": "185_baseball_dataset",
-            "to": "185_baseball_dataset_TEST"
-          }
-        ],
-        "score": [
-          {
-            "from": "185_baseball_dataset",
-            "to": "185_baseball_dataset_SCORE"
-          }
-        ]
-      }
-    },
-    "performanceMetrics": [
-      {
-        "metric": "f1Macro"
-      }
-    ]
-  },
-  "expectedOutputs": {
-    "predictionsFile": "predictions.csv"
-  }
-}

datasets/anomaly_reserve/transform.py

@@ -1,160 +0,0 @@
-# TODO: Wrap it as a class and connect it to GUI
-# A script to transform anomaly data to d3m format
-import pandas as pd
-import numpy as np
-import os
-import json
-
-##############################
-# Some information for the dataset to be transformed
-# Designed for time series data
-name = 'kpi'
-src_path = './raw_data/kpi.csv'
-label_name = 'label'
-timestamp_name = 'timestamp'
-value_names = ['value']
-ratio = 0.8 # Ratio of training data, the rest is for testing
-
-###############################
-
-
-
-dst_root = './' + name
-dirs = ['./', 'SCORE', 'TEST', 'TRAIN']
-maps = {'./': None, 'SCORE': 'TEST', 'TEST': 'TEST', 'TRAIN': 'TRAIN'}
-
-# Create the corresponding directories
-for d in dirs:
-    if maps[d] is not None:
-        dataset_name = 'dataset_' + maps[d]
-        problem_name = 'problem_' + maps[d]
-    else:
-        dataset_name = name + '_dataset'
-        problem_name = name + '_problem'
-    tables_dir = os.path.join(dst_root, d, dataset_name, 'tables')
-    if not os.path.exists(tables_dir):
-        os.makedirs(tables_dir)
-    problem_dir = os.path.join(dst_root, d, problem_name)
-    if not os.path.exists(problem_dir):
-        os.makedirs(problem_dir)
-
-# Process data
-_df = pd.DataFrame()
-df = pd.read_csv(src_path)
-_df['d3mIndex'] = df.index
-_df['timestamp'] = df[timestamp_name]
-for value_name in value_names:
-    _df[value_name] = df[value_name]
-_df['ground_truth'] = df[label_name]
-df = _df
-cols = df.columns.tolist()
-
-# Save all the data
-df.to_csv(os.path.join(dst_root, name+'_dataset', 'tables', 'learningData.csv'), index=False)
-
-# Save training and testing data
-train_df, test_df = df[:int(df.shape[0]*ratio)], df[int(df.shape[0]*ratio):]
-
-train_df.to_csv(os.path.join(dst_root, 'TRAIN', 'dataset_TRAIN', 'tables', 'learningData.csv'), index=False)
-test_df.to_csv(os.path.join(dst_root, 'TEST', 'dataset_TEST', 'tables', 'learningData.csv'), index=False)
-test_df.to_csv(os.path.join(dst_root, 'SCORE', 'dataset_TEST', 'tables', 'learningData.csv'), index=False)
-
-# Data splits
-row_0 = train_df.shape[0]
-row_1 = train_df.shape[0]
-row = row_0 + row_1
-df = pd.DataFrame(np.array([[i for i in range(row)], ['TRAIN' for _ in range(row_0)] + ['TEST' for _ in range(row_1)], [0 for _ in range(row)], [0 for _ in range(row)]]).transpose(), columns = ['d3mIndex', 'type', 'repeat', 'fold'])
-
-# Save data splits for all data
-train_df.to_csv(os.path.join(dst_root, name+'_problem', 'dataSplits.csv'), index=False)
-
-# Save training and testing splits
-train_df, test_df = df[:row_0], df[row_0:]
-train_df.to_csv(os.path.join(dst_root, 'TRAIN', 'problem_TRAIN', 'dataSplits.csv'), index=False)
-test_df.to_csv(os.path.join(dst_root, 'TEST', 'problem_TEST', 'dataSplits.csv'), index=False)
-test_df.to_csv(os.path.join(dst_root, 'SCORE', 'problem_TEST', 'dataSplits.csv'), index=False)
-
-
-# Dataset JSON files
-# Load template
-with open('template/datasetDoc.json') as json_file:
-    data = json.load(json_file)
-columns = []
-for i in range(len(cols)):
-    c = {}
-    c['colIndex'] = i
-    c['colName'] = cols[i]
-    if i == 0:
-        c['colType'] = 'integer'
-        c['role'] = ['index']
-    elif i == 1:
-        c['colType'] = 'integer'
-        c['role'] = ['attribute']
-    elif i == len(cols)-1:
-        c['colType'] = 'integer'
-        c['role'] = ['suggestedTarget']
-    else:
-        c['colType'] = 'real'
-        c['role'] = ['attribute']
-    columns.append(c)
-data['dataResources'][0]['columns'] = columns
-data['dataResources'][0]['columnsCount'] = len(cols)
- 
-data['about']['datasetID'] = name + '_dataset'
-data['about']['datasetName'] = name
-with open(os.path.join(dst_root, name+'_dataset', 'datasetDoc.json'), 'w') as outfile:
-    json.dump(data, outfile, indent=4)
-
-data['about']['datasetID'] = name +'_dataset_TRAIN'
-data['about']['datasetName'] = "NULL"
-with open(os.path.join(dst_root, 'TRAIN', 'dataset_TRAIN', 'datasetDoc.json'), 'w') as outfile:
-    json.dump(data, outfile, indent=4)
-
-data['about']['datasetID'] = name + '_dataset_TEST'
-data['about']['datasetName'] = 'NULL'
-with open(os.path.join(dst_root, 'TEST', 'dataset_TEST', 'datasetDoc.json'), 'w') as outfile:
-    json.dump(data, outfile, indent=4)
-
-data['about']['datasetID'] = name + '_dataset_TEST'
-data['about']['datasetName'] = 'NULL'
-with open(os.path.join(dst_root, 'SCORE', 'dataset_TEST', 'datasetDoc.json'), 'w') as outfile:
-    json.dump(data, outfile, indent=4)
-
-# Problem JSON files
-# Load template
-with open('template/problemDoc.json') as json_file:
-    data = json.load(json_file)
-
-data['about']['problemID'] = name+'_problem'
-data['about']['problemName'] = name+'_problem'
-data['about']['problemDescription'] = 'Anomaly detection'
-data['about']['taskKeywords'] = ['classification', 'binary', 'tabular']
-data['inputs']['data'][0]['datasetID'] = name + '_dataset'
-data['inputs']['data'][0]['targets'][0]['colIndex'] = len(cols)-1
-data['inputs']['data'][0]['targets'][0]['colName'] = cols[-1]
-data['inputs']['dataSplits']['datasetViewMaps']['train'][0]['from'] = name+'_dataset'
-data['inputs']['dataSplits']['datasetViewMaps']['test'][0]['from'] = name+'_dataset'
-data['inputs']['dataSplits']['datasetViewMaps']['score'][0]['from'] = name+'_dataset'
-data['inputs']['dataSplits']['datasetViewMaps']['train'][0]['to'] = name+'_dataset_TRAIN'
-data['inputs']['dataSplits']['datasetViewMaps']['test'][0]['to'] = name+'_dataset_TEST'
-data['inputs']['dataSplits']['datasetViewMaps']['score'][0]['to'] = name+'_dataset_SCORE'
-
-with open(os.path.join(dst_root, name+'_problem', 'problemDoc.json'), 'w') as outfile:
-    json.dump(data, outfile, indent=4)
-
-with open(os.path.join(dst_root, 'TRAIN', 'problem_TRAIN', 'problemDoc.json'), 'w') as outfile:
-    json.dump(data, outfile, indent=4)
-
-with open(os.path.join(dst_root, 'TEST', 'problem_TEST', 'problemDoc.json'), 'w') as outfile:
-    json.dump(data, outfile, indent=4)
-
-with open(os.path.join(dst_root, 'SCORE', 'problem_TEST', 'problemDoc.json'), 'w') as outfile:
-    json.dump(data, outfile, indent=4)
-
-# Make an empty targets.csv
-with open(os.path.join(dst_root, 'SCORE', 'targets.csv'), 'w') as outfile:
-    outfile.write('')
-
-
-
-

datasets/anomaly_reserve/yahoo_sub_5/SCORE/dataset_TEST/datasetDoc.json

@@ -1,95 +0,0 @@
-{
-    "about": {
-        "datasetID": "yahoo_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": "value_1",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 4,
-                    "colName": "value_2",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 5,
-                    "colName": "value_3",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 6,
-                    "colName": "value_4",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 7,
-                    "colName": "ground_truth",
-                    "colType": "integer",
-                    "role": [
-                        "suggestedTarget"
-                    ]
-                }
-            ],
-            "columnsCount": 8
-        }
-    ]
-}

datasets/anomaly_reserve/yahoo_sub_5/SCORE/dataset_TEST/tables/learningData.csv

@@ -1,141 +0,0 @@
-d3mIndex,timestamp,value_0,value_1,value_2,value_3,value_4,ground_truth
-1260,1261,7782,0.034280386319742985,2.5072222222222003,104,3119,0
-1261,1262,7829,0.039360296791109,2.5927777777778,82,3590,0
-1262,1263,7902,0.0,2.6894444444444,208,3893,0
-1263,1264,8039,0.038944065994356014,2.6291666666667,92,3264,0
-1264,1265,8350,0.18176011684739,2.6469444444444,53,3963,0
-1265,1266,8142,0.18521047165852,2.7461111111111003,65,2757,0
-1266,1267,7886,0.13079770999921,2.9363888888889,62,2306,0
-1267,1268,7743,0.13310058077443,3.2797222222222,73,2549,0
-1268,1269,7707,0.054750658073534006,3.5194444444444,84,2212,0
-1269,1270,7726,0.030588852697706,3.8130555555556,90,2286,0
-1270,1271,7717,0.12998124134227002,3.7941666666667,80,2979,0
-1271,1272,10331,0.09100057249197198,3.6086111111111,90,3158,0
-1272,1273,10515,0.19464543002904006,3.3858333333333,84,2645,0
-1273,1274,10415,0.22178651521516,3.3336111111111,34,3161,0
-1274,1275,10387,0.22983578430825,3.3116666666667003,67,4460,0
-1275,1276,10471,0.298229429356,3.2616666666667005,74,2630,0
-1276,1277,10385,0.12923377484588,3.0044444444444003,44,2593,0
-1277,1278,10439,0.19609416059774,2.6741666666667,64,2625,0
-1278,1279,10516,0.040518533819385014,2.3191666666667,70,4834,0
-1279,1280,10587,0.07099894663641,2.0597222222222,96,4056,0
-1280,1281,10586,0.07584150637714701,2.0547222222222,110,5713,0
-1281,1282,10684,0.08180100127782801,2.1511111111111,68,3940,0
-1282,1283,10880,0.0,2.2602777777778,90,4414,0
-1283,1284,10830,0.0,2.2883333333333,90,5044,0
-1284,1285,10794,0.09140162014739303,2.3736111111111,69,3894,0
-1285,1286,10843,0.0,2.5869444444444,46,3993,0
-1286,1287,10805,0.0,2.6480555555556,74,4404,0
-1287,1288,10996,0.0,2.6077777777777995,68,4072,0
-1288,1289,11327,0.05363316840061,2.6069444444444,67,4182,0
-1289,1290,11090,0.26818151064716,2.6908333333333,51,3351,0
-1290,1291,10578,0.21887772653901,2.9019444444444003,39,4183,0
-1291,1292,10528,0.32371296573811,3.2711111111111,26,4068,0
-1292,1293,10475,0.12565805017257,3.5872222222222,25,8139,0
-1293,1294,10664,0.092277247744574,3.6913888888889,32,11000,0
-1294,1295,10513,0.077016875742983,3.6313888888889,17,2975,0
-1295,1296,9072,0.3714480797312501,3.5605555555556,19,2692,0
-1296,1297,9069,0.19332372237792,3.4402777777778,16,2502,0
-1297,1298,9089,0.06345811641554701,3.35,28,2510,0
-1298,1299,9027,0.2267121559473,3.3469444444444,24,2663,0
-1299,1300,8969,0.053072279964629,3.2708333333333,35,3575,0
-1300,1301,9073,0.13336345197744,3.2519444444444,49,2586,0
-1301,1302,8957,0.1252855094715,2.7311111111111,106,2908,0
-1302,1303,9126,0.096211952864224,2.3875,80,3530,0
-1303,1304,9122,0.096524467517755,2.0847222222222,90,2776,0
-1304,1305,9231,0.08924770147957402,2.0975,169,2962,0
-1305,1306,9368,0.11889606284162,2.1763888888889,98,3441,0
-1306,1307,9458,0.031429841710104,2.2327777777777995,92,4376,0
-1307,1308,9463,0.0,2.2725,91,3857,0
-1308,1309,9356,0.036512411627868,2.3202777777778,99,4685,0
-1309,1310,9340,0.0,2.5425,90,4585,0
-1310,1311,9340,0.0,2.5986111111111,126,3542,0
-1311,1312,9276,0.0,2.6319444444444,102,3370,0
-1312,1313,9611,0.10106696361212,2.5836111111111,132,3515,0
-1313,1314,9532,0.14854949043035,2.675,88,3793,0
-1314,1315,9156,0.08612162048398897,2.8522222222222,135,2954,0
-1315,1316,9222,0.16494200410492002,3.1302777777778,114,2627,0
-1316,1317,9282,0.28637713141253,3.4805555555556,35,2550,0
-1317,1318,9573,0.13206535647488,3.5994444444444,24,2480,0
-1318,1319,9333,0.27364025607799,3.5847222222222,44,2521,0
-1319,1320,9987,0.38382339961227,3.4963888888889,26,2860,0
-1320,1321,10133,0.08426242877623301,3.3825,37,3675,0
-1321,1322,10010,0.3290413568025901,3.2694444444444,45,2704,0
-1322,1323,10028,0.22632868808708,3.2322222222222,42,3121,0
-1323,1324,9984,0.17914189971361,3.1936111111111005,47,2603,0
-1324,1325,10041,0.30046815361859003,3.0536111111111004,34,3984,0
-1325,1326,10072,0.22650915594248,2.7819444444444,56,2537,0
-1326,1327,10025,0.0,2.4152777777778,87,3349,0
-1327,1328,10116,0.1223093269317,2.1569444444444,74,3958,0
-1328,1329,10232,0.1696074188221,2.1125,90,4243,0
-1329,1330,10516,0.0,2.1833333333333003,79,4159,0
-1330,1331,10449,0.028193633007367,2.205,97,5637,0
-1331,1332,10598,0.0,2.1697222222222,90,8142,0
-1332,1333,10337,0.0,2.3075,77,5713,0
-1333,1334,10469,0.097305232437507,2.4575,101,3668,0
-1334,1335,10426,0.11905908868379,2.6077777777777995,74,4307,0
-1335,1336,10531,0.11660374103282,2.6275,439,4354,0
-1336,1337,10875,0.060474297756584014,2.6144444444444,79,4262,0
-1337,1338,10494,0.22568442027805,2.6477777777777995,165,3446,0
-1338,1339,10195,0.14077736537045002,2.8594444444444003,139,2677,0
-1339,1340,9918,0.1924574892026,3.2675,56,4450,0
-1340,1341,9889,0.18922597300629,3.5136111111111004,102,3044,0
-1341,1342,9947,0.041593949118095004,3.5725,101,3428,0
-1342,1343,9977,0.2502095174271,3.6863888888889,41,2845,0
-1343,1344,10835,0.18663972932643,3.5636111111111,94,2781,0
-1344,1345,10765,0.07351854082400297,3.4127777777778,116,2743,0
-1345,1346,10656,0.081949111399618,3.295,94,4470,0
-1346,1347,10485,0.20148511394009,3.2666666666667004,89,2596,0
-1347,1348,10681,0.11515101921294,3.1933333333333,141,3249,0
-1348,1349,10852,0.07797276382811,3.0688888888889,167,2529,0
-1349,1350,10728,0.07244862879413201,2.8102777777778,148,2452,0
-1350,1351,10874,0.07310929970435699,2.42,105,2934,0
-1351,1352,10964,0.066868365737218,2.1358333333333,210,3159,0
-1352,1353,10984,0.05788512501593701,1.9916666666667,145,3974,0
-1353,1354,11055,0.09727414207464803,2.0947222222222,136,4305,0
-1354,1355,11233,0.033270317741558,2.1591666666667,126,5012,0
-1355,1356,11161,0.0,2.2377777777778,157,4455,0
-1356,1357,10966,0.038270957919533,2.2511111111111,105,4108,0
-1357,1358,11193,0.08728058888363299,2.4208333333333,114,4339,0
-1358,1359,11167,0.10536774813238,2.5241666666667,104,5056,0
-1359,1360,11367,0.1233991317089,2.5794444444444,69,5573,0
-1360,1361,51251,0.042565915766552,2.5936111111111,75,3366,1
-1361,1362,17953,0.23147422367229,2.6830555555556,73,2559,1
-1362,1363,170029,0.08983405162538903,2.8188888888889,74,1999,1
-1363,1364,10955,0.07464756469365201,2.9513888888888995,126,1993,0
-1364,1365,10984,0.099244104918934,3.2830555555556,67,1913,0
-1365,1366,10964,0.11535172009194,3.4819444444444,32,1760,0
-1366,1367,10980,0.21774881707852,3.5886111111111005,38,1890,0
-1367,1368,10852,0.1305066423559,3.4836111111111,34,2469,0
-1368,1369,10786,0.10054853030204,3.3955555555556,36,2133,0
-1369,1370,10841,0.02468393737575,3.2847222222222,26,3359,0
-1370,1371,10762,0.10018007414459,3.2383333333332995,74,3783,0
-1371,1372,10419,0.12522619841308,3.2188888888889,85,1809,0
-1372,1373,10467,0.11781887197077,2.9483333333333,67,2143,0
-1373,1374,10502,0.13417256350298,2.5855555555556,84,2567,0
-1374,1375,10519,0.07474686582090599,2.3005555555556003,1630,2176,0
-1375,1376,10579,0.13570963056519,2.0855555555556,1435,1929,0
-1376,1377,10502,0.076431907457478,1.9027777777778,857,2244,0
-1377,1378,10661,0.0,1.9411111111111,31,1810,0
-1378,1379,10818,0.1936428046839,2.0444444444444,500,2088,0
-1379,1380,10918,0.052826773889684014,2.1363888888889,53,2371,0
-1380,1381,10871,0.0,2.22,61,1843,0
-1381,1382,10796,0.054466597481213,2.3530555555556,158,2668,0
-1382,1383,10774,0.057459020289436,2.545,184,2309,0
-1383,1384,10898,0.28750562005936,2.6202777777778,91,1998,0
-1384,1385,11442,0.075538554674309,2.6847222222222,60,2480,0
-1385,1386,11113,0.08112608570492501,2.6591666666667004,107,2147,0
-1386,1387,10888,0.21563803296368,2.7863888888888995,5157,1802,0
-1387,1388,10894,0.095725002305685,3.0269444444444003,28,1789,0
-1388,1389,10888,0.17516056892320994,3.3227777777778,24,1999,0
-1389,1390,10896,0.32902836018586,3.6097222222222,21,2142,0
-1390,1391,10800,0.10216065221678,3.6805555555556,12,1904,0
-1391,1392,11000,0.19741931250852,3.6075,24,1876,0
-1392,1393,10985,0.10149107903671,3.4091666666667004,17,2434,0
-1393,1394,11017,0.17479255893624,3.3666666666667004,48,2472,0
-1394,1395,10863,0.034385029573777,3.3158333333333,41,1744,0
-1395,1396,10875,0.21988771218053,3.1622222222222,1088,2404,0
-1396,1397,10987,0.10149107903671,3.1086111111111,68,1971,0
-1397,1398,10778,0.10269981175445,2.6552777777778,2575,1713,0
-1398,1399,10957,0.11258759940039,2.2730555555556,4688,1765,0
-1399,1400,10832,0.13022351806001,2.0591666666667,477,3156,0

datasets/anomaly_reserve/yahoo_sub_5/SCORE/problem_TEST/problemDoc.json

@@ -1,65 +0,0 @@
-{
-    "about": {
-        "problemID": "yahoo_sub_5_problem",
-        "problemName": "yahoo_sub_5_problem",
-        "problemDescription": "Anomaly detection",
-        "problemVersion": "4.0.0",
-        "problemSchemaVersion": "4.0.0",
-        "taskKeywords": [
-            "classification",
-            "binary",
-            "tabular"
-        ]
-    },
-    "inputs": {
-        "data": [
-            {
-                "datasetID": "yahoo_sub_5_dataset",
-                "targets": [
-                    {
-                        "targetIndex": 0,
-                        "resID": "learningData",
-                        "colIndex": 7,
-                        "colName": "ground_truth"
-                    }
-                ]
-            }
-        ],
-        "dataSplits": {
-            "method": "holdOut",
-            "testSize": 0.2,
-            "stratified": true,
-            "numRepeats": 0,
-            "randomSeed": 42,
-            "splitsFile": "dataSplits.csv",
-            "datasetViewMaps": {
-                "train": [
-                    {
-                        "from": "yahoo_sub_5_dataset",
-                        "to": "yahoo_sub_5_dataset_TRAIN"
-                    }
-                ],
-                "test": [
-                    {
-                        "from": "yahoo_sub_5_dataset",
-                        "to": "yahoo_sub_5_dataset_TEST"
-                    }
-                ],
-                "score": [
-                    {
-                        "from": "yahoo_sub_5_dataset",
-                        "to": "yahoo_sub_5_dataset_SCORE"
-                    }
-                ]
-            }
-        },
-        "performanceMetrics": [
-            {
-                "metric": "f1Macro"
-            }
-        ]
-    },
-    "expectedOutputs": {
-        "predictionsFile": "predictions.csv"
-    }
-}

datasets/anomaly_reserve/yahoo_sub_5/TEST/dataset_TEST/datasetDoc.json

@@ -1,95 +0,0 @@
-{
-    "about": {
-        "datasetID": "yahoo_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": "value_1",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 4,
-                    "colName": "value_2",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 5,
-                    "colName": "value_3",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 6,
-                    "colName": "value_4",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 7,
-                    "colName": "ground_truth",
-                    "colType": "integer",
-                    "role": [
-                        "suggestedTarget"
-                    ]
-                }
-            ],
-            "columnsCount": 8
-        }
-    ]
-}

datasets/anomaly_reserve/yahoo_sub_5/TEST/dataset_TEST/tables/learningData.csv

@@ -1,141 +0,0 @@
-d3mIndex,timestamp,value_0,value_1,value_2,value_3,value_4,ground_truth
-1260,1261,7782,0.034280386319742985,2.5072222222222003,104,3119,0
-1261,1262,7829,0.039360296791109,2.5927777777778,82,3590,0
-1262,1263,7902,0.0,2.6894444444444,208,3893,0
-1263,1264,8039,0.038944065994356014,2.6291666666667,92,3264,0
-1264,1265,8350,0.18176011684739,2.6469444444444,53,3963,0
-1265,1266,8142,0.18521047165852,2.7461111111111003,65,2757,0
-1266,1267,7886,0.13079770999921,2.9363888888889,62,2306,0
-1267,1268,7743,0.13310058077443,3.2797222222222,73,2549,0
-1268,1269,7707,0.054750658073534006,3.5194444444444,84,2212,0
-1269,1270,7726,0.030588852697706,3.8130555555556,90,2286,0
-1270,1271,7717,0.12998124134227002,3.7941666666667,80,2979,0
-1271,1272,10331,0.09100057249197198,3.6086111111111,90,3158,0
-1272,1273,10515,0.19464543002904006,3.3858333333333,84,2645,0
-1273,1274,10415,0.22178651521516,3.3336111111111,34,3161,0
-1274,1275,10387,0.22983578430825,3.3116666666667003,67,4460,0
-1275,1276,10471,0.298229429356,3.2616666666667005,74,2630,0
-1276,1277,10385,0.12923377484588,3.0044444444444003,44,2593,0
-1277,1278,10439,0.19609416059774,2.6741666666667,64,2625,0
-1278,1279,10516,0.040518533819385014,2.3191666666667,70,4834,0
-1279,1280,10587,0.07099894663641,2.0597222222222,96,4056,0
-1280,1281,10586,0.07584150637714701,2.0547222222222,110,5713,0
-1281,1282,10684,0.08180100127782801,2.1511111111111,68,3940,0
-1282,1283,10880,0.0,2.2602777777778,90,4414,0
-1283,1284,10830,0.0,2.2883333333333,90,5044,0
-1284,1285,10794,0.09140162014739303,2.3736111111111,69,3894,0
-1285,1286,10843,0.0,2.5869444444444,46,3993,0
-1286,1287,10805,0.0,2.6480555555556,74,4404,0
-1287,1288,10996,0.0,2.6077777777777995,68,4072,0
-1288,1289,11327,0.05363316840061,2.6069444444444,67,4182,0
-1289,1290,11090,0.26818151064716,2.6908333333333,51,3351,0
-1290,1291,10578,0.21887772653901,2.9019444444444003,39,4183,0
-1291,1292,10528,0.32371296573811,3.2711111111111,26,4068,0
-1292,1293,10475,0.12565805017257,3.5872222222222,25,8139,0
-1293,1294,10664,0.092277247744574,3.6913888888889,32,11000,0
-1294,1295,10513,0.077016875742983,3.6313888888889,17,2975,0
-1295,1296,9072,0.3714480797312501,3.5605555555556,19,2692,0
-1296,1297,9069,0.19332372237792,3.4402777777778,16,2502,0
-1297,1298,9089,0.06345811641554701,3.35,28,2510,0
-1298,1299,9027,0.2267121559473,3.3469444444444,24,2663,0
-1299,1300,8969,0.053072279964629,3.2708333333333,35,3575,0
-1300,1301,9073,0.13336345197744,3.2519444444444,49,2586,0
-1301,1302,8957,0.1252855094715,2.7311111111111,106,2908,0
-1302,1303,9126,0.096211952864224,2.3875,80,3530,0
-1303,1304,9122,0.096524467517755,2.0847222222222,90,2776,0
-1304,1305,9231,0.08924770147957402,2.0975,169,2962,0
-1305,1306,9368,0.11889606284162,2.1763888888889,98,3441,0
-1306,1307,9458,0.031429841710104,2.2327777777777995,92,4376,0
-1307,1308,9463,0.0,2.2725,91,3857,0
-1308,1309,9356,0.036512411627868,2.3202777777778,99,4685,0
-1309,1310,9340,0.0,2.5425,90,4585,0
-1310,1311,9340,0.0,2.5986111111111,126,3542,0
-1311,1312,9276,0.0,2.6319444444444,102,3370,0
-1312,1313,9611,0.10106696361212,2.5836111111111,132,3515,0
-1313,1314,9532,0.14854949043035,2.675,88,3793,0
-1314,1315,9156,0.08612162048398897,2.8522222222222,135,2954,0
-1315,1316,9222,0.16494200410492002,3.1302777777778,114,2627,0
-1316,1317,9282,0.28637713141253,3.4805555555556,35,2550,0
-1317,1318,9573,0.13206535647488,3.5994444444444,24,2480,0
-1318,1319,9333,0.27364025607799,3.5847222222222,44,2521,0
-1319,1320,9987,0.38382339961227,3.4963888888889,26,2860,0
-1320,1321,10133,0.08426242877623301,3.3825,37,3675,0
-1321,1322,10010,0.3290413568025901,3.2694444444444,45,2704,0
-1322,1323,10028,0.22632868808708,3.2322222222222,42,3121,0
-1323,1324,9984,0.17914189971361,3.1936111111111005,47,2603,0
-1324,1325,10041,0.30046815361859003,3.0536111111111004,34,3984,0
-1325,1326,10072,0.22650915594248,2.7819444444444,56,2537,0
-1326,1327,10025,0.0,2.4152777777778,87,3349,0
-1327,1328,10116,0.1223093269317,2.1569444444444,74,3958,0
-1328,1329,10232,0.1696074188221,2.1125,90,4243,0
-1329,1330,10516,0.0,2.1833333333333003,79,4159,0
-1330,1331,10449,0.028193633007367,2.205,97,5637,0
-1331,1332,10598,0.0,2.1697222222222,90,8142,0
-1332,1333,10337,0.0,2.3075,77,5713,0
-1333,1334,10469,0.097305232437507,2.4575,101,3668,0
-1334,1335,10426,0.11905908868379,2.6077777777777995,74,4307,0
-1335,1336,10531,0.11660374103282,2.6275,439,4354,0
-1336,1337,10875,0.060474297756584014,2.6144444444444,79,4262,0
-1337,1338,10494,0.22568442027805,2.6477777777777995,165,3446,0
-1338,1339,10195,0.14077736537045002,2.8594444444444003,139,2677,0
-1339,1340,9918,0.1924574892026,3.2675,56,4450,0
-1340,1341,9889,0.18922597300629,3.5136111111111004,102,3044,0
-1341,1342,9947,0.041593949118095004,3.5725,101,3428,0
-1342,1343,9977,0.2502095174271,3.6863888888889,41,2845,0
-1343,1344,10835,0.18663972932643,3.5636111111111,94,2781,0
-1344,1345,10765,0.07351854082400297,3.4127777777778,116,2743,0
-1345,1346,10656,0.081949111399618,3.295,94,4470,0
-1346,1347,10485,0.20148511394009,3.2666666666667004,89,2596,0
-1347,1348,10681,0.11515101921294,3.1933333333333,141,3249,0
-1348,1349,10852,0.07797276382811,3.0688888888889,167,2529,0
-1349,1350,10728,0.07244862879413201,2.8102777777778,148,2452,0
-1350,1351,10874,0.07310929970435699,2.42,105,2934,0
-1351,1352,10964,0.066868365737218,2.1358333333333,210,3159,0
-1352,1353,10984,0.05788512501593701,1.9916666666667,145,3974,0
-1353,1354,11055,0.09727414207464803,2.0947222222222,136,4305,0
-1354,1355,11233,0.033270317741558,2.1591666666667,126,5012,0
-1355,1356,11161,0.0,2.2377777777778,157,4455,0
-1356,1357,10966,0.038270957919533,2.2511111111111,105,4108,0
-1357,1358,11193,0.08728058888363299,2.4208333333333,114,4339,0
-1358,1359,11167,0.10536774813238,2.5241666666667,104,5056,0
-1359,1360,11367,0.1233991317089,2.5794444444444,69,5573,0
-1360,1361,51251,0.042565915766552,2.5936111111111,75,3366,1
-1361,1362,17953,0.23147422367229,2.6830555555556,73,2559,1
-1362,1363,170029,0.08983405162538903,2.8188888888889,74,1999,1
-1363,1364,10955,0.07464756469365201,2.9513888888888995,126,1993,0
-1364,1365,10984,0.099244104918934,3.2830555555556,67,1913,0
-1365,1366,10964,0.11535172009194,3.4819444444444,32,1760,0
-1366,1367,10980,0.21774881707852,3.5886111111111005,38,1890,0
-1367,1368,10852,0.1305066423559,3.4836111111111,34,2469,0
-1368,1369,10786,0.10054853030204,3.3955555555556,36,2133,0
-1369,1370,10841,0.02468393737575,3.2847222222222,26,3359,0
-1370,1371,10762,0.10018007414459,3.2383333333332995,74,3783,0
-1371,1372,10419,0.12522619841308,3.2188888888889,85,1809,0
-1372,1373,10467,0.11781887197077,2.9483333333333,67,2143,0
-1373,1374,10502,0.13417256350298,2.5855555555556,84,2567,0
-1374,1375,10519,0.07474686582090599,2.3005555555556003,1630,2176,0
-1375,1376,10579,0.13570963056519,2.0855555555556,1435,1929,0
-1376,1377,10502,0.076431907457478,1.9027777777778,857,2244,0
-1377,1378,10661,0.0,1.9411111111111,31,1810,0
-1378,1379,10818,0.1936428046839,2.0444444444444,500,2088,0
-1379,1380,10918,0.052826773889684014,2.1363888888889,53,2371,0
-1380,1381,10871,0.0,2.22,61,1843,0
-1381,1382,10796,0.054466597481213,2.3530555555556,158,2668,0
-1382,1383,10774,0.057459020289436,2.545,184,2309,0
-1383,1384,10898,0.28750562005936,2.6202777777778,91,1998,0
-1384,1385,11442,0.075538554674309,2.6847222222222,60,2480,0
-1385,1386,11113,0.08112608570492501,2.6591666666667004,107,2147,0
-1386,1387,10888,0.21563803296368,2.7863888888888995,5157,1802,0
-1387,1388,10894,0.095725002305685,3.0269444444444003,28,1789,0
-1388,1389,10888,0.17516056892320994,3.3227777777778,24,1999,0
-1389,1390,10896,0.32902836018586,3.6097222222222,21,2142,0
-1390,1391,10800,0.10216065221678,3.6805555555556,12,1904,0
-1391,1392,11000,0.19741931250852,3.6075,24,1876,0
-1392,1393,10985,0.10149107903671,3.4091666666667004,17,2434,0
-1393,1394,11017,0.17479255893624,3.3666666666667004,48,2472,0
-1394,1395,10863,0.034385029573777,3.3158333333333,41,1744,0
-1395,1396,10875,0.21988771218053,3.1622222222222,1088,2404,0
-1396,1397,10987,0.10149107903671,3.1086111111111,68,1971,0
-1397,1398,10778,0.10269981175445,2.6552777777778,2575,1713,0
-1398,1399,10957,0.11258759940039,2.2730555555556,4688,1765,0
-1399,1400,10832,0.13022351806001,2.0591666666667,477,3156,0

datasets/anomaly_reserve/yahoo_sub_5/TEST/problem_TEST/problemDoc.json

@@ -1,65 +0,0 @@
-{
-    "about": {
-        "problemID": "yahoo_sub_5_problem",
-        "problemName": "yahoo_sub_5_problem",
-        "problemDescription": "Anomaly detection",
-        "problemVersion": "4.0.0",
-        "problemSchemaVersion": "4.0.0",
-        "taskKeywords": [
-            "classification",
-            "binary",
-            "tabular"
-        ]
-    },
-    "inputs": {
-        "data": [
-            {
-                "datasetID": "yahoo_sub_5_dataset",
-                "targets": [
-                    {
-                        "targetIndex": 0,
-                        "resID": "learningData",
-                        "colIndex": 7,
-                        "colName": "ground_truth"
-                    }
-                ]
-            }
-        ],
-        "dataSplits": {
-            "method": "holdOut",
-            "testSize": 0.2,
-            "stratified": true,
-            "numRepeats": 0,
-            "randomSeed": 42,
-            "splitsFile": "dataSplits.csv",
-            "datasetViewMaps": {
-                "train": [
-                    {
-                        "from": "yahoo_sub_5_dataset",
-                        "to": "yahoo_sub_5_dataset_TRAIN"
-                    }
-                ],
-                "test": [
-                    {
-                        "from": "yahoo_sub_5_dataset",
-                        "to": "yahoo_sub_5_dataset_TEST"
-                    }
-                ],
-                "score": [
-                    {
-                        "from": "yahoo_sub_5_dataset",
-                        "to": "yahoo_sub_5_dataset_SCORE"
-                    }
-                ]
-            }
-        },
-        "performanceMetrics": [
-            {
-                "metric": "f1Macro"
-            }
-        ]
-    },
-    "expectedOutputs": {
-        "predictionsFile": "predictions.csv"
-    }
-}

datasets/anomaly_reserve/yahoo_sub_5/TRAIN/dataset_TRAIN/datasetDoc.json

@@ -1,95 +0,0 @@
-{
-    "about": {
-        "datasetID": "yahoo_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": "value_1",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 4,
-                    "colName": "value_2",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 5,
-                    "colName": "value_3",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 6,
-                    "colName": "value_4",
-                    "colType": "real",
-                    "role": [
-                        "attribute"
-                    ]
-                },
-                {
-                    "colIndex": 7,
-                    "colName": "ground_truth",
-                    "colType": "integer",
-                    "role": [
-                        "suggestedTarget"
-                    ]
-                }
-            ],
-            "columnsCount": 8
-        }
-    ]
-}

datasets/anomaly_reserve/yahoo_sub_5/TRAIN/problem_TRAIN/problemDoc.json

@@ -1,65 +0,0 @@
-{
-    "about": {
-        "problemID": "yahoo_sub_5_problem",
-        "problemName": "yahoo_sub_5_problem",
-        "problemDescription": "Anomaly detection",
-        "problemVersion": "4.0.0",
-        "problemSchemaVersion": "4.0.0",
-        "taskKeywords": [
-            "classification",
-            "binary",
-            "tabular"
-        ]
-    },
-    "inputs": {
-        "data": [
-            {
-                "datasetID": "yahoo_sub_5_dataset",
-                "targets": [
-                    {
-                        "targetIndex": 0,
-                        "resID": "learningData",
-                        "colIndex": 7,
-                        "colName": "ground_truth"
-                    }
-                ]
-            }
-        ],
-        "dataSplits": {
-            "method": "holdOut",
-            "testSize": 0.2,
-            "stratified": true,
-            "numRepeats": 0,
-            "randomSeed": 42,
-            "splitsFile": "dataSplits.csv",
-            "datasetViewMaps": {
-                "train": [
-                    {
-                        "from": "yahoo_sub_5_dataset",
-                        "to": "yahoo_sub_5_dataset_TRAIN"
-                    }
-                ],
-                "test": [
-                    {
-                        "from": "yahoo_sub_5_dataset",
-                        "to": "yahoo_sub_5_dataset_TEST"
-                    }
-                ],
-                "score": [
-                    {
-                        "from": "yahoo_sub_5_dataset",
-                        "to": "yahoo_sub_5_dataset_SCORE"
-                    }
-                ]
-            }
-        },
-        "performanceMetrics": [
-            {
-                "metric": "f1Macro"
-            }
-        ]
-    },
-    "expectedOutputs": {
-        "predictionsFile": "predictions.csv"
-    }
-}