You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

datasetDoc.json 2.1 kB

first commit Former-commit-id: 08bc23ba02cffbce3cf63962390a65459a132e48 [formerly 0795edd4834b9b7dc66db8d10d4cbaf42bbf82cb] [formerly b5010b42541add7e2ea2578bf2da537efc457757 [formerly a7ca09c2c34c4fc8b3d8e01fcfa08eeeb2cae99d]] [formerly 615058473a2177ca5b89e9edbb797f4c2a59c7e5 [formerly 743d8dfc6843c4c205051a8ab309fbb2116c895e] [formerly bb0ea98b1e14154ef464e2f7a16738705894e54b [formerly 960a69da74b81ef8093820e003f2d6c59a34974c]]] [formerly 2fa3be52c1b44665bc81a7cc7d4cea4bbf0d91d5 [formerly 2054589f0898627e0a17132fd9d4cc78efc91867] [formerly 3b53730e8a895e803dfdd6ca72bc05e17a4164c1 [formerly 8a2fa8ab7baf6686d21af1f322df46fd58c60e69]] [formerly 87d1e3a07a19d03c7d7c94d93ab4fa9f58dada7c [formerly f331916385a5afac1234854ee8d7f160f34b668f] [formerly 69fb3c78a483343f5071da4f7e2891b83a49dd18 [formerly 386086f05aa9487f65bce2ee54438acbdce57650]]]] Former-commit-id: a00aed8c934a6460c4d9ac902b9a74a3d6864697 [formerly 26fdeca29c2f07916d837883983ca2982056c78e] [formerly 0e3170d41a2f99ecf5c918183d361d4399d793bf [formerly 3c12ad4c88ac5192e0f5606ac0d88dd5bf8602dc]] [formerly d5894f84f2fd2e77a6913efdc5ae388cf1be0495 [formerly ad3e7bc670ff92c992730d29c9d3aa1598d844e8] [formerly 69fb3c78a483343f5071da4f7e2891b83a49dd18]] Former-commit-id: 3c19c9fae64f6106415fbc948a4dc613b9ee12f8 [formerly 467ddc0549c74bb007e8f01773bb6dc9103b417d] [formerly 5fa518345d958e2760e443b366883295de6d991c [formerly 3530e130b9fdb7280f638dbc2e785d2165ba82aa]] Former-commit-id: 9f5d473d42a435ec0d60149939d09be1acc25d92 [formerly be0b25c4ec2cde052a041baf0e11f774a158105d] Former-commit-id: 9eca71cb73ba9edccd70ac06a3b636b8d4093b04
5 years ago
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798
  1. {
  2. "about": {
  3. "datasetID": "text_dataset_1",
  4. "datasetName": "Test text dataset",
  5. "description": "Based on 30_personae_dataset",
  6. "datasetSchemaVersion": "4.0.0",
  7. "redacted": false,
  8. "datasetVersion": "4.0.0",
  9. "digest": "93b2d6fda19ce0c64a9fb49f88c3a3c4444318df923ed424c3c7911336dfd34f"
  10. },
  11. "dataResources": [
  12. {
  13. "resID": "0",
  14. "resPath": "text/",
  15. "resType": "text",
  16. "resFormat": {
  17. "text/plain": [
  18. "txt"
  19. ]
  20. },
  21. "isCollection": true
  22. },
  23. {
  24. "resID": "learningData",
  25. "resPath": "tables/learningData.csv",
  26. "resType": "table",
  27. "resFormat": {
  28. "text/csv": [
  29. "csv"
  30. ]
  31. },
  32. "isCollection": false,
  33. "columnsCount": 7,
  34. "columns": [
  35. {
  36. "colIndex": 0,
  37. "colName": "d3mIndex",
  38. "colType": "integer",
  39. "role": [
  40. "index"
  41. ]
  42. },
  43. {
  44. "colIndex": 1,
  45. "colName": "raw_text_file",
  46. "colType": "string",
  47. "role": [
  48. "attribute"
  49. ],
  50. "refersTo": {
  51. "resID": "0",
  52. "resObject": "item"
  53. }
  54. },
  55. {
  56. "colIndex": 2,
  57. "colName": "text_language",
  58. "colType": "categorical",
  59. "role": [
  60. "attribute"
  61. ]
  62. },
  63. {
  64. "colIndex": 3,
  65. "colName": "author_gender",
  66. "colType": "categorical",
  67. "role": [
  68. "attribute"
  69. ]
  70. },
  71. {
  72. "colIndex": 4,
  73. "colName": "author_language",
  74. "colType": "categorical",
  75. "role": [
  76. "attribute"
  77. ]
  78. },
  79. {
  80. "colIndex": 5,
  81. "colName": "author_region",
  82. "colType": "categorical",
  83. "role": [
  84. "attribute"
  85. ]
  86. },
  87. {
  88. "colIndex": 6,
  89. "colName": "extrovert",
  90. "colType": "categorical",
  91. "role": [
  92. "suggestedTarget"
  93. ]
  94. }
  95. ]
  96. }
  97. ]
  98. }

全栈的自动化机器学习系统,主要针对多变量时间序列数据的异常检测。TODS提供了详尽的用于构建基于机器学习的异常检测系统的模块,它们包括:数据处理(data processing),时间序列处理( time series processing),特征分析(feature analysis),检测算法(detection algorithms),和强化模块( reinforcement module)。这些模块所提供的功能包括常见的数据预处理、时间序列数据的平滑或变换,从时域或频域中抽取特征、多种多样的检测算

Contributors (1)