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.

multitable.datasetDoc.json 5.6 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
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232
  1. {
  2. "about": {
  3. "datasetID":"mt_mtc_1",
  4. "datasetName":"Sample multitable relational dataset",
  5. "humanSubjectsResearch": false,
  6. "license":"CC",
  7. "datasetSchemaVersion":"3.0",
  8. "redacted":false
  9. },
  10. "dataResources":[
  11. {
  12. "resID":"0",
  13. "resPath":"tables/customers.csv",
  14. "resType":"table",
  15. "resFormat":["text/csv"],
  16. "isCollection":false,
  17. "columns":[
  18. {
  19. "colIndex":0,
  20. "colName":"custID",
  21. "colType":"integer",
  22. "role":["index"]
  23. },
  24. {
  25. "colIndex":1,
  26. "colName":"country",
  27. "colType":"categorical",
  28. "role":["attribute"]
  29. },
  30. {
  31. "colIndex":2,
  32. "colName":"first_invoices_time",
  33. "colType":"dateTime",
  34. "role":["attribute"]
  35. },
  36. {
  37. "colIndex":3,
  38. "colName":"facebookHandle",
  39. "colType":"string",
  40. "role":["attribute", "key"]
  41. }
  42. ]
  43. },
  44. {
  45. "resID":"1",
  46. "resPath":"tables/invoices.csv",
  47. "resType":"table",
  48. "resFormat":["text/csv"],
  49. "isCollection":false,
  50. "columns":[
  51. {
  52. "colIndex":0,
  53. "colName":"invoiceNo",
  54. "colType":"integer",
  55. "role":["index"]
  56. },
  57. {
  58. "colIndex":1,
  59. "colName":"customerID",
  60. "colType":"integer",
  61. "role":["attribute"],
  62. "refersTo":{
  63. "resID":"0",
  64. "resObject":{
  65. "columnName":"custID"}}
  66. },
  67. {
  68. "colIndex":2,
  69. "colName":"first_item_purchases_time",
  70. "colType":"dateTime",
  71. "role":["attribute"]
  72. }
  73. ]
  74. },
  75. {
  76. "resID":"2",
  77. "resPath":"tables/items.csv",
  78. "resType":"table",
  79. "resFormat":["text/csv"],
  80. "isCollection":false,
  81. "columns":[
  82. {
  83. "colIndex":0,
  84. "colName":"stockCode",
  85. "colType":"string",
  86. "role":["index"]
  87. },
  88. {
  89. "colIndex":1,
  90. "colName":"first_item_purchases_time",
  91. "colType":"dateTime",
  92. "role":["attribute"]
  93. },
  94. {
  95. "colIndex":2,
  96. "colName":"Description",
  97. "colType":"string",
  98. "role":["attribute"]
  99. }
  100. ]
  101. },
  102. {
  103. "resID":"learningData",
  104. "resPath":"tables/learningData.csv",
  105. "resType":"table",
  106. "resFormat":["text/csv"],
  107. "isCollection":false,
  108. "columns":[
  109. {
  110. "colIndex":0,
  111. "colName":"item_purchase_ID",
  112. "colType":"integer",
  113. "role":["index"]
  114. },
  115. {
  116. "colIndex":1,
  117. "colName":"invoiceNo",
  118. "colType":"integer",
  119. "role":["attribute"],
  120. "refersTo":{
  121. "resID":"1",
  122. "resObject":{
  123. "columnIndex":0}}
  124. },
  125. {
  126. "colIndex":2,
  127. "colName":"invoiceDate",
  128. "colType":"dateTime",
  129. "role":["attribute"]
  130. },
  131. {
  132. "colIndex":3,
  133. "colName":"stockCode",
  134. "colType":"string",
  135. "role":["attribute"],
  136. "refersTo":{
  137. "resID":"2",
  138. "resObject":{
  139. "columnName":"stockCode"
  140. }
  141. }
  142. },
  143. {
  144. "colIndex":4,
  145. "colName":"unitPrice",
  146. "colType":"real",
  147. "role":["attribute"]
  148. },
  149. {
  150. "colIndex":5,
  151. "colName":"quantity",
  152. "colType":"integer",
  153. "role":["attribute"]
  154. },
  155. {
  156. "colIndex":6,
  157. "colName":"customerSatisfied",
  158. "colType":"categorical",
  159. "role":["suggestedTarget"]
  160. },
  161. {
  162. "colIndex":7,
  163. "colName":"profitMargin",
  164. "colType":"real",
  165. "role":["suggestedTarget"]
  166. }
  167. ]
  168. }
  169. ],
  170. "qualities":[
  171. {
  172. "qualName":"multiRelationalTables",
  173. "qualValue":true,
  174. "qualValueType":"boolean"
  175. },
  176. {
  177. "qualityName":"LUPI",
  178. "qualityValue":true,
  179. "qualValueType":"boolean"
  180. },
  181. {
  182. "qualName":"privilegedFeature",
  183. "qualValue":true,
  184. "qualValueType":"boolean",
  185. "restrictedTo":{
  186. "resID":"0",
  187. "resComponent":{"colName":"facebookHandle"}
  188. }
  189. },
  190. {
  191. "qualName":"approximateSize",
  192. "qualValue":300,
  193. "qualValueType":"integer",
  194. "qualValueUnits":"MB"
  195. },
  196. {
  197. "qualName":"maxSkewOfNumericAttributes",
  198. "qualValue":6.57,
  199. "qualValueType":"real",
  200. "restrictedTo":{
  201. "resID":"3"
  202. }
  203. },
  204. {
  205. "qualName":"classEntropy",
  206. "qualValue":3.63,
  207. "qualValueType":"real",
  208. "restrictedTo":{
  209. "resID":"3",
  210. "resComponent":{"colName":"customerSatisfied"}
  211. }
  212. },
  213. {
  214. "qualName":"numUniqueValues",
  215. "qualValue":3667,
  216. "qualValueType":"integer",
  217. "restrictedTo":{
  218. "resID":"3",
  219. "resComponent":{"columnIndex":1}
  220. }
  221. },
  222. {
  223. "qualName":"numMissingValues",
  224. "qualValue":12,
  225. "qualValueType":"integer",
  226. "restrictedTo":{
  227. "resID":"3",
  228. "resComponent":{"columnName":"customerSatisfied"}
  229. }
  230. }
  231. ]
  232. }

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