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.

106.csv 3.3 kB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364
  1. 8.600000000000000000e+01,3.800000000000000000e+01
  2. 7.200000000000000000e+01,2.200000000000000000e+01
  3. 1.680000000000000000e+02,-5.800000000000000000e+01
  4. 2.760000000000000000e+02,-1.280000000000000000e+02
  5. 2.100000000000000000e+02,-1.000000000000000000e+00
  6. 2.200000000000000000e+02,7.200000000000000000e+01
  7. 9.200000000000000000e+01,9.600000000000000000e+01
  8. -3.400000000000000000e+01,1.540000000000000000e+02
  9. -3.600000000000000000e+01,2.120000000000000000e+02
  10. -3.600000000000000000e+01,2.800000000000000000e+02
  11. -8.600000000000000000e+01,3.380000000000000000e+02
  12. -9.000000000000000000e+01,2.660000000000000000e+02
  13. -6.600000000000000000e+01,1.380000000000000000e+02
  14. -1.220000000000000000e+02,1.000000000000000000e+01
  15. -1.180000000000000000e+02,-8.000000000000000000e+00
  16. -1.080000000000000000e+02,-2.200000000000000000e+01
  17. -1.440000000000000000e+02,-2.000000000000000000e+01
  18. -1.640000000000000000e+02,-3.200000000000000000e+01
  19. -1.680000000000000000e+02,-4.200000000000000000e+01
  20. -1.980000000000000000e+02,-4.000000000000000000e+01
  21. -1.980000000000000000e+02,-5.200000000000000000e+01
  22. -2.260000000000000000e+02,-4.800000000000000000e+01
  23. -1.900000000000000000e+02,-6.200000000000000000e+01
  24. -2.640000000000000000e+02,-7.400000000000000000e+01
  25. -2.640000000000000000e+02,-9.800000000000000000e+01
  26. -2.740000000000000000e+02,-1.020000000000000000e+02
  27. -2.560000000000000000e+02,-1.120000000000000000e+02
  28. -2.620000000000000000e+02,-1.260000000000000000e+02
  29. -2.440000000000000000e+02,-1.260000000000000000e+02
  30. -2.140000000000000000e+02,-1.300000000000000000e+02
  31. -1.900000000000000000e+02,-1.340000000000000000e+02
  32. -1.500000000000000000e+02,-1.240000000000000000e+02
  33. -1.060000000000000000e+02,-1.320000000000000000e+02
  34. -9.400000000000000000e+01,-1.120000000000000000e+02
  35. -2.000000000000000000e+01,-9.400000000000000000e+01
  36. -2.200000000000000000e+01,-8.200000000000000000e+01
  37. -6.000000000000000000e+00,-7.000000000000000000e+01
  38. 2.400000000000000000e+01,-5.200000000000000000e+01
  39. 3.200000000000000000e+01,-4.200000000000000000e+01
  40. 2.800000000000000000e+01,-2.200000000000000000e+01
  41. 4.200000000000000000e+01,-2.000000000000000000e+00
  42. 5.400000000000000000e+01,0.000000000000000000e+00
  43. 6.000000000000000000e+01,6.000000000000000000e+00
  44. 4.600000000000000000e+01,1.000000000000000000e+01
  45. 6.200000000000000000e+01,8.000000000000000000e+00
  46. 6.800000000000000000e+01,1.000000000000000000e+01
  47. 5.600000000000000000e+01,2.200000000000000000e+01
  48. 5.800000000000000000e+01,2.800000000000000000e+01
  49. 8.200000000000000000e+01,2.400000000000000000e+01
  50. 8.400000000000000000e+01,4.000000000000000000e+01
  51. 9.000000000000000000e+01,3.400000000000000000e+01
  52. 1.040000000000000000e+02,2.800000000000000000e+01
  53. 7.000000000000000000e+01,5.000000000000000000e+01
  54. 1.280000000000000000e+02,4.000000000000000000e+01
  55. 1.280000000000000000e+02,1.000000000000000000e+01
  56. 1.320000000000000000e+02,-2.000000000000000000e+00
  57. 1.080000000000000000e+02,-2.200000000000000000e+01
  58. 9.000000000000000000e+01,-2.800000000000000000e+01
  59. 1.460000000000000000e+02,-2.200000000000000000e+01
  60. 9.000000000000000000e+01,-9.000000000000000000e+01
  61. 1.720000000000000000e+02,-1.680000000000000000e+02
  62. 1.320000000000000000e+02,-1.720000000000000000e+02
  63. 1.720000000000000000e+02,-1.600000000000000000e+02
  64. 4.400000000000000000e+01,-2.880000000000000000e+02

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