The document discusses various data analysis techniques used in a PyCon Taiwan 2019 presentation, focusing on vibration data processing and analysis methods. It mentions statistical tests like the Mann-Kendall test and Kolmogorov-Smirnov test for trend analysis and distribution comparison. Additionally, it highlights XGBoost, a machine learning library optimized for efficient gradient boosting.

1. 報告人 張楦涵 徐仕杰 | PyCon Taiwan 2019

16. Edge Server
Database

20. 


25. from nptdms import TdmsFile
tdms_file = TdmsFile(path)
obj=tdms_file.object(‘vibration_X’)
data = obj.data
震動 X 震動Y 震動Z
0.5047 -0.938 1.156
… … …
-1.717 -0.286 1.759

26. 日期 時間 毫秒 … X軸座標 Y軸座標 Z軸座標 進給 轉速 主軸負載
2018/5/26 08:13:15 481 … 0.8501 -239.158 -254.203 0 1999.969 4.257332
2018/5/26 08:13:15 496 … 0.8501 -239.158 -254.203 0 1999.969 4.257332
2018/5/26 08:13:15 512 … 0.8501 -239.158 -254.203 0 1999.969 4.257332

28. •
•
•

30. 10/24/11 05/11/12 11/27/12 06/15/13 01/01/14 07/20/14 02/05/15
0
0.5
1
1.5
2
2.5
3
x 10
4
Time
Energy(mJ)
09/23/13 11/12/13 01/01/14 02/20/14 04/11/14 05/31/14 07/20/14 09/08/14
5600
5800
6000
6200
6400
6600
6800
7000
7200
Time
Energy(mJ)
256,908,800 155,456,000

31. •
•
•
•
•
•

33. •
•
•
•

34. 1 x 155,456,000
342,968 x 7,680

39. 342,968 x 7,680
342,968 x 281

40. •
• The Mann-Kendall Test is used to determine whether a time series has a
monotonic upward or downward trend. It does not require that the data be
normally distributed or linear. It does require that there is no autocorrelation.
•
• Kolmogorov–Smirnov test is a nonparametric test of the equality of
continuous (or discontinuous), one-dimensional probability distributions that
can be used to compare a sample with a reference probability distribution
•
• A type of statistical significance test in which the distribution of the test
statistic under the null hypothesis is obtained by calculating all possible values
of the test statistic under rearrangements of the labels on the observed data
points.

42. •
• XGBoost is an optimized distributed gradient boosting library designed to be
highly efficient, flexible and portable. It implements machine learning
algorithms under the Gradient Boosting framework. XGBoost provides a
parallel tree boosting (also known as GBDT, GBM) that solve many data
science problems in a fast and accurate way.
•
•
•
•
•

44. •
•

45. ‧