Statistical_test

Description

This API performs statistical testing on the data of a specific Tag Table. While it is not an essential process, it can help establish a direction for data preprocessing.

There are six testing methods for time series data, as follows:

  • Stationarity Test
    • ADF(Augmented Dickey-Fuller) Test
    • KPSS(Kwiatkowski-Phillips-Schmidt-Shin) Test
    • PP(Phillips-Perron) Test
  • Autocorrelation Test
    • Ljung-Box Test
  • Heteroscedasticity Test
    • ARCH(Autoregressive Conditional Heteroskedasticity) Test
  • Multicollinearity Test
    • VIF(Variance Inflation Factor) Test

API module path

from api.v2.eda.Statistical_test import adf_test, kpss_test, pp_test, ljung_box_test, arch_test, vif_test

Parameters

Df

  • Specifies the DataFrame composed of time series data.

Lag

  • Specifies the Time Lag.
  • It is used only in the Ljung-Box Test.
  • A value that determines how many lags to consider in order to check the correlation between the current time point and previous time points.
  • Defalut : 10
  • Example
    • lag = 10

Example Sample Code (Python)

Results

  • Due to the large output, only the VIF test results are provided.

Check the entire module code.

datahub/api/v2/eda/Statistical_test.py at main · machbase/datahub
All Industrial IoT DataHub with data visualization and AI source - machbase/datahub

Back to Top