Generic Time Series Modeling with trading data in Python (STATISTICAL MODELING)

to make a time series model to plot an X Y scatter plot based on price data for several assets all at once (several currency pairs would be clustered together and have their own scatter plot, same for commodities, same for cryptocurrency, etc) with "momentum" as the x axis and "mean reverting" as the Y axis. The model would use both the variance ratio test and Ornstein–Uhlenbeck (OU) Process to determine whether if the asset should be classified as a momentum asset or mean reverting asset. I would want the ability to run the model for various the trading periods (i.e. monthly, weekly, daily, 4hr, 1 hr, 30 min, 15 min, 5 min, 1 min). The variance ratio test would plot on the scatter plot based on the following: Decreasing variance/ (variance ratio between 0 and .8), a random walk (.8 to 1.2) or increasing variance/momentum (ratio of 1.2 to 2). The OU process would calculate the mean reversion rate. I would want to visualize whether the mean reversion rate was high or low on the plot and be able to compare that to the results of the variance ratio test. So essentially, I am looking for a scatter plot that plots results for two test (variance ratio test and OU process) using a cluster of trading data (i.e. currency pair data, etc) for different time frames. I am looking for a way to constantly scan the markets (multiple assets) and determine the results of the tests on this scatter plot at any given time.