Bayesian trend filtering micro library
I am currently redesigning the API and will release an alpha version in late August.
The documentation can be found here.
Contribution will be welcomed once a first stable release is ready. [Contact Me]()
Data is imported from a file (trendpy only supports csv for now).
# import data from csv file (with dates and price) -- for now trendpy only
# support 1D time series
from trendpy import filter
from pandas import read_csv
filename='data.csv'
data = read_csv(filename)
filtered = filter(data['time series'])
These requirements reflect the testing environment. It is possible that trendpy will work with older versions.
Research papers that helped develop this library
Having trouble with trendpy? Check out our documentation.