Hirokazu Takaya
Hirokazu Takaya
Dear @manisci , Thank you for your great idea! `pytrends` has some APIs and we can use them to understand interest trend of the words (specified by users, like "lockdown"...
Do you have any ideas regarding the output dataframe of the new data loader?
FYI: Documentation of "COVID-19 Data Hub" https://covid19datahub.io/articles/doc/data.html
Yes, could be. `.map` method should be inplemented in the new class.
This may be dicussed laiter, but not required at this time.
To achieve this, a method of `Scenario` will be necessary to registers future values of extra datasets.
In `analysis.DataHandler` class internally, - save subsets for the selected country/province with a dataframe, not instances of data cleaning class. (related to #741) - add a method to to register...
`future_regressor` functionality of AutoTS package can be used. https://winedarksea.github.io/AutoTS/build/html/source/tutorial.html#simulation-forecasting-1
Class for feature engineering, feature selection, extending (add new records on future dates) and easy visualization will be required. Named `MLEngineer` as instance.
The new class also Includes forecasting with/without regression.