-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
to answer question one try just running a simple correlation matrix among your yearly and the average of your daily figures For years 2012+ when you have all four inputs. I frequently use the small convenience library Dython Dython in Github. If your features are very independent then you will not be able to fill in missing values and will need to find other surrogates such as “is my crop largely a fixed percentage of overall exports and are overall exports available for missing years?” If your features are highly dependent then essentially you don’t need them all - both XGBoost and LightGBM have simple fill-in-with-the-mean type imputation of missing values - run across all your data with imputation on and removing low impact features will remove all but one highly interdependent features.
Related posts
-
Do not Reinvent the Wheel: Utilize Django’s Built-in Auth App to Create a Robust Authentication System
-
Llama3.np: pure NumPy implementation of Llama3
-
Show HN: Open-source tool for data cleaning with LLM
-
Python VS Common Lisp applied: print, log and icecream
-
Who's worked with dbt and how does it compare with Qlik load script or SQL & SSIS?