Data¶
Large collections¶
Python libraries statsmodels, sci-learn and seaborn and R itself have build-in datasets.
gretl has extensive selection of datasets, including data from key textbooks.
Well known dataset repository is UCI.
Kaggle obviously has plenty of datasets.
Sheffield University made a good listing of datasets for teaching.
Australian National Centre for Econometric Research website has a useful Data and code section.
Google Dataset search is not yet as good as main Google search, but will surely improve.
FRED, Quandl and dbnomics are standard sources for macroeconomic data. My own effort for clean Russian macro time series - mini-kep.
Individual datasets¶
Tidy Tuesday publishes weekly datasets and accompanying articles.
Nick Huntington-Klein provides a variety of extra examples of data importable into R.
I extracted a small, but illustartive dataset about lightbulb survival rate.
Sunspot data is listed at variety of sources.