Aggregated datasets

In this section we will find aggregated datasets with multiple information provided by the data providers defillama and coingecko. Each dataset, has a daily snapshot of some of the most interesting attributes to create ML models such as the price of multiple tokens, the TVL of some of the largest protocols in the DeFi ecosystem or the APY of the most important pools of these protocols.

These datasets have been created with the intention of providing a high-level view of the DeFi ecosystem. Furthermore, they have been designed in such a way that they are very easy to merge and create a single dataset with all the information needed to train an ML model for a specific purpose. The following ERD shows the relationship between these datasets:

In each of the subsections of this section we show in detail the content of each dataset as well as an example of use using our library to load them.