crypticorn
What is Crypticorn?
Crypticorn is at the forefront of cutting-edge artificial intelligence cryptocurrency trading. Crypticorn offers AI-based solutions for both active and passive investors, including:
- Prediction Dashboard with trading terminal,
- AI Trading Bots with different strategies,
- DEX AI Signals for newly launched tokens,
- DEX AI Bots
Use this API Client to contribute to the so-called Hive AI, a community driven AI Meta Model for predicting the cryptocurrency market.
Changelog
[1.0.0] - 2024-11-30
- Initial public release
A client for interacting with the crypticorn API, offering functionality to create and evaluate models, download data, and retrieve information about available coins, targets, and features.
Creates a new model based on the specified coin_id and target.
Parameters
- coin_id: The id of the coin to be used for the model.
- target: The target variable for the model.
Evaluates an existing model using the provided data.
Parameters
- model_id: The id of the model to evaluate.
- data: The data to use for evaluation, which can be a pandas DataFrame or a file path with
extensions
.feather
or.parquet
. - version: (optional) Specifies the data version for evaluation. Defaults to the latest version.
If a different version than the latest is specified, the evaluation will not be stored
or counted on the leaderboard. This is useful for testing your model with different versions.
Ensure to specify a
version
if your model was trained on older data versions; otherwise, it will be evaluated against the latest data, potentially affecting the results.
Downloads training data for models.
Either pass a model_id or coin_id. For more details about available data, use data_info()
.
Parameters
- model_id: id of the model to download data for.
- version: (optional) Data version to download. Defaults to the latest version if not specified.
- feature_size: (optional) Size of the feature set to download. Default is "large".
Returns information about the training data.
Useful in combination with download_data()
and create_model()
.