load_cardano_sentiment¶

load_cardano_sentiment(split=None, return_type='numpy3d')[source]¶

Load dataset of historical sentiment data for Cardano cryptocurrency.

Parameters:

split: None or str{“train”, “test”}, default=None: Whether to load the train or test partition of the problem. By default, it loads both.
return_type: string, default=”numpy3d”: Data structure to use for time series, should be either “numpy2d” or “numpy3d”.

Returns:

X: np.ndarray: The time series data.
y: np.ndarray: The regression values for each case in X.

Notes

Dimensionality: multivariate Series length: 24 Train cases: 74 Test cases: 33 Number of classes: -

By combining historical sentiment data for Cardano cryptocurrency, extracted from EODHistoricalData and made available on Kaggle, with historical price data for the same cryptocurrency, extracted from CryptoDataDownload, we created the CardanoSentiment dataset, with 107 instances. The predictors are hourly close price (in USD) and traded volume during a day, resulting in 2-dimensional time series of length 24. The response variable is the normalized sentiment score on the day spanned by the timepoints.

EODHistoricalData: https://perma.cc/37GN-BMRL CryptoDataDownload: https://perma.cc/4M79-7QY4 Dataset details: https://arxiv.org/pdf/2305.01429.pdf

Examples

>>> from aeon.datasets import load_cardano_sentiment
>>> X, y = load_cardano_sentiment()