Protein¶

class itergp.datasets.uci.Protein(dir='data/uci/protein', overwrite=False)¶

Bases: UCIDataset

Protein dataset (45,730 × 9).

This is a data set of Physicochemical Properties of Protein Tertiary Structure. The data set is taken from CASP 5-9. There are 45730 decoys and size varying from 0 to 21 armstrong.

Source: https://archive.ics.uci.edu/ml/datasets/Physicochemical+Properties+of+Protein+Tertiary+Structure

Attributes Summary

`URL`
`input_shape`	Input shape of the data.
`output_shape`	Output shape of the data.
`test`	Test data.
`train`	Training data.

Methods Summary

`from_disk`(dir)
`resample`(rng_state)	Resample the training and test set from the entire data set.
`save`([dir, overwrite])	Save dataset to disk.

Attributes Documentation

Parameters

dir (Optional[str]) –
overwrite (bool) –

URL = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00265/'¶

input_shape¶: Input shape of the data.

output_shape¶: Output shape of the data.

test¶: Test data.

train¶: Training data.

Methods Documentation

classmethod from_disk(dir)¶

Parameters: dir (str) –
Return type: Dataset

resample(rng_state)¶

Resample the training and test set from the entire data set.

Randomly selects new datapoints for the training and test set of the same sizes as the original dataset.

Parameters: rng_state (SeedSequence) – Random number generator state.
Return type: Dataset

save(dir='data', overwrite=False)¶

Save dataset to disk.

Parameters

dir (str) – Directory to save data to.
overwrite – Whether to overwrite existing data.

Return type

None