Helper Module for Deep Learning.

Module provides functions to prepare different toy datasets from UKB.: 1) toy example about height in UKB with no NaN and known signif snps 2)

class pynet.datasets.ukb.Item(input_path, output_path, metadata_path, labels)¶

pynet.datasets.ukb.fetch_height_biobank(datasetdir, to_categorical=False, check=False)[source]¶

Fetch/prepare the height biobank prediction dataset for pynet.

Matrix Y contains the average grain yield, column 1: Grain yield for environment 1 and so on. Matrix X contains marker genotypes.

Parameters

datasetdir: str

the dataset destination folder.

to_categorical: bool, default False

if set convert the observation to categories.

check: bool, default False

if set check results against the downloaded .check file data

Returns

item: namedtuple

a named tuple containing ‘input_path’, ‘output_path’, and ‘metadata_path’.