08_1_dataset_loader.py

# References
# https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/01-basics/pytorch_basics/main.py
# http://pytorch.org/tutorials/beginner/data_loading_tutorial.html#dataset-class
from torch.utils.data import Dataset, DataLoader
from torch import from_numpy, tensor
import numpy as np

class DiabetesDataset(Dataset):
    """ Diabetes dataset."""

    # Initialize your data, download, etc.
    def __init__(self):
        xy = np.loadtxt('./data/diabetes.csv.gz',
                        delimiter=',', dtype=np.float32)
        self.len = xy.shape[0]
        self.x_data = from_numpy(xy[:, 0:-1])
        self.y_data = from_numpy(xy[:, [-1]])

    def __getitem__(self, index):
        return self.x_data[index], self.y_data[index]

    def __len__(self):
        return self.len


dataset = DiabetesDataset()
train_loader = DataLoader(dataset=dataset,
                          batch_size=32,
                          shuffle=True,
                          num_workers=2)

for epoch in range(2):
    for i, data in enumerate(train_loader, 0):
        # get the inputs
        inputs, labels = data

        # wrap them in Variable
        inputs, labels = tensor(inputs), tensor(labels)

        # Run your training process
        print(f'Epoch: {i} | Inputs {inputs.data} | Labels {labels.data}')