[PyTorch] Dataset and DataLoader

 import torch
 import torchvision
 from torch.utils.data import Dataset, DataLoader
 import numpy as np
 import math
 import pandas as pd
 import io

# Github에 있는 wine.csv을 읽어오기 위한 작업
import requests

url = "https://raw.githubusercontent.com/python-engineer/pytorchTutorial/master/data/wine/wine.csv"
download = requests.get(url).content

df = pd.read_csv(io.StringIO(download.decode('utf-8')))

# pd.set_option('max_columns', 100)
# pd.set_option('max_rows', 100)

# pd.options.display.float_format = lambda x: f'{x:.8f}'

df

	Wine	Alcohol	Malic.acid	Ash	Acl	Mg	Phenols	Flavanoids	Nonflavanoid.phenols	Proanth	Color.int	Hue	OD	Proline
0	1	14.23	1.71	2.43	15.6	127	2.80	3.06	0.28	2.29	5.64	1.04	3.92	1065
1	1	13.20	1.78	2.14	11.2	100	2.65	2.76	0.26	1.28	4.38	1.05	3.40	1050
2	1	13.16	2.36	2.67	18.6	101	2.80	3.24	0.30	2.81	5.68	1.03	3.17	1185
3	1	14.37	1.95	2.50	16.8	113	3.85	3.49	0.24	2.18	7.80	0.86	3.45	1480
4	1	13.24	2.59	2.87	21.0	118	2.80	2.69	0.39	1.82	4.32	1.04	2.93	735
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
173	3	13.71	5.65	2.45	20.5	95	1.68	0.61	0.52	1.06	7.70	0.64	1.74	740
174	3	13.40	3.91	2.48	23.0	102	1.80	0.75	0.43	1.41	7.30	0.70	1.56	750
175	3	13.27	4.28	2.26	20.0	120	1.59	0.69	0.43	1.35	10.20	0.59	1.56	835
176	3	13.17	2.59	2.37	20.0	120	1.65	0.68	0.53	1.46	9.30	0.60	1.62	840
177	3	14.13	4.10	2.74	24.5	96	2.05	0.76	0.56	1.35	9.20	0.61	1.60	560

178 rows × 14 columns

# pandas dataframe 저장
# df.to_csv("wine.csv")

# 불러온 데이터들을 그냥 써도 된다. 파일로도 하는법을 보여주는것

 class WineDataset(Dataset):
  def __init__(self):
    # data loading
    xy = np.loadtxt('/content/sample_data/wine.csv', delimiter=",", dtype=np.float32, skiprows=1)
    self.x = torch.from_numpy(xy[:, 1:])
    self.y = torch.from_numpy(xy[:, [0]]) # n_samples, 1
    self.n_samples = xy.shape[0]
  def __getitem__(self, index):
    return self.x[index], self.y[index]
  def __len__(self):
    return self.n_smaples

dataset = WineDataset()
dataloader = DataLoader(dataset=dataset, batch_size=4)
# dataloader = DataLoader(dataset=dataset1, batch_size=4, shuffle=True, num_workers=2)

dataiter = iter(dataloader)
data = dataiter.next()
features, labels = data
print(features, labels)