[PyTorch] Dataset Transform

from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive

import torch
import torchvision
from torch.utils.data import Dataset
import numpy as np


import requests
import pandas as pd
import io

# 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')))
# df.to_csv("wine.csv")

df = pd.read_csv("/content/drive/MyDrive/Study/data/wine.csv")
df

	Unnamed: 0	Wine	Alcohol	Malic.acid	Ash	Acl	Mg	Phenols	Flavanoids	Nonflavanoid.phenols	Proanth	Color.int	Hue	OD	Proline
0	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	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	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	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	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	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	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	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	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	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 × 15 columns

class WineDataset(Dataset):
  def __init__(self, transform=None):
    xy = np.loadtxt("/content/drive/MyDrive/Study/data/wine.csv", delimiter=',', dtype=np.float32, skiprows=1)
    self.n_samples = xy.shape[0]

    self.x = xy[:, 1:]
    self.y = xy[:, [0]]

    self.transform = transform

  def __getitem__(self, index):
    sample = self.x[index], self.y[index]

    if self.transform:
      sample = self.transform(sample)
    
    return sample

  def __len__(self):
    return self.n_samples

class ToTensor:
  def __call__(self, sample):
    inputs, targets = sample
    return torch.from_numpy(inputs), torch.from_numpy(targets)


class MulTransform:
  def __init__(self, factor):
    self.factor = factor
  
  def __call__(self, sample):
    inputs, target = sample
    inputs *= self.factor
    return inputs, target
  

# dataset = WineDataset(transform=ToTensor())          # tensor로 바꿔줘야한다.
dataset = WineDataset()
first_data = dataset[0]
features, labels = first_data
print(features)
print(type(features), type(labels))

[1.000e+00 1.423e+01 1.710e+00 2.430e+00 1.560e+01 1.270e+02 2.800e+00
 3.060e+00 2.800e-01 2.290e+00 5.640e+00 1.040e+00 3.920e+00 1.065e+03]
<class 'numpy.ndarray'> <class 'numpy.ndarray'>

composed = torchvision.transforms.Compose([ToTensor(), MulTransform(2)])
dataset = WineDataset(transform=composed)
first_data = dataset[0]
features, labels = first_data
print(features)
print(type(features), type(labels))

tensor([2.0000e+00, 2.8460e+01, 3.4200e+00, 4.8600e+00, 3.1200e+01, 2.5400e+02,
        5.6000e+00, 6.1200e+00, 5.6000e-01, 4.5800e+00, 1.1280e+01, 2.0800e+00,
        7.8400e+00, 2.1300e+03])
<class 'torch.Tensor'> <class 'torch.Tensor'>