I am trying to write a custom torch data loader so that large CSV files can be loaded incrementally (by chunks).
I have a rough idea of how to do that. However, I keep getting some PyTorch error that I do not know how to solve.
import numpy as np
import pandas as pd
import torch
from torch.utils.data import Dataset, DataLoader
# Create dummy csv data
nb_samples = 110
a = np.arange(nb_samples)
df = pd.DataFrame(a, columns=['data'])
df.to_csv('data.csv', index=False)
# Create Dataset
class CSVDataset(Dataset):
def __init__(self, path, chunksize, nb_samples):
self.path = path
self.chunksize = chunksize
self.len = nb_samples / self.chunksize
def __getitem__(self, index):
x = next(
pd.read_csv(
self.path,
skiprows=index * self.chunksize + 1, #+1, since we skip the header
chunksize=self.chunksize,
names=['data']))
x = torch.from_numpy(x.data.values)
return x
def __len__(self):
return self.len
dataset = CSVDataset('data.csv', chunksize=10, nb_samples=nb_samples)
loader = DataLoader(dataset, batch_size=10, num_workers=1, shuffle=False)
for batch_idx, data in enumerate(loader):
print('batch: {}\tdata: {}'.format(batch_idx, data))
I get 'float' object cannot be interpreted as an integer
error