python遍历迭代器自动链式处理数据的实例代码

from torch.utils.data import IterableDataset
# ...

import random

class Process(IterableDataset):
    def __init__(self, data, f):
        self.data = data
        # 绑定处理函数
        self.f = f   
    def __iter__(self):
        # for循环遍历时，返回一个当前环节处理的迭代器对象
        return self.f(iter(self.data)) 

a = ['a0', 'a1', 'a2', 'a3', 'a4', 'a5', 'a6', 'a7', 'a8', 'a9']
b = ['b0', 'b1', 'b2', 'b3', 'b4', 'b5', 'b6', 'b7', 'b8', 'b9']
c = ['c0', 'c1', 'c2', 'c3', 'c4', 'c5', 'c6', 'c7', 'c8', 'c9']
# data = [[j + str(i) for i in range(10)] for j in ['a','b', 'c'] ]
data = [a, b, c]
def travel(d):
    for i in d:
        # print('travel ', i)
        yield i
def deep(d):
    for arr in d:
        for item in arr:
            yield item

def shuffle(d, sf_size=5):
    buf = []
    for i in d:
        buf.append(i)
        if len(buf) >= sf_size:
            random.shuffle(buf)
            for j in buf:
                # print('shuffle', j)
                yield j
            buf = []
    for k in buf:
        yield k

def sort(d):
    buf = []
    for i in d:
        buf.append(i)
        if len(buf) >= 3:
            for i in buf:
                # print('sort', i)
                yield i
            buf = []
    for k in buf:
        yield k

def batch(d):
    buf = []
    for i in d:
        buf.append(i)
        if len(buf) >= 16:
            for i in buf:
                # print('batch', i)
                yield i
            buf = []
# 对训练数据进行的多个预处理步骤
dataset = Process(data, travel)
dataset = Process(dataset , deep)
dataset = Process(dataset , shuffle)
dataset = Process(dataset , sort)
train_dataset = Process(p, batch)

# 可在此处断点测试
for i in p:
    print(i, 'train')

# train_data_loader = DataLoader(train_dataset,num_workers=args.num_workers,prefetch_factor=args.prefetch)
# train(model , train_data_loader）

def manual_iter():
    with open('/etc/passwd') as f:
        try:
            while True:
                line = next(f)
                print(line, end='')
        except StopIteration:
            pass

with open('/etc/passwd') as f:
    while True:
        line = next(f)
        if line is None:
            break
    print(line, end='')

>>> items = [1, 2, 3]
>>> # Get the iterator
>>> it = iter(items) # Invokes items.__iter__()
>>> # Run the iterator
>>> next(it) # Invokes it.__next__()
1
>>> next(it)
2
>>> next(it)
3
>>> next(it)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
StopIteration
>>>