Say I have two async generators:
async def get_rules():
while True:
yield 'rule=1'
asyncio.sleep(2)
async def get_snapshots():
while True:
yield 'snapshot=1'
asyncio.sleep(5)
I want to merge them into a single async generator that returns 2-tuples, with the latest value from both. Sort of combineLatest.
What is the best way to do this?
You might want to have a look at aiostream, especially stream.merge and stream.accumulate:
import asyncio
from itertools import count
from aiostream import stream
async def get_rules():
for x in count():
await asyncio.sleep(2)
yield 'rule', x
async def get_snapshots():
for x in count():
await asyncio.sleep(5)
yield 'snapshot', x
async def main():
xs = stream.merge(get_rules(), get_snapshots())
ys = stream.map(xs, lambda x: {x[0]: x[1]})
zs = stream.accumulate(ys, lambda x, e: {**x, **e}, {})
async with zs.stream() as streamer:
async for z in streamer:
print(z)
loop = asyncio.get_event_loop()
loop.run_until_complete(main())
loop.close()
Output:
{}
{'rule': 0}
{'rule': 1}
{'rule': 1, 'snapshot': 0}
{'rule': 2, 'snapshot': 0}
[...]
See the project page and the documentation for further information.
Disclaimer: I am the project maintainer.
I came up with this:
async def combine(**generators):
"""Given a bunch of async generators, merges the events from
all of them. Each should have a name, i.e. `foo=gen, bar=gen`.
"""
combined = Channel()
async def listen_and_forward(name, generator):
async for value in generator:
await combined.put({name: value})
for name, generator in generators.items():
asyncio.Task(listen_and_forward(name, generator))
async for item in combined:
yield item
async def combine_latest(**generators):
"""Like "combine", but always includes the latest value from
every generator.
"""
current = {}
async for value in combine(**generators):
current.update(value)
yield current
Call it like so:
async for item in combine_latest(rules=rulesgen, snap=snapgen):
print(item)
Output looks like this:
{'rules': 'rule-1'}
{'rules': 'rule-1', 'snap': 'snapshot-1'}
{'rules': 'rule-1', 'snap': 'snapshot-1'}
....
I am using aiochannel, but a normal asyncio.Queue should be fine, too.
Related
The requirement is to concurrently perform a time consuming operation for a list of data.
My current implementation:
async def expensive_routine(service) -> Optional[Any]:
await asyncio.sleep(5)
if service % 2:
return service
return None
async def producer():
# let's say
services = range(10)
#
for future in asyncio.as_completed(
[expensive_routine(service) for service in services]
):
result = await future
if result:
yield result
This is then used by:
async for x, y in producer():
print(f"I have my {x} and {y}")
the function expensive_routine returns Optional[Any]. I want to yield only the not None results.
Is there a way to perform this more efficiently or using a Comprehension ?
You mean if you can cram your nice little producer coroutine into a single-line generator expression abomination of unreadability? Why, yes!
import asyncio
import random
async def expensive_routine(service):
await asyncio.sleep(random.randint(0, 5))
if random.choice([0, 1]):
return service
return None
async def main():
async for x in (
res
for coro in asyncio.as_completed(
[expensive_routine(service) for service in range(10)]
)
if (res := (await coro)) # Python 3.8+
):
print(x)
asyncio.run(main())
Jokes aside, I don't see anything wrong with your code and I'm not sure what you mean by more efficient, since your speed here is dominated by the slow expensive_routine.
I wrote this small example because I think this is what you meant with a comprehension, but I would prefer your much more readable producer.
I have gone through the documentation of aiter and anext (New in version 3.10). But not understanding how to use them.
I have the following program:
import asyncio
async def get_range():
for i in range(10):
print(f"start {i}")
await asyncio.sleep(1)
print(f"end {i}")
yield i
class AIter:
def __init__(self, N):
self.i = 0
self.N = N
def __aiter__(self):
return self
async def __anext__(self):
i = self.i
print(f"start {i}")
await asyncio.sleep(1)
print(f"end {i}")
if i >= self.N:
raise StopAsyncIteration
self.i += 1
return i
async def main():
async for p in AIter(10):
print(f"finally {p}")
if __name__ == "__main__":
asyncio.run(main())
How can I use aiter and anext builtin here?
Like with the regular synchronous iter and next builtins, you rarely need to use the new builtins directly. The async for loop in main calls the __aiter__ and __anext__ methods of your class already. If that does all you want, you're home free.
You only need to explicitly use aiter and anext if you are writing code that interacts with an asynchronous iterator in some way not directly supported by a async for loop. For instance, here's an asynchronous generator that yields pairs of values from the iterable it's given:
async def pairwise(aiterable, default=None):
ait = aiter(aiterable) # get a reference to the iterator
async for x in ait:
yield x, await anext(ait, default) # get an extra value, yield a 2-tuple
If you loop on pairwise(AIter(10)) in your main function, you'll find that it now prints tuples of numbers, like finally (0, 1). Before each tuple, you'll see two sets of the begin and end lines printed by the iterator class, one for each value that ends up in the paired result.
Got an async iterable. Need a regular iterable.
asyc def aiter2iter(aiter):
l = []
async for chunk in aiter:
l.append(chunk)
return l
regular_iterable = await aiter2iter(my_async_iterable)
for chunk in regular_iterable:
print('Hooray! No async required here!')
Is this the way to go or am I reinventing the wheel?
Is there any way provided by Python to convert an async iterable to a regular iterable?
Also is what I wrote even correct? Did I not miss anything?
Your way works alright. I would also try unsync when working between async/sync functions.
Given
import time
import random
import asyncio
from unsync import unsync
# Sample async iterators
class AsyncIterator:
"""Yield random numbers."""
def __aiter__(self):
return self
async def __anext__(self):
await asyncio.sleep(0.1)
return random.randint(0, 10)
async def anumbers(n=10):
"""Yield the first `n` random numbers."""
i = 0
async for x in AsyncIterator():
if i == n:
return
yield x
i +=1
Code
Rather than awaiting and reiterating the result, we can just call the result():
#unsync
async def aiterate(aiter):
"""Return a list from an aiter object."""
return [x async for x in aiter]
aiterate(anumbers(5)).result()
# [8, 2, 5, 8, 9]
Details
Here's a description, from Python Byte's episode 73:
You just take any async function, and put an #unsync decorator. ... it will basically wrap it up and do all that asyncio initialization stuff ... then you can wait on the result, or not wait on the result, however you like. ... then if you put that on a regular function, not an async one, it'll cause it to run on a thread pool thread, on thread pool executor.
I'm trying to merge a bunch of asynchronous generators in Python 3.7 while still adding new async generators on iteration. I'm currently using aiostream to merge my generators:
from asyncio import sleep, run
from aiostream.stream import merge
async def go():
yield 0
await sleep(1)
yield 50
await sleep(1)
yield 100
async def main():
tasks = merge(go(), go(), go())
async for v in tasks:
print(v)
if __name__ == '__main__':
run(main())
However, I need to be able to continue to add to the running tasks once the loop has begun. Something like.
from asyncio import sleep, run
from aiostream.stream import merge
async def go():
yield 0
await sleep(1)
yield 50
await sleep(1)
yield 100
async def main():
tasks = merge(go(), go(), go())
async for v in tasks:
if v == 50:
tasks.merge(go())
print(v)
if __name__ == '__main__':
run(main())
The closest I've got to this is using the aiostream library but maybe this can also be written fairly neatly with just the native asyncio standard library.
Here is an implementation that should work efficiently even with a large number of async iterators:
class merge:
def __init__(self, *iterables):
self._iterables = list(iterables)
self._wakeup = asyncio.Event()
def _add_iters(self, next_futs, on_done):
for it in self._iterables:
it = it.__aiter__()
nfut = asyncio.ensure_future(it.__anext__())
nfut.add_done_callback(on_done)
next_futs[nfut] = it
del self._iterables[:]
return next_futs
async def __aiter__(self):
done = {}
next_futs = {}
def on_done(nfut):
done[nfut] = next_futs.pop(nfut)
self._wakeup.set()
self._add_iters(next_futs, on_done)
try:
while next_futs:
await self._wakeup.wait()
self._wakeup.clear()
for nfut, it in done.items():
try:
ret = nfut.result()
except StopAsyncIteration:
continue
self._iterables.append(it)
yield ret
done.clear()
if self._iterables:
self._add_iters(next_futs, on_done)
finally:
# if the generator exits with an exception, or if the caller stops
# iterating, make sure our callbacks are removed
for nfut in next_futs:
nfut.remove_done_callback(on_done)
def append_iter(self, new_iter):
self._iterables.append(new_iter)
self._wakeup.set()
The only change required for your sample code is that the method is named append_iter, not merge.
This can be done using stream.flatten with an asyncio queue to store the new generators.
import asyncio
from aiostream import stream, pipe
async def main():
queue = asyncio.Queue()
await queue.put(go())
await queue.put(go())
await queue.put(go())
xs = stream.call(queue.get)
ys = stream.cycle(xs)
zs = stream.flatten(ys, task_limit=5)
async with zs.stream() as streamer:
async for item in streamer:
if item == 50:
await queue.put(go())
print(item)
Notice that you may tune the number of tasks that can run at the same time using the task_limit argument. Also note that zs can be elegantly defined using the pipe syntax:
zs = stream.call(queue.get) | pipe.cycle() | pipe.flatten(task_limit=5)
Disclaimer: I am the project maintainer.
Is there a good way, or a well-supported library, for merging async iterators in python3?
The desired behavior is basically the same as that of merging observables in reactivex.
That is, in the normal case, if I'm merging two async iterator, I want the resulting async iterator to yield results chronologically. An error in one of the iterators should derail the merged iterator.
(Source: http://reactivex.io/documentation/operators/merge.html)
This is my best attempt, but it seems like something there might be a standard solution to:
async def drain(stream, q, sentinal=None):
try:
async for item in stream:
await q.put(item)
if sentinal:
await q.put(sentinal)
except BaseException as e:
await q.put(e)
async def merge(*streams):
q = asyncio.Queue()
sentinal = namedtuple("QueueClosed", ["truthy"])(True)
futures = {
asyncio.ensure_future(drain(stream, q, sentinal)) for stream in streams
}
remaining = len(streams)
while remaining > 0:
result = await q.get()
if result is sentinal:
remaining -= 1
continue
if isinstance(result, BaseException):
raise result
yield result
if __name__ == "__main__":
# Example: Should print:
# 1
# 2
# 3
# 4
loop = asyncio.get_event_loop()
async def gen():
yield 1
await asyncio.sleep(1.5)
yield 3
async def gen2():
await asyncio.sleep(1)
yield 2
await asyncio.sleep(1)
yield 4
async def go():
async for x in merge(gen(), gen2()):
print(x)
loop.run_until_complete(go())
You can use aiostream.stream.merge:
from aiostream import stream
async def go():
async for x in stream.merge(gen(), gen2()):
print(x)
More examples in the documentation and this answer.