how to use asyncio to split streaming data and its working - python

have the following code to stream data and execute certain calculations
the codes are made async for the functions to run one after the another after certain breaks.
async def on_ticks gives the streaming data.
async def on_connect connects to the web socket.
async def works does the calculation of the streamed data.
although the code seems correct i get warning
RuntimeWarning: coroutine 'on_connect' was never awaited
self.on_connect(self, response
RuntimeWarning: Enable tracemalloc to get the object allocation traceback
where am i wrong.
'''
df=pd.DataFrame(data=None)
async def on_ticks(ws, ticks):
global df
for sc in ticks:
token=sc['instrument_token']
name=trd_portfolio[token]['name']
ltp=sc['last_price']
df1=pd.DataFrame([name,ltp]).T
df1.columns=['name','ltp']
df=df.append(df1,ignore_index=True)
await asyncio.sleep(5)
async def work():
global df
df['change']=df.groupby('name')['ltp'].pct_change()
g = df.groupby('name')['change']
g = g.agg(
pos_count=lambda s: s.gt(0).sum(),
neg_count=lambda s: s.lt(0).sum(),
net_count=lambda s: s.gt(0).sum()- s.lt(0).sum()).astype(int)
g=g.sort_values(by=['net_count'])
print(g)
await asyncio.sleep(1)
async def on_connect(ws, response):
ws.subscribe(inst_token)
ws.set_mode(ws.MODE_LTP,inst_token)
await asyncio.sleep(1)
kws.on_ticks = on_ticks
kws.on_connect = on_connect
kws.connect()
async def main():
await asyncio.gather(
on_connect(),
on_ticks(),
work()
)
asyncio.run(main())
'''

Related

After returning value from Async function, it takes 10-15 seconds to close the event loop

Here I am using async function for connecting the websocket,
async def getData(list):
async with websockets.connect(endpoint) as websocket:
result = await getConnection(websocket)
if result:
await websocket.send(str(strMessage))
response = await websocket.recv()
print('Returning from async function.....')
return response
return False
Function call :
def callingFunction():
result = asyncio.run(getData(list))
print(result)
here even if the print('Returning from async function.....') line executes, it takes 10-15 seconds to get back to the callingFunction() and print the result.
Thank You !!!

Correct destruction process for async code running in a thread

Below is (working) code for a generic websocket streamer.
It creates a daemon thread from which performs asyncio.run(...).
The asyncio code spawns 2 tasks, which never complete.
How to correctly destroy this object?
One of the tasks is executing a keepalive 'ping', so I can easily exit that loop using a flag. But the other is blocking on a message from the websocket.
import json
import aiohttp
import asyncio
import gzip
import asyncio
from threading import Thread
class WebSocket:
KEEPALIVE_INTERVAL_S = 10
def __init__(self, url, on_connect, on_msg):
self.url = url
self.on_connect = on_connect
self.on_msg = on_msg
self.streams = {}
self.worker_thread = Thread(name='WebSocket', target=self.thread_func, daemon=True).start()
def thread_func(self):
asyncio.run(self.aio_run())
async def aio_run(self):
async with aiohttp.ClientSession() as session:
self.ws = await session.ws_connect(self.url)
await self.on_connect(self)
async def ping():
while True:
print('KEEPALIVE')
await self.ws.ping()
await asyncio.sleep(WebSocket.KEEPALIVE_INTERVAL_S)
async def main_loop():
async for msg in self.ws:
def extract_data(msg):
if msg.type == aiohttp.WSMsgType.BINARY:
as_bytes = gzip.decompress(msg.data)
as_string = as_bytes.decode('utf8')
as_json = json.loads(as_string)
return as_json
elif msg.type == aiohttp.WSMsgType.TEXT:
return json.loads(msg.data)
elif msg.type == aiohttp.WSMsgType.ERROR:
print('⛔️ aiohttp.WSMsgType.ERROR')
return msg.data
data = extract_data(msg)
self.on_msg(data)
# May want this approach if we want to handle graceful shutdown
# W.task_ping = asyncio.create_task(ping())
# W.task_main_loop = asyncio.create_task(main_loop())
await asyncio.gather(
ping(),
main_loop()
)
async def send_json(self, J):
await self.ws.send_json(J)
I'd suggest the use of asyncio.run_coroutine_threadsafe instead of asyncio.run. It returns a concurrent.futures.Future object which you can cancel:
def thread_func(self):
self.future = asyncio.run_coroutine_threadsafe(
self.aio_run(),
asyncio.get_event_loop()
)
# somewhere else
self.future.cancel()
Another approach would be to make ping and main_loop a task, and cancel them when necessary:
# inside `aio_run`
self.task_ping = asyncio.create_task(ping())
self.main_loop_task = asyncio.create_task(main_loop())
await asyncio.gather(
self.task_ping,
self.main_loop_task
return_exceptions=True
)
# somewhere else
self.task_ping.cancel()
self.main_loop_task.cancel()
This doesn't change the fact that aio_run should also be called with asyncio.run_coroutine_threadsafe. asyncio.run should be used as a main entry point for asyncio programs and should be only called once.
I would like to suggest one more variation of the solution. When finishing coroutines (tasks), I prefer minimizing the use of cancel() (but not excluding), since sometimes it can make it difficult to debug business logic (keep in mind that asyncio.CancelledError does not inherit from an Exception).
In your case, the code might look like this(only changes):
class WebSocket:
KEEPALIVE_INTERVAL_S = 10
def __init__(self, url, on_connect, on_msg):
# ...
self.worker_thread = Thread(name='WebSocket', target=self.thread_func)
self.worker_thread.start()
async def aio_run(self):
self._loop = asyncio.get_event_loop()
# ...
self._ping_task = asyncio.create_task(ping())
self._main_task = asyncio.create_task(main_loop())
await asyncio.gather(
self._ping_task,
self._main_task,
return_exceptions=True
)
# ...
async def stop_ping(self):
self._ping_task.cancel()
try:
await self._ping_task
except asyncio.CancelledError:
pass
async def _stop(self):
# wait ping end before socket closing
await self.stop_ping()
# lead to correct exit from `async for msg in self.ws`
await self.ws.close()
def stop(self):
# wait stopping ping and closing socket
asyncio.run_coroutine_threadsafe(
self._stop(), self._loop
).result()
self.worker_thread.join() # wait thread finish

How to run async coroutines from init, wait until it is complete

I am connecting to aioredis from __init__ (I do not want to move it out since this means I have to some extra major changes). How can I wait for aioredis connection task in below __init__ example code and have it print self.sub and self.pub object? Currently it gives an error saying
abc.py:42> exception=AttributeError("'S' object has no attribute
'pub'")
I do see redis connections created and coro create_connetion done.
Is there a way to call blocking asyncio calls from __init__. If I replace asyncio.wait with asyncio.run_until_complete I get an error that roughly says
loop is already running.
asyncio.gather is
import sys, json
from addict import Dict
import asyncio
import aioredis
class S():
def __init__(self, opts):
print(asyncio.Task.all_tasks())
task = asyncio.wait(asyncio.create_task(self.create_connection()), return_when="ALL_COMPLETED")
print(asyncio.Task.all_tasks())
print(task)
print(self.pub, self.sub)
async def receive_message(self, channel):
while await channel.wait_message():
message = await channel.get_json()
await asyncio.create_task(self.callback_loop(Dict(json.loads(message))))
async def run_s(self):
asyncio.create_task(self.listen())
async def callback_loop(msg):
print(msg)
self.callback_loop = callback_loop
async def create_connection(self):
self.pub = await aioredis.create_redis("redis://c8:7070/0", password="abc")
self.sub = await aioredis.create_redis("redis://c8:7070/0", password="abc")
self.db = await aioredis.create_redis("redis://c8:7070/0", password="abc")
self.listener = await self.sub.subscribe(f"abc")
async def listen(self):
self.tsk = asyncio.ensure_future(self.receive_message(self.listener[0]))
await self.tsk
async def periodic(): #test function to show current tasks
number = 5
while True:
await asyncio.sleep(number)
print(asyncio.Task.all_tasks())
async def main(opts):
loop.create_task(periodic())
s = S(opts)
print(s.pub, s.sub)
loop.create_task(s.run_s())
if __name__ == "__main__":
loop = asyncio.get_event_loop()
main_task = loop.create_task(main(sys.argv[1:]))
loop.run_forever() #I DONT WANT TO MOVE THIS UNLESS IT IS NECESSARY
I think what you want to do is to make sure the function create_connections runs to completion BEFORE the S constructor. A way to do that is to rearrange your code a little bit. Move the create_connections function outside the class:
async def create_connection():
pub = await aioredis.create_redis("redis://c8:7070/0", password="abc")
sub = await aioredis.create_redis("redis://c8:7070/0", password="abc")
db = await aioredis.create_redis("redis://c8:7070/0", password="abc")
listener = await self.sub.subscribe(f"abc")
return pub, sub, db, listener
Now await that function before constructing S. So your main function becomes:
async def main(opts):
loop.create_task(periodic())
x = await create_connections()
s = S(opts, x) # pass the result of create_connections to S
print(s.pub, s.sub)
loop.create_task(s.run_s())
Now modify the S constructor to receive the objects created:
def __init__(self, opts, x):
self.pub, self.sub, self.db, self.listener = x
I'm not sure what you're trying to do with the return_when argument and the call to asyncio.wait. The create_connections function doesn't launch a set of parallel tasks, but rather awaits each of the calls before moving on to the next one. Perhaps you could improve performance by running the four calls in parallel but that's a different question.

Manage asyncio coroutines in dict

I want to manage some coroutines in a dict, while running a main coroutine.
Specifically I want to start endless coroutines, put the handler of them in a dict and cancel them via a dict call again. In my example I want to start 4 Coroutines and they shall cancel one by one again with the coroutine doomsday. I'm using Python 3.6.
import asyncio
import traceback
async def add_to_handler(node, func):
func_handler[node] = asyncio.ensure_future(func, loop=loop)
return
async def test_func1():
while True:
print("1 - HeNlO")
await asyncio.sleep(1)
async def test_func2():
while True:
print("2 - TestFunc2")
await asyncio.sleep(2)
async def test_func3():
while True:
print("3 - Tukan")
await asyncio.sleep(3)
async def test_func4():
while True:
print("4 - Do Coro!")
await asyncio.sleep(4)
async def doomsday():
# Cancel coroutine every 10 seconds
print("launch doomsday")
for i in range(len(func_handler)):
await asyncio.sleep(10)
print("start cancelling with {}".format(i))
func_handler[str(i + 1)].cancel()
return
async def main():
await add_to_handler("1", test_func1)
await add_to_handler("2", test_func2)
await add_to_handler("3", test_func3)
await add_to_handler("4", test_func4)
await doomsday()
while True:
print("z..z..Z..Z...Z")
print(func_handler)
await asyncio.sleep(5)
func_handler = {}
loop = asyncio.get_event_loop()
try:
loop.run_until_complete(main())
except KeyboardInterrupt:
print("stop loop")
loop.close()
I tried it with the .call_latermethod of AbstractEventLoop instead of an endless while loop, but it still doesn't want to work and it seems, that my coroutines are seen as function, but I don't know why. Where is my fault?
try to change this function:
async def add_to_handler(node, func):
func_handler[node] = asyncio.ensure_future(func(), loop=loop)
return None
pay attention on asyncio.ensure_future(func(),loop=loop)

Making async calls from an async library?

The toy script shows an application using a class that is dependent on an implementation that is not asyncio-aware, and obviously doesn't work.
How would the fetch method of MyFetcher be implemented, using the asyncio-aware client, while still maintaining the contract with the _internal_validator method of FetcherApp? To be very clear, FetcherApp and AbstractFetcher cannot be modified.
To use async fetch_data function inside fetch both fetch and is_fetched_data_valid functions should be async too. You can change them in child classes without modify parent:
import asyncio
class AsyncFetcherApp(FetcherApp):
async def is_fetched_data_valid(self): # async here
data = await self.fetcher_implementation.fetch() # await here
return self._internal_validator(data)
class AsyncMyFetcher(AbstractFetcher):
def __init__(self, client):
super().__init__()
self.client = client
async def fetch(self): # async here
result = await self.client.fetch_data() # await here
return result
class AsyncClient:
async def fetch_data(self):
await asyncio.sleep(1) # Just to sure it works
return 1
async def main():
async_client = AsyncClient()
my_fetcher = AsyncMyFetcher(async_client)
fetcherApp = AsyncFetcherApp(my_fetcher)
# ...
is_valid = await fetcherApp.is_fetched_data_valid() # await here
print(repr(is_valid))
if __name__ == "__main__":
loop = asyncio.get_event_loop()
loop.run_until_complete(main())

Categories