ray/streaming/python/examples/simple.py
Sven 60d4d5e1aa Remove future imports (#6724)
* Remove all __future__ imports from RLlib.

* Remove (object) again from tf_run_builder.py::TFRunBuilder.

* Fix 2xLINT warnings.

* Fix broken appo_policy import (must be appo_tf_policy)

* Remove future imports from all other ray files (not just RLlib).

* Remove future imports from all other ray files (not just RLlib).

* Remove future import blocks that contain `unicode_literals` as well.
Revert appo_tf_policy.py to appo_policy.py (belongs to another PR).

* Add two empty lines before Schedule class.

* Put back __future__ imports into determine_tests_to_run.py. Fails otherwise on a py2/print related error.
2020-01-09 00:15:48 -08:00

52 lines
1.4 KiB
Python

import argparse
import logging
import time
import ray
from ray.streaming.config import Config
from ray.streaming.streaming import Environment, Conf
logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)
parser = argparse.ArgumentParser()
parser.add_argument("--input-file", required=True, help="the input text file")
# Test functions
def splitter(line):
return line.split()
def filter_fn(word):
if "f" in word:
return True
return False
if __name__ == "__main__":
args = parser.parse_args()
ray.init(local_mode=False)
# A Ray streaming environment with the default configuration
env = Environment(config=Conf(channel_type=Config.NATIVE_CHANNEL))
# Stream represents the ouput of the filter and
# can be forked into other dataflows
stream = env.read_text_file(args.input_file) \
.shuffle() \
.flat_map(splitter) \
.set_parallelism(2) \
.filter(filter_fn) \
.set_parallelism(2) \
.inspect(lambda x: print("result", x)) # Prints the contents of the
# stream to stdout
start = time.time()
env_handle = env.execute()
ray.get(env_handle) # Stay alive until execution finishes
env.wait_finish()
end = time.time()
logger.info("Elapsed time: {} secs".format(end - start))
logger.debug("Output stream id: {}".format(stream.id))