Python Executor._start方法代码示例

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test_with_data(s, a, b):
    ss = HTTPScheduler(s)
    ss.listen(0)

    e = Executor((s.ip, s.port), start=False)
    yield e._start()

    L = e.map(inc, [1, 2, 3])
    L2 = yield e._scatter(['Hello', 'world!'])
    yield _wait(L)

    client = AsyncHTTPClient()
    response = yield client.fetch('http://localhost:%s/memory-load.json' %
                                  ss.port)
    out = json.loads(response.body.decode())

    assert all(isinstance(v, int) for v in out.values())
    assert set(out) == {a.address_string, b.address_string}
    assert sum(out.values()) == sum(map(sys.getsizeof,
                                        [1, 2, 3, 'Hello', 'world!']))

    response = yield client.fetch('http://localhost:%s/memory-load-by-key.json'
                                  % ss.port)
    out = json.loads(response.body.decode())
    assert set(out) == {a.address_string, b.address_string}
    assert all(isinstance(v, dict) for v in out.values())
    assert all(k in {'inc', 'data'} for d in out.values() for k in d)
    assert all(isinstance(v, int) for d in out.values() for v in d.values())

    assert sum(v for d in out.values() for v in d.values()) == \
            sum(map(sys.getsizeof, [1, 2, 3, 'Hello', 'world!']))

    ss.stop()
    yield e._shutdown()

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test_read_text(s, a, b):
    pytest.importorskip('dask.bag')
    import dask.bag as db
    from dask.imperative import Value
    e = Executor((s.ip, s.port), start=False)
    yield e._start()

    b = read_text(test_bucket_name, 'test/accounts', lazy=True,
                  collection=True, anon=True)
    assert isinstance(b, db.Bag)
    yield gen.sleep(0.2)
    assert not s.tasks

    future = e.compute(b.filter(None).map(json.loads).pluck('amount').sum())
    result = yield future._result()

    assert result == (1 + 2 + 3 + 4 + 5 + 6 + 7 + 8) * 100

    text = read_text(test_bucket_name, 'test/accounts', lazy=True,
                     collection=False, anon=True)
    assert all(isinstance(v, Value) for v in text)

    text = read_text(test_bucket_name, 'test/accounts', lazy=False,
                     collection=False, anon=True)
    assert all(isinstance(v, Future) for v in text)

    yield e._shutdown()

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test__futures_to_collection(s, a, b):
    e = Executor((s.ip, s.port), start=False)
    yield e._start()

    remote_dfs = e.map(identity, dfs)
    ddf = yield _futures_to_collection(remote_dfs, divisions=True)
    ddf2 = yield _futures_to_dask_dataframe(remote_dfs, divisions=True)
    assert isinstance(ddf, dd.DataFrame)

    assert ddf.dask == ddf2.dask

    remote_arrays = e.map(np.arange, range(3, 5))
    x = yield _futures_to_collection(remote_arrays)
    y = yield _futures_to_dask_array(remote_arrays)

    assert type(x) == type(y)
    assert x.dask == y.dask

    remote_lists = yield e._scatter([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
    b = yield _futures_to_collection(remote_lists)
    c = yield _futures_to_dask_bag(remote_lists)

    assert type(b) == type(c)
    assert b.dask == b.dask

    yield e._shutdown()

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def dont_test_dataframes(s, a):  # slow
    pytest.importorskip('pandas')
    n = 3000000
    fn = '/tmp/test/file.csv'
    with make_hdfs() as hdfs:
        data = (b'name,amount,id\r\n' +
                b'Alice,100,1\r\nBob,200,2\r\n' * n)
        with hdfs.open(fn, 'w') as f:
            f.write(data)

        e = Executor((s.ip, s.port), start=False)
        yield e._start()

        futures = read_bytes(fn, hdfs=hdfs, delimiter=b'\r\n')
        assert len(futures) > 1

        def load(b, **kwargs):
            assert b
            from io import BytesIO
            import pandas as pd
            bio = BytesIO(b)
            return pd.read_csv(bio, **kwargs)

        dfs = e.map(load, futures, names=['name', 'amount', 'id'], skiprows=1)
        dfs2 = yield e._gather(dfs)
        assert sum(map(len, dfs2)) == n * 2 - 1

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test_avro(s, a, b):
    e = Executor((s.ip, s.port), start=False)
    yield e._start()

    avro_files = {'/tmp/test/1.avro': avro_bytes,
                  '/tmp/test/2.avro': avro_bytes}

    with make_hdfs() as hdfs:
        for k, v in avro_files.items():
            with hdfs.open(k, 'w') as f:
                f.write(v)

            assert hdfs.info(k)['size'] > 0

        L = yield _read_avro('/tmp/test/*.avro', lazy=False)
        assert isinstance(L, list)
        assert all(isinstance(x, Future) for x in L)

        results = yield e._gather(L)
        assert all(isinstance(r, list) for r in results)
        assert results[0][:5] == data[:5]
        assert results[-1][-5:] == data[-5:]

        L = yield _read_avro('/tmp/test/*.avro', lazy=True)
        assert isinstance(L, list)
        assert all(isinstance(x, Value) for x in L)

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
    def f(c, a, b):
        e = Executor((c.ip, c.port), start=False, loop=loop)
        yield e._start()

        x_dsk = {('x', i, j): np.random.random((3, 3)) for i in range(3)
                                                       for j in range(2)}
        y_dsk = {('y', i, j): np.random.random((3, 3)) for i in range(2)
                                                       for j in range(3)}
        x_futures = yield e._scatter(x_dsk)
        y_futures = yield e._scatter(y_dsk)

        dt = np.random.random(0).dtype
        x_local = da.Array(x_dsk, 'x', ((3, 3, 3), (3, 3)), dt)
        y_local = da.Array(y_dsk, 'y', ((3, 3), (3, 3, 3)), dt)

        x_remote = da.Array(x_futures, 'x', ((3, 3, 3), (3, 3)), dt)
        y_remote = da.Array(y_futures, 'y', ((3, 3), (3, 3, 3)), dt)

        exprs = [lambda x, y: x.T + y,
                 lambda x, y: x.mean() + y.mean(),
                 lambda x, y: x.dot(y).std(axis=0),
                 lambda x, y: x - x.mean(axis=1)[:, None]]

        for expr in exprs:
            local = expr(x_local, y_local)
            local_results = dask.get(local.dask, local._keys())
            local_result = da.Array._finalize(local, local_results)

            remote = expr(x_remote, y_remote)
            remote_results = yield e._get(remote.dask, remote._keys())
            remote_result = da.Array._finalize(remote, remote_results)

            assert np.all(local_result == remote_result)

        yield e._shutdown()

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test_lazy_values(s, a, b):
    with make_hdfs() as hdfs:
        data = b'a'

        for i in range(3):
            hdfs.mkdir('/tmp/test/data-%d' % i)
            for j in range(2):
                fn = '/tmp/test/data-%d/file-%d.csv' % (i, j)
                with hdfs.open(fn, 'w', repl=1) as f:
                    f.write(data)

        e = Executor((s.ip, s.port), start=False)
        yield e._start()

        values = read_bytes('/tmp/test/', hdfs=hdfs, lazy=True)
        assert all(isinstance(v, Value) for v in values)

        while not s.restrictions:
            yield gen.sleep(0.01)
        assert not s.dask

        results = e.compute(*values, sync=False)
        results = yield e._gather(results)
        assert len(results) == 6
        assert all(x == b'a' for x in results)

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test__dask_array_collections(s, a, b):
    import dask.array as da
    e = Executor((s.ip, s.port), start=False)
    yield e._start()

    x_dsk = {('x', i, j): np.random.random((3, 3)) for i in range(3)
                                                   for j in range(2)}
    y_dsk = {('y', i, j): np.random.random((3, 3)) for i in range(2)
                                                   for j in range(3)}
    x_futures = yield e._scatter(x_dsk)
    y_futures = yield e._scatter(y_dsk)

    dt = np.random.random(0).dtype
    x_local = da.Array(x_dsk, 'x', ((3, 3, 3), (3, 3)), dt)
    y_local = da.Array(y_dsk, 'y', ((3, 3), (3, 3, 3)), dt)

    x_remote = da.Array(x_futures, 'x', ((3, 3, 3), (3, 3)), dt)
    y_remote = da.Array(y_futures, 'y', ((3, 3), (3, 3, 3)), dt)

    exprs = [lambda x, y: x.T + y,
             lambda x, y: x.mean() + y.mean(),
             lambda x, y: x.dot(y).std(axis=0),
             lambda x, y: x - x.mean(axis=1)[:, None]]

    for expr in exprs:
        local = expr(x_local, y_local).compute(get=dask.get)

        remote = e.compute(expr(x_remote, y_remote))
        remote = yield remote._result()

        assert np.all(local == remote)

    yield e._shutdown()

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test__futures_to_dask_bag(s, a, b):
    import dask.bag as db
    e = Executor((s.ip, s.port), start=False)
    yield e._start()

    L = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
    futures = yield e._scatter(L)

    rb = yield _futures_to_dask_bag(futures)
    assert isinstance(rb, db.Bag)
    assert rb.npartitions == len(L)

    lb = db.from_sequence([1, 2, 3, 4, 5, 6, 7, 8, 9], npartitions=3)

    exprs = [lambda x: x.map(lambda x: x + 1).sum(),
             lambda x: x.filter(lambda x: x % 2)]

    for expr in exprs:
        local = expr(lb).compute(get=dask.get)
        remote = e.compute(expr(rb))
        remote = yield remote._result()

        assert local == remote

    yield e._shutdown()

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test_no_divisions(s, a, b):
    e = Executor((s.ip, s.port), start=False)
    yield e._start()
    dfs = e.map(tm.makeTimeDataFrame, range(5, 10))

    df = yield _futures_to_dask_dataframe(dfs)
    assert not df.known_divisions
    assert list(df.columns) == list(tm.makeTimeDataFrame(5).columns)

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test_read_bytes(s, a, b):
    e = Executor((s.ip, s.port), start=False)
    yield e._start()

    futures = read_bytes(test_bucket_name, prefix='test/', anon=True)
    assert len(futures) >= len(files)
    results = yield e._gather(futures)
    assert set(results).issuperset(set(files.values()))

    yield e._shutdown()

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test_multiple_executors_restart(s, a, b):
    e1 = Executor((s.ip, s.port), start=False)
    yield e1._start()
    e2 = Executor((s.ip, s.port), start=False)
    yield e2._start()

    x = e1.submit(inc, 1)
    y = e2.submit(inc, 2)
    xx = yield x._result()
    yy = yield y._result()
    assert xx == 2
    assert yy == 3

    yield e1._restart()

    assert x.cancelled()
    assert y.cancelled()

    yield e1._shutdown(fast=True)
    yield e2._shutdown(fast=True)

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test_read_csv_with_names(s, a, b):
    with make_hdfs() as hdfs:
        e = Executor((s.ip, s.port), start=False)
        yield e._start()

        with hdfs.open('/tmp/test/1.csv', 'wb') as f:
            f.write(b'name,amount,id\nAlice,100,1\nBob,200,2')

        df = yield _read_csv('/tmp/test/*.csv', names=['amount', 'name'],
                             lineterminator='\n', lazy=False)
        assert list(df.columns) == ['amount', 'name']

        yield e._shutdown()

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test_read_bytes_lazy(s, a, b):
    e = Executor((s.ip, s.port), start=False)
    yield e._start()

    values = read_bytes(test_bucket_name, 'test/', lazy=True, anon=True)
    assert all(isinstance(v, Value) for v in values)

    results = e.compute(values, sync=False)
    results = yield e._gather(results)

    assert set(results).issuperset(set(files.values()))

    yield e._shutdown()

# 需要导入模块: from distributed import Executor [as 别名]
# 或者: from distributed.Executor import _start [as 别名]
def test__futures_to_dask_dataframe(s, a, b):
    e = Executor((s.ip, s.port), start=False)
    yield e._start()

    remote_dfs = e.map(identity, dfs)
    ddf = yield _futures_to_dask_dataframe(remote_dfs, divisions=True,
            executor=e)

    assert isinstance(ddf, dd.DataFrame)
    assert ddf.divisions == (0, 30, 60, 80)
    expr = ddf.x.sum()
    result = yield e._get(expr.dask, expr._keys())
    assert result == [sum([df.x.sum() for df in dfs])]

    yield e._shutdown()