Python pool.MemmapingPool类代码示例

def test_pool_with_memmap_array_view(tmpdir):
    """Check that subprocess can access and update shared memory array"""
    assert_array_equal = np.testing.assert_array_equal

    # Fork the subprocess before allocating the objects to be passed
    pool_temp_folder = tmpdir.mkdir('pool').strpath
    p = MemmapingPool(10, max_nbytes=2, temp_folder=pool_temp_folder)
    try:

        filename = tmpdir.join('test.mmap').strpath
        a = np.memmap(filename, dtype=np.float32, shape=(3, 5), mode='w+')
        a.fill(1.0)

        # Create an ndarray view on the memmap instance
        a_view = np.asarray(a)
        assert not isinstance(a_view, np.memmap)
        assert has_shareable_memory(a_view)

        p.map(inplace_double, [(a_view, (i, j), 1.0)
                               for i in range(a.shape[0])
                               for j in range(a.shape[1])])

        # Both a and the a_view have been updated
        assert_array_equal(a, 2 * np.ones(a.shape))
        assert_array_equal(a_view, 2 * np.ones(a.shape))

        # Passing memmap array view to the pool should not trigger the
        # creation of new files on the FS
        assert os.listdir(pool_temp_folder) == []

    finally:
        p.terminate()
        del p

def test_memmaping_on_dev_shm():
    """Check that MemmapingPool uses /dev/shm when possible"""
    p = MemmapingPool(3, max_nbytes=10)
    try:
        # Check that the pool has correctly detected the presence of the
        # shared memory filesystem.
        pool_temp_folder = p._temp_folder
        folder_prefix = '/dev/shm/joblib_memmaping_pool_'
        assert pool_temp_folder.startswith(folder_prefix)
        assert os.path.exists(pool_temp_folder)

        # Try with a file larger than the memmap threshold of 10 bytes
        a = np.ones(100, dtype=np.float64)
        assert a.nbytes == 800
        p.map(id, [a] * 10)
        # a should have been memmaped to the pool temp folder: the joblib
        # pickling procedure generate one .pkl file:
        assert len(os.listdir(pool_temp_folder)) == 1

        # create a new array with content that is different from 'a' so that
        # it is mapped to a different file in the temporary folder of the
        # pool.
        b = np.ones(100, dtype=np.float64) * 2
        assert b.nbytes == 800
        p.map(id, [b] * 10)
        # A copy of both a and b are now stored in the shared memory folder
        assert len(os.listdir(pool_temp_folder)) == 2

    finally:
        # Cleanup open file descriptors
        p.terminate()
        del p

    # The temp folder is cleaned up upon pool termination
    assert not os.path.exists(pool_temp_folder)

def test_memmaping_on_dev_shm():
    """Check that MemmapingPool uses /dev/shm when possible"""
    p = MemmapingPool(3, max_nbytes=10)
    try:
        # Check that the pool has correctly detected the presence of the
        # shared memory filesystem.
        pool_temp_folder = p._temp_folder
        folder_prefix = '/dev/shm/joblib_memmaping_pool_'
        assert_true(pool_temp_folder.startswith(folder_prefix))
        assert_true(os.path.exists(pool_temp_folder))

        # Try with a file larger than the memmap threshold of 10 bytes
        a = np.ones(100, dtype=np.float64)
        assert_equal(a.nbytes, 800)
        p.map(id, [a] * 10)
        # a should have been memmaped to the pool temp folder: the joblib
        # pickling procedure generate a .pkl and a .npy file:
        assert_equal(len(os.listdir(pool_temp_folder)), 2)

        b = np.ones(100, dtype=np.float64)
        assert_equal(b.nbytes, 800)
        p.map(id, [b] * 10)
        # A copy of both a and b are not stored in the shared memory folder
        assert_equal(len(os.listdir(pool_temp_folder)), 4)

    finally:
        # Cleanup open file descriptors
        p.terminate()
        del p

    # The temp folder is cleaned up upon pool termination
    assert_false(os.path.exists(pool_temp_folder))

def test_memmaping_pool_for_large_arrays_in_return(tmpdir):
    """Check that large arrays are not copied in memory in return"""
    assert_array_equal = np.testing.assert_array_equal

    # Build an array reducers that automaticaly dump large array content
    # but check that the returned datastructure are regular arrays to avoid
    # passing a memmap array pointing to a pool controlled temp folder that
    # might be confusing to the user

    # The MemmapingPool user can always return numpy.memmap object explicitly
    # to avoid memory copy
    p = MemmapingPool(3, max_nbytes=10, temp_folder=tmpdir.strpath)
    try:
        res = p.apply_async(np.ones, args=(1000,))
        large = res.get()
        assert not has_shareable_memory(large)
        assert_array_equal(large, np.ones(1000))
    finally:
        p.terminate()
        del p

def test_memmaping_pool_for_large_arrays_disabled(tmpdir):
    """Check that large arrays memmaping can be disabled"""
    # Set max_nbytes to None to disable the auto memmaping feature
    p = MemmapingPool(3, max_nbytes=None, temp_folder=tmpdir.strpath)
    try:

        # Check that the tempfolder is empty
        assert os.listdir(tmpdir.strpath) == []

        # Try with a file largish than the memmap threshold of 40 bytes
        large = np.ones(100, dtype=np.float64)
        assert large.nbytes == 800
        p.map(check_array, [(large, i, 1.0) for i in range(large.shape[0])])

        # Check that the tempfolder is still empty
        assert os.listdir(tmpdir.strpath) == []

    finally:
        # Cleanup open file descriptors
        p.terminate()
        del p

def test_workaround_against_bad_memmap_with_copied_buffers(tmpdir):
    """Check that memmaps with a bad buffer are returned as regular arrays

    Unary operations and ufuncs on memmap instances return a new memmap
    instance with an in-memory buffer (probably a numpy bug).
    """
    assert_array_equal = np.testing.assert_array_equal

    p = MemmapingPool(3, max_nbytes=10, temp_folder=tmpdir.strpath)
    try:
        # Send a complex, large-ish view on a array that will be converted to
        # a memmap in the worker process
        a = np.asarray(np.arange(6000).reshape((1000, 2, 3)),
                       order='F')[:, :1, :]

        # Call a non-inplace multiply operation on the worker and memmap and
        # send it back to the parent.
        b = p.apply_async(_worker_multiply, args=(a, 3)).get()
        assert not has_shareable_memory(b)
        assert_array_equal(b, 3 * a)
    finally:
        p.terminate()
        del p

 def initialize(self, n_parallel):
     self.n_parallel = n_parallel
     if self.pool is not None:
         print("Warning: terminating existing pool")
         self.pool.terminate()
         self.queue.close()
         self.worker_queue.close()
         self.G = SharedGlobal()
     if n_parallel > 1:
         self.queue = mp.Queue()
         self.worker_queue = mp.Queue()
         self.pool = MemmapingPool(
             self.n_parallel,
             temp_folder="/tmp",
         )

def test_pool_with_memmap(tmpdir_path):
    """Check that subprocess can access and update shared memory memmap"""
    assert_array_equal = np.testing.assert_array_equal

    # Fork the subprocess before allocating the objects to be passed
    pool_temp_folder = os.path.join(tmpdir_path, 'pool')
    os.makedirs(pool_temp_folder)
    p = MemmapingPool(10, max_nbytes=2, temp_folder=pool_temp_folder)
    try:
        filename = os.path.join(tmpdir_path, 'test.mmap')
        a = np.memmap(filename, dtype=np.float32, shape=(3, 5), mode='w+')
        a.fill(1.0)

        p.map(inplace_double, [(a, (i, j), 1.0)
                               for i in range(a.shape[0])
                               for j in range(a.shape[1])])

        assert_array_equal(a, 2 * np.ones(a.shape))

        # Open a copy-on-write view on the previous data
        b = np.memmap(filename, dtype=np.float32, shape=(5, 3), mode='c')

        p.map(inplace_double, [(b, (i, j), 2.0)
                               for i in range(b.shape[0])
                               for j in range(b.shape[1])])

        # Passing memmap instances to the pool should not trigger the creation
        # of new files on the FS
        assert os.listdir(pool_temp_folder) == []

        # the original data is untouched
        assert_array_equal(a, 2 * np.ones(a.shape))
        assert_array_equal(b, 2 * np.ones(b.shape))

        # readonly maps can be read but not updated
        c = np.memmap(filename, dtype=np.float32, shape=(10,), mode='r',
                      offset=5 * 4)

        assert_raises(AssertionError, p.map, check_array,
                      [(c, i, 3.0) for i in range(c.shape[0])])

        # depending on the version of numpy one can either get a RuntimeError
        # or a ValueError
        assert_raises((RuntimeError, ValueError), p.map, inplace_double,
                      [(c, i, 2.0) for i in range(c.shape[0])])
    finally:
        # Clean all filehandlers held by the pool
        p.terminate()
        del p

def test_memmaping_pool_for_large_arrays():
    """Check that large arrays are not copied in memory"""
    assert_array_equal = np.testing.assert_array_equal

    # Check that the tempfolder is empty
    assert_equal(os.listdir(TEMP_FOLDER), [])

    # Build an array reducers that automaticaly dump large array content
    # to filesystem backed memmap instances to avoid memory explosion
    p = MemmapingPool(3, max_nbytes=40, temp_folder=TEMP_FOLDER)
    try:
        # The tempory folder for the pool is not provisioned in advance
        assert_equal(os.listdir(TEMP_FOLDER), [])
        assert_false(os.path.exists(p._temp_folder))

        small = np.ones(5, dtype=np.float32)
        assert_equal(small.nbytes, 20)
        p.map(check_array, [(small, i, 1.0) for i in range(small.shape[0])])

        # Memory has been copied, the pool filesystem folder is unused
        assert_equal(os.listdir(TEMP_FOLDER), [])

        # Try with a file larger than the memmap threshold of 40 bytes
        large = np.ones(100, dtype=np.float64)
        assert_equal(large.nbytes, 800)
        p.map(check_array, [(large, i, 1.0) for i in range(large.shape[0])])

        # The data has been dumped in a temp folder for subprocess to share it
        # without per-child memory copies
        assert_true(os.path.isdir(p._temp_folder))
        dumped_filenames = os.listdir(p._temp_folder)
        assert_equal(len(dumped_filenames), 2)

        # Check that memmory mapping is not triggered for arrays with
        # dtype='object'
        objects = np.array(['abc'] * 100, dtype='object')
        results = p.map(has_shareable_memory, [objects])
        assert_false(results[0])

    finally:
        # check FS garbage upon pool termination
        p.terminate()
        assert_false(os.path.exists(p._temp_folder))
        del p

class StatefulPool(object):
    def __init__(self):
        self.n_parallel = 1
        self.pool = None
        self.queue = None
        self.worker_queue = None
        self.G = SharedGlobal()

    def initialize(self, n_parallel):
        self.n_parallel = n_parallel
        if self.pool is not None:
            print("Warning: terminating existing pool")
            self.pool.terminate()
            self.queue.close()
            self.worker_queue.close()
            self.G = SharedGlobal()
        if n_parallel > 1:
            self.queue = mp.Queue()
            self.worker_queue = mp.Queue()
            self.pool = MemmapingPool(
                self.n_parallel,
                temp_folder="/tmp",
            )

    def run_each(self, runner, args_list=None):
        """
        Run the method on each worker process, and collect the result of execution.
        The runner method will receive 'G' as its first argument, followed by the arguments
        in the args_list, if any
        :return:
        """
        if args_list is None:
            args_list = [tuple()] * self.n_parallel
        assert len(args_list) == self.n_parallel
        if self.n_parallel > 1:
            #return [runner(self.G, *args_list[i]) for i in range(self.n_parallel)]
            results = self.pool.map_async(
                _worker_run_each, [(runner, args) for args in args_list]
            )
            for i in range(self.n_parallel):
                self.worker_queue.get()
            for i in range(self.n_parallel):
                self.queue.put(None)
            return results.get()
        return [runner(self.G, *args_list[0])]

    def run_map(self, runner, args_list):
        if self.n_parallel > 1:
            return self.pool.map(_worker_run_map, [(runner, args) for args in args_list])
        else:
            ret = []
            for args in args_list:
                ret.append(runner(self.G, *args))
            return ret

    def run_imap_unordered(self, runner, args_list):
        if self.n_parallel > 1:
            for x in self.pool.imap_unordered(_worker_run_map, [(runner, args) for args in args_list]):
                yield x
        else:
            for args in args_list:
                yield runner(self.G, *args)

    def run_collect(self, collect_once, threshold, args=None, show_prog_bar=True, multi_task=False):
        """
        Run the collector method using the worker pool. The collect_once method will receive 'G' as
        its first argument, followed by the provided args, if any. The method should return a pair of values.
        The first should be the object to be collected, and the second is the increment to be added.
        This will continue until the total increment reaches or exceeds the given threshold.

        Sample script:

        def collect_once(G):
            return 'a', 1

        stateful_pool.run_collect(collect_once, threshold=3) # => ['a', 'a', 'a']

        :param collector:
        :param threshold:
        :return:
        """
        if args is None:
            args = tuple()
        if self.pool and multi_task:
            manager = mp.Manager()
            counter = manager.Value('i', 0)
            lock = manager.RLock()

            inputs = [(collect_once, counter, lock, threshold, arg) for arg in args]
            results = self.pool.map_async(
                _worker_run_collect,
                inputs,
            )
            if show_prog_bar:
                pbar = ProgBarCounter(threshold)
            last_value = 0
            while True:
                time.sleep(0.1)
                with lock:
                    if counter.value >= threshold:
#.........这里部分代码省略.........

def get_score(data, labels, fold_pairs,
              name, model, param):
    """
    Function to get score for a classifier.

    Parameters
    ----------
    data: array-like
        Data from which to derive score.
    labels: array-like or list.
        Corresponding labels for each sample.
    fold_pairs: list of pairs of array-like
        A list of train/test indicies for each fold
        (Why can't we just use the KFold object?)
    name: string
        Name of classifier.
    model: WRITEME
    param: WRITEME
        Parameters for the classifier.
    """
    assert isinstance(name, str)
    logger.info("Classifying %s" % name)

    ksplit = len(fold_pairs)
    if name not in NAMES:
        raise ValueError("Classifier %s not supported. "
                         "Did you enter it properly?" % name)

    # Redefine the parameters to be used for RBF SVM (dependent on
    # training data)

    if True:  #better identifier here
        logger.info("Attempting to use grid search...")
        fScore = []
        for i, fold_pair in enumerate(fold_pairs):
            print ("Classifying a %s the %d-th out of %d folds..."
                   % (name, i+1, len(fold_pairs)))
            classifier = get_classifier(name, model, param, data[fold_pair[0], :])
            area = classify(data, labels, fold_pair, classifier)
            fScore.append(area)
    else:
        warnings.warn("Multiprocessing splits not tested yet.")
        pool = Pool(processes=min(ksplit, PROCESSORS))
        classify_func = lambda f : classify(
            data,
            labels,
            fold_pairs[f],
            classifier=get_classifier(
                name,
                model,
                param,
                data=data[fold_pairs[f][0], :]))
        fScore = pool.map(functools.partial(classify_func, xrange(ksplit)))
        pool.close()
        pool.join()

    return classifier, fScore