def _coverage_mapper(qresult, dx, filter):
filter, filter_args = unpack_callable(filter)
for rows in qresult:
assert len(rows)
if filter is not None:
rows = filter(rows, *filter_args)
lon, lat = list(rows.as_columns())[:2]
# Work around PS1 bugs:
tofix = (lon < 0) | (lon >= 360)
if np.any(tofix):
#print "Fixing RIGHT ASCENSION in cell ", rows.info.cell_id
lon[tofix] = np.fmod(np.fmod(lon[tofix], 360.) + 360., 360.)
tofix = (lat < -90) | (lat > 90)
if np.any(tofix):
print "Fixing DECLINATION in cell ", rows.info.cell_id
lat[lat < -90] = -90
lat[lat > 90] = 90
i = (lon / dx).astype(int)
j = ((90 - lat) / dx).astype(int)
assert len(lon)
assert len(lat)
assert len(i)
assert len(j)
(imin, imax, jmin, jmax) = (i.min(), i.max(), j.min(), j.max())
w = imax - imin + 1
h = jmax - jmin + 1
i -= imin
j -= jmin
if w <= 0 or h <= 0 or w > 10800 or h > 5400:
print w, h
print rows.info.cell_id
exit()
if False:
# Binning (method #1, straightforward but slow)
sky = np.zeros((w, h))
for (ii, jj) in izip(i, j):
sky[ii, jj] += 1
else:
# Binning (method #2, fast)
sky2 = np.zeros(w * h)
idx = np.bincount(j + i * h)
sky2[0:len(idx)] = idx
sky = sky2.reshape((w, h))
yield (sky, imin, jmin)
def _coverage_mapper(qresult, dx, filter): filter, filter_args = unpack_callable(filter) for rows in qresult: assert len(rows) if filter is not None: rows = filter(rows, *filter_args) lon, lat = list(rows.as_columns())[:2] # Work around PS1 bugs: tofix = (lon < 0) | (lon >= 360) if np.any(tofix): #print "Fixing RIGHT ASCENSION in cell ", rows.info.cell_id lon[tofix] = np.fmod(np.fmod(lon[tofix], 360.) + 360., 360.) tofix = (lat < -90) | (lat > 90) if np.any(tofix): print "Fixing DECLINATION in cell ", rows.info.cell_id lat[lat < -90] = -90 lat[lat > 90] = 90 i = (lon / dx).astype(int) j = ((90 - lat) / dx).astype(int) assert len(lon) assert len(lat) assert len(i) assert len(j) (imin, imax, jmin, jmax) = (i.min(), i.max(), j.min(), j.max()) w = imax - imin + 1 h = jmax - jmin + 1 i -= imin; j -= jmin if w <= 0 or h <= 0 or w > 10800 or h > 5400: print w, h print rows.info.cell_id exit() if False: # Binning (method #1, straightforward but slow) sky = np.zeros((w, h)) for (ii, jj) in izip(i, j): sky[ii, jj] += 1 else: # Binning (method #2, fast) sky2 = np.zeros(w*h) idx = np.bincount(j + i*h) sky2[0:len(idx)] = idx sky = sky2.reshape((w, h)) yield (sky, imin, jmin)
def map_reduce_chain(self, input, kernels, progress_callback=None):
""" A poor-man's map-reduce implementation.
Calls the mapper for each value in the <input> iterable.
The mapper shall return a list of key/value pairs as a
result. Once all mappers have run, reducers will be
called with a key, and a list of values associated with
that key, once for each key. The reducer's return
values are yielded to the user.
Input: Any iterable
Output: Iterable (generated)
Notes:
- mapper must return a dictionary of (key, value) pairs
- reducer must expect a (key, value) pair as the first
argument, where the value will be an iterable
"""
if progress_callback == None:
progress_callback = progress_default
progress_callback('mapreduce', 'begin', input, None, None)
if back_to_disk:
fp, prev_fp = None, None
mm, prev_mm = None, None
for i, K in enumerate(kernels):
K_fun, K_args = unpack_callable(K)
last_step = (i + 1 == len(kernels))
stage = where(i == 0, 'map', 'reduce')
if back_to_disk:
# Reinitialize the unique_hash->file_offset map
unique_objects = {}
# Insert picklers/unpicklers
if i != 0:
# Insert unpickler
K_fun, K_args = _reduce_from_pickle_jar, (prev_fp.name, K_fun, K_args)
if not last_step:
# Insert pickler
K_fun, K_args = _output_pickled_kv, (K_fun, K_args)
# Create a disk backing store for intermediate results
fp = tempfile.NamedTemporaryFile(mode='wb', prefix='mapresults-', dir=os.getenv('LSD_TEMPDIR'), suffix='.pkl', delete=True)
if use_mmap:
fd = fp.file.fileno()
os.ftruncate(fd, BUFSIZE)
mm = mmap.mmap(fd, 0)
else:
mm = fp
try:
# Call the distributed mappers
mresult = defaultdict(list)
for r in self.imap_unordered(input, K_fun, K_args, progress_callback=progress_callback, progress_callback_stage=stage):
if last_step:
# yield the final result
yield r
else:
(k, v) = r
if back_to_disk:
(hash, v) = v
if hash in unique_objects:
v = unique_objects[hash]
else:
# The output value has already been pickled (but not the key). Store the
# pickled value into the pickle jar, and keep the (key, offset) tuple.
offs = mm.tell()
mm.write(v)
assert len(v) == mm.tell() - offs
v = offs
unique_objects[hash] = offs
# Prepare for next reduction
mresult[k].append(v)
input = mresult.items()
except:
# In case of an exception, delete the temporary file so the kernel
# won't attempt to flush them to the disk
if back_to_disk:
if mm is not None and use_mmap:
mm.resize(1)
mm.close()
mm = None
if fp is not None:
os.ftruncate(fp.file.fileno(), 0)
fp.close()
fp = None
raise
finally:
if back_to_disk:
# Close/clear the intermediate result backing store from the previous step
# ensuring it's truncated first so it doesn't hit the disk if it hasn't
# already.
if prev_fp is not None:
if use_mmap:
prev_mm.resize(1)
prev_mm.close()
os.ftruncate(prev_fp.file.fileno(), 0)
prev_fp.close()
if fp is not None:
prev_fp, prev_mm = fp, mm
fp, mm = None, None
if progress_callback != None:
progress_callback('mapreduce', 'end', None, None, None)
def map_reduce_chain(self, input, kernels, progress_callback=None):
""" A poor-man's map-reduce implementation.
Calls the mapper for each value in the <input> iterable.
The mapper shall return a list of key/value pairs as a
result. Once all mappers have run, reducers will be
called with a key, and a list of values associated with
that key, once for each key. The reducer's return
values are yielded to the user.
Input: Any iterable
Output: Iterable (generated)
Notes:
- mapper must return a dictionary of (key, value) pairs
- reducer must expect a (key, value) pair as the first
argument, where the value will be an iterable
"""
if progress_callback == None:
progress_callback = progress_default
progress_callback('mapreduce', 'begin', input, None, None)
if back_to_disk:
fp, prev_fp = None, None
mm, prev_mm = None, None
for i, K in enumerate(kernels):
K_fun, K_args = unpack_callable(K)
last_step = (i + 1 == len(kernels))
stage = where(i == 0, 'map', 'reduce')
if back_to_disk:
# Reinitialize the unique_hash->file_offset map
unique_objects = {}
# Insert picklers/unpicklers
if i != 0:
# Insert unpickler
K_fun, K_args = _reduce_from_pickle_jar, (prev_fp.name,
K_fun, K_args)
if not last_step:
# Insert pickler
K_fun, K_args = _output_pickled_kv, (K_fun, K_args)
# Create a disk backing store for intermediate results
fp = tempfile.NamedTemporaryFile(
mode='wb',
prefix='mapresults-',
dir=os.getenv('LSD_TEMPDIR'),
suffix='.pkl',
delete=True)
if use_mmap:
fd = fp.file.fileno()
os.ftruncate(fd, BUFSIZE)
mm = mmap.mmap(fd, 0)
else:
mm = fp
try:
# Call the distributed mappers
mresult = defaultdict(list)
for r in self.imap_unordered(
input,
K_fun,
K_args,
progress_callback=progress_callback,
progress_callback_stage=stage):
if last_step:
# yield the final result
yield r
else:
(k, v) = r
if back_to_disk:
(hash, v) = v
if hash in unique_objects:
v = unique_objects[hash]
else:
# The output value has already been pickled (but not the key). Store the
# pickled value into the pickle jar, and keep the (key, offset) tuple.
offs = mm.tell()
mm.write(v)
assert len(v) == mm.tell() - offs
v = offs
unique_objects[hash] = offs
# Prepare for next reduction
mresult[k].append(v)
input = mresult.items()
except:
# In case of an exception, delete the temporary file so the kernel
# won't attempt to flush them to the disk
if back_to_disk:
if mm is not None and use_mmap:
mm.resize(1)
mm.close()
mm = None
if fp is not None:
os.ftruncate(fp.file.fileno(), 0)
fp.close()
fp = None
raise
finally:
if back_to_disk:
# Close/clear the intermediate result backing store from the previous step
# ensuring it's truncated first so it doesn't hit the disk if it hasn't
# already.
if prev_fp is not None:
if use_mmap:
prev_mm.resize(1)
prev_mm.close()
os.ftruncate(prev_fp.file.fileno(), 0)
prev_fp.close()
if fp is not None:
prev_fp, prev_mm = fp, mm
fp, mm = None, None
if progress_callback != None:
progress_callback('mapreduce', 'end', None, None, None)
