def test_get_traces_intern_traceback(self):
# dummy wrappers to get more useful and identical frames in the traceback
def allocate_bytes2(size):
return allocate_bytes(size)
def allocate_bytes3(size):
return allocate_bytes2(size)
def allocate_bytes4(size):
return allocate_bytes3(size)
# Ensure that two identical tracebacks are not duplicated
tracemalloc.stop()
tracemalloc.start(4)
obj_size = 123
obj1, obj1_traceback = allocate_bytes4(obj_size)
obj2, obj2_traceback = allocate_bytes4(obj_size)
traces = tracemalloc._get_traces()
trace1 = self.find_trace(traces, obj1_traceback)
trace2 = self.find_trace(traces, obj2_traceback)
size1, traceback1 = trace1
size2, traceback2 = trace2
self.assertEqual(traceback2, traceback1)
self.assertIs(traceback2, traceback1)
def test_stop_track(self):
tracemalloc.start()
tracemalloc.stop()
with self.assertRaises(RuntimeError):
self.track()
self.assertIsNone(self.get_traceback())
def test_get_traced_memory(self):
# Python allocates some internals objects, so the test must tolerate
# a small difference between the expected size and the real usage
max_error = 2048
# allocate one object
obj_size = 1024 * 1024
tracemalloc.clear_traces()
obj, obj_traceback = allocate_bytes(obj_size)
size, peak_size = tracemalloc.get_traced_memory()
self.assertGreaterEqual(size, obj_size)
self.assertGreaterEqual(peak_size, size)
self.assertLessEqual(size - obj_size, max_error)
self.assertLessEqual(peak_size - size, max_error)
# destroy the object
obj = None
size2, peak_size2 = tracemalloc.get_traced_memory()
self.assertLess(size2, size)
self.assertGreaterEqual(size - size2, obj_size - max_error)
self.assertGreaterEqual(peak_size2, peak_size)
# clear_traces() must reset traced memory counters
tracemalloc.clear_traces()
self.assertEqual(tracemalloc.get_traced_memory(), (0, 0))
# allocate another object
obj, obj_traceback = allocate_bytes(obj_size)
size, peak_size = tracemalloc.get_traced_memory()
self.assertGreaterEqual(size, obj_size)
# stop() also resets traced memory counters
tracemalloc.stop()
self.assertEqual(tracemalloc.get_traced_memory(), (0, 0))
def test_stop_untrack(self):
tracemalloc.start()
self.track()
tracemalloc.stop()
with self.assertRaises(RuntimeError):
self.untrack()
def stop():
""" Stops application memory profiling """
logging.debug("Stopping memory profiling")
with _lock:
if is_running():
snapshot(_make_snapshot_name)
tracemalloc.clear_traces()
tracemalloc.stop()
def stop(self):
if not self.profiling:
return
self.profiling = False
tracemalloc.stop()
self.timer.stop()
self.trace_stream.close()
self.trace_stream = None
self.timer = None
def _stop_memory_tracing():
try:
import tracemalloc
except ImportError:
return
snapshot = tracemalloc.take_snapshot()
_log_memory_top(snapshot)
tracemalloc.stop()
def measure_memory_diff(self, func):
import tracemalloc
tracemalloc.start()
try:
before = tracemalloc.take_snapshot()
# Keep the result and only delete it after taking a snapshot
res = func()
after = tracemalloc.take_snapshot()
del res
return after.compare_to(before, 'lineno')
finally:
tracemalloc.stop()
def exec_with_profiler(filename, profiler, backend):
choose_backend(backend)
if _backend == 'tracemalloc' and has_tracemalloc:
tracemalloc.start()
builtins.__dict__['profile'] = profiler
# shadow the profile decorator defined above
ns = dict(_CLEAN_GLOBALS, profile=profiler)
try:
with open(filename) as f:
exec(compile(f.read(), filename, 'exec'), ns, ns)
finally:
if has_tracemalloc and tracemalloc.is_tracing():
tracemalloc.stop()
def stop_profiler(self):
self.agent.log('Deactivating memory allocation profiler.')
with self.profile_lock:
if self.overhead_monitor:
self.overhead_monitor.cancel()
self.overhead_monitor = None
if tracemalloc.is_tracing():
snapshot = tracemalloc.take_snapshot()
self.agent.log('Allocation profiler memory overhead {0} bytes'.format(tracemalloc.get_tracemalloc_memory()))
tracemalloc.stop()
self.process_snapshot(snapshot, time.time() - self.start_ts)
def exec_with_profiler(filename, profiler, backend, passed_args=[]):
from runpy import run_module
builtins.__dict__['profile'] = profiler
ns = dict(_CLEAN_GLOBALS, profile=profiler)
_backend = choose_backend(backend)
sys.argv = [filename] + passed_args
try:
if _backend == 'tracemalloc' and has_tracemalloc:
tracemalloc.start()
with open(filename) as f:
exec(compile(f.read(), filename, 'exec'), ns, ns)
finally:
if has_tracemalloc and tracemalloc.is_tracing():
tracemalloc.stop()
def test_get_traces(self):
tracemalloc.clear_traces()
obj_size = 12345
obj, obj_traceback = allocate_bytes(obj_size)
traces = tracemalloc._get_traces()
trace = self.find_trace(traces, obj_traceback)
self.assertIsInstance(trace, tuple)
domain, size, traceback = trace
self.assertEqual(size, obj_size)
self.assertEqual(traceback, obj_traceback._frames)
tracemalloc.stop()
self.assertEqual(tracemalloc._get_traces(), [])
def run_module_with_profiler(module, profiler, backend, passed_args=[]):
from runpy import run_module
builtins.__dict__['profile'] = profiler
ns = dict(_CLEAN_GLOBALS, profile=profiler)
_backend = choose_backend(backend)
sys.argv = [module] + passed_args
if PY2:
run_module(module, run_name="__main__", init_globals=ns)
else:
if _backend == 'tracemalloc' and has_tracemalloc:
tracemalloc.start()
try:
run_module(module, run_name="__main__", init_globals=ns)
finally:
if has_tracemalloc and tracemalloc.is_tracing():
tracemalloc.stop()
def test_does_not_leak_too_much(self):
tracemalloc.start()
gc.collect()
series = []
snapshot1 = tracemalloc.take_snapshot()
for i in range(100):
try:
execute_script(self.feature, self)
except Exception:
pass
gc.collect()
snapshot2 = tracemalloc.take_snapshot()
stats = snapshot2.compare_to(snapshot1, "lineno")
snapshot1 = snapshot2
series.append(sum(stat.size / 1024 for stat in stats))
tracemalloc.stop()
series = series[1:] # ignore first run, which creates regex
cv = statistics.stdev(series) / statistics.mean(series)
assert cv < 0.1
def test_snapshot(self):
obj, source = allocate_bytes(123)
# take a snapshot
snapshot = tracemalloc.take_snapshot()
# write on disk
snapshot.dump(support.TESTFN)
self.addCleanup(support.unlink, support.TESTFN)
# load from disk
snapshot2 = tracemalloc.Snapshot.load(support.TESTFN)
self.assertEqual(snapshot2.traces, snapshot.traces)
# tracemalloc must be tracing memory allocations to take a snapshot
tracemalloc.stop()
with self.assertRaises(RuntimeError) as cm:
tracemalloc.take_snapshot()
self.assertEqual(str(cm.exception),
"the tracemalloc module must be tracing memory "
"allocations to take a snapshot")
def compute(self):
args = self.args
if args.track_memory:
if MS_WINDOWS:
from perf._win_memory import get_peak_pagefile_usage
else:
from perf._memory import PeakMemoryUsageThread
mem_thread = PeakMemoryUsageThread()
mem_thread.start()
if args.tracemalloc:
import tracemalloc
tracemalloc.start()
WorkerTask.compute(self)
if args.tracemalloc:
traced_peak = tracemalloc.get_traced_memory()[1]
tracemalloc.stop()
if not traced_peak:
raise RuntimeError("tracemalloc didn't trace any Python "
"memory allocation")
# drop timings, replace them with the memory peak
self._set_memory_value(traced_peak)
if args.track_memory:
if MS_WINDOWS:
mem_peak = get_peak_pagefile_usage()
else:
mem_thread.stop()
mem_peak = mem_thread.peak_usage
if not mem_peak:
raise RuntimeError("failed to get the memory peak usage")
# drop timings, replace them with the memory peak
self._set_memory_value(mem_peak)
def pyfaidx_fasta(n):
print('timings for pyfaidx.Fasta')
ti = []
tf = []
for _ in range(n):
t = time.time()
f = pyfaidx.Fasta(fa_file.name)
ti.append(time.time() - t)
t = time.time()
read_dict(f, headers)
tf.append(time.time() - t)
os.remove(index)
# profile memory usage and report timings
tracemalloc.start()
f = pyfaidx.Fasta(fa_file.name)
read_dict(f, headers)
os.remove(index)
print(tracemalloc.get_traced_memory())
print(mean(ti))
print(mean(tf)/nreads/10*1000*1000)
tracemalloc.stop()
def show(filename=None):
global before_objects
gc.collect()
after_objects = gc.get_objects()
frame = sys._getframe()
globals_ = globals()
num_leaks = 0
before_id_set = set(map(id, before_objects))
if filename is not None:
f = open(filename, 'w')
else:
f = sys.stderr
for obj in after_objects:
if id(obj) not in before_id_set:
if obj in (before_objects, frame):
continue
num_leaks += 1
print("Leak: id=0x{:x} type={} {}".format(id(obj), type(obj), _get_detail(obj)), file=f)
tb = tracemalloc.get_object_traceback(obj)
if tb is None:
print("Traceback: None", file=f)
else:
print("Traceback:", file=f)
print("\n".join(tb.format(MAX_FRAMES)), file=f)
print(file=f)
print("Referrers:", file=f)
for ref in gc.get_referrers(obj):
if ref in (after_objects, before_objects, frame, globals_):
continue
print(" id=0x{:x} type={} {}".format(id(ref), type(ref), _get_detail(ref)), file=f)
print(" traceback: {}".format(tracemalloc.get_object_traceback(ref)), file=f)
print(file=f)
print(file=f)
print("Total leaks: {}".format(num_leaks), file=f)
if filename is not None:
f.close()
tracemalloc.stop()
gc.enable()
def pyfaidx_bgzf_faidx(n):
print('timings for pyfaidx.Faidx with bgzf compression')
ti = []
tf = []
for _ in range(n):
t = time.time()
f = pyfaidx.Faidx(fa_file.name + '.gz')
ti.append(time.time() - t)
t = time.time()
read_faidx(f, headers)
tf.append(time.time() - t)
os.remove(index)
# profile memory usage and report timings
tracemalloc.start()
f = pyfaidx.Faidx(fa_file.name + '.gz')
read_faidx(f, headers)
os.remove(index)
print(tracemalloc.get_traced_memory())
print(mean(ti))
print(mean(tf)/nreads/10*1000*1000)
tracemalloc.stop()
def bench(func, trace=True, nframe=1):
if trace:
tracemalloc.stop()
tracemalloc.start(nframe)
gc.collect()
best = None
for run in range(BENCH_RUNS):
start = time.monotonic()
func()
dt = time.monotonic() - start
if best is not None:
best = min(best, dt)
else:
best = dt
if trace:
mem = tracemalloc.get_tracemalloc_memory()
ntrace = len(tracemalloc.take_snapshot().traces)
tracemalloc.stop()
else:
mem = ntrace = None
gc.collect()
return best * 1e3, mem, ntrace
def fastahack_fetch(n):
print('timings for fastahack.FastaHack')
ti = []
tf = []
for _ in range(n):
t = time.time()
f = fastahack.FastaHack(fa_file.name)
ti.append(time.time() - t)
t = time.time()
read_fastahack(f, headers)
tf.append(time.time() - t)
os.remove(index)
# profile memory usage and report timings
tracemalloc.start()
f = fastahack.FastaHack(fa_file.name)
read_fastahack(f, headers)
os.remove(index)
print(tracemalloc.get_traced_memory())
print(mean(ti))
print(mean(tf)/nreads/10*1000*1000)
tracemalloc.stop()
def seqio_read(n):
print('timings for Bio.SeqIO')
ti = []
tf = []
for _ in range(n):
t = time.time()
fh = open(fa_file.name)
f = SeqIO.to_dict(SeqIO.parse(fh, "fasta"))
ti.append(time.time() - t)
t = time.time()
read_dict(f, headers)
tf.append(time.time() - t)
fh.close()
# profile memory usage and report timings
tracemalloc.start()
fh = open(fa_file.name)
f = SeqIO.to_dict(SeqIO.parse(fh, "fasta"))
read_dict(f, headers)
fh.close()
print(tracemalloc.get_traced_memory())
print(mean(ti))
print(mean(tf)/nreads/100*1000*1000)
tracemalloc.stop()
def pyfasta_fseek(n):
print('timings for pyfasta.Fasta (fseek)')
ti = []
tf = []
for _ in range(n):
t = time.time()
f = pyfasta.Fasta(fa_file.name, record_class=pyfasta.FastaRecord)
ti.append(time.time() - t)
t = time.time()
read_dict(f, headers)
tf.append(time.time() - t)
os.remove(fa_file.name + '.flat')
os.remove(fa_file.name + '.gdx')
# profile memory usage and report timings
tracemalloc.start()
f = pyfasta.Fasta(fa_file.name, record_class=pyfasta.FastaRecord)
read_dict(f, headers)
os.remove(fa_file.name + '.flat')
os.remove(fa_file.name + '.gdx')
print(tracemalloc.get_traced_memory())
print(mean(ti))
print(mean(tf)/nreads/10*1000*1000)
tracemalloc.stop()
def test_set_traceback_limit(self):
obj_size = 10
tracemalloc.stop()
self.assertRaises(ValueError, tracemalloc.start, -1)
tracemalloc.stop()
tracemalloc.start(10)
obj2, obj2_traceback = allocate_bytes(obj_size)
traceback = tracemalloc.get_object_traceback(obj2)
self.assertEqual(len(traceback), 10)
self.assertEqual(traceback, obj2_traceback)
tracemalloc.stop()
tracemalloc.start(1)
obj, obj_traceback = allocate_bytes(obj_size)
traceback = tracemalloc.get_object_traceback(obj)
self.assertEqual(len(traceback), 1)
self.assertEqual(traceback, obj_traceback)
def __del__(self):
tracemalloc.stop()
async def app_after_serving():
tracemalloc.stop()
def search_summary(selected_search, puzzle, round_times):
print('')
print(f'***** {selected_search.__name__} *****')
print('Search Algorithm in Progress ...\n')
export_text = f'\n***** {selected_search.__name__} *****\n'
start_time = time.time() # start timer
tracemalloc.start() # start memory tracking
initial_mem, _ = tracemalloc.get_traced_memory()
actions = selected_search(puzzle) # perform search algorithm
current_mem, peak_mem = tracemalloc.get_traced_memory()
tracemalloc.stop() # stop memory tracking
end_time = time.time() # end timer
time_taken = end_time - start_time
time_taken = round(time_taken, 2)
# Convert to MiB
initial_mem = round(initial_mem / (1024 ** 2), 6)
current_mem = round(current_mem / (1024 ** 2), 6)
peak_mem = round(peak_mem / (1024 ** 2), 6)
print('Done.\n')
if actions is not None:
if len(actions) < 30:
print(f'Path -------------------------------> {actions}')
export_text += f'Path -------------------------------> {actions}\n'
else:
print(
f'Path -------------------------------> {actions[0:29]} ...too long, omit rest actions')
export_text += f'Path -------------------------------> {actions[0:29]} ...too long, omit rest actions\n'
print(
f'Path length --------------------------------> {get_cost_of_actions(actions)} actions')
export_text += f'Path length --------------------------------> {get_cost_of_actions(actions)} actions\n'
print(
f'Time taken in seconds ----------------------> {time_taken} seconds')
export_text += f'Time taken in seconds ----------------------> {time_taken} seconds\n'
print(
f'Expanded nodes -----------------------------> {puzzle.expanded_nodes} nodes')
export_text += f'Expanded nodes -----------------------------> {puzzle.expanded_nodes} nodes\n'
print(
f'Initial memory is --------------------------> {initial_mem} MiB')
export_text += f'Initial memory is --------------------------> {initial_mem} MiB\n'
print(
f'Current memory is --------------------------> {current_mem} MiB')
export_text += f'Current memory is --------------------------> {current_mem} MiB\n'
print(
f'Peak memory is -----------------------------> {peak_mem} MiB (=Memory Usage)')
export_text += f'Peak memory is -----------------------------> {peak_mem} MiB (=Memory Usage)\n'
print('Preparing Solution for Animation ...\n')
solution=puzzle.get_solution_as_list_of_states(actions)
print('Done.\n')
# Export the collected data to .txt file for better user reading
fileName = f'algo_summary_report{round_times}.txt'
export_file = open('result/'+fileName, 'a')
export_file.write(export_text)
export_file.close()
return solution
def run_evodevo(nfactors=5,
Ndown=3,
warp=False,
save=True,
warping_ref="Mouse",
sample_seed=4891,
seed=2020,
species=["Mouse", "Rabbit", "Rat", "Human", "Opossum"],
views=["Brain", "Cerebellum", "Heart", "Liver", "Testis"],
model_groups=True,
nm=None,
tissue_as_sample=False):
if tissue_as_sample:
assert not warp, "Need to adapt warping reference if tissues are treated as groups"
# specify data directory of normalized gene expression data
if species == ["Mouse", "Rabbit", "Rat"] and not warp:
nmtmp = "MRRab"
datadir = "data/input_data/MRRab_matched/"
elif warp:
nmtmp = "warping"
datadir = "data/input_data/all_unmatched/"
else:
print("Matched inputs are only provided for [Mouse, Rabbit, Rat]")
sys.exit()
# set filenames for output
if nm is not None:
nm = nm
else:
nm = nmtmp
# load data and covariate
data = []
times = []
samples_names = []
if tissue_as_sample:
group_names = []
data_view = []
for m in views:
for g in species:
df = pd.read_csv(datadir + "view_" + m + "_group_" + g +
".csv",
header=0,
index_col=0)
data_view.append(np.asarray(df).transpose())
times.append(
np.asarray(
pd.read_csv(datadir + "times_group_" + g + ".csv",
header=0,
index_col=0)).transpose())
samples_names.append(df.columns)
group_names.append(m + "-" + g)
data = [data_view]
features_names = [df.index]
else:
for m in views:
data_view = []
for g in species:
data_view.append(
np.asarray(
pd.read_csv(datadir + "view_" + m + "_group_" + g +
".csv",
header=0,
index_col=0)).transpose())
if m == "Brain": # only needed once
times.append(
np.asarray(
pd.read_csv(datadir + "times_group_" + g + ".csv",
header=0,
index_col=0)).transpose())
data.append(data_view)
# convert warping ref to numeric
warping_ref = np.where(
[species[i] == warping_ref for i in range(len(species))])[0][0]
# mask values at random
if Ndown > 0:
np.random.seed(sample_seed)
if tissue_as_sample:
for i in range(len(data[0])):
Ng = data[0][i].shape[0]
masked_samples = np.random.choice(Ng, Ndown, replace=False)
data[0][i][masked_samples, :] = np.nan
else:
for m in range(len(views)):
for g in range(len(species)):
Ng = data[m][g].shape[0]
masked_samples = np.random.choice(Ng, Ndown, replace=False)
data[m][g][masked_samples, :] = np.nan
# check dimension and name views and groups
if tissue_as_sample:
assert len(data) == 1, "problem in loading data, wrong number of views"
assert len(data[0]) == len(species) * len(
views), "problem in loading data, wrong number of groups"
view_names = ["mRNA"]
else:
assert len(data) == len(
views), "problem in loading data, wrong number of views"
assert len(data[0]) == len(
species), "problem in loading data, wrong number of groups"
view_names = views
group_names = species
# prepare MOFA model with time as covariate
ent = entry_point()
ent.set_data_options()
ent.set_data_matrix(data, groups_names=group_names, views_names=view_names)
ent.set_model_options(factors=nfactors)
ent.set_train_options(seed=seed, convergence_mode="medium")
ent.set_covariates(times, covariates_names="time")
ent.set_smooth_options(warping=warp,
warping_ref=warping_ref,
model_groups=model_groups)
# Build and run the model
tracemalloc.start()
ent.build()
t0 = time.time()
ent.run()
t1 = time.time()
total = t1 - t0
current, peak = tracemalloc.get_traced_memory()
tracemalloc.stop()
# save model
if save:
if Ndown == 0:
if model_groups:
outfile = "out/evodevo_groups_%s-seed_%s.hdf5" % (nm, seed)
else:
outfile = "out/evodevo_%s-seed_%s.hdf5" % (nm, seed)
# interpolate for missing time points
ent.predict_factor(
new_covariates=ent.model.nodes["Sigma"].covariates)
else:
if model_groups:
outfile = "out/evodevo_groups_%s-N%s-sample_seed_%s.hdf5" % (
nm, Ndown, sample_seed)
else:
outfile = "out/evodevo_%s-N%s-sample_seed_%s.hdf5" % (
nm, Ndown, sample_seed)
ent.save(outfile)
# write output to csv
results = {
'time': total,
'mem_usage': peak,
'n_down': Ndown,
'sample_seed': sample_seed,
'seed': seed
}
df = pd.DataFrame.from_dict(data=results, orient='index').T
if model_groups:
stats_file = 'out/evodevo_groups_%s_stats.csv' % nm
else:
stats_file = 'out/evodevo_%s_stats.csv' % nm
if os.path.exists(stats_file):
df.to_csv(stats_file, mode='a', header=False)
else:
df.to_csv(stats_file, header=True)
def end(self):
_, peak = tracemalloc.get_traced_memory()
tracemalloc.stop()
self._result_list.append(peak)
def search_algo(n, maze, start, end):
tracemalloc.start()
start_time = time.time()
current, peak = tracemalloc.get_traced_memory()
print(f"Current memory usage before search {current / 10**6}MB")
from queue import PriorityQueue
pos = start
delay = 0.0
grid, rect, screen, wid = make_screen(n)
queue = PriorityQueue() # VCS priority queue stores (cost,position)
queue.put((0, 0))
row = 0
col = 0
maze[row][col] = -1
total_cost = 0
moves = []
parent = [-1] * (n * n) # stores parent of every node
search_cost = 0
costs = [10**5] * (n * n) #stores current best cost path till that node
while pos != end:
curr_elem = queue.get(
) # get top element from priority queue takes O(Size) Time
curr_cost = curr_elem[0]
pos = curr_elem[1]
costs[pos] = min(curr_cost, costs[pos])
row = pos // n
col = pos % n
maze[row][col] = -1
expanded = True
# expanding current node
if (col + 1 < n) and (maze[row][col + 1] not in [1]):
# adding to priority queue if cost is less than current path cost to that node
if costs[row * n + col + 1] > curr_cost + 2:
costs[row * n + col + 1] = curr_cost + 2
queue.put((curr_cost + 2, row * n + col + 1))
parent[row * n + col + 1] = pos
expanded = True
if row * n + col + 1 == end:
pos = end
total_cost = curr_cost + 2
if (row + 1 < n) and (maze[row + 1][col] not in [1]):
if costs[(row + 1) * n + col] > curr_cost + 3:
costs[(row + 1) * n + col] = curr_cost + 3
queue.put((curr_cost + 3, (row + 1) * n + col))
parent[(row + 1) * n + col] = pos
expanded = True
if (row + 1) * n + col == end:
pos = end
total_cost = curr_cost + 3
if (col - 1 >= 0) and (maze[row][col - 1] not in [1]):
if costs[row * n + col - 1] > curr_cost + 2:
costs[row * n + col - 1] = curr_cost + 2
queue.put((curr_cost + 2, row * n + col - 1))
parent[row * n + col - 1] = pos
expanded = True
if row * n + col - 1 == end:
pos = end
total_cost = curr_cost + 2
if (row - 1 >= 0) and (maze[row - 1][col] not in [1]):
if costs[(row - 1) * n + col] > curr_cost + 2:
costs[(row - 1) * n + col] = curr_cost + 2
queue.put((curr_cost + 2, (row - 1) * n + col))
parent[(row - 1) * n + col] = pos
expanded = True
if (row - 1) * n + col == end:
pos = end
total_cost = curr_cost + 2
redraw_maze(grid, rect, screen, n, maze, pos, delay, wid, end)
if expanded:
search_cost += 2
if parent[pos] == pos - n:
search_cost += 1
curr_node = end
# printing the path from start to end
while parent[curr_node] != -1:
maze[curr_node // n][curr_node % n] = 2
if parent[curr_node] == curr_node - 1:
moves.append("Right")
elif parent[curr_node] == curr_node + 1:
moves.append("Left")
elif parent[curr_node] == curr_node + n:
moves.append("Up")
elif parent[curr_node] == curr_node - n:
moves.append("Down")
curr_node = parent[curr_node]
moves = moves[::-1]
maze[0][0] = 2
redraw_maze(grid, rect, screen, n, maze, pos, delay, wid, end)
end_time = time.time()
current, peak = tracemalloc.get_traced_memory()
print("Total Search Time : {} seconds".format(end_time - start_time))
print(f"Peak Memory usage was was {peak / 10**6}MB")
print(f"Total Expanding Search Cost is {search_cost} Units")
print(f"Best Path Total Cost is {total_cost} Units")
tracemalloc.stop()
print(moves)
popup_win(str(total_cost), "Score", "./final.png", screen)
def trace_stop(self):
tracemalloc.stop()
return "<p>tracemalloc stopped</p>"
items = []
for l in read_data:
i, b, w = l.split(' ')
items.append(Item(i, b, w))
print("Breadth first search\n")
t_start = time.time()
for i in range(1000):
tracemalloc.start()
solution = search(items, 420, "BFS")
current, peak = tracemalloc.get_traced_memory()
print(
f"Current memory usage is {current / 10 ** 6}MB; Peak was {peak / 10 ** 6}MB"
)
tracemalloc.stop()
t_end = time.time()
print("\nHighest benefit solution:")
# solution.print(items)
print("Elapsed time: {}\n".format((t_end - t_start) / 1000))
print("Depth first search:")
t_start = time.time()
for i in range(1000):
tracemalloc.start()
solution = search(items, 420, "DFS")
current, peak = tracemalloc.get_traced_memory()
print(
f"Current memory usage is {current / 10 ** 6}MB; Peak was {peak / 10 ** 6}MB"
)
tracemalloc.stop()
def run_grid(nfactors = 2, G = 1, N = 20, Dm = 100, M = 4,
noise_level = 1, missing = 0.1,
missing_all = 0.1, seed = 1234567,
method = "MEFISTO", note = "none",
lscales = [0.2, 0.1], scales = [1, 0.6], n_factors_sim = None,
save = False, max_iter = 1000):
nfactors = int(nfactors)
if n_factors_sim is None:
n_factors_sim = nfactors
assert len(lscales) == n_factors_sim
assert len(scales) == n_factors_sim
groupsidx = np.repeat(range(G), N)
# simulate data
np.random.seed(seed)
views_nms = [str(m) for m in range(M)]
sim = simmofa.simulate_data(N=N, seed=seed, views=views_nms, D=[Dm] * M,
K=n_factors_sim, G=G, lscales=lscales, noise_level=noise_level,
scales = scales, shared = True)
# keep unmasked data in data_full and center as done in MOFA (per group)
data_full = copy.deepcopy(sim['data'])
for g in range(G):
for m in range(M):
data_full[m][g]-= np.nanmean(data_full[m][g], axis=0)
# mask parts of the data
sim['data'] = simmofa.mask_samples(sim, perc = missing, perc_all_views = missing_all)
data_masked = copy.deepcopy(sim['data'])
# fit models
tracemalloc.start()
t0 = time.time()
if method != "univGPs":
if method == "MEFISTO":
GP_factors = True
else:
GP_factors = False
predictions, ent = fit_MOFA(data = sim['data'],
times = sim['sample_cov'],
nfactors = nfactors,
seed = 2020,
GP_factors = GP_factors,
warping = False,
warping_ref = 0,
model_groups = True,
iter = max_iter)
else:
predictions, model, likelihood = fit_GP(data = sim['data'],
times = sim['sample_cov'],
iter = max_iter)
t1 = time.time()
total_time = t1 - t0
current, peak = tracemalloc.get_traced_memory()
tracemalloc.stop()
# evaluate interpolation MSE
mse, mse_mean, n_missing = calc_mse(data_masked = data_masked,
data_full = data_full,
predictions = predictions)
# save results
outdir = 'out/'
if not os.path.exists(outdir):
os.mkdir(outdir)
# save summary statistics if not the model itself is saved
if not save:
results = {'time': total_time, 'method': method,
'N': N, 'G': G, 'M': M, 'Dm': Dm,
'noise_level': noise_level, 'missing': missing, 'missing_all': missing_all,
'seed': seed, 'date': date.today(), 'note': note,
'mem_usage': peak, 'scales' : scales, 'lscales' :lscales,
'n_factors': nfactors, 'n_factors_sim' : n_factors_sim,
'mse': mse, 'mse_mean': mse_mean,
'n_missing': n_missing}
df = pd.DataFrame.from_dict(data=results, orient='index').T
for nm in ['scales', 'lscales']: # expand multi-factor columns
dfsplit = df[nm].apply(pd.Series)
dfsplit = dfsplit.rename(columns=lambda x: nm + "_" + str(x))
df = pd.concat([df, dfsplit], axis=1)
df = df.drop(columns=[nm])
filenm = 'interpolation_results_%s.csv' % method
if os.path.exists(outdir + filenm):
df.to_csv(outdir + filenm, mode='a', header=False)
else:
df.to_csv(outdir + filenm, header=True)
# save model + predictions
else:
if method != "univGPs":
ent.save(outdir + "grid_model.hdf5")
save_predictions(predictions = predictions,
data_masked = data_masked,
times = sim['sample_cov'],
method = method,
outdir= outdir)
save_predictions(predictions = [np.vstack(data_full[m]) for m in range(M)],
data_masked = data_masked,
times = sim['sample_cov'],
method = "ground_truth",
outdir = outdir)
def test_reproject_3D_memory():
pytest.importorskip('reproject')
tracemalloc.start()
snap1 = tracemalloc.take_snapshot()
# create a 64 MB cube
cube, _ = utilities.generate_gaussian_cube(shape=[200, 200, 200])
sz = _.dtype.itemsize
# check that cube is loaded into memory
snap2 = tracemalloc.take_snapshot()
diff = snap2.compare_to(snap1, 'lineno')
diffvals = np.array([dd.size_diff for dd in diff])
# at this point, the generated cube should still exist in memory
assert diffvals.max() * u.B >= 200**3 * sz * u.B
wcs_in = cube.wcs
wcs_out = wcs_in.deepcopy()
wcs_out.wcs.ctype = ['GLON-SIN', 'GLAT-SIN', cube.wcs.wcs.ctype[2]]
wcs_out.wcs.crval = [0.001, 0.001, cube.wcs.wcs.crval[2]]
wcs_out.wcs.crpix = [2., 2., cube.wcs.wcs.crpix[2]]
header_out = (wcs_out.to_header())
header_out['NAXIS'] = 3
header_out['NAXIS1'] = int(cube.shape[2] / 2)
header_out['NAXIS2'] = int(cube.shape[1] / 2)
header_out['NAXIS3'] = cube.shape[0]
# First the unfilled reprojection test: new memory is allocated for
# `result`, but nowhere else
result = cube.reproject(header_out, filled=False)
snap3 = tracemalloc.take_snapshot()
diff = snap3.compare_to(snap2, 'lineno')
diffvals = np.array([dd.size_diff for dd in diff])
# result should have the same size as the input data, except smaller in two dims
# make sure that's all that's allocated
assert diffvals.max() * u.B >= 200 * 100**2 * sz * u.B
assert diffvals.max() * u.B < 200 * 110**2 * sz * u.B
# without masking the cube, nothing should change
result = cube.reproject(header_out, filled=True)
snap4 = tracemalloc.take_snapshot()
diff = snap4.compare_to(snap3, 'lineno')
diffvals = np.array([dd.size_diff for dd in diff])
assert diffvals.max() * u.B <= 1 * u.MB
assert result.wcs.wcs.crval[0] == 0.001
assert result.wcs.wcs.crpix[0] == 2.
# masking the cube will force the fill to create a new in-memory copy
mcube = cube.with_mask(cube > 0.1 * cube.unit)
# `_is_huge` would trigger a use_memmap
assert not mcube._is_huge
assert mcube.mask.any()
# take a new snapshot because we're not testing the mask creation
snap5 = tracemalloc.take_snapshot()
tracemalloc.stop()
tracemalloc.start() # stop/start so we can check peak mem use from here
current_b4, peak_b4 = tracemalloc.get_traced_memory()
result = mcube.reproject(header_out, filled=True)
current_aftr, peak_aftr = tracemalloc.get_traced_memory()
snap6 = tracemalloc.take_snapshot()
diff = snap6.compare_to(snap5, 'lineno')
diffvals = np.array([dd.size_diff for dd in diff])
# a duplicate of the cube should have been created by filling masked vals
# (this should be near-exact since 'result' should occupy exactly the
# same amount of memory)
assert diffvals.max() * u.B <= 1 * u.MB #>= 200**3*sz*u.B
# the peak memory usage *during* reprojection will have that duplicate,
# but the memory gets cleaned up afterward
assert (peak_aftr - peak_b4) * u.B >= (200**3 * sz * u.B +
200 * 100**2 * sz * u.B)
assert result.wcs.wcs.crval[0] == 0.001
assert result.wcs.wcs.crpix[0] == 2.
tracemalloc.start() # Start profiling memory use
three_letter_combos_list = [
letter_1 + letter_2 + letter_3 for letter_1 in LETTERS
for letter_2 in LETTERS for letter_3 in LETTERS
]
# TODO: Update this definition
three_letter_combos_generator = None
# DON'T EDIT THE CODE BELOW THIS LINE
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# This code looks at current memory usage, and displays the results
memory_snapshot = tracemalloc.take_snapshot()
display_malloc_snapshot(memory_snapshot)
tracemalloc.stop() # Stop profiling memory use
print("---------------------------------")
print("The first three letter combos are:")
print(next(three_letter_combos_generator))
print(next(three_letter_combos_generator))
print(next(three_letter_combos_generator))
print("---------------------------------")
print()
print("Generator expression contains",
len(list(three_letter_combos_generator)), "items")
print("List comprehension contains", len(three_letter_combos_list), "items")
def run_grid(nfactors=5,
Tmissing=5,
GP_factors=True,
note="",
masking_seed=1234,
Nviews=1,
seed=2020,
model_groups=True,
method="FA",
max_iter=1000,
species=["Mouse", "Rabbit", "Rat", "Human", "Opossum"],
views=["Brain", "Cerebellum", "Heart", "Liver", "Testis"],
nm="all",
warping=True,
frac_features=1,
n_genes=1000):
M = len(views)
G = len(species)
# specify data directory of normalized gene expression data
datadir = "data/input_data/all_unmatched/"
# set and check number of views to mask a time point in
if Nviews == "all":
Nviews = len(views)
if Nviews > len(views):
print(
"Nviews is larger than available number of views, setting to all views."
)
Nviews = min(Nviews, len(views))
# load data
data = []
times = []
for m in views:
data_view = []
for g in species:
dd_m_g = np.asarray(
pd.read_csv(datadir + "view_" + m + "_group_" + g + ".csv",
header=0,
index_col=0)).transpose()
data_view.append(dd_m_g)
if m == views[0]: # only needed once
times.append(
np.asarray(
pd.read_csv(datadir + "times_group_" + g + ".csv",
header=0,
index_col=0)).transpose())
data.append(data_view)
if n_genes != "all":
np.random.seed(masking_seed + 2020)
genes2keep = np.random.choice(
range(data[0][0].shape[1]), n_genes,
replace=False) # keep a subset of genes in all species and organs
for m in range(M):
for g in range(G):
data[m][g] = data[m][g][:, genes2keep]
# check dimension
assert len(data) == M, "problem in loading data, wrong number of groups"
assert len(data[0]) == G, "problem in loading data, wrong number of views"
# keep unmasked data in data_full and center as done in MOFA (per group)
data_full = copy.deepcopy(data)
for g in range(len(species)):
for m in range(len(views)):
data_full[m][g] -= np.nanmean(data_full[m][g], axis=0)
# mask values (draw timepoint - species combinations and views at random)
times_spec = np.vstack([
np.repeat(range(len(species)),
[len(times[g]) for g in range(len(species))]),
np.concatenate([np.arange(len(times[g])) for g in range(len(species))])
])
np.random.seed(masking_seed)
times_spec2mask = np.random.choice(range(times_spec.shape[1]),
Tmissing,
replace=False)
if frac_features < 1:
D = data[0][0].shape[1]
genes2mask = np.random.choice(range(D),
int(frac_features * D),
replace=False)
for ts in times_spec2mask:
g2mask = times_spec[0, ts]
t2mask = times_spec[1, ts]
views2mask = np.random.choice(range(len(views)), Nviews, replace=False)
for m in views2mask:
if frac_features < 1:
data[m][g2mask][t2mask, genes2mask] = np.nan
else:
data[m][g2mask][t2mask, :] = np.nan
data_masked = copy.deepcopy(data)
# warping reference as in full training
warping_ref = "Mouse"
warping_ref = np.where(
[species[i] == warping_ref for i in range(len(species))])[0][0]
tracemalloc.start()
t0 = time.time()
if method != "univGPs":
predictions, ent = fit_MOFA(data=data,
times=times,
nfactors=nfactors,
seed=seed,
GP_factors=GP_factors,
warping=warping,
warping_ref=warping_ref,
model_groups=model_groups,
iter=max_iter)
else:
predictions, model, likelihood = fit_GP(data, times, iter=max_iter)
t1 = time.time()
total_time = t1 - t0
current, peak = tracemalloc.get_traced_memory()
tracemalloc.stop()
# evaluate interpolation MSE (on missing values that hava a ground truth)
mse, mse_mean, n_missing = calc_mse(data_masked, data_full, predictions)
# write output to csv
results = {
'mse': mse,
'mse_mean': mse_mean,
'time': total_time,
'GP_factors': GP_factors,
'n_missing': n_missing,
'Tmissing': Tmissing,
'masking_seed': masking_seed,
'date': date.today(),
'note': note,
'mem_usage': peak,
'Nviews': Nviews,
'method': method,
'n_genes': n_genes,
'frac_features': frac_features
}
df = pd.DataFrame.from_dict(data=results, orient='index').T
filenm = 'out/interpol_results_evodevo_%s_%s.csv' % (nm, method)
if os.path.exists(filenm):
df.to_csv(filenm, mode='a', header=False)
else:
df.to_csv(filenm, header=True)
def _stop_tracemalloc(self): tracemalloc.stop() self.running = False
def peak_monitor_stop(self):
tracemalloc.stop()
self.peak_monitoring = False
def stop_tracemalloc(self):
tracemalloc.stop()
def activated_tracemalloc():
tracemalloc.start()
try:
yield
finally:
tracemalloc.stop()
def loadData(analyzer, contexto, user, sentiment):
"""
Carga los datos de los archivos CSV en el modelo
"""
tracemalloc.start()
start_time = getTime()
start_memory = getMemory()
#sentimen = cf.data_dir + sentiment
#input_file3 = csv.DictReader(open(sentimen, encoding="utf-8"),delimiter=",")
contexto = cf.data_dir + contexto
input_file = csv.DictReader(open(contexto, encoding="utf-8"),
delimiter=",")
#user= cf.data_dir + user
#input_file2 = csv.DictReader(open(user, encoding="utf-8"),delimiter=",")
#x=0
#lst=lt.newList()
#sss=lt.newList()
# for senti in input_file3:
# lt.addLast(sss,senti)
#itet=it.newIterator(sss)
#x=0
#lst=lt.newList()
#for hashtag in input_file2:
# lt.addLast(lst,hashtag)
#new=it.newIterator(lst)
#x+=1
#if x==5:
#break#Se usaba para mirar que cantidad de datos mirar
#i=0"instrumentalness","liveness","speechiness","danceability","valence","loudness","tempo","acousticness",
# "energy","mode","key","artist_id","tweet_lang","track_id","created_at","lang","time_zone","user_id","id"
x = 0
for track in input_file:
#No es lo mismo comparar str que con numeros
track['tempo'] = float(
track['tempo']
) #Se habia hecho primero un orden de str(eterolexico?(que se comparan str en om.values())) Es necesario tenerlos en int
track['energy'] = float(track['energy'])
track['liveness'] = float(track['liveness'])
track['instrumentalness'] = float(track['instrumentalness'])
hora = track['created_at'][11:19]
t = datetime.time.fromisoformat(
hora
) #Fromisoformat crea un formato iso del datetime() Formato de libreria para poder hacer operaciones (su inversa es isoFormat (ponerlo en str))
track['horas'] = t
track['created_at'] = str(track['created_at'])
track['speechiness'] = float(track['speechiness'])
track['danceability'] = float(track['danceability'])
track['valence'] = float(track['valence'])
track['user_id'] = int(track['user_id'])
track['loudness'] = float(track['loudness'])
track['acousticness'] = float(track['acousticness'])
track['energy'] = float(track['energy'])
track['mode'] = float(track['mode'])
track['key'] = float(track['key'])
track['id'] = int(track['id'])
#track['hashtag']=""
#track['hashtag']=lt.getElement(lst,x+1)
#if track['hashtag']==None:
#track['hashtag']=""
#for x in
model.addTrack(analyzer, track)
x += 1
# if x==1000: #Se usaba para mirar que cantidad de datos mirar
# break
#i+=1
stop_memory = getMemory()
stop_time = getTime()
tracemalloc.stop()
delta_time = stop_time - start_time
delta_memory = deltaMemory(start_memory, stop_memory)
return analyzer, delta_time, delta_memory
def stop(self):
if tracemalloc is not None:
tracemalloc.stop()
super(MemoryCollector, self).stop()
import tracemalloc as t
print("*start")
print([t._format_size(x, False) for x in t.get_traced_memory()])
t.start()
L = [[_ for _ in range(10000)] for i in range(100)]
print("*gen")
print([t._format_size(x, False) for x in t.get_traced_memory()])
snapshot = t.take_snapshot()
for stats in snapshot.statistics("traceback")[:3]:
print(stats)
print("----------------------------------------")
snapshot = t.take_snapshot()
for stats in snapshot.statistics("lineno", cumulative=True)[:3]:
print(stats)
t.stop()
print([t._format_size(x, False) for x in t.get_traced_memory()])
async def app_after_serving():
tracemalloc.stop()
await app.db.disconnect()
def test_reproject_3D_memory():
pytest.importorskip('reproject')
tracemalloc.start()
snap1 = tracemalloc.take_snapshot()
# create a 64 MB cube
cube,_ = utilities.generate_gaussian_cube(shape=[200,200,200])
sz = _.dtype.itemsize
# check that cube is loaded into memory
snap2 = tracemalloc.take_snapshot()
diff = snap2.compare_to(snap1, 'lineno')
diffvals = np.array([dd.size_diff for dd in diff])
# at this point, the generated cube should still exist in memory
assert diffvals.max()*u.B >= 200**3*sz*u.B
wcs_in = cube.wcs
wcs_out = wcs_in.deepcopy()
wcs_out.wcs.ctype = ['GLON-SIN', 'GLAT-SIN', cube.wcs.wcs.ctype[2]]
wcs_out.wcs.crval = [0.001, 0.001, cube.wcs.wcs.crval[2]]
wcs_out.wcs.crpix = [2., 2., cube.wcs.wcs.crpix[2]]
header_out = (wcs_out.to_header())
header_out['NAXIS'] = 3
header_out['NAXIS1'] = int(cube.shape[2]/2)
header_out['NAXIS2'] = int(cube.shape[1]/2)
header_out['NAXIS3'] = cube.shape[0]
# First the unfilled reprojection test: new memory is allocated for
# `result`, but nowhere else
result = cube.reproject(header_out, filled=False)
snap3 = tracemalloc.take_snapshot()
diff = snap3.compare_to(snap2, 'lineno')
diffvals = np.array([dd.size_diff for dd in diff])
# result should have the same size as the input data, except smaller in two dims
# make sure that's all that's allocated
assert diffvals.max()*u.B >= 200*100**2*sz*u.B
assert diffvals.max()*u.B < 200*110**2*sz*u.B
# without masking the cube, nothing should change
result = cube.reproject(header_out, filled=True)
snap4 = tracemalloc.take_snapshot()
diff = snap4.compare_to(snap3, 'lineno')
diffvals = np.array([dd.size_diff for dd in diff])
assert diffvals.max()*u.B <= 1*u.MB
assert result.wcs.wcs.crval[0] == 0.001
assert result.wcs.wcs.crpix[0] == 2.
# masking the cube will force the fill to create a new in-memory copy
mcube = cube.with_mask(cube > 0.1*cube.unit)
# `_is_huge` would trigger a use_memmap
assert not mcube._is_huge
assert mcube.mask.any()
# take a new snapshot because we're not testing the mask creation
snap5 = tracemalloc.take_snapshot()
tracemalloc.stop()
tracemalloc.start() # stop/start so we can check peak mem use from here
current_b4, peak_b4 = tracemalloc.get_traced_memory()
result = mcube.reproject(header_out, filled=True)
current_aftr, peak_aftr = tracemalloc.get_traced_memory()
snap6 = tracemalloc.take_snapshot()
diff = snap6.compare_to(snap5, 'lineno')
diffvals = np.array([dd.size_diff for dd in diff])
# a duplicate of the cube should have been created by filling masked vals
# (this should be near-exact since 'result' should occupy exactly the
# same amount of memory)
assert diffvals.max()*u.B <= 1*u.MB #>= 200**3*sz*u.B
# the peak memory usage *during* reprojection will have that duplicate,
# but the memory gets cleaned up afterward
assert (peak_aftr-peak_b4)*u.B >= (200**3*sz*u.B + 200*100**2*sz*u.B)
assert result.wcs.wcs.crval[0] == 0.001
assert result.wcs.wcs.crpix[0] == 2.
def on_stop_test(self) -> None:
tracemalloc.stop()
def main(args):
path = None
if args.path is not None:
path = args.path
if not os.path.isdir(path):
os.mkdir(path)
file_name = args.file_name
alignment1, alignment2 = None, None
if args.alignment1 is not None and args.alignment2 is not None:
alignment1 = args.alignment1
alignment2 = args.alignment2
if os.path.isfile(alignment1):
alignment = ''
with open(alignment1, 'r') as f:
lines = f.readlines()
for line in lines:
alignment += ''.join(c for c in line if c.isalpha())
alignment1 = alignment
if os.path.isfile(alignment2):
alignment = ''
with open(alignment2, 'r') as f:
lines = f.readlines()
for line in lines:
alignment += ''.join(c for c in line if c.isalpha())
alignment2 = alignment
else:
print("Missing one or more sequences to align with!")
exit(0)
delta = None
score = None
keys = None
if args.delta is not None:
delta, keys = read_delta(args.delta)
else:
if args.match is not None and args.mismatch is not None and args.gap is not None:
score = {
'match': args.match,
'mismatch': args.mismatch,
'gap': args.gap
}
if args.keys is not None:
keys = args.keys.split(',')
if '-' not in keys:
keys.append('-')
else:
print("Symbols will be used by the sequences are missing!")
exit(0)
hs = NeedlemanWunsch(score, keys, delta)
tracemalloc.start()
start_time = time.time()
score, alignments = hs.align(alignment1, alignment2)
current, peak = tracemalloc.get_traced_memory()
end_time = time.time()
print(
f"Current memory usage is {current / 10 ** 6}MB; Peak was {peak / 10 ** 6}MB"
)
tracemalloc.stop()
elapsed_time = end_time - start_time
if path is None:
print("Best Alignment Score:", score)
print("Sequence 1: ", alignments[0])
print("Sequence 2: ", alignments[1])
print("Alignment is done in %.4f seconds!" % elapsed_time)
else:
with open(os.path.join(path, file_name), 'w+') as f:
f.write("Best Alignment Score: %s \n" % str(score))
f.write("Sequence 1: %s \n" % alignments[0])
f.write("Sequence 2: %s \n" % alignments[1])
print("Alignment is done in %.4f seconds!" % elapsed_time)
print("Result saved at %s" % (path + file_name))
def checkrun(
raw_datapath,
tform_config_path,
classifier_config_path,
# Optional for Data
iterator_mode='arrays',
plot_format="RGBrgb",
print_out=True,
skiprows=0,
# Optional for Classifier
scale=1.0,
classifier='tuner',
split=0.1,
target_size=(80, 80),
batch_size=32,
classes=['class_1', 'class_2'],
project_name='tuner_run',
k_fold=False,
k=None,
color_mode='rgb',
seed=None):
''' Check run function that when executed runs all the transformations over
1% of the data and returns the time and memory required for the complete
preprocessing of data step.
Parameters
----------
raw_datapath : str
path to the raw .csv files containing the data to classify
tform_config_path : str
string containing the path to the yaml file
containing the transformations to use and which
data in the .csv file to perform it on
classifier_config_path : str
string containing the path to the yaml file
representing the classifier hyperparameters
iterator_mode : str
option to use images from arrays directly or save the
.png and use a directory iterator mode
plot_format : str
option for standard or RGB color gradient
print_out : bool
option for printing out feedback on conputational time taken to
initialize the data and generate the images
num_test_files_class : int or float
numebr of files per class to select for the test
set
classifier : str
option cnn or tuner
scale : float
percentage fo the image to reduce its size to.
split : float
the percentage of the learning set to use for the validation step
target_size : tuple
image target size. Presented as a tuble indicating number of
pixels composing the two dimensions of the image (w x h)
batch_size : int
The number of files to group up into a batch
classes : list
A list containing strings of the classes the data is divided in.
The class name represent the folder name the files are contained
in.
project_name : str
name of the folder to be created for storing the results of
the tuning
k_fold: bool
bool value indicating if the k_fold is to be performed. Not valid
for tuner
k: int
integer value indicating how many k folds needs to be performed.
seed: int
used in hold_out_test_set to isolate the testing data randomly for
use in training of neural network. Can be assigned value to repeat
the selection.
'''
# listing down the filenames
file_names = [
item for item in os.listdir(raw_datapath) if item.endswith('.csv')
]
# calculations for extracting 1% of data
range_filename = int(len(file_names) * 0.01)
# check to pass test or when the dataset is very small
if range_filename == 0:
range_filename += 1
range_classes = len(classes)
# calculating files per class to pass to hold_out_test_set
# for getting filesnames to be transferring to temporary
# folder
file_per_class = round(range_filename / range_classes)
# check to pass test or when the dataset is very small
if file_per_class == 0:
file_per_class += 1
# calculating the test_set_filenames to be used for
# the hold_out_test_set in the checkpoint_datacreation
# function
num_test_files_class = round(0.25 * file_per_class)
# start measuring time here
time_1 = perf_counter()
# starting memory tracer
tracemalloc.start()
# getting filenames to collect files for checkrun
file_names_for_test = preprocessing.hold_out_test_set(
raw_datapath,
number_of_files_per_class=file_per_class,
classes=classes)
# addding .csv extension to the filenames and storing it in
# seperate list
file_names_csv = []
for item in file_names_for_test:
file_names_csv.append(item + '.csv')
# making directory to store the temporary data
os.mkdir(os.path.join(raw_datapath, 'temp/'))
# copying the 1% data to seperate folder
for item in file_names_csv:
shutil.copy(os.path.join(raw_datapath, item),
os.path.join(raw_datapath + 'temp/'))
# creating new data path to be passed to checkpoint_
# datacreation function
new_data_path = os.path.join(raw_datapath, 'temp/')
checkpoint_datacreation(
new_data_path,
tform_config_path,
classifier_config_path,
# Optional for Data
iterator_mode=iterator_mode,
plot_format=plot_format,
print_out=print_out,
skiprows=skiprows,
# Optional for Classifier
num_test_files_class=num_test_files_class,
scale=scale,
classifier=classifier,
split=split,
target_size=target_size,
batch_size=batch_size,
classes=classes,
project_name=project_name,
k_fold=k_fold,
k=k,
color_mode=color_mode,
seed=seed)
# getting feedback from memory tracer
current, peak = tracemalloc.get_traced_memory()
# stopping memory tracer
tracemalloc.stop()
time_2 = perf_counter()
time_elapsed = time_2 - time_1
print("The total time required for data creation will be approx.\
{} hours".format(round((time_elapsed * 100) / 3600, 3)))
print("The total memory required for the process will be approx.\
{} Gigabytes".format(round(peak * 100 / (10**9), 3)))
# removing the temporary data folder
shutil.rmtree(new_data_path)
print("Temporary files created by process are successfully deleted")
def test_is_tracing(self):
tracemalloc.stop()
self.assertFalse(tracemalloc.is_tracing())
tracemalloc.start()
self.assertTrue(tracemalloc.is_tracing())
async def stop(self, exception: Exception = None) -> None:
tracemalloc.stop()
def excec_program(list, args, file):
list_dup = list.copy()
swaps = 0
compares = 0
my_time = 0
print("-------------------")
tracemalloc.start()
if args[0] == "insert":
if file:
t1_start = time.process_time()
insertion.insertion_sort_stat(list, args[1])
t1_stop = time.process_time()
else:
t1_start = time.process_time()
insertion.insertion_sort(list, args[1])
t1_stop = time.process_time()
swaps = insertion.swaps
compares = insertion.compares
my_time = round(t1_stop - t1_start, 8)
elif args[0] == "merge":
merge.reset_counters()
if file:
t1_start = time.process_time()
merge.merge_sort_stat(list, args[1])
t1_stop = time.process_time()
else:
t1_start = time.process_time()
merge.merge_sort(list, args[1])
t1_stop = time.process_time()
swaps = merge.swaps
compares = merge.compares
my_time = round(t1_stop - t1_start, 8)
elif args[0] == "quick":
quick.reset_counters()
if file:
t1_start = time.process_time()
quick.quick_sort_stat(list, 0, len(list) - 1, args[1])
t1_stop = time.process_time()
else:
t1_start = time.process_time()
quick.quick_sort(list, 0, len(list) - 1, args[1])
t1_stop = time.process_time()
swaps = quick.swaps
compares = quick.compares
my_time = round(t1_stop - t1_start, 8)
elif args[0] == "dual_pivot":
dual_pivot.reset_counters()
if file:
t1_start = time.process_time()
dual_pivot.dual_sort_stat(list, 0, len(list) - 1, args[1])
t1_stop = time.process_time()
else:
t1_start = time.process_time()
dual_pivot.dual_sort(list, 0, len(list) - 1, args[1])
t1_stop = time.process_time()
swaps = dual_pivot.swaps
compares = dual_pivot.compares
my_time = round(t1_stop - t1_start, 8)
elif args[0] == "hybrid":
hybrid.reset_counters()
if file:
t1_start = time.process_time()
hybrid.hybrid_sort(list, args[1])
t1_stop = time.process_time()
else:
t1_start = time.process_time()
hybrid.hybrid_sort(list, args[1])
t1_stop = time.process_time()
swaps = hybrid.swaps
compares = hybrid.compares
my_time = round(t1_stop - t1_start, 8)
elif args[0] == "radix":
radix.reset_counters()
t1_start = time.process_time()
radix.radix_sort(list, args[1])
t1_stop = time.process_time()
swaps = radix.swaps
compares = '-'
my_time = round(t1_stop - t1_start, 8)
elif args[0] == "select_dual":
select_dual.reset_counters()
t1_start = time.process_time()
select_dual.dual_sort(list, 0, len(list) - 1, args[1])
t1_stop = time.process_time()
swaps = select_dual.swaps
compares = select_dual.compares
my_time = round(t1_stop - t1_start, 8)
elif args[0] == "select_quick":
select_quick.reset_counters()
t1_start = time.process_time()
select_quick.quick_sort(list, 0, len(list) - 1, args[1])
t1_stop = time.process_time()
swaps = select_quick.swaps
compares = select_quick.compares
my_time = round(t1_stop - t1_start, 8)
mem = tracemalloc.get_traced_memory()[1]
tracemalloc.stop()
if file:
info = str(len(list)) + ';'
info += str(swaps) + ';'
info += str(compares) + ';'
info += str(my_time) + ';'
info += str(mem) + ';'
info += ('\n')
try:
file_name = args[2]
with open(file_name, 'a+') as f:
f.write(info)
except FileNotFoundError:
print("Creating new file ...")
with open(file_name, 'a+') as f:
f.write(info)
else:
print("-----------------")
print("Time: %.10f" % (t1_stop - t1_start))
print("Swaps: ", swaps)
print("Compares: ", compares)
print("Memory: ", mem, "B")
sorted_info(list_dup, list)
if check_order(list, args[1]) or args[0] == "select_dual":
print(list)
else:
print("Something went wrong :( ")
def tearDown(self):
tracemalloc.stop()
def test_is_tracing(self):
tracemalloc.stop()
self.assertFalse(tracemalloc.is_tracing())
tracemalloc.start()
self.assertTrue(tracemalloc.is_tracing())
def read_write(plot=False):
# mesh = generate_tetrahedral_mesh()
mesh = generate_triangular_mesh()
print(mesh)
mem_size = mesh.points.nbytes + mesh.cells[0].data.nbytes
mem_size /= 1024.0**2
print(f"mem_size: {mem_size:.2f} MB")
formats = {
"Abaqus": (meshio.abaqus.write, meshio.abaqus.read, ["out.inp"]),
"Ansys (ASCII)": (
lambda f, m: meshio.ansys.write(f, m, binary=False),
meshio.ansys.read,
["out.ans"],
),
# "Ansys (binary)": (
# lambda f, m: meshio.ansys.write(f, m, binary=True),
# meshio.ansys.read,
# ["out.ans"],
# ),
"AVS-UCD": (meshio.avsucd.write, meshio.avsucd.read, ["out.ucd"]),
# "CGNS": (meshio.cgns.write, meshio.cgns.read, ["out.cgns"]),
"Dolfin-XML": (meshio.dolfin.write, meshio.dolfin.read, ["out.xml"]),
"Exodus": (meshio.exodus.write, meshio.exodus.read, ["out.e"]),
# "FLAC3D": (meshio.flac3d.write, meshio.flac3d.read, ["out.f3grid"]),
"Gmsh 4.1 (ASCII)": (
lambda f, m: meshio.gmsh.write(f, m, binary=False),
meshio.gmsh.read,
["out.msh"],
),
"Gmsh 4.1 (binary)": (
lambda f, m: meshio.gmsh.write(f, m, binary=True),
meshio.gmsh.read,
["out.msh"],
),
"MDPA": (meshio.mdpa.write, meshio.mdpa.read, ["out.mdpa"]),
"MED": (meshio.med.write, meshio.med.read, ["out.med"]),
"Medit": (meshio.medit.write, meshio.medit.read, ["out.mesh"]),
"MOAB": (meshio.h5m.write, meshio.h5m.read, ["out.h5m"]),
"Nastran": (meshio.nastran.write, meshio.nastran.read, ["out.bdf"]),
"OBJ": (meshio.obj.write, meshio.obj.read, ["out.obj"]),
"OFF": (meshio.off.write, meshio.off.read, ["out.off"]),
"Permas": (meshio.permas.write, meshio.permas.read, ["out.dato"]),
"PLY (binary)": (
lambda f, m: meshio.ply.write(f, m, binary=True),
meshio.ply.read,
["out.ply"],
),
"PLY (ASCII)": (
lambda f, m: meshio.ply.write(f, m, binary=False),
meshio.ply.read,
["out.ply"],
),
"STL (binary)": (
lambda f, m: meshio.stl.write(f, m, binary=True),
meshio.stl.read,
["out.stl"],
),
"STL (ASCII)": (
lambda f, m: meshio.stl.write(f, m, binary=False),
meshio.stl.read,
["out.stl"],
),
# "TetGen": (meshio.tetgen.write, meshio.tetgen.read, ["out.node", "out.ele"],),
"VTK (binary)": (
lambda f, m: meshio.vtk.write(f, m, binary=True),
meshio.vtk.read,
["out.vtk"],
),
"VTK (ASCII)": (
lambda f, m: meshio.vtk.write(f, m, binary=False),
meshio.vtk.read,
["out.vtk"],
),
"VTU (binary, uncompressed)": (
lambda f, m: meshio.vtu.write(f, m, binary=True, compression=None),
meshio.vtu.read,
["out.vtu"],
),
"VTU (binary, zlib)": (
lambda f, m: meshio.vtu.write(
f, m, binary=True, compression="zlib"),
meshio.vtu.read,
["out.vtu"],
),
"VTU (binary, LZMA)": (
lambda f, m: meshio.vtu.write(
f, m, binary=True, compression="lzma"),
meshio.vtu.read,
["out.vtu"],
),
"VTU (ASCII)": (
lambda f, m: meshio.vtu.write(f, m, binary=False),
meshio.vtu.read,
["out.vtu"],
),
"Wavefront .obj": (meshio.obj.write, meshio.obj.read, ["out.obj"]),
# "wkt": ".wkt",
"XDMF (binary)": (
lambda f, m: meshio.xdmf.write(f, m, data_format="Binary"),
meshio.xdmf.read,
["out.xdmf", "out0.bin", "out1.bin"],
),
"XDMF (HDF, GZIP)": (
lambda f, m: meshio.xdmf.write(
f, m, data_format="HDF", compression="gzip"),
meshio.xdmf.read,
["out.xdmf", "out.h5"],
),
"XDMF (HDF, uncompressed)": (
lambda f, m: meshio.xdmf.write(
f, m, data_format="HDF", compression=None),
meshio.xdmf.read,
["out.xdmf", "out.h5"],
),
"XDMF (XML)": (
lambda f, m: meshio.xdmf.write(f, m, data_format="XML"),
meshio.xdmf.read,
["out.xdmf"],
),
}
# formats = {
# # "VTK (ASCII)": formats["VTK (ASCII)"],
# # "VTK (binary)": formats["VTK (binary)"],
# # "VTU (ASCII)": formats["VTU (ASCII)"],
# # "VTU (binary)": formats["VTU (binary)"],
# # "Gmsh 4.1 (binary)": formats["Gmsh 4.1 (binary)"],
# # "FLAC3D": formats["FLAC3D"],
# "MDPA": formats["MDPA"],
# }
# max_key_length = max(len(key) for key in formats)
elapsed_write = []
elapsed_read = []
file_sizes = []
peak_memory_write = []
peak_memory_read = []
print()
print("format " + "write (s) " + "read(s) " +
"file size " + "write mem " + "read mem ")
print()
with tempfile.TemporaryDirectory() as directory:
directory = pathlib.Path(directory)
for name, (writer, reader, filenames) in formats.items():
filename = directory / filenames[0]
tracemalloc.start()
t = time.time()
writer(filename, mesh)
# snapshot = tracemalloc.take_snapshot()
elapsed_write.append(time.time() - t)
peak_memory_write.append(tracemalloc.get_traced_memory()[1])
tracemalloc.stop()
file_sizes.append(
sum(os.stat(directory / f).st_size for f in filenames))
tracemalloc.start()
t = time.time()
reader(filename)
elapsed_read.append(time.time() - t)
peak_memory_read.append(tracemalloc.get_traced_memory()[1])
tracemalloc.stop()
print("{:<26} {:e} {:e} {:e} {:e} {:e}".format(
name,
elapsed_write[-1],
elapsed_read[-1],
file_sizes[-1] / 1024.0**2,
peak_memory_write[-1] / 1024.0**2,
peak_memory_read[-1] / 1024.0**2,
))
names = list(formats.keys())
# convert to MB
file_sizes = numpy.array(file_sizes)
file_sizes = file_sizes / 1024.0**2
peak_memory_write = numpy.array(peak_memory_write)
peak_memory_write = peak_memory_write / 1024.0**2
peak_memory_read = numpy.array(peak_memory_read)
peak_memory_read = peak_memory_read / 1024.0**2
if plot:
plot_speed(names, elapsed_write, elapsed_read)
plot_file_sizes(names, file_sizes, mem_size)
plot_memory_usage(names, peak_memory_write, peak_memory_read, mem_size)
def tearDown(self):
tracemalloc.stop()
def run(args, device, data):
# Unpack data
n_classes, train_g, val_g, test_g, train_nfeat, train_labels, \
val_nfeat, val_labels, test_nfeat, test_labels = data
in_feats = train_nfeat.shape[1]
train_nid = th.nonzero(train_g.ndata['train_mask'], as_tuple=True)[0]
val_nid = th.nonzero(val_g.ndata['val_mask'], as_tuple=True)[0]
test_nid = th.nonzero(
~(test_g.ndata['train_mask'] | test_g.ndata['val_mask']),
as_tuple=True)[0]
print("in_feats " + str(in_feats))
# print("train_g.shape "+ str(train_g.shape))
print("train_labels.shape " + str(train_labels.shape))
# print("val_g.shape "+ str(val_g.shape))
# Create PyTorch DataLoader for constructing blocks
sampler = dgl.dataloading.MultiLayerNeighborSampler(
[int(fanout) for fanout in args.fan_out.split(',')])
# see_memory_usage("-----------------------------------------after sampler------------------------")
dataloader = dgl.dataloading.NodeDataLoader(train_g,
train_nid,
sampler,
batch_size=args.batch_size,
shuffle=True,
drop_last=False,
num_workers=args.num_workers)
print("args.batch_size " + str(args.batch_size))
# see_memory_usage("-----------------------------------------after data loader------------------------")
# Define model and optimizer
model = SAGE(in_feats, args.num_hidden, n_classes, args.num_layers, F.relu,
args.dropout)
print(model)
# see_memory_usage("-----------------------------------------before model to gpu------------------------")
model = model.to(device)
loss_fcn = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=args.lr)
# see_memory_usage("-----------------------------------------before start------------------------")
# Training loop
avg = 0
iter_tput = []
tracemalloc.start()
CPU_mem(
"-----------------------------------------before start------------------------"
)
for epoch in range(args.num_epochs):
tic = time.time()
# Loop over the dataloader to sample the computation dependency graph as a list of
# blocks.
tic_step = time.time()
for step, (input_nodes, seeds, blocks) in enumerate(dataloader):
# if step>1:
# break
# print("*"*80 +str(step))
# print("input_nodes.shape "+str(input_nodes.shape))
# print("output_nodes.shape "+str(seeds.shape))
# print("blocks.length "+str(len(blocks)))
# print("blocks.shape "+str(blocks.shape))
# print(blocks)
# see_memory_usage("-----------------------------------------step start------------------------")
# Load the input features as well as output labels
batch_inputs, batch_labels = load_subtensor(
train_nfeat, train_labels, seeds, input_nodes, device)
CPU_mem(
"-----------------------------------------before blocks to device"
)
# see_memory_usage("-----------------------------------------before blocks to device")
blocks = [block.int().to(device) for block in blocks]
CPU_mem(
"-----------------------------------------after blocks to device"
)
# see_memory_usage("-----------------------------------------after blocks to device")
print(
"---------------------------------------------------------batch_inputs.shape "
+ str(batch_inputs.shape))
# Compute loss and prediction
batch_pred = model(blocks, batch_inputs)
CPU_mem(
"-----------------------------------------after batch train")
# see_memory_usage("-----------------------------------------after batch train")
loss = loss_fcn(batch_pred, batch_labels)
# see_memory_usage("-----------------------------------------after batch loss")
CPU_mem(
"-----------------------------------------after batch loss")
optimizer.zero_grad()
loss.backward()
# see_memory_usage("-----------------------------------------after batch loss backward")
CPU_mem(
"-----------------------------------------after batch loss backward"
)
optimizer.step()
# iter_tput.append(len(seeds) / (time.time() - tic_step))
# if step % args.log_every==0:
# print('Epoch {:05d} | Step {:05d} | Loss {:.4f} | Train Acc {:.4f} | Speed (samples/sec) {:.4f} | GPU {:.1f} MB'.format(
# epoch, step, loss.item(), 0, np.mean(iter_tput[3:]), 0))
# # acc = compute_acc(batch_pred, batch_labels)
# # gpu_mem_alloc = th.cuda.max_memory_allocated() / 1000000 if th.cuda.is_available() else 0
# # print('Epoch {:05d} | Step {:05d} | Loss {:.4f} | Train Acc {:.4f} | Speed (samples/sec) {:.4f} | GPU {:.1f} MB'.format(
# # epoch, step, loss.item(), acc.item(), np.mean(iter_tput[3:]), gpu_mem_alloc))
# # print(a
# # 'Epoch {:05d} | Step {:05d} | Loss {:.4f} | Train Acc {:.4f} | Speed (samples/sec) {:.4f} | GPU {:.1f} MB'.format(
# # epoch, step, loss.item(), 0, np.mean(iter_tput[3:]), gpu_mem_alloc))
# # print('Epoch {:05d} | Step {:05d} | Loss {:.4f} | Train Acc {:.4f} | Speed (samples/sec) {:.4f} | GPU {:.1f} MB'.format(
# # epoch, step, loss.item(), 0, np.mean(iter_tput[3:]), 0))
# tic_step = time.time()
toc = time.time()
print('Epoch Time(s): {:.4f}'.format(toc - tic))
if epoch >= 2:
avg += toc - tic
# if epoch % args.eval_every==0 and epoch!=0:
# eval_acc = evaluate(model, val_g, val_nfeat, val_labels, val_nid, device)
# print('Eval Acc {:.4f}'.format(eval_acc))
# test_acc = evaluate(model, test_g, test_nfeat, test_labels, test_nid, device)
# print('Test Acc: {:.4f}'.format(test_acc))
print('Avg epoch time: {}'.format(avg / (epoch - 1)))
current, peak = tracemalloc.get_traced_memory()
print(
f"Current memory usage is {current / 10 ** 6}MB; Peak was {peak / 10 ** 6}MB"
)
tracemalloc.stop()
def stop(self) -> None:
"""Stop the profiler."""
self._t0 = self._timefunc()
tracemalloc.stop()
def peak_monitor_stop(self):
tracemalloc.stop()
self.peak_monitoring = False
def wrapper(*args, **kwargs):
tracemalloc.start()
result = func(*args, **kwargs)
print(f"Memory Usage: {tracemalloc.get_traced_memory()}")
tracemalloc.stop()
return result
def on_stop_test(self):
tracemalloc.stop()
