for mean1 in [(-1, 0), (1, 1)]:
for mean2 in [(0, -1), (1, -1)]:
jobs.append(generate_data(size, mean1, mean2))
def worker(model, args):
X, Y = args
model.compute_coefficients(X, Y)
# Profile the python implementation
model = LogisticRegressionPy()
timer = Timer()
for i, job in enumerate(jobs):
worker(model, job)
py_time = timer.split()
# Profile the C++ implementation
model = LogisticRegressionCpp()
timer = Timer()
for job in jobs:
worker(model, job)
cpp_time = timer.split()
# Build a nice graph
labels = ["Python", "C++"]
times = [py_time, cpp_time]
index = range(len(labels))
plt.bar(index, times)
plt.xlabel('Implementation language')
plt.ylabel('Runtime')
def profiler(payload_size, num_calls):
payload = [float(i) for i in range(payload_size)]
timer = Timer()
for _ in range(num_calls):
noop(payload)
return timer.split()
for mean2 in [(0, -1), (1, -1)]:
jobs.append(generate_data(size, mean1, mean2))
# Profile with differing numbers of python threads with a model that is
# single-threaded.
model = LogisticRegressionCpp()
def worker(args):
X, Y = args
model.compute_coefficients(X, Y)
times = []
for num_threads in range(1, 9):
pool = ThreadPool(num_threads)
timer = Timer()
pool.map(worker, jobs)
times.append((num_threads, timer.split()))
# Build a nice graph
labels = [n for n, _ in times]
times = [t for _, t in times]
index = range(len(labels))
plt.bar(index, times)
plt.xlabel('Number of threads')
plt.ylabel('Runtime')
plt.xticks(index, labels)
plt.title("C++ speed with varying numbers of python(!) threads")
plt.savefig("profile_pythreads.png")
from multiprocessing.pool import ThreadPool
from data import Timer
from module import noop
payload = [float(i) for i in range(1000000)]
def worker(arg):
noop(payload)
jobs = range(200)
print("Threads", "Runtime", sep="\t")
for num_threads in range(1, 9):
pool = ThreadPool(num_threads)
timer = Timer()
pool.map(worker, jobs)
elapsed_time = timer.split()
print(num_threads, elapsed_time, sep="\t")