def benchmark_times(plays, iterations=3):
times = defaultdict(lambda: defaultdict(list))
def store_time(model, name):
def inner(iteration, elapsed):
print(name, model.factors, iteration, elapsed)
times[name][model.factors].append(elapsed)
return inner
output = defaultdict(list)
for factors in range(32, 257, 32):
for steps in [2, 3, 4]:
model = AlternatingLeastSquares(factors=factors, use_native=True, use_cg=True,
regularization=0, iterations=iterations)
model.fit_callback = store_time(model, 'cg%i' % steps)
model.cg_steps = steps
model.fit(plays)
model = AlternatingLeastSquares(factors=factors, use_native=True, use_cg=False,
regularization=0, iterations=iterations)
model.fit_callback = store_time(model, 'cholesky')
model.fit(plays)
if has_cuda:
model = AlternatingLeastSquares(factors=factors, use_native=True, use_gpu=True,
regularization=0, iterations=iterations)
model.fit_callback = store_time(model, 'gpu')
model.fit(plays)
# take the min time for the output
output['factors'].append(factors)
for name, stats in times.items():
output[name].append(min(stats[factors]))
return output
def benchmark_accuracy(plays):
output = defaultdict(list)
def store_loss(model, name):
def inner(iteration, elapsed):
loss = calculate_loss(plays, model.item_factors, model.user_factors, 0)
print("model %s iteration %i loss %.5f" % (name, iteration, loss))
output[name].append(loss)
return inner
for steps in [2, 3, 4]:
model = AlternatingLeastSquares(factors=100, use_native=True, use_cg=True, regularization=0,
iterations=25)
model.cg_steps = steps
model.fit_callback = store_loss(model, 'cg%i' % steps)
model.fit(plays)
if has_cuda:
model = AlternatingLeastSquares(factors=100, use_native=True, use_gpu=True,
regularization=0, iterations=25)
model.fit_callback = store_loss(model, 'gpu')
model.use_gpu = True
model.fit(plays)
model = AlternatingLeastSquares(factors=100, use_native=True, use_cg=False, regularization=0,
iterations=25)
model.fit_callback = store_loss(model, 'cholesky')
model.fit(plays)
return output
def benchmark_times(plays, iterations=3):
times = defaultdict(lambda: defaultdict(list))
def store_time(model, name):
def inner(iteration, elapsed):
print(name, model.factors, iteration, elapsed)
times[name][model.factors].append(elapsed)
return inner
output = defaultdict(list)
for factors in range(32, 257, 32):
for steps in [2, 3, 4]:
model = AlternatingLeastSquares(
factors=factors,
use_native=True,
use_cg=True,
regularization=0,
iterations=iterations,
)
model.fit_callback = store_time(model, "cg%i" % steps)
model.cg_steps = steps
model.fit(plays)
model = AlternatingLeastSquares(factors=factors,
use_native=True,
use_cg=False,
regularization=0,
iterations=iterations)
model.fit_callback = store_time(model, "cholesky")
model.fit(plays)
if has_cuda:
model = AlternatingLeastSquares(
factors=factors,
use_native=True,
use_gpu=True,
regularization=0,
iterations=iterations,
)
model.fit_callback = store_time(model, "gpu")
model.fit(plays)
# take the min time for the output
output["factors"].append(factors)
for name, stats in times.items():
output[name].append(min(stats[factors]))
return output
def benchmark_accuracy(plays):
output = defaultdict(list)
def store_loss(model, name):
def inner(iteration, elapsed):
loss = calculate_loss(plays, model.item_factors,
model.user_factors, 0)
print("model %s iteration %i loss %.5f" % (name, iteration, loss))
output[name].append(loss)
return inner
for steps in [2, 3, 4]:
model = AlternatingLeastSquares(factors=100,
use_native=True,
use_cg=True,
regularization=0,
iterations=25)
model.cg_steps = steps
model.fit_callback = store_loss(model, 'cg%i' % steps)
model.fit(plays)
if has_cuda:
model = AlternatingLeastSquares(factors=100,
use_native=True,
use_gpu=True,
regularization=0,
iterations=25)
model.fit_callback = store_loss(model, 'gpu')
model.use_gpu = True
model.fit(plays)
model = AlternatingLeastSquares(factors=100,
use_native=True,
use_cg=False,
regularization=0,
iterations=25)
model.fit_callback = store_loss(model, 'cholesky')
model.fit(plays)
return output