def benchmark(args, predictor, X):
total = 0.0
for _ in range(args.iterations):
gc.collect()
start = datetime.now()
predictor.predict(X)
end = datetime.now()
total += total_seconds(end - start)
return total / args.iterations
def benchmark(args, predictor, X):
total = 0.0
for _ in range(args.iterations):
gc.collect()
start = datetime.now()
predictor.predict(X)
end = datetime.now()
total += total_seconds(end - start)
return total / args.iterations
def bench_isotonic_regression(Y):
"""
Runs a single iteration of isotonic regression on the input data,
and reports the total time taken (in seconds).
"""
gc.collect()
tstart = datetime.now()
isotonic_regression(Y)
delta = datetime.now() - tstart
return total_seconds(delta)
def bench_isotonic_regression(Y):
"""
Runs a single iteration of isotonic regression on the input data,
and reports the total time taken (in seconds).
"""
gc.collect()
tstart = datetime.now()
isotonic_regression(Y)
delta = datetime.now() - tstart
return total_seconds(delta)
dimensions = 500 * np.arange(1, n_iter + 1)
for i in range(n_iter):
print 'Iteration %s of %s' % (i, n_iter)
n_samples, n_features = 10 * i + 3, 10 * i + 3
X = np.random.randn(n_samples, n_features)
Y = np.random.randn(n_samples)
start = datetime.now()
ridge = linear_model.Ridge(alpha=1.)
ridge.fit(X, Y)
time_ridge[i] = total_seconds(datetime.now() - start)
start = datetime.now()
ols = linear_model.LinearRegression()
ols.fit(X, Y)
time_ols[i] = total_seconds(datetime.now() - start)
start = datetime.now()
lasso = linear_model.LassoLars()
lasso.fit(X, Y)
time_lasso[i] = total_seconds(datetime.now() - start)
pl.xlabel('Dimesions')
pl.ylabel('Time (in seconds)')
pl.plot(dimensions, time_ridge, color='r')
pl.plot(dimensions, time_ols, color='g')
def test_total_seconds():
delta = (datetime.datetime(2012, 1, 1, 5, 5, 1)
- datetime.datetime(2012, 1, 1, 5, 5, 4))
assert_equal(86397, total_seconds(delta))
dimensions = 500 * np.arange(1, n_iter + 1)
for i in range(n_iter):
print('Iteration %s of %s' % (i, n_iter))
n_samples, n_features = 10 * i + 3, 10 * i + 3
X = np.random.randn(n_samples, n_features)
Y = np.random.randn(n_samples)
start = datetime.now()
ridge = linear_model.Ridge(alpha=1.)
ridge.fit(X, Y)
time_ridge[i] = total_seconds(datetime.now() - start)
start = datetime.now()
ols = linear_model.LinearRegression()
ols.fit(X, Y)
time_ols[i] = total_seconds(datetime.now() - start)
start = datetime.now()
lasso = linear_model.LassoLars()
lasso.fit(X, Y)
time_lasso[i] = total_seconds(datetime.now() - start)
pl.figure('scikit-learn GLM benchmark results')
pl.xlabel('Dimensions')
pl.ylabel('Time (s)')
pl.plot(dimensions, time_ridge, color='r')
def test_total_seconds():
delta = (datetime.datetime(2012, 1, 1, 5, 5, 1) -
datetime.datetime(2012, 1, 1, 5, 5, 4))
assert_equal(86397, total_seconds(delta))
