def test_grid_search():
cv = ShuffleSplit(n_iter=5, random_state=0)
mf = ExplicitMF(n_components=3, max_iter=10, random_state=0)
param_grid = {"alpha": [0.1, 1.0, 10]}
gcv = GridSearchCV(mf, param_grid, cv)
gcv.fit(X)
assert_equal(gcv.best_estimator_.alpha, 0.1)
assert_equal(gcv.best_params_, {"alpha": 0.1})
mf = ExplicitMF(alpha=0.1, n_components=3, max_iter=10, random_state=0)
mf.fit(X)
assert_almost_equal(mf.score(X), gcv.score(X))
def test_matrix_fact_cd():
# Generate some toy data.
rng = np.random.RandomState(0)
U = rng.rand(50, 3)
V = rng.rand(3, 20)
X = np.dot(U, V)
mf = ExplicitMF(n_components=3, max_iter=10, alpha=1e-3, random_state=0,
verbose=0)
mf.fit(X)
Y = np.dot(mf.P_, mf.Q_)
Y2 = mf.predict(X).toarray()
assert_array_almost_equal(Y, Y2)
rmse = np.sqrt(np.mean((X - Y) ** 2))
rmse2 = mf.score(X)
assert_almost_equal(rmse, rmse2)
def test_cross_val_score():
# Generate some toy data.
rng = np.random.RandomState(0)
U = rng.rand(50, 3)
V = rng.rand(3, 20)
X = np.dot(U, V)
cv = ShuffleSplit(n_iter=10)
mf = ExplicitMF(n_components=3, max_iter=10, alpha=1e-3, random_state=0,
verbose=0)
scores = cross_val_score(mf, X, cv)
assert_equal(len(scores), cv.n_iter)
def test_grid_search():
cv = ShuffleSplit(n_iter=5, random_state=0)
mf = ExplicitMF(n_components=3, max_iter=10, random_state=0)
param_grid = {"alpha": [0.1, 1.0, 10]}
gcv = GridSearchCV(mf, param_grid, cv)
gcv.fit(X)
assert_equal(gcv.best_estimator_.alpha, 0.1)
assert_equal(gcv.best_params_, {"alpha": 0.1})
mf = ExplicitMF(alpha=0.1, n_components=3, max_iter=10, random_state=0)
mf.fit(X)
assert_almost_equal(mf.score(X), gcv.score(X))
def test_matrix_fact_cd():
# Generate some toy data.
rng = np.random.RandomState(0)
U = rng.rand(50, 3)
V = rng.rand(3, 20)
X = np.dot(U, V)
mf = ExplicitMF(n_components=3,
max_iter=10,
alpha=1e-3,
random_state=0,
verbose=0)
mf.fit(X)
Y = np.dot(mf.P_, mf.Q_)
Y2 = mf.predict(X).toarray()
assert_array_almost_equal(Y, Y2)
rmse = np.sqrt(np.mean((X - Y)**2))
rmse2 = mf.score(X)
assert_almost_equal(rmse, rmse2)
self.times.append(time.clock() - self.start_time - self.test_time)
try:
version = sys.argv[1]
except:
version = "100k"
X = load_movielens(version)
print X.shape
X_tr, X_te = train_test_split(X, train_size=0.75, random_state=0)
X_tr = X_tr.tocsr()
X_te = X_te.tocsr()
cb = Callback(X_tr, X_te)
mf = ExplicitMF(n_components=30, max_iter=50, alpha=0.1, verbose=1, callback=cb)
mf.fit(X_tr)
plt.figure()
plt.plot(cb.times, cb.obj)
plt.xlabel("CPU time")
plt.xscale("log")
plt.ylabel("Objective value")
plt.figure()
plt.plot(cb.times, cb.rmse)
plt.xlabel("CPU time")
plt.xscale("log")
plt.ylabel("RMSE")
plt.show()
def main(version='100k', n_jobs=1, random_state=0, cross_val=False):
dl_params = {}
dl_params['100k'] = dict(learning_rate=1, batch_size=10, offset=0, alpha=1)
dl_params['1m'] = dict(learning_rate=.75,
batch_size=60,
offset=0,
alpha=.8)
dl_params['10m'] = dict(learning_rate=.75,
batch_size=600,
offset=0,
alpha=3)
dl_params['netflix'] = dict(learning_rate=.8,
batch_size=4000,
offset=0,
alpha=0.16)
cd_params = {
'100k': dict(alpha=.1),
'1m': dict(alpha=.03),
'10m': dict(alpha=.04),
'netflix': dict(alpha=.1)
}
if version in ['100k', '1m', '10m']:
X = load_movielens(version)
X_tr, X_te = train_test_split(X,
train_size=0.75,
random_state=random_state)
X_tr = X_tr.tocsr()
X_te = X_te.tocsr()
elif version is 'netflix':
X_tr = load(expanduser('~/spira_data/nf_prize/X_tr.pkl'))
X_te = load(expanduser('~/spira_data/nf_prize/X_te.pkl'))
cd_mf = ExplicitMF(
n_components=60,
max_iter=50,
alpha=.1,
normalize=True,
verbose=1,
)
dl_mf = DictMF(n_components=30,
n_epochs=20,
alpha=1.17,
verbose=5,
batch_size=10000,
normalize=True,
fit_intercept=True,
random_state=0,
learning_rate=.75,
impute=False,
partial=False,
backend='python')
dl_mf_partial = DictMF(n_components=60,
n_epochs=20,
alpha=1.17,
verbose=5,
batch_size=10000,
normalize=True,
fit_intercept=True,
random_state=0,
learning_rate=.75,
impute=False,
partial=True,
backend='python')
timestamp = datetime.datetime.now().strftime('%Y-%m-%d_%H' '-%M-%S')
if cross_val:
subdir = 'benches_ncv'
else:
subdir = 'benches'
output_dir = expanduser(join('~/output/recommender/', timestamp, subdir))
if not os.path.exists(output_dir):
os.makedirs(output_dir)
alphas = np.logspace(-2, 1, 10)
mf_list = [dl_mf_partial]
dict_id = {cd_mf: 'cd', dl_mf: 'dl', dl_mf_partial: 'dl_partial'}
names = {
'cd': 'Coordinate descent',
'dl': 'Proposed online masked MF',
'dl_partial': 'Proposed algorithm (with partial projection)'
}
if os.path.exists(
join(output_dir, 'results_%s_%s.json' % (version, random_state))):
with open(
join(output_dir,
'results_%s_%s.json' % (version, random_state)),
'r') as f:
results = json.load(f)
else:
results = {}
for mf in mf_list:
results[dict_id[mf]] = {}
if not cross_val:
if isinstance(mf, DictMF):
mf.set_params(
learning_rate=dl_params[version]['learning_rate'],
batch_size=dl_params[version]['batch_size'],
alpha=dl_params[version]['alpha'])
else:
mf.set_params(alpha=cd_params[version]['alpha'])
else:
if isinstance(mf, DictMF):
mf.set_params(
learning_rate=dl_params[version]['learning_rate'],
batch_size=dl_params[version]['batch_size'])
if version != 'netflix':
cv = ShuffleSplit(n_iter=3, train_size=0.66, random_state=0)
mf_scores = Parallel(n_jobs=n_jobs, verbose=10)(
delayed(single_fit)(mf, alpha, X_tr, cv)
for alpha in alphas)
else:
mf_scores = Parallel(n_jobs=n_jobs, verbose=10)(
delayed(single_fit)(mf, alpha, X_tr, X_te, nested=False)
for alpha in alphas)
mf_scores = np.array(mf_scores).mean(axis=1)
best_alpha_arg = mf_scores.argmin()
best_alpha = alphas[best_alpha_arg]
mf.set_params(alpha=best_alpha)
cb = Callback(X_tr, X_te, refit=False)
mf.set_params(callback=cb)
mf.fit(X_tr)
results[dict_id[mf]] = dict(name=names[dict_id[mf]],
time=cb.times,
rmse=cb.rmse)
if cross_val:
results[dict_id[mf]]['alphas'] = alphas.tolist()
results[dict_id[mf]]['cv_alpha'] = mf_scores.tolist()
results[dict_id[mf]]['best_alpha'] = mf.alpha
with open(
join(output_dir,
'results_%s_%s.json' % (version, random_state)),
'w+') as f:
json.dump(results, f)
print('Done')
try:
version = sys.argv[1]
except:
version = "100k"
X = load_movielens(version)
print X.shape
alphas = np.logspace(-3, 0, 10)
mf_scores = []
cv = ShuffleSplit(n_iter=3, train_size=0.75, random_state=0)
for alpha in alphas:
mf = ExplicitMF(n_components=30, max_iter=10, alpha=alpha)
mf_scores.append(cross_val_score(mf, X, cv))
# Array of size n_alphas x n_folds.
mf_scores = np.array(mf_scores)
dummy = Dummy()
dummy_scores = cross_val_score(dummy, X, cv)
dummy = Dummy(axis=0)
dummy_scores2 = cross_val_score(dummy, X, cv)
plt.figure()
plt.plot(alphas, mf_scores.mean(axis=1), label="Matrix Factorization")
plt.plot(alphas, [dummy_scores.mean()] * len(alphas), label="User mean")
plt.plot(alphas, [dummy_scores2.mean()] * len(alphas), label="Movie mean")
import sys
import time
from spira.datasets import load_movielens
from spira.cross_validation import train_test_split
from spira.completion import ExplicitMF
try:
version = sys.argv[1]
except:
version = "100k"
X = load_movielens(version)
print(X.shape)
X_tr, X_te = train_test_split(X, train_size=0.75, random_state=0)
start = time.time()
mf = ExplicitMF(n_components=30, max_iter=10, alpha=1e-1, random_state=0,
verbose=1)
mf.fit(X_tr)
print("Time", time.time() - start)
print("RMSE", mf.score(X_te))
import sys
import time
from spira.datasets import load_movielens
from spira.cross_validation import train_test_split
from spira.completion import ExplicitMF
try:
version = sys.argv[1]
except:
version = "100k"
X = load_movielens(version)
print X.shape
X_tr, X_te = train_test_split(X, train_size=0.75, random_state=0)
start = time.time()
mf = ExplicitMF(n_components=30, max_iter=10, alpha=1e-1, random_state=0,
verbose=1)
mf.fit(X_tr)
print "Time", time.time() - start
print "RMSE", mf.score(X_te)
try:
version = sys.argv[1]
except:
version = "100k"
X = load_movielens(version)
print X.shape
X_tr, X_te = train_test_split(X, train_size=0.75, random_state=0)
X_tr = X_tr.tocsr()
X_te = X_te.tocsr()
cb = Callback(X_tr, X_te)
mf = ExplicitMF(n_components=30,
max_iter=50,
alpha=0.1,
verbose=1,
callback=cb)
mf.fit(X_tr)
plt.figure()
plt.plot(cb.times, cb.obj)
plt.xlabel("CPU time")
plt.xscale("log")
plt.ylabel("Objective value")
plt.figure()
plt.plot(cb.times, cb.rmse)
plt.xlabel("CPU time")
plt.xscale("log")
plt.ylabel("RMSE")
rmse = np.sqrt(np.mean((X_pred.data - self.X_te.data)**2))
print(rmse)
self.rmse.append(rmse)
self.test_time += time.clock() - test_time
self.times.append(time.clock() - self.start_time - self.test_time)
X_tr = load(expanduser('~/spira_data/nf_prize/X_tr.pkl'))
X_te = load(expanduser('~/spira_data/nf_prize/X_te.pkl'))
# X_te = X_te.T.tocsr()
cb = {}
cd_mf = ExplicitMF(
n_components=30,
max_iter=50,
alpha=0.1,
verbose=1,
)
dl_mf = DictMF(n_components=30,
n_epochs=5,
alpha=.3,
verbose=10,
batch_size=10000,
normalize=True,
impute=False,
fit_intercept=True,
random_state=0,
learning_rate=.75,
backend='c')
for mf in [dl_mf]: