def compare_learning_rate(version='100k', n_jobs=1, random_state=0):
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'))
mf = DictMF(
n_components=30,
n_epochs=20 if version == '10m' else 7,
alpha=0.1373823795883263 if version == '10m' else 0.16681005372000587,
verbose=5,
batch_size=600 if version == '10m' else 4000,
normalize=True,
fit_intercept=True,
random_state=0,
learning_rate=.75,
impute=False,
partial=True,
backend='c')
timestamp = datetime.datetime.now().strftime('%Y-%m-%d_%H' '-%M-%S')
subdir = 'learning_rate'
output_dir = expanduser(join('~/output/recommender/', timestamp, subdir))
if not os.path.exists(output_dir):
os.makedirs(output_dir)
results = {}
par_res = Parallel(n_jobs=n_jobs, max_nbytes=None)(
delayed(single_learning_rate)(mf, learning_rate, X_tr, X_te)
for learning_rate in np.linspace(0.5, 1, 10))
for i, learning_rate in enumerate(np.linspace(0.5, 1, 10)):
results[learning_rate] = par_res[i]
with open(join(output_dir, 'results_%s.json' % version), 'w+') as f:
json.dump(results, f)
def compare_learning_rate(version='100k', n_jobs=1, random_state=0):
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'))
mf = DictMF(n_components=30, n_epochs=20 if version == '10m' else 7,
alpha=0.1373823795883263 if version == '10m' else 0.16681005372000587,
verbose=5,
batch_size=600 if version == '10m' else 4000,
normalize=True,
fit_intercept=True,
random_state=0,
learning_rate=.75,
impute=False,
partial=True,
backend='c')
timestamp = datetime.datetime.now().strftime('%Y-%m-%d_%H'
'-%M-%S')
subdir = 'learning_rate'
output_dir = expanduser(join('~/output/recommender/', timestamp, subdir))
if not os.path.exists(output_dir):
os.makedirs(output_dir)
results = {}
par_res = Parallel(n_jobs=n_jobs, max_nbytes=None)(
delayed(single_learning_rate)(mf, learning_rate, X_tr, X_te) for
learning_rate in np.linspace(0.5, 1, 10 ))
for i, learning_rate in enumerate(np.linspace(0.5, 1, 10)):
results[learning_rate] = par_res[i]
with open(join(output_dir, 'results_%s.json' % version), 'w+') as f:
json.dump(results, f)
loss = 0.5 * error(self.X_tr, mf.P_, mf.Q_)
regul = 0.5 * mf.alpha * (sqnorm(mf.P_) + sqnorm(mf.Q_))
self.obj.append(loss + regul)
X_pred = mf.predict(self.X_te)
self.f1.append(f1_score(self.X_te, X_pred))
self.test_time += time.clock() - test_time
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)
# Binarize and pretend this is implicit feedback.
cond = X.data > X.data.mean()
X.data[cond] = 1
X.data[~cond] = 0
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 = ImplicitMF(n_components=30, max_iter=50, alpha=0.1, callback=cb,
random_state=0)
mf.fit(X_tr)
dump(estimator, join(debug_folder, 'estimator'), compress=9)
return score
output_dir = expanduser(join('~/output/dl_recommender/',
datetime.datetime.now().strftime('%Y-%m-%d_%H'
'-%M-%S'))
)
os.makedirs(output_dir)
random_state = check_random_state(0)
mem = Memory(cachedir=expanduser("~/cache"), verbose=10)
# X_csr = mem.cache(fetch_ml_10m)(expanduser('~/data/own/ml-10M100K'),
# remove_empty=True)
X_csr = sp.csr_matrix(load_movielens('1m'))
permutation = random_state.permutation(X_csr.shape[0])
X_csr = X_csr[permutation]
X, y = array_to_fm_format(X_csr)
uniform_split = ShuffleSplit(n_iter=1,
test_size=.25, random_state=random_state)
fm_decoder = FMDecoder(n_samples=X_csr.shape[0], n_features=X_csr.shape[1])
base_estimator = BaseRecommender(fm_decoder)
dl_list = [DLRecommender(fm_decoder,
n_components=n_components,
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')
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')
