def fit(self, ratings):
n_users = max(imap(key_u, ratings)) + 1
n_items = max(imap(key_i, ratings)) + 1
mat = to_sparse(ratings,
shape=(n_users, n_items))
svd = TruncatedSVD(n_components=self.K, algorithm='arpack')
self.U = svd.fit_transform(mat) # U.dot(Sigma)
self.VT = svd.components_ # VT
def fit(self, ratings):
super(SvdAvgPredictor, self).fit(ratings)
n_users = max(imap(key_u, ratings)) + 1
n_items = max(imap(key_i, ratings)) + 1
offset = [(u, i, r - self.offset_user[u] - self.avg_item[i])
for u, i, r in ratings]
mat = to_sparse(offset,
shape=(n_users, n_items))
svd = TruncatedSVD(n_components=self.K, algorithm='arpack')
self.U = svd.fit_transform(mat) # U.dot(Sigma)
self.VT = svd.components_ # VT
def __init__(self, ratings, users, items):
self.users = {k - 1: v for k, v in users.iteritems()}
self.items = {k - 1: v for k, v in items.iteritems()}
self.data = [(uid - 1, iid - 1, r) for uid, iid, r in ratings]
self.mat = to_sparse(self.data, shape=(len(users), len(items)))
pass
