def fit(self, ratings):
self.avg_item = {iid: np.mean(map(key_r, data))
for iid, data in sgroupby(ratings, key_i)}
self.global_avg_item = np.mean(map(key_r, ratings))
self.offset_user = {
uid: np.mean([r - self.avg_item[i] for _, i, r in data])
for uid, data in sgroupby(ratings, key_u)}
self.global_offset_user = np.mean(
[r - self.avg_item[i] for _, i, r in ratings]
)
def better_mean(data, key):
rs = map(key_r, data)
global_var = np.var(rs)
global_avg = np.mean(rs)
grouped = [(id, map(key_r, d)) for id, d in sgroupby(data, key)]
K = {id: np.var(d) / global_var for id, d in grouped}
avg_item = {id: (global_avg * K[id] + np.sum(r)) / (K[id] + len(r))
for id, r in grouped}
return avg_item, global_avg
