def baselines(self, data, reg_i, reg_u, reg_it, width_mu, width_it):
logging.info("Computing mu...")
self.mu = WindowedAverage(width_mu)
for v1, v2, r, t in data.iter_ratings():
self.mu.add(t, r)
self.mu.process()
logging.info("Computing item baselines...")
self.cbi = []
for ratings in data.r_i:
t = 0
n = 0
for user_id, r, timestamp in ratings:
t += (r - self.mu.query(timestamp))
n += 1
self.cbi.append(t / float(reg_i + n))
self.cbi = array(self.cbi)
logging.info("Computing item baseline functions...")
self.cbit = []
for item_id, ratings in enumerate(data.r_i):
cb = WindowedAverage(width_it, reg_it)
for user_id, r, t in ratings:
cb.add(t, r - self.cbi[item_id] - self.mu.query(t))
self.cbit.append(cb.process())
logging.info("Computing user baselines...")
self.cbu = []
for user_id, ratings in data.iter_users():
t = 0
n = 0
for item_id, r, timestamp in ratings:
t += (r - self.cbi[item_id] - self.cbit[item_id].query(timestamp) - self.mu.query(timestamp))
n += 1
self.cbu.append(t / float(reg_u + n))
self.cbu = array(self.cbu)
self.bi = array(self.cbi)
self.bu = array(self.cbu)
class CFModel(CFModelBase):
def cbui(self, user_id, item_id, t):
return self.mu.query(t) + self.cbu[user_id] + self.cbi[item_id] + self.cbit[item_id].query(t)
def bui(self, user_id, item_id, t):
return self.mu.query(t) + self.bu[user_id] + self.bi[item_id] + self.cbit[item_id].query(t)
def load(self, filename):
with open(filename) as file_read:
self.mu, self.bu, self.bi, \
self.cbu, self.cbi, self.cbit, self.q, self.x, \
self.alpha, self.f = cPickle.loads(file_read.read())
return self
def save(self, filename):
with open(filename, "w") as file_write:
file_write.write(cPickle.dumps((self.mu, self.bu, self.bi, self.cbu, self.cbi, self.cbit, self.q, self.x, self.alpha, self.f), protocol=-1))
def baselines(self, data, reg_i, reg_u, reg_it, width_mu, width_it):
logging.info("Computing mu...")
self.mu = WindowedAverage(width_mu)
for v1, v2, r, t in data.iter_ratings():
self.mu.add(t, r)
self.mu.process()
logging.info("Computing item baselines...")
self.cbi = []
for ratings in data.r_i:
t = 0
n = 0
for user_id, r, timestamp in ratings:
t += (r - self.mu.query(timestamp))
n += 1
self.cbi.append(t / float(reg_i + n))
self.cbi = array(self.cbi)
logging.info("Computing item baseline functions...")
self.cbit = []
for item_id, ratings in enumerate(data.r_i):
cb = WindowedAverage(width_it, reg_it)
for user_id, r, t in ratings:
cb.add(t, r - self.cbi[item_id] - self.mu.query(t))
self.cbit.append(cb.process())
logging.info("Computing user baselines...")
self.cbu = []
for user_id, ratings in data.iter_users():
t = 0
n = 0
for item_id, r, timestamp in ratings:
t += (r - self.cbi[item_id] - self.cbit[item_id].query(timestamp) - self.mu.query(timestamp))
n += 1
self.cbu.append(t / float(reg_u + n))
self.cbu = array(self.cbu)
self.bi = array(self.cbi)
self.bu = array(self.cbu)
def train(self, data, reg, reg_i, reg_u, reg_it, width_mu, width_it, min_iter, max_iter, step_size):
self.baselines(data, reg_i, reg_u, reg_it, width_mu, width_it)
logging.info("Performing optimization...")
if self.x is None:
self.x = [array([(random.random()-0.5)/100000.0 \
for i in range(self.f)]) for j in range(data.m)]
if self.q is None:
self.q = [array([(random.random()-0.5)/100000.0 \
for i in range(self.f)]) for j in range(data.m)]
last_tot = float('inf')
for iter in range(max_iter):
tot = 0
rmse = 0
n = 0
for user_id in range(data.n):
cw = len(data.r_u[user_id])**(-self.alpha)
p = cw * sum((r - self.cbui(user_id, item_id, t))*self.x[item_id] \
for item_id, r, t in data.r_u[user_id])
s = 0
for item_id, r, t in data.r_u[user_id]:
rp = self.bui(user_id, item_id, t) + dot(self.q[item_id], p)
e = r - rp
tot += e**2 + reg*(self.bu[user_id]**2 + self.bi[item_id]**2 + \
dot(self.q[item_id], self.q[item_id]))
s += e*self.q[item_id]
self.q[item_id] += step_size * (e*p - reg*self.q[item_id])
self.bu[user_id] += step_size * (e - reg*self.bu[user_id])
self.bi[item_id] += step_size * (e - reg*self.bi[item_id])
rmse += e**2
n += 1
for item_id, r, t in data.r_u[user_id]:
tot += reg * len(data.r_u[user_id]) * \
dot(self.x[item_id], self.x[item_id])
self.x[item_id] += step_size * (cw * \
(r - self.cbui(user_id, item_id, t))*s - reg*self.x[item_id])
logging.info("%s: %s, %s", iter, (rmse / n) ** 0.5, tot)
if iter >= min_iter and tot > last_tot:
logging.info("Stopping early")
return
last_tot = tot