def predict(self, uid, iid, distribution = True):
"""
predict rating matrix entry given userID and itemID,
distribution == True when probability distribution is output
"""
self.initialize(uid, iid, predict = True) # set avg embeddings for cold-start entries
m = np.sum(np.multiply(self.u[uid], self.v[iid]), axis=1)
return softmaxOutput(m, distribution=distribution)
def predict(self, uid, iid, distribution = True):
self.initialize(uid, iid, predict = True)
m = TDreconstruct(self.c, self.u[uid], self.v[iid], self.r)
return softmaxOutput(m, distribution=distribution)
def predict(self, uid, iid, distribution=True):
self.initialize(uid, iid, predict=True)
L1 = self._L1(uid, iid)
outL1 = self._outL1(L1)
L2 = denseLayer(outL1, self.W2, self.B2)
return softmaxOutput(L2, distribution=distribution)
def predict(self, uid, iid, distribution = True):
self.initialize(uid, iid, predict = True)
L1 = self._L1(uid, iid)
return softmaxOutput(L1, distribution = distribution)
def predict(self, uid, iid, distribution=True):
self.initialize(uid, iid, predict=True)
L1 = self._L1(uid, iid)
outL1 = self._outL1(L1)
m = np.sum(np.multiply(self.W2, outL1), axis=1)
return softmaxOutput(m, distribution=distribution)