for k in range(K):
print("cross-val", k)
trainUser = []
testUser = []
for i in range(K):
if i == k:
testUser = KshuffleUserId[i]
else:
trainUser.extend(KshuffleUserId[i])
data["rnd"] = np.random.random(data.shape[0])
trainInd = list(map(lambda x: x in trainUser, data["userId"])) | (data["rnd"] < 0.7)
dataTrain = data[trainInd]
dataTest = data[np.invert(trainInd)]
bob = graphALS(num_factors=5, num_iterations=20, verbose=True)
bob.fit(dataTrain[["userId", "movieId", "rating"]], userContextSparseGraph, itemContextSparseGraph)
Rhat = bob.user_vectors.dot(bob.item_vectors.T)
R_test = csr_matrix((dataTest["rating"], (dataTest["userId"], dataTest["movieId"])), shape=(numUser, numItem))
W = R_test.nonzero()
rmse = RMSE(R_test, Rhat, W)
print(rmse)
R = csr_matrix((dataTrain["rating"], (dataTrain["userId"], dataTrain["movieId"])), shape=(numUser, numItem))
bobALS = ALS(5)
bobALS.fit(R)
Rhat_ALS = bobALS.U.dot(bobALS.V.T)
rmseALS = RMSE(R_test, Rhat_ALS, W)
print(rmseALS)
if i == k:
testUser = KshuffleUserId[i]
else:
trainUser.extend(KshuffleUserId[i])
data['rnd'] = np.random.random(data.shape[0])
trainInd = (list(map(lambda x: x in trainUser, data['userId'])) |
(data['rnd'] < 0.7))
dataTrain = data[trainInd]
dataTest = data[np.invert(trainInd)]
bob = graphALS(num_factors=5, num_iterations=20, verbose=True)
bob.fit(dataTrain[['userId', 'movieId', 'rating']], userContextSparseGraph,
itemContextSparseGraph)
Rhat = bob.user_vectors.dot(bob.item_vectors.T)
R_test = csr_matrix(
(dataTest['rating'], (dataTest['userId'], dataTest['movieId'])),
shape=(numUser, numItem))
W = R_test.nonzero()
rmse = RMSE(R_test, Rhat, W)
print(rmse)
R = csr_matrix(
(dataTrain['rating'], (dataTrain['userId'], dataTrain['movieId'])),
shape=(numUser, numItem))
bobALS = ALS(5)
bobALS.fit(R)
Rhat_ALS = bobALS.U.dot(bobALS.V.T)
rmseALS = RMSE(R_test, Rhat_ALS, W)
print(rmseALS)
lambdas = params['ALS-WR']['params']['lambda']
rank = params['ALS-WR']['params']['rank']
current_perf = dict.fromkeys(['model','lambda','rank','crossval'])
for elt in itertools.product(*[lambdas,rank,range(K)]):
l, r, k = elt
current_perf['model'] = 'ALS-WR'
current_perf['lambda'] = l
current_perf['rank'] = r
current_perf['crossval'] = k
print(current_perf)
bob = ALS(d=r,num_users=numUser,num_items=numItem,lbda=l,parallel=True)
train = data[data['cv']!=k][['row','col','val']].to_dict(orient='list')
test = data[data['cv']==k][['row','col','val']].to_dict(orient='list')
t0 = time()
bob.fit(train)
T = time()-t0
Rhat = bob.U.dot(bob.V.T)
R_test = sparse_matrix(test,numUser,numItem)
rmse = RMSE(R_test,Rhat)
print(rmse)
ind = getLine_fromdict(perf,current_perf)
perf.loc[ind,['model','rank','lambda','crossval','rmse','runningTime']] = ['ALS-WR',r,l,k,rmse,T]
print('-'*50)
#==============================================================================
# bagging ALS-WR
#==============================================================================
if params['bagging ALS-WR']['learn']=="True":