def run():
args = NGCF_Args(parse_args())
# 获取训练集的dataloader形式
data = DATA(args.data_path, args.dataset_name)
train_set, train_U2I, test_U2I, edge_indices, edge_weight, n_users, n_items = data.load(
)
train_dl = get_loader(train_set, train_U2I, n_items, args.batch_size,
args.cores)
# 获取归一化的拉普拉斯矩阵
laplace_graph = Graph(edge_indices, edge_weight)
laplace_graph.add_self_loop()
laplace_graph.norm()
norm_adj = laplace_graph.mat.cuda()
# 定义网络
model = NGCF(n_users, n_items, norm_adj, args)
model = model.cuda()
optimizer = optim.Adam(model.parameters(), lr=args.lr)
# 定义会话
sess = Session(model)
for epoch in range(args.num_epochs):
loss, mf_loss, emb_loss = sess.train(train_dl, optimizer)
print("epoch: {:d}, loss = [{:.6f} == {:.6f} + {:.6f}]".format(
epoch, loss, mf_loss, emb_loss))
perf_info = evaluate(model, n_users, n_items, train_U2I, test_U2I,
args)
print("precision: [{:.6f}] recall: [{:.6f}] ndcg: [{:.6f}]".format(
perf_info[0], perf_info[1], perf_info[2]))
def run():
args = BPRMF_Args(parse_args())
# 获取训练集的dataloader形式
data = DATA(args.data_path, args.dataset_name)
train_set, train_U2I, test_U2I, n_users, n_items = data.load()
train_dl = get_loader(train_set, train_U2I, n_items, args.batch_size,
args.cores)
# 定义网络
model = BPRMF(n_users, n_items, args)
model = model.cuda()
optimizer = optim.Adam(model.parameters(), lr=args.lr)
# 定义会话
sess = Session(model)
for epoch in range(args.num_epochs):
loss, mf_loss, emb_loss = sess.train(train_dl, optimizer)
print("epoch: {:d}, loss = [{:.6f} == {:.6f} + {:.6f}]".format(
epoch, loss, mf_loss, emb_loss))
perf_info = evaluate(model, n_users, n_items, train_U2I, test_U2I,
args)
print("precision: [{:.6f}] recall: [{:.6f}] ndcg: [{:.6f}]".format(
perf_info[0], perf_info[1], perf_info[2]))
def build_args(self):
if self.model_name in ['kgat', 'cfkg', 'nfm', 'cke']:
from utility.parser import parse_args
elif self.model_name.startswith('EKGCN'):
from main import parse_args
elif self.model_name == 'ripple':
from ripple_main import parse_args
args = parse_args()
if self.arg_file is not None:
args = load_args(self.arg_file, args)
return args
def run():
parser = parse_args()
d = Movielens(parser.data_path, parser.threshold)
train_dl, test_dl = get_Dataloader(d.train_set, d.test_set,
parser.batch_size, parser.cores)
model = FactorMachine(d.sparse_n_features, d.dense_n_features,
parser.n_classes, parser.n_factors,
parser.batch_size, parser.decay)
model = model.cuda()
optimizer = optim.Adam(model.parameters(), lr=parser.lr)
sess = Session(model, d.max_user_id, d.max_item_id)
for epoch in range(parser.num_epoch):
loss, cross_loss, l2_loss = sess.train(train_dl, optimizer)
print("epoch: {:d}, loss = [{:.6f} == {:.6f} + {:.6f}]".format(
epoch, loss, cross_loss, l2_loss))
loss, cross_loss, l2_loss, auc = sess.test(test_dl)
print("loss = [{:.6f} == {:.6f} + {:.6f}], auc = [{:.6f}]".format(
loss, cross_loss, l2_loss, auc))
print('\n')
from utility.parser import parse_args
from utility.load_data import *
import subprocess
import torch
args = parse_args()
data_generator = Data(path=args.data_path + args.dataset,
batch_size=args.batch_size)
doc_dict, doc_dict_rev = data_generator.doc_dict, data_generator.doc_dict_rev
qrl_dict, qrl_dict_rev = data_generator.qrl_dict, data_generator.qrl_dict_rev
qrelf = args.data_path + args.dataset + '/qrels'
def pad_sequences(items, maxlen, value=data_generator.n_words):
result = []
for item in items:
if len(item) < maxlen:
item = item + [value] * (maxlen - len(item))
if len(item) > maxlen:
item = item[:maxlen]
result.append(item)
return result
def words_lookup(docs):
if args.model == 'GHRM':
return [data_generator.doc_unqiue_word_list[i] for i in docs]
else:
return [data_generator.doc_word_list[i] for i in docs]
''' Created on Oct 10, 2018 Tensorflow Implementation of Neural Graph Collaborative Filtering (NGCF) model in: Wang Xiang et al. Neural Graph Collaborative Filtering. In SIGIR 2019. @author: Xiang Wang ([email protected]) ''' import utility.metrics as metrics from utility.parser import parse_args from utility.load_data import * import multiprocessing import heapq cores = multiprocessing.cpu_count() // 2 args = parse_args() # It can be called in other scripts Ks = eval(args.Ks) # transfer string into dict, tuple and list data_generator = Data(path=args.data_path + args.dataset, batch_size=args.batch_size) USR_NUM, ITEM_NUM = data_generator.n_users, data_generator.n_items N_TRAIN, N_TEST = data_generator.n_train, data_generator.n_test BATCH_SIZE = args.batch_size def ranklist_by_heapq(user_pos_test, test_items, rating, Ks): item_score = {} for i in test_items: item_score[i] = rating[i] K_max = max(Ks)
