def cal_comm_mat_UBB(path_str):
'''
200k ratings
calculate the commuting matrix in U-B-*-B style
in fact, only need to calculate BB
'''
print "path str:", path_str
uid_filename = dir_ + 'uids.txt'#users
print 'run cal_comm_mat_samples for 10k users in ', uid_filename
lines = open(uid_filename, 'r').readlines()
uids = [int(l.strip()) for l in lines]
uid2ind = {v:k for k,v in enumerate(uids)}
ind2uid = reverse_map(uid2ind)
bid_filename = dir_ + 'bids.txt'#items
lines = open(bid_filename, 'r').readlines()
bids = [int(l.strip()) for l in lines]
bid2ind = {v:k for k,v in enumerate(bids)}
ind2bid = reverse_map(bid2ind)
upb_filename = dir_ + 'uid_pos_bid.txt'# positive rating
upb = np.loadtxt(upb_filename, dtype=int)
# generate users items adjacency matrix
adj_ub, adj_ub_t = generate_adj_mat(upb, uid2ind, bid2ind)
# print uid2ind[640698], bid2ind[51874]
# print type(adj_ub), adj_ub.toarray()[uid2ind[640698]][bid2ind[51874]], adj_ub.toarray().shape
# print type(adj_ub_t), adj_ub_t.toarray()[bid2ind[51874]][uid2ind[640698]], adj_ub_t.toarray().shape
# generate items object adjacency matrix (cat, state, city, star)
adj_bo, adj_bo_t = get_bo(path_str, bid2ind)
t1 = time.time()
# compute u-> b -> o(cat,city) <- b
comm_res = cal_mat_ubb(path_str, adj_ub, adj_bo, adj_bo_t)
t2 = time.time()
print 'cal res of %s cost %2.f seconds' % (path_str, t2 - t1)
print 'comm_res shape=%s,densit=%s' % (comm_res.shape, comm_res.nnz * 1.0/comm_res.shape[0]/comm_res.shape[1])
K = 500
wfilename = dir_ + 'sim_res/path_count/%s_top%s.res' % (path_str, K)
triplets = get_topK_items(comm_res, ind2uid, ind2bid, topK=K)
save_triplets(wfilename, triplets)
#batch_save_comm_res(path_str, wfilename, comm_res, ind2uid, ind2bid)
t3 = time.time()
print 'save res of %s cost %2.f seconds' % (path_str, t3 - t2)
def cal_comm_mat_sm(path_str):
'''
calculate commuting matrix for U-*-U-pos-B style in merge way with 7 simple motifs (sm)
'''
uid_filename = dir_ + 'uids.txt'
bid_filename = dir_ + 'bids.txt'
ub_filename = dir_ + 'uid_bid.txt'
print 'cal commut mat with motif for %s, filenames: %s, %s, %s' % (
path_str, uid_filename, bid_filename, ub_filename)
uids, uid2ind, ind2uid = load_eids(uid_filename, 'user')
bids, bid2ind, ind2bid = load_eids(bid_filename, 'biz')
# upb = np.loadtxt(upb_filename, dtype=np.int64)
ub = np.loadtxt(ub_filename, dtype=np.int64)
# adj_upb, adj_upb_t = generate_adj_mat(upb, uid2ind, bid2ind)
adj_ub, adj_ub_t = generate_adj_mat(ub, uid2ind, bid2ind)
social_filename = dir_ + 'user_social.txt'
uu = np.loadtxt(social_filename, dtype=np.int64)
adj_uu, adj_uu_t = generate_adj_mat(uu, uid2ind, uid2ind)
motif_matrix = compute_motif_matrix(adj_uu, adj_uu_t, path_str)
if path_str[:3] == 'UUB':
base_matrix = adj_uu
if path_str[:4] == 'UBUB':
base_matrix = adj_ub.dot(adj_ub_t)
#for n in range(1, 10):
for n in range(11):
alpha = n * 0.1
UBU_merge = (1 - alpha) * base_matrix + alpha * motif_matrix
start = time.time()
UBUB = UBU_merge.dot(adj_ub)
print 'UBUB(%s), density=%.5f cost %.2f seconds' % (
UBUB.shape, UBUB.nnz * 1.0 / UBUB.shape[0] / UBUB.shape[1],
time.time() - start)
start = time.time()
K = 500
#normal way
triplets = get_topK_items(UBUB, ind2uid, ind2bid, topK=K)
wfilename = dir_ + 'sim_res/path_count/%s_%s_top%s.res' % (path_str,
alpha, K)
save_triplets(wfilename, triplets)
print 'finish saving %s %s entries in %s, cost %.2f seconds' % (
len(triplets), path_str, wfilename, time.time() - start)
def batch_save_comm_res(path_str, wfilename, comm_res, ind2row, ind2col):
coo = comm_res.tocoo(copy=False)
step = 10000000
N = len(coo.row) / step
for i in range(N+1):
start_time = time.time()
triplets = []
start = i * step
end = start + step
rows = coo.row[start:end]
cols = coo.col[start:end]
vs = coo.data[start:end]
for r, c, v in zip(rows, cols, vs):
triplets.append((ind2row[r], ind2col[c], v))
save_triplets(wfilename, triplets, is_append=True)
print 'finish saving 10M %s triplets in %s, progress: %s/%s, cost %.2f seconds' % (path_str, wfilename, (i+1) * step, len(coo.data), time.time() - start_time)
def cal_comm_mat_UBB(path_str):
'''
200k ratings
calculate the commuting matrix in U-B-*-B style
in fact, only need to calculate BB
'''
uid_filename = dir_ + 'uids.txt'
print 'run cal_comm_mat_samples for 10k users in ', uid_filename
lines = open(uid_filename, 'r').readlines()
uids = [int(l.strip()) for l in lines]
uid2ind = {v: k for k, v in enumerate(uids)}
ind2uid = reverse_map(uid2ind)
bid_filename = dir_ + 'bids.txt'
lines = open(bid_filename, 'r').readlines()
bids = [int(l.strip()) for l in lines]
bid2ind = {v: k for k, v in enumerate(bids)}
ind2bid = reverse_map(bid2ind)
upb_filename = dir_ + 'uid_pos_bid.txt'
upb = np.loadtxt(upb_filename, dtype=int)
adj_ub, adj_ub_t = generate_adj_mat(upb, uid2ind, bid2ind)
adj_bo, adj_bo_t = get_bo(path_str, bid2ind)
t1 = time.time()
comm_res = cal_mat_ubb(path_str, adj_ub, adj_bo, adj_bo_t)
t2 = time.time()
print 'cal res of %s cost %2.f seconds' % (path_str, t2 - t1)
print 'comm_res shape=%s,densit=%s' % (comm_res.shape, comm_res.nnz * 1.0 /
comm_res.shape[0] /
comm_res.shape[1])
K = 500
wfilename = dir_ + 'sim_res/path_count/%s_top%s.res' % (path_str, K)
triplets = get_topK_items(comm_res, ind2uid, ind2bid, topK=K)
save_triplets(wfilename, triplets)
#batch_save_comm_res(path_str, wfilename, comm_res, ind2uid, ind2bid)
t3 = time.time()
print 'save res of %s cost %2.f seconds' % (path_str, t3 - t2)
def save_comm_res(path_str, filename, comm_res, ind2row, ind2col):
triplets = []
coo = comm_res.tocoo()
for r, c, v in zip(coo.row, coo.col,coo.data):
triplets.append((ind2row[r], ind2col[c], v))
save_triplets(filename, triplets)
def cal_comm_mat_UUB(path_str, cikm=False):
'''
calculate commuting matrix for U-*-U-pos-B style
'''
print "path str:", path_str
uid_filename = dir_ + 'uids.txt'
bid_filename = dir_ + 'bids.txt'
upb_filename = dir_ + 'uid_pos_bid.txt'
if not cikm:
rid_filename = dir_ + 'rids.txt'
aid_filename = dir_ + 'aids.txt'
print 'cal commut mat for %s, filenames: %s, %s, %s' % (path_str, uid_filename, bid_filename, upb_filename)
uids, uid2ind, ind2uid = load_eids(uid_filename, 'user')
bids, bid2ind, ind2bid = load_eids(bid_filename, 'biz')
if not cikm:
rids, rid2ind, ind2rid = load_eids(rid_filename, 'review')
aids, aid2ind, ind2aid = load_eids(aid_filename, 'aspect')
upb = np.loadtxt(upb_filename, dtype=np.int64)
adj_upb, adj_upb_t = generate_adj_mat(upb, uid2ind, bid2ind)
if path_str == 'UPBUB':
start = time.time()
UBU = adj_upb.dot(adj_upb_t)
print 'UBU(%s), density=%.5f cost %.2f seconds' % (UBU.shape, UBU.nnz * 1.0/UBU.shape[0]/UBU.shape[1], time.time() - start)
elif path_str in ['UPBCatBUB', 'UPBCityBUB']:
start = time.time()
adj_bo, adj_bo_t = get_bo(path_str, bid2ind)
UBO = adj_upb.dot(adj_bo)
UBU = UBO.dot(UBO.transpose())
print 'UBU(%s), density=%.5f cost %.2f seconds' % (UBU.shape, UBU.nnz * 1.0/UBU.shape[0]/UBU.shape[1], time.time() - start)
elif path_str in ['UNBCatBUB', 'UNBCityBUB']:
unb_filename = dir_ + 'uid_neg_bid.txt'
unb = np.loadtxt(unb_filename, dtype=np.int64)
adj_unb, adj_unb_t = generate_adj_mat(unb, uid2ind, bid2ind)
start = time.time()
adj_bo, adj_bo_t = get_bo(path_str, bid2ind)
UBO = adj_unb.dot(adj_bo)
UBU = UBO.dot(UBO.transpose())
print 'UBU(%s), density=%.5f cost %.2f seconds' % (UBU.shape, UBU.nnz * 1.0/UBU.shape[0]/UBU.shape[1], time.time() - start)
elif path_str == 'UNBUB':
unb_filename = dir_ + 'uid_neg_bid.txt'
unb = np.loadtxt(unb_filename, dtype=np.int64)
adj_unb, adj_unb_t = generate_adj_mat(unb, uid2ind, bid2ind)
start = time.time()
UBU = adj_unb.dot(adj_unb_t)
print 'UBU(%s), density=%.5f cost %.2f seconds' % (UBU.shape, UBU.nnz * 1.0/UBU.shape[0]/UBU.shape[1], time.time() - start)
elif path_str == 'UUB':
social_filename = dir_ + 'user_social.txt'
uu = np.loadtxt(social_filename, dtype=np.int64)
adj_uu, adj_uu_t = generate_adj_mat(uu, uid2ind, uid2ind)
start = time.time()
UBU = adj_uu.copy()
print 'UBU(%s), density=%.5f cost %.2f seconds' % (UBU.shape, UBU.nnz * 1.0/UBU.shape[0]/UBU.shape[1], time.time() - start)
elif path_str == 'UCompUB':
uid_comp_filename = dir_ + 'uid_comp.txt'
uc = np.loadtxt(uid_comp_filename, dtype=np.int64)
cids = set(uc[:,1])
cid2ind = {v:k for k,v in enumerate(cids)}
ind2cnd = reverse_map(cid2ind)
adj_uc, adj_uc_t = generate_adj_mat(uc, uid2ind, cid2ind)
start = time.time()
UBU = adj_uc.dot(adj_uc_t)
print 'UBU(%s), density=%.5f cost %.2f seconds' % (UBU.shape, UBU.nnz * 1.0/UBU.shape[0]/UBU.shape[1], time.time() - start)
elif path_str == 'URPARUB':
urpa_filename = dir_ + 'uid_rid_pos_aid.txt'
urpa = np.loadtxt(urpa_filename)
ur = list(set([(u,r) for u, r in urpa[:,(0,1)]]))# u, r multiple aspects, thus u-r can be duplicate
adj_ur, adj_ur_t = generate_adj_mat(ur, uid2ind, rid2ind)
ra = urpa[:,(1,2)]
adj_ra, adj_ua_t = generate_adj_mat(ra, rid2ind, aid2ind)
start = time.time()
URA = adj_ur.dot(adj_ra)
UBU = URA.dot(URA.transpose())#it should be URARU, here we use UBU for convenience
print 'UBU(%s), density=%.5f cost %.2f seconds' % (UBU.shape, UBU.nnz * 1.0/UBU.shape[0]/UBU.shape[1], time.time() - start)
elif path_str == 'URNARUB':
urpa_filename = dir_ + 'uid_rid_neg_aid.txt'
urpa = np.loadtxt(urpa_filename)
ur = list(set([(u,r) for u, r in urpa[:,(0,1)]]))# u, r multiple aspects, thus u-r can be duplicate
adj_ur, adj_ur_t = generate_adj_mat(ur, uid2ind, rid2ind)
ra = urpa[:,(1,2)]
adj_ra, adj_ua_t = generate_adj_mat(ra, rid2ind, aid2ind)
start = time.time()
URA = adj_ur.dot(adj_ra)
UBU = URA.dot(URA.transpose())#it should be URARU, here we use UBU for convenience
print 'UBU(%s), density=%.5f cost %.2f seconds' % (UBU.shape, UBU.nnz * 1.0/UBU.shape[0]/UBU.shape[1], time.time() - start)
start = time.time()
UBUB = UBU.dot(adj_upb)
print 'UBUB(%s), density=%.5f cost %.2f seconds' % (UBUB.shape, UBUB.nnz * 1.0/UBUB.shape[0]/UBUB.shape[1], time.time() - start)
start = time.time()
K = 500
triplets = get_topK_items(UBUB, ind2uid, ind2bid, topK=K)
wfilename = dir_ + 'sim_res/path_count/%s_top%s.res' % (path_str, K)
save_triplets(wfilename, triplets)
#save_comm_res(path_str, wfilename, UBUB, ind2uid, ind2bid)
print 'finish saving %s %s entries in %s, cost %.2f seconds' % (len(triplets), path_str, wfilename, time.time() - start)
