def exp():
'''
编写实验逻辑
'''
filepath = r'./data/netflix5k_result.txt'
train_data, test_data = readData(filepath, split=',', train_ratio=0.7)
train_data = train_data.rename(columns={0: 'uid', 1: 'iid'})
test_data = test_data.rename(columns={0: 'uid', 1: 'iid'})
train, _, udegree, idegree = process_data(train_data, test_data)
# userid从1开始的情况
total_item_score = np.zeros(train.shape[1], dtype=np.float64)
for user in tqdm(range(1, train.shape[0]), ascii=True):
# userid从0开始的情况
# for user in range(train.shape[0]):
one_item_score = massDiffisionForOne(train,
user,
udegree,
idegree,
K=1000)
total_item_score += one_item_score
# 获得度-itemset 分布信息
Ndegree_items = getNdegree_items(idegree, N=20)
# 获得testset item度分布
test_item_degree = test_data.iid.value_counts()
corr_score = trend_predict(total_item_score,
Ndegree_items,
test_item_degree,
method='pearson')
print(corr_score)
def exp(mylambda):
'''
编写实验逻辑
'''
# score_filepath = 'temp/md_delicious111.pkl'
# filepath = r'./data/delicious/delicious_subset2.txt'
# filepath = r'./data/Amazon/amazon_gpu.csv'
# score_filepath = 'temp/md_amazon_nok1.pkl'
# filepath = r'./data/netflix5k_result.txt'
# score_filepath = 'temp/md_nf_noknn1.pkl'
filepath = r'./data/movielen5000_7533_link864581_day0_1096.txt'
score_filepath = 'temp/md_ml_noknn.pkl'
# train_data, test_data = readData(filepath, split='\t', train_ratio=0.7)
train_data, test_data = readData(filepath, split=',', train_ratio=0.7)
train_data = train_data.rename(columns={0:'uid',1:'iid'})
test_data = test_data.rename(columns={0:'uid',1:'iid'})
train, _, udegree, idegree = process_data(train_data, test_data)
# 获得度-itemset 分布信息
degreedistrev = degree_item_map(idegree)
Ndegree_items = getNdegree_items(degreedistrev, N=10)
# 获得testset item度分布
test_item_degree = test_data.iid.value_counts()
# userid从1开始的情况
total_item_score = np.zeros(train.shape[1], dtype=np.float64)
if os.path.exists(score_filepath):
item_scores = pickle.load(open(score_filepath,'rb'))
for user in tqdm(range(1,train.shape[0]),ascii=True):
if udegree.get(user, 0.0) == 0.0:
continue
one_item_score = item_scores[user]
total_item_score += one_item_score * pow(udegree.get(user), mylambda)
else:
item_scores = {}
for user in tqdm(range(1,train.shape[0]),ascii=True):
# userid从0开始的情况
# for user in range(train.shape[0]):
if udegree.get(user, 0.0) == 0.0:
continue
one_item_score = massDiffisionForOne(train, user, udegree, idegree, mylambda)
total_item_score += one_item_score * pow(udegree.get(user), mylambda)
item_scores[user] = one_item_score
pickle.dump(item_scores, open(score_filepath,'wb'))
corr_score = trend_predict(total_item_score,
Ndegree_items,
test_item_degree,
method='pearson')
print(corr_score)
return corr_score