def main():
# 读取数据集
file_path = '~/file/rs/dataset/ml-1m/ratings.dat'
d_file = eva.readData(file_path, '::')
M = 8 # 分组数
N = 10 # 推荐个数
K = [5, 10, 20, 40, 80, 120, 160]
# seeds = np.arange(M)
seeds = [0]
columns_list = [
'PrecisionUserCF', 'PrecisionItemCF', 'RecallUserCF', 'RecallItemCF',
'CoverageUserCF', 'CoverageItemCF', 'PopularityUserCF',
'PopularityItemCF'
]
userCF_columns = [
'PrecisionUserCF', 'RecallUserCF', 'CoverageUserCF', 'PopularityUserCF'
]
itemCF_columns = [
'PrecisionItemCF', 'RecallItemCF', 'CoverageItemCF', 'PopularityItemCF'
]
d = pd.DataFrame(np.zeros([len(K), len(columns_list)]),
index=K,
columns=columns_list)
for index, seed in enumerate(seeds):
train, test = eva.SplitData(d_file, M, seed)
item_popularity = eva.ItemsPopularity(d_file, M, seed)
W_user = UserCF.UserSimilarityVersion3(train)
W_item = ItemCF.ItemSimilarityVersion2(train)
for k in K:
precision, recall, coverage, popularity = eva.PrecisionAndRecallAndCoverageAndPopularity(
train, test, item_popularity, k, W_user, N, 1)
d.loc[k,
userCF_columns] += [precision, recall, coverage, popularity]
precision, recall, coverage, popularity = eva.PrecisionAndRecallAndCoverageAndPopularity(
train, test, item_popularity, k, W_item, N, 2)
d.loc[k,
itemCF_columns] += [precision, recall, coverage, popularity]
d.loc[k] /= (index + 1)
d.to_excel('Result-UserCF-ItemCF-K.xlsx', 'UserCF-ItemCF-K')
fig, axes = plt.subplots(2, 2)
axes[0][0].set_title('Precision')
d.iloc[:, 0:2].plot(ax=axes[0][0], style=['o-', 'o-'])
axes[0][1].set_title('Recall')
d.iloc[:, 2:4].plot(ax=axes[0][1], style=['o-', 'o-'])
axes[1][0].set_title('Coverage')
d.iloc[:, 4:6].plot(ax=axes[1][0], style=['o-', 'o-'])
axes[1][1].set_title('Popularity')
d.iloc[:, 6:8].plot(ax=axes[1][1], style=['o-', 'o-'])
plt.show()
def test_recommend():
""" 对比原版推荐算法和改进后的推荐算法
Desc:
Args:
Returns:
"""
file_path = '~/file/rs/dataset/ml-1m/ratings.dat'
d_file = eva.readData(file_path, '::')
M = 8 # 分组数
N = 10 # 推荐个数
K = [5, 10, 20, 40, 80, 120, 160]
# K = [5, 10, 20, 40]
train, test, train_items_list, item_popularity, items_user = SplitData(d_file, M, 0) # 0: seed
# W = ItemCF.ItemSimilarityVersion1(train, item_popularity, items_user)
W = ItemCF.ItemSimilarityVersion2(train, item_popularity, items_user)
columns_list = [
'Precision-I', 'Precision-II', 'Recall-I', 'Recall-II',
'Coverage-I', 'Coverage-II', 'Popularity-I',
'Popularity-II'
]
I_columns = [
'Precision-I', 'Recall-I', 'Coverage-I', 'Popularity-I'
]
II_columns = [
'Precision-II', 'Recall-II', 'Coverage-II', 'Popularity-II'
]
d = pd.DataFrame(
np.zeros([len(K), len(columns_list)]), index=K, columns=columns_list)
# ItemCF
p = Pool(4)
resultI = dict()
resultII = dict()
for k in K:
resultI[k] = p.apply_async(Evaluation, args=(k, train, test, item_popularity, W, N, 1))
resultII[k] = p.apply_async(Evaluation, args=(k, train, test, item_popularity, W, N, 2))
p.close()
p.join() # 等待所有子进程执行完毕
for k, v in resultI.items():
d.loc[k, I_columns] += v.get()
for k, v in resultII.items():
d.loc[k, II_columns] += v.get()
d.to_excel('Result-ItemCF-Recommend-K.xlsx', 'ItemCF-K')
fig, axes = plt.subplots(2, 2)
axes[0][0].set_title('Precision')
d.iloc[:, 0:2].plot(ax=axes[0][0], style=['o-', 'o-'])
axes[0][1].set_title('Recall')
d.iloc[:, 2:4].plot(ax=axes[0][1], style=['o-', 'o-'])
axes[1][0].set_title('Coverage')
d.iloc[:, 4:6].plot(ax=axes[1][0], style=['o-', 'o-'])
axes[1][1].set_title('Popularity')
d.iloc[:, 6:8].plot(ax=axes[1][1], style=['o-', 'o-'])
plt.legend()
plt.show()
