def TestItemCF():
""" 测试 ItemCF 算法
Desc:
Args:
Returns:
"""
start = time.time()
path = '~/file/rs/dataset/ml-1m/ratingsTest.dat'
d_file = pd.read_csv(path, sep='::', usecols=[0, 1, 2])
M = 8 # 分组数
N = 10 # 推荐个数
K = [5, 10, 20, 40, 80, 120, 160]
train, test, train_items_list, item_popularity, items_user = SplitData(d_file, M, 1) # 0: seed
w_item = ItemCF.ItemSimilarityVersion1(train, item_popularity, items_user)
columns_list = [
'precision', 'recall', 'coverage', 'popularity'
]
d = pd.DataFrame(
np.zeros([len(K), len(columns_list)]), index=K, columns=columns_list)
p = Pool(4)
result = dict()
for k in K:
result[k] = p.apply_async(Evaluation, args=(k, train, test, item_popularity, w_item, N, 2))
p.close()
p.join() # 等待所有子进程执行完毕
for k, v in result.items():
d.loc[k, columns_list] += v.get()
end = time.time()
print('total time: %.2fs' % (end - start))
d.to_excel('Result-ItemCF-K.xlsx', 'ItemCF-K')
fig, axes = plt.subplots(2, 2)
axes[0][0].set_title('Precision')
axes[0][0].plot(d.iloc[:, 0], 'o-', label='precision')
axes[0][1].set_title('Recall')
axes[0][1].plot(d.iloc[:, 1], 'o-', label='recall')
axes[1][0].set_title('Coverage')
axes[1][0].plot(d.iloc[:, 2], 'o-', label='coverage')
axes[1][1].set_title('Popularity')
axes[1][1].plot(d.iloc[:, 3], 'o-', label='popularity')
plt.legend()
plt.show()
def TestItemCF_Norm():
""" 对比 ItemCF 和 ItemCF-Norm
Desc:
Args:
Returns:
"""
file_path = '~/file/rs/dataset/ml-1m/ratings.dat'
start = time.time()
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]
train, test, train_items_list, item_popularity, items_user = SplitData(d_file, M, 0) # 0: seed
W_ItemCF = ItemCF.ItemSimilarityVersion1(train, item_popularity, items_user)
W_Norm = ItemCF.ItemSimilarityNorm(train, item_popularity, items_user)
columns_list = [
'Precision-ItemCF', 'Precision-Norm', 'Recall-ItemCF', 'Recall-Norm',
'Coverage-ItemCF', 'Coverage-Norm', 'Popularity-ItemCF',
'Popularity-Norm'
]
I_columns = [
'Precision-ItemCF', 'Recall-ItemCF', 'Coverage-ItemCF', 'Popularity-ItemCF'
]
II_columns = [
'Precision-Norm', 'Recall-Norm', 'Coverage-Norm', 'Popularity-Norm'
]
d = pd.DataFrame(
np.zeros([len(K), len(columns_list)]), index=K, columns=columns_list)
# ItemCF
p = Pool(4)
resultItemCF = dict()
resultNorm = dict()
for k in K:
resultItemCF[k] = p.apply_async(Evaluation, args=(k, train, test, item_popularity, W_ItemCF, N))
resultNorm[k] = p.apply_async(Evaluation, args=(k, train, test, item_popularity, W_Norm, N))
p.close()
p.join() # 等待所有子进程执行完毕
for k, v in resultItemCF.items():
d.loc[k, I_columns] += v.get()
for k, v in resultNorm.items():
d.loc[k, II_columns] += v.get()
end = time.time()
print('total time: %.2fs' % (end - start))
d.to_excel('Result-ItemCF-Norm-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()
