def test_classifier(model, filename=None, itemkey="track", selector="SELECT * FROM train"):
conn = sqlite3.connect("db.sqlite")
conn.row_factory = dict_factory
cur = conn.cursor()
s = 0
c = 0
t_p = 0
for i in range(0,10):
svd = SVD()
if filename is not None:
svd.load_model(filename)
l = list(cur.execute(selector))
random.shuffle(l)
count = len(l)
svd.set_data([(x["rating"],x["track"],x["user"]) for x in l[0:int(count*0.7)]])
K = 1000
svd.compute(k=K, min_values=0.0, pre_normalize=None, mean_center=True, post_normalize=True)
pairs = []
for idx,item in enumerate(l[int(count*0.7):]):
user = item["user"]
track = item[itemkey]
pairs.append((predict_item(svd, track,user), item["rating"]))
t_p += len(pairs)
s += RMSE(pairs).compute()
c += 1.0
print "iteration"
print s/c, t_p
def getSimilarityMatrix(svd_model_file): """ Returns similarity matrix from svd_model_file """ #Import SVD from file svd=SVD() svd.load_model(svd_model_file) return svd.get_matrix_similarity()
def test_load_model():
svd2 = SVD()
svd2.load_model(os.path.join(MOVIELENS_DATA_PATH, 'SVD_matrix'))
recs_svd = svd.recommend(USERID1, NUM_SIMILARS, is_row=False)
recs_svd2 = svd2.recommend(USERID1, NUM_SIMILARS, is_row=False)
assert_equal(recs_svd, recs_svd2)
def test_load_model():
svd2 = SVD()
svd2.load_model(os.path.join(MOVIELENS_DATA_PATH, 'SVD_matrix'))
recs_svd = svd.recommend(USERID1, NUM_SIMILARS, is_row=False)
recs_svd2 = svd2.recommend(USERID1, NUM_SIMILARS, is_row=False)
assert_equal(recs_svd, recs_svd2)
class RecommendSystem(object):
def __init__(self, filename, sep, **format):
self.filename = filename
self.sep = sep
self.format = format
# 训练参数
self.k = 100
self.min_values = 10
self.post_normalize = True
self.svd = SVD()
# 判断是否加载
self.is_load = False
# 添加数据处理
self.data = Data()
# 添加模型评估
self.rmse = RMSE()
def get_data(self):
"""
获取数据
:return: None
"""
# 如果模型不存在
if not os.path.exists(tmpfile):
# 如果数据文件不存在
if not os.path.exists(self.filename):
sys.exit()
# self.svd.load_data(filename=self.filename, sep=self.sep, format=self.format)
# 使用Data()来获取数据
self.data.load(self.filename, sep=self.sep, format=self.format)
train, test = self.data.split_train_test(percent=80)
return train, test
else:
self.svd.load_model(tmpfile)
self.is_load = True
return None, None
def train(self, train):
"""
训练模型
:param train: 训练数据
:return: None
"""
if not self.is_load:
self.svd.set_data(train)
self.svd.compute(k=self.k,
min_values=self.min_values,
post_normalize=self.post_normalize,
savefile=tmpfile[:-4])
return None
def rs_predict(self, itemid, userid):
"""
评分预测
:param itemid: 电影id
:param userid: 用户id
:return: None
"""
score = self.svd.predict(itemid, userid)
print "推荐的分数为：%f" % score
return score
def recommend_to_user(self, userid):
"""
推荐给用户
:param userid: 用户id
:return: None
"""
recommend_list = self.svd.recommend(userid, is_row=False)
# 读取文件里的电影名称
movie_list = []
for line in open(moviefile, "r"):
movie_list.append(' '.join(line.split("::")[1:2]))
# 推荐具体电影名字和分数
for itemid, rate in recommend_list:
print "给您推荐了%s,我们预测分数为%s" % (movie_list[itemid], rate)
return None
def evaluation(self, test):
"""
模型的评估
:param test: 测试集
:return: None
"""
# 如果模型不是直接加载
if not self.is_load:
# 循环取出测试集里面的元组数据<评分，电影，用户>
for value, itemid, userid in test.get():
try:
predict = self.rs_predict(itemid, userid)
self.rmse.add(value, predict)
except KeyError:
continue
# 计算返回误差（均方误差）
error = self.rmse.compute()
print "模型误差为%s:" % error
return None
def load_svd(filename):
svd = SVD()
svd.load_model(filename)
return svd
class RecommendSystem(object):
def __init__(self, filename, sep, **format):
# 文件信息
self.filename = filename
self.sep = sep
self.format = format
# 初始化矩阵分解
self.svd = SVD()
# 矩阵信息
self.k = 100 # 矩阵的隐因子睡昂
self.min_values = 10 # 删除评分少于10人的电影
self.post_normalize = False
# 设置是否加载模型标志
self.load_model = False
# 初始化均方误差
self.rmse = RMSE()
def get_data(self):
# 如果模型不存在，则需要加载数据
if not os.path.exists(filename):
if not os.path.exists(self.filename):
sys.exit()
# SVD加载数据
# self.svd.load_data(filename=self.filename, sep=self.sep, format=self.format)
data = Data()
data.load(self.filename, sep=self.sep, format=self.format)
# 分割数据集
train, test = data.split_train_test(percent=80)
return train, test
else:
# 直接加载模型
self.svd.load_model(filename)
# 将是否加载模型设为True
self.load_model = True
return None, None
def train(self, train):
"""
训练数据
:param train: 训练集
:return:
"""
if not self.load_model:
# svd去获取训练数据集
self.svd.set_data(train)
# 注意传入的文件名字，不是带后缀名
self.svd.compute(k=self.k,
min_values=self.min_values,
post_normalize=self.post_normalize,
savefile=filename[:-4])
return None
def recommend_to_user(self, userid):
"""
推荐结果
:param usrid: 用于ID
:return: None
"""
recommend_list = self.svd.recommend(userid, is_row=False)
# 打印电影的名称，和预测的评分
# 构建电影名字的列表
movies_list = []
for line in open("./data/ml-1m/movies.dat", "r"):
movies_list.append(' '.join(line.split("::")[1:2]))
# 依次取出推荐ID
for itemid, rating in recommend_list:
print "给你推荐的电影叫%s, 预测你对它的评分是%f" % (movies_list[itemid], rating)
return None
def rs_predict(self, userid, itemid):
"""
得出评分
:param userid: 用户ID
:param itemid: 物品ID
:return: 评分
"""
score = self.svd.predict(itemid, userid)
return score
def evaluation(self, test):
"""
均方误差评估模型
:param test: 测试数据
:return: None
"""
if not self.load_model:
# 获取测试数据中的id,rat, <rat, row(itemid), col(userid)>
for rating, itemid, userid in test.get():
try:
# rating真是值
score = self.rs_predict(userid, itemid)
# 添加所有的测试数据
self.rmse.add(rating, score)
except KeyError:
continue
error = self.rmse.compute()
print "均方误差为：%s" % error
return None
