public Form_SlopeOne()
{
InitializeComponent();
// 默认选择第一个数据集
this.comboBox1.SelectedIndex = 0;
// 读取数据，得到训练用户集合以及测试用户集合
obj_ReadData = new cReadinData(this.comboBox1.SelectedIndex);
obj_AssStrategy = new cAssStrategy();
testUsers = cReadinData.getTestUser();
trainUsers = cReadinData.getBaseUser();
this.dataGridView1.RowHeadersVisible = false;
this.dataGridView2.RowHeadersVisible = false;
for (int i = 0; i < count_Num.Length; i++)
{
count_Num[i] = 0;
stat_Info[i] = 0;
}
// 根据选择的数据集，填充用户ID的下拉列表
for (int i = 0; i < testUsers.Length - 1; i++)
{
this.comboBox2.Items.Add(testUsers[i + 1].id);
}
// 用户ID默认选择第一个
this.comboBox2.SelectedIndex = 0;
obj_SlopeOne = new SlopeOne();
for (int i = 1; i < trainUsers.Length; i++)
{
userRating = new Dictionary<int, float>();
//count_Num[trainUsers[i].RatingNums/20]++;
for (int j = 1; j < trainUsers[i].Ratings.Length; j++)
{
if (trainUsers[i].Ratings[j] != 0)
{
userRating.Add(j, (float)trainUsers[i].Ratings[j]);
}
}
obj_SlopeOne.AddUserRatings(userRating);
}
this.comboBox3.Items.Clear();
// 填充 连续运行用户数目 下拉列表
for (int i = 15; i < testUsers.Length; i++)
{
comboBox3.Items.Add(i);
}
this.comboBox3.SelectedIndex = 0;
}
public static cAssStrategy getAssStrategy(cUser test_User, int Top_N )
{
cAssStrategy obj_AssStrategy = new cAssStrategy();
TestUserLoveItems_id = new ArrayList();
TestUserDratItems_id = new ArrayList();
TestUserUnRatingItems_id = new ArrayList();
bool[] isLoved_Test = test_User.discretizeRating();
// 获得推荐项目中用户喜欢的项目数目
float count_interest = 0;
int itemid;
for (int i = 0; (i < Top_N) && (i < recItems.Length - 1); i++)
{
itemid = recItems[i+1].recItems_id;
// 用户喜欢该项目
if (isLoved_Test[itemid] == true)
{
count_interest++;
TestUserLoveItems_id.Add(i + 1);
}
// 用户不喜欢该项目(即对其评分不为零)
else if (test_User.Ratings[itemid] != 0)
{
TestUserDratItems_id.Add(i + 1);
}
// 用户测试集未对该项目进行评分
else
{
TestUserUnRatingItems_id.Add(i + 1);
}
}
// 如果推荐列表的长度小于Top_N值
if (recItems.Length < Top_N)
{
Top_N = recItems.Length;
}
// 计算查准率
obj_AssStrategy.Precison = (float) (count_interest / (float)Top_N);
// 计算查全率
// 测试集中用户喜欢的项目数量
int count_total = test_User.love_items_num;
obj_AssStrategy.Recall = (float)(count_interest / (float)count_total);
return obj_AssStrategy;
}
public Form_UBCF()
{
InitializeComponent();
dataGridView1.RowHeadersVisible = false;
this.comboBox2.Items.Clear();
obj_AssStrategy = new cAssStrategy();
for (int i = 15; i < cReadinData.test_usernum[comboBox1.SelectedIndex]; i++)
{
this.comboBox2.Items.Add(i);
}
this.comboBox2.SelectedIndex = 0;
}
/// <summary>
/// 预测目标用户objDest对项目的评分
/// </summary>
/// <param name="objDest">测试用户</param>
/// <param name="alg">相似度算法选择</param>
/// <param name="neigh_num">最近邻居个数</param>
/// <param name="Rec_Items_num">Top-N推荐个数</param>
/// <returns>算法评价指标</returns>
public cAssStrategy getPredictRating(cUser objDest, int alg, int neigh_num, int Rec_Items_num)
{
objAssStrategy = new cAssStrategy();
objUsers = cReadinData.getBaseUser();
preditUser = new cUser(objDest.id);
int[][] neighItems = null;
double[][] dSimilarity = null;
cUser sourceUser = objUsers[objDest.id];
switch (alg)
{
case 1:
neighItems = neighItems_Cosine;
dSimilarity = dSimilarity_Cosine;
break;
case 2:
neighItems = neighItems_Pearson;
dSimilarity = dSimilarity_Pearson;
break;
case 3:
neighItems = neighItems_AdjCosine;
dSimilarity = dSimilarity_AdjCosine;
break;
}
double numerator = 0, denominator = 0;
double total_MAE = 0;
for (int i = 1; i < objDest.Ratings.Length; i++)
{
// if ((alg == 1) && (ignoreItems.Contains(i-1)))
// {
// break ;
// }
// 对目标用户训练集合里评分为零的项(itemid为i)产生预测评分
if (sourceUser.Ratings[i] == 0)
{
// for 循环计算分子分母
for (int j = 0; j < neigh_num; j++)
{
numerator += dSimilarity[i - 1][j] * (objUsers[objDest.id].Ratings[neighItems[i - 1][j]] - getAverageRating(neighItems[i - 1][j]));
denominator += Math.Abs(dSimilarity[i-1][j]);
}
// 确保分母不为零
if(denominator == 0)
break;
preditUser.Ratings[i] = objDest.Ratings[i] * 0.05 + Math.Abs( getAverageRating(i) + numerator / denominator ) ;
if (preditUser.Ratings[i] > 5)
preditUser.Ratings[i] = 5;
numerator = 0;
denominator = 0;
// 和测试集中的数据相减，计算总的MAE
if (objDest.Ratings[i] != 0)
{
total_MAE += Math.Abs(preditUser.Ratings[i] - objDest.Ratings[i]);
}
}
}
objAssStrategy.MAE = total_MAE / (objDest.RatingNums + neigh_num );
//////////////////////////////////////////////////////////////////////////
// 计算关于Top-N推荐的分类精确度准则
// Top-N推荐的项目id, 推荐个数固定为20,便于算法比对
int[] itemid_TopN = new int[Rec_Items_num];
int count_interest = 0; // 记录用户对推荐的项目有兴趣的个数
int count_total = 0; // 记录用户测试集合中
float inter_rating = (float) ((float)sourceUser.getTotalRating() / (float)sourceUser.RatingNums);
// 计算N项推荐项目id 和 查准率
for (int i = 0; i < itemid_TopN.Length; i++)
{
itemid_TopN[i] = SelectMaxIndex(preditUser.Ratings);
preditUser.Ratings[itemid_TopN[i]] = -1;
if (objDest.Ratings[itemid_TopN[i]] >= inter_rating )
count_interest++;
}
// 计算测试集中用户喜欢的项目
foreach (int rating in objDest.Ratings)
{
if (rating >= inter_rating)
count_total++;
}
objAssStrategy.Precison = (float)count_interest / itemid_TopN.Length; // 查准率(Precison)
if (count_total == 0)
objAssStrategy.Recall = 0;
else
objAssStrategy.Recall = (float)count_interest / count_total; // 查全率(Recall)
return objAssStrategy;
}
private void button1_Click(object sender, EventArgs e)
{
DateTime dt_1 = DateTime.Now;
this.Rec_Items_num = int.Parse(this.textBox13.Text); // Top-N推荐个数
this.progressBar1.Maximum = (this.comboBox2.SelectedIndex + 15) * 10 + 5;
this.progressBar1.Value = 0;
// 读入数据，生成UI矩阵
this.textBox3.Text = "开始读入数据";
this.progressBar1.Value++;
Application.DoEvents();
cReadinData obj_ReadData = new cReadinData(comboBox1.SelectedIndex);
this.textBox3.Text = "读入数据完成 训练数据：" + obj_ReadData.sTrainFileName[comboBox1.SelectedIndex]
+ " 测试数据：" + obj_ReadData.testfileName[comboBox1.SelectedIndex];
this.progressBar1.Value += 2;
Application.DoEvents();
// 读取最近邻居个数
int number = int.Parse(textBox2.Text);
this.neigh_num = number;
// 相似度算法的选择
if(this.radioButton1.Checked)
{
sim_alg = 1;
}
else if(this.radioButton2.Checked)
{
sim_alg = 2;
}
else if(this.radioButton3.Checked)
{
sim_alg = 3;
}
// 测试用户数目，最少为15
testUserNum = this.comboBox2.SelectedIndex + 15;
cUserBased_CF obj_UserBased_CF = new cUserBased_CF(this.neigh_num);
cUser[] testUsers = cReadinData.getTestUser();
this.textBox3.Text = "初始化完成 相似度算法:" + sim_alg.ToString() +
" 最近邻居个数:" + this.neigh_num.ToString() + " 测试用户数:" + testUserNum.ToString();
this.progressBar1.Value += 2;
Application.DoEvents();
double MAE_1, Precison, Recall, F_Measure;
double total_MAE = 0, total_Precison = 0, total_Recall = 0, total_F_Measure = 0;
double average_MAE, average_Precison, average_Recall, average_F_Measure;
for (int i = 1; i <= this.testUserNum; i++)
{
this.progressBar1.Value += 5;
obj_AssStrategy = obj_UserBased_CF.getPredictRating(testUsers[i], this.sim_alg, Rec_Items_num);
// 取得各项算法评价指标
MAE_1 = obj_AssStrategy.MAE;
Precison = obj_AssStrategy.Precison;
Recall = obj_AssStrategy.Recall;
F_Measure = obj_AssStrategy.calculateF_Measure();
// 累计各项指标的和
total_MAE += MAE_1;
total_Precison += Precison;
total_Recall += Recall;
total_F_Measure += F_Measure;
this.textBox3.Text = "第 " + i.ToString() + " 个用户计算完成.";
this.progressBar1.Value += 5;
Application.DoEvents();
}
// 计算各个评价准则的平均值
average_MAE = total_MAE / this.testUserNum;
average_Precison = total_Precison / this.testUserNum;
average_Recall = total_Recall / this.testUserNum;
average_F_Measure = total_F_Measure / this.testUserNum;
DateTime dt_2 = DateTime.Now;
TimeSpan ts = dt_2.Subtract(dt_1);
this.textBox3.Text = "所有用户计算完成 总耗时:" + ts.TotalMilliseconds + " ms";
Application.DoEvents();
this.textBox4.Text = average_MAE.ToString();
this.textBox5.Text = ts.TotalMilliseconds + " ms";
this.textBox6.Text = this.sSimAlg[this.sim_alg - 1];
this.textBox7.Text = this.neigh_num.ToString();
this.textBox9.Text = average_Precison.ToString();
this.textBox10.Text = average_Recall.ToString();
this.textBox11.Text = average_F_Measure.ToString();
this.textBox12.Text = "20";
this.dataGridView1.Rows.Add(count_dgv++, sSimAlg[sim_alg - 1], this.neigh_num, this.Rec_Items_num,average_MAE,
average_Precison, average_Recall, average_F_Measure, ( ts.TotalMilliseconds / this.testUserNum) + " ms" );
}
// 方法描述：预测目标用户objDest对项目的评分
// 方法参数：objDest(cUser) — 目标用户 alg — 相似度算法的选择
// 返 回：MAE(double) — 该目标用户的统计精度度量
public cAssStrategy getPredictRating(cUser objDest, int alg, int item_nums)
{
objAssStrategy = new cAssStrategy();
cUser[] objUser = new cUser[cReadinData.totalUserNum + 1];
objUser = cReadinData.getBaseUser();
int userid = objDest.id;
cUser destUser = objUser[userid];
// 最近邻居搜索
NNS(destUser, alg);
preditUser = new cUser(destUser.id);
preditUser.RatingNums = objDest.RatingNums;
double numerator = 0, denominator = 0;
double sum = 0;
// 计算分母
for (int i = 0; i < neigh_num; i++)
{
denominator += Math.Abs(dSimilarity[i]);
}
int count = 0;
// 对用户训练集中未评分的每一项产生预测评分
for (int i = 1; i < objDest.Ratings.Length; i++)
{
if (destUser.Ratings[i] == 0)
{
for (int j = 0; j < neigh_num; j++)
{
numerator += dSimilarity[j] * (neighUser[j].Ratings[i] - neighUser[j].getTotalRating() / neighUser[j].RatingNums);
}
preditUser.Ratings[i] = Math.Abs(numerator / denominator + destUser.getTotalRating() / destUser.RatingNums) ;
if (preditUser.Ratings[i] > 5)
{
preditUser.Ratings[i] = 5;
}
// 预测的评分值减去实际的评分值
if (objDest.Ratings[i] != 0)
{
sum += Math.Abs(preditUser.Ratings[i] - objDest.Ratings[i]);
// preditUser.Ratings[i] += 2;
count++;
}
numerator = 0;
}
}
// 计算MAE值
objAssStrategy.MAE = sum / (count);
// if (alg != 1)
// {
// objAssStrategy.MAE -= 1.8;
// }
//////////////////////////////////////////////////////////////////////////
// 计算关于Top-N推荐的分类精确度准则
// Top-N推荐的项目id
int[] itemid_TopN = new int[item_nums];
int count_interest = 0; // 记录用户对推荐的项目有兴趣(评分大于该用户的平均评分)的个数
int count_total = 0; // 记录用户测试集合中
float inter_rating = (float)((float)destUser.getTotalRating() / (float)destUser.RatingNums); // 用户的平均评分
// 计算N项推荐项目id和推荐的项目中用户喜欢的个数
for (int i = 0; i < itemid_TopN.Length; i++)
{
itemid_TopN[i] = SelectMaxIndex(preditUser.Ratings);
preditUser.Ratings[itemid_TopN[i]] = -1;
if (objDest.Ratings[itemid_TopN[i]] >= inter_rating)
count_interest++;
}
// 计算测试集中该用户喜欢的项目数量
foreach (int rating in objDest.Ratings)
{
if (rating >= inter_rating)
count_total++;
}
objAssStrategy.Precison = (float)count_interest / itemid_TopN.Length; // 查准率(Precison)
if (count_total == 0)
objAssStrategy.Recall = 0;
else
objAssStrategy.Recall = (float)count_interest / count_total; // 查全率(Recall)
return objAssStrategy;
}
private void button1_Click(object sender, EventArgs e)
{
// 记录当前时间
int count_predit = 0;
DateTime dt_1 = DateTime.Now;
Rec_Items_num = int.Parse( this.textBox9.Text );
userRating = new Dictionary<int, float>();
// 得到用户
cUser testUser = testUsers[comboBox2.SelectedIndex + 1];
userid = testUser.id;
userRating = new Dictionary<int, float>();
for (int j = 1; j < trainUsers[userid].Ratings.Length; j++)
{
if (trainUsers[userid].Ratings[j] != 0)
{
userRating.Add(j, (float)trainUsers[userid].Ratings[j]);
}
}
// count_predit = trainUsers[userID].Ratings.Length - trainUsers[userID].RatingNums;
// 得到该用户的预测评分
IDictionary<int, float> Predictions = obj_SlopeOne.Predict(userRating);
obj_AssStrategy = obj_SlopeOne.getAssStrategy(userid, Predictions, Rec_Items_num, testUser);
DateTime dt_2 = DateTime.Now;
TimeSpan ts = dt_2.Subtract(dt_1);
this.textBox4.Text = obj_AssStrategy.MAE.ToString(); // MAE
this.textBox5.Text = ts.TotalMilliseconds + "ms"; // 时间
this.textBox6.Text = obj_AssStrategy.Precison.ToString(); // 查准率
this.textBox8.Text = obj_AssStrategy.Recall.ToString(); // 查全率
float F = obj_AssStrategy.calculateF_Measure(); // F1指标
this.textBox7.Text = F.ToString();
this.textBox2.Text = this.Rec_Items_num.ToString(); // Top-N 推荐数
this.textBox3.Text = "MAE:" + obj_AssStrategy.MAE + " 查准率:" + obj_AssStrategy.Precison + " 查全率:" +
obj_AssStrategy.Recall + " F值:" + F + " 总耗时:" + ts.TotalMilliseconds + "ms";
// this.dataGridView1.Rows.Add(count_dgv++, trainUsers[userIndex].id, this.Rec_Items_num, trainUsers[userIndex].RatingNums, obj_AssStrategy.MAE, obj_AssStrategy.Precison,
// obj_AssStrategy.Recall, F, ts.TotalMilliseconds + " ms");
Application.DoEvents();
stat_Info[trainUsers[userid].RatingNums / 50] += obj_AssStrategy.MAE;
count_Num[trainUsers[userid].RatingNums / 50]++;
// 累加相关数据
total_MAE += obj_AssStrategy.MAE;
total_Precison += obj_AssStrategy.Precison;
total_Recall += obj_AssStrategy.Recall;
total_F_Measure += F;
total_Time += ts.TotalMilliseconds;
}
// 开始运行
private void button5_Click(object sender, EventArgs e)
{
int test_num = this.comboBox1.SelectedIndex + 15; // 测试用户数量
int N = int.Parse(this.textBox11.Text); // 推荐数目
cUser curTestUser; // 当前测试用户
cAssStrategy obj_AssStrategy = new cAssStrategy(); // 评价准则与指标
this.textBox7.Text = "测试用户数:" + test_num.ToString()
+ " Top-N 推荐数:" + N;
this.progressBar1.Maximum = (test_num-1) * 3; ; // 进度条最大值
this.progressBar1.Value = 0;
//////////////////////////////////////////////////////////////////////////
double total_N = 0, total_Precison = 0, total_Recall = 0, total_F = 0, total_Time = 0;
double Precison, Recall, F_Measure, Time;
DateTime dt_1, dt_2;
TimeSpan ts;
int real_RecNum = N;
// 对测试集中的用户开始产生推荐
int userid;
for (int i = 0; i < test_num-1; i++)
{
curTestUser = testUsers[i + 1];
userid = curTestUser.id;
dt_1 = DateTime.Now; // 获取当前时间
// 得到ID为userid的用户所支持的关联规则集合
supp_AssRules[userid] = cApriori.getSupport_AssRules(userid);
this.textBox7.Text = "第 " + (i + 1) + " 个用户所支持的关联规则生成.";
this.progressBar1.Value++;
Application.DoEvents();
// 得到推荐电影列表
recItems[userid] = cApriori.getRecItems(supp_AssRules[userid], userid);
real_RecNum = (recItems[userid].Length > N ? N : recItems[userid].Length);
this.textBox7.Text = "第 " + (i + 1) + " 个用户的推荐列表生成.";
this.progressBar1.Value++;
Application.DoEvents();
// 评价准则与指标的计算
obj_AssStrategy = cApriori.getAssStrategy(curTestUser, N);
dt_2 = DateTime.Now;
ts = dt_2.Subtract(dt_1); // 时间间隔
Time = ts.TotalMilliseconds;
Precison = obj_AssStrategy.Precison;
Recall = obj_AssStrategy.Recall;
F_Measure = obj_AssStrategy.calculateF_Measure();
// this.label22.Text = userid.ToString(); // 用户ID
// this.label35.Text = real_RecNum.ToString(); // 实际推荐数目
total_N += real_RecNum;
this.label20.Text = Precison.ToString(); // 查准率
total_Precison += Precison;
this.label23.Text = Recall.ToString(); // 查全率
total_Recall += Recall;
this.label24.Text = F_Measure.ToString(); // F值
total_F += F_Measure;
this.label37.Text = Time + " ms"; // 算法运行时间
total_Time += Time;
this.textBox7.Text = "完成第 " + (i + 1) + " 个用户的结果分析.";
this.progressBar1.Value++;
Application.DoEvents();
}
// 计算平均值
int num = test_num - 1;
double average_N = ((double)total_N / (double)num);
double average_Precison = (double) ( (double)total_Precison / num );
double average_Recall = (double) ( (double)total_Recall / num );
double average_F = (double) ( (double)total_F / num );
double average_Time = (double)total_Time / num;
this.label29.Text = average_N.ToString();
this.label30.Text = average_Precison.ToString();
this.label31.Text = average_Recall.ToString();
this.label32.Text = average_F.ToString();
this.label33.Text = average_Time.ToString() + " ms";
Application.DoEvents();
}
