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;
}
public void TestNewUserInTestSet()
{
var recommender = new SlopeOne();
var training_data = new Ratings();
training_data.Add(0, 0, 1.0f);
training_data.Add(1, 1, 5.0f);
training_data.InitScale();
recommender.Ratings = training_data;
recommender.Train();
Assert.AreEqual(3.0, recommender.Predict(2, 1));
}
public void TestNewItemInTestSet()
{
var recommender = new SlopeOne();
recommender.MinRating = 1;
recommender.MaxRating = 5;
var training_data = new Ratings();
training_data.Add(0, 0, 1.0);
training_data.Add(1, 1, 5.0);
recommender.Ratings = training_data;
recommender.Train();
Assert.AreEqual(3.0, recommender.Predict(0, 2));
}
