R语言使用决策树预测NBA球员投篮结果

我不是女神ヾ 2022-05-25 08:40 348阅读 0赞

##  ##

## 1、3种最常见的决策树： ##

CART分类回归树(classification and regression tree)（一棵二叉树）。每个节点采用二分法(与C4.5最大的区别，c4.5可以有很多分支)；用Gini Ratio作为衡量指标，如果分散指标程度很高的说明数据有很多类别。

C4.5。最新有5.0版本；先建完整的决策树；使用自定义的错误率（Predicted Error Rate)对节点修剪。

CHAID 卡方自动交互检验 （Chi-squared Automatic Interaction）。计算节点中类别的p值。根据p值的大小决定决策树是否生长不需要修剪（与前两者的区别）。![2018051809581215][]

![20180518095824772][]

\#条件推理决策树(CHAID算法)

#条件推理决策树(CHAID算法)
    #探索和收集数据
    setwd("D://data")
    NBA<-read.table("shot_logs.csv",header = T,sep = ",")#读取数据
    set.seed(1234)
    hist(NBA$SHOT_DIST)#投球距离的直方图
    
    NBA$SHOT_RESULT <- factor(NBA$SHOT_RESULT, levels=c("made","missed"), 
                              labels=c("命中", "未中")) #分为投中和未投中球
    set.seed(1234) #设置随机种子
    train <- sample(nrow(NBA), 0.80*nrow(NBA)) #取训练集为80%，验证集为20%
    testData <- NBA[train,] #测试集
    trainData <- NBA[-train,] #验证集
    table(trainData$SHOT_RESULT) 
    table(testData$SHOT_RESULT) #记录频数的方法
    
    library(party)
    #建立决策树模型预测投篮结果
    myFormula <- SHOT_RESULT ~ LOCATION+FINAL_MARGIN+PERIOD+DRIBBLES+TOUCH_TIME+SHOT_DIST+PTS_TYPE+CLOSE_DEF_DIST
    NBA_ctree <- ctree(myFormula, data=trainData)
    # 查看预测的结果
    table(predict(NBA_ctree), trainData$SHOT_RESULT)
    #画出决策树图
    plot(NBA_ctree, type="simple")
    
    #在测试集上做预测
    testPred <- predict(NBA_ctree, newdata = testData)
    table(testPred, testData$SHOT_RESULT)
    correct = sum(as.numeric(testPred)==as.numeric(testData$SHOT_RESULT))/nrow(testData)
    correct
    
    #在验证集上做预测
    trainPred <- predict(NBA_ctree, newdata = trainData)
    table(trainPred, trainData$SHOT_RESULT)
    correct = sum(as.numeric(trainPred)==as.numeric(trainData$SHOT_RESULT))/nrow(trainData)
    correct

## 1、CP参数定义 ##

cp: complexity parameter复杂性参数，用来修剪树的.

当决策树复杂度超过一定程度后，随着复杂度的提高，测试集的分类精确度反而会降低。因此，建立的决策树不宜太复杂，需进行剪枝。该剪枝算法依赖于复杂性参数cp,cp随树复杂度的增加而减小，当增加一个节点引起的分类精确度变化量小于树复杂度变化的cp倍时，则须剪去该节点。故建立一棵既能精确分类，又不过度适合的决策树的关键是求解一个合适的cp值。一般选择错判率最小值对应的cp值来修树.

## 2、CP选择问题。 ##

建立树模型要权衡两方面问题，一个是要拟合得使分组后的变异较小，另一个是要防止过度拟合，而使模型的误差过大，前者的参数是CP，后者的参数是Xerror。所以要在Xerror最小的情况下，也使CP尽量小。

### \#分类回归树CART ###

#分类回归树CART
    #NBA demo
    
    #探索和收集数据
    setwd("D://data")
    NBA<-read.table("shot_logs_1.csv",header = T,sep = ",")
    str(NBA)#查看表中的特征值
    hist(NBA$SHOT_DIST)#投球距离的直方图
    
    
    NBA$SHOT_RESULT <- factor(NBA$SHOT_RESULT, levels=c("made","missed"), 
                       labels=c("命中", "未中")) #分为投中和未投中球
    set.seed(12345) #设置随机种子
    train <- sample(nrow(NBA), 0.80*nrow(NBA)) #取训练集为80%，验证集为20%
    trainData <- NBA[train,] 
    testData <- NBA[-train,] #验证集
    table(trainData$SHOT_RESULT) 
    table(testData$SHOT_RESULT) #记录频数的方法
    #
    library(rpart) 
    set.seed(12345) 
    #method="class"离散型:class,
    #参数split可以是gini（基尼系数）或者information（信息增益）；
    #生成一棵树
    dtree <- rpart(SHOT_RESULT ~ LOCATION+FINAL_MARGIN+PERIOD+DRIBBLES+TOUCH_TIME+SHOT_DIST+PTS_TYPE+CLOSE_DEF_DIST, data=trainData, method="class", 
                   parms=list(split="information"))
    
    dtree$cptable 
    
    #剪枝
    plotcp(dtree) 
    
    #cp全称为complexity parameter，指某个点的复杂度，对每一步拆分,
    #模型的拟合优度必须提高的程度，用来节省剪枝浪费的不必要的时间
    NBA_ctree <- prune(dtree, cp=0.01)
    library(rpart.plot) 
    
    #画决策树
    rpart.plot(NBA_ctree, branch=1, branch.type=2, type=1, extra=102,
               shadow.col="gray", box.col="green",
               border.col="blue", split.col="red",
               split.cex=1.2, main="决策树")
     
    
    #在测试集上做预测
    testPred <- predict(NBA_ctree, testData, type="class")
    table(testPred, testData$SHOT_RESULT,dnn=c("真实值", "预测值"))
    correct = sum(as.numeric(testPred)==as.numeric(testData$SHOT_RESULT))/nrow(testData)
    correct
    
    #在验证集上做预测
    trainPred <- predict(NBA_ctree, trainData, type="class")
    table(trainPred, trainData$SHOT_RESULT,dnn=c("真实值", "预测值"))
    correct = sum(as.numeric(trainPred)==as.numeric(trainData$SHOT_RESULT))/nrow(trainData)
    correct

### \#C4.5算法 ###

#C4.5算法
    library(RWeka)  
    library(party) 
    #探索和收集数据
    setwd("D://data")
    NBA<-read.table("shot_logs_1.csv",header = T,sep = ",")
    
    NBA$SHOT_RESULT <- factor(NBA$SHOT_RESULT, levels=c("made","missed"), 
                              labels=c("命中", "未中")) #分为投中和未投中球
    set.seed(12345) #设置随机种子
    train <- sample(nrow(NBA), 0.80*nrow(NBA)) #取训练集为80%，验证集为20%
    trainData <- NBA[train,] 
    testData <- NBA[-train,] #验证集
    
    NBA_ctree<-J48(SHOT_RESULT ~ FINAL_MARGIN+DRIBBLES+TOUCH_TIME+SHOT_DIST+CLOSE_DEF_DIST, data=trainData)
    plot(NBA_ctree)
    
    #在测试集上做预测
    testPred <- predict(NBA_ctree, newdata = testData)
    table(testPred, testData$SHOT_RESULT)
    correct = sum(as.numeric(testPred)==as.numeric(testData$SHOT_RESULT))/nrow(testData)
    correct
    
    #在验证集上做预测
    trainPred <- predict(NBA_ctree, newdata = trainData)
    table(trainPred, trainData$SHOT_RESULT)
    correct = sum(as.numeric(trainPred)==as.numeric(trainData$SHOT_RESULT))/nrow(trainData)
    correct

### \#随机森林 ###

#随机森林
    library(randomForest) 
    #探索和收集数据
    setwd("D://data")
    NBA<-read.table("shot_logs_1.csv",header = T,sep = ",")
    
    NBA$SHOT_RESULT <- factor(NBA$SHOT_RESULT, levels=c("made","missed"), 
                              labels=c("命中", "未中")) #分为投中和未投中球
    set.seed(12345) #设置随机种子
    train <- sample(nrow(NBA), 0.80*nrow(NBA)) #取训练集为80%，验证集为20%
    trainData <- NBA[train,] 
    testData <- NBA[-train,] #验证集
    
    rf <- randomForest(SHOT_RESULT ~ DRIBBLES, data=trainData) 
    
    NBA_ctree <- randomForest(SHOT_RESULT ~ CLOSE_DEF_DIST, data=trainData, ntree=10, proximity=TRUE)
    plot(margin(rf, testData$SHOT_RESULT))
    
    #在测试集上做预测
    testPred <- predict(NBA_ctree, testData, type="class")
    table(testPred, testData$SHOT_RESULT,dnn=c("真实值", "预测值"))
    correct = sum(as.numeric(testPred)==as.numeric(testData$SHOT_RESULT))/nrow(testData)
    correct
    
    #在验证集上做预测
    trainPred <- predict(NBA_ctree, trainData, type="class")
    table(trainPred, trainData$SHOT_RESULT,dnn=c("真实值", "预测值"))
    correct = sum(as.numeric(trainPred)==as.numeric(trainData$SHOT_RESULT))/nrow(trainData)
    correct

--------------------

### 项目推荐： ###

**[2000多G的计算机各行业电子资源分享（持续更新）][2000_G]**

**[2020年微信小程序全栈项目之喵喵交友【附课件和源码】][2020]**

**[Spring Boot开发小而美的个人博客【附课件和源码】][Spring Boot]**

**[Java微服务实战296集大型视频-谷粒商城【附代码和课件】][Java_296_-]**

**[Java开发微服务畅购商城实战【全357集大项目】-附代码和课件][Java_357_-]**

**[最全最详细数据结构与算法视频-【附课件和源码】][-]**

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQwNTg3NTc1_size_16_color_FFFFFF_t_70_pic_center]

[2018051809581215]: /images/20220525/d752942f224648b8bf5c0e1a6e283d5c.png
[20180518095824772]: /images/20220525/91fb79b47b974546a0364ebf2c5374c6.png
[2000_G]: https://mp.weixin.qq.com/s/sP4JgGWkCzpgwKr9sAV2_Q
[2020]: https://mp.weixin.qq.com/s?__biz=MzIyNTI3NDQ4NQ==&mid=2247487704&idx=1&sn=5f4b2127c4d49fd07ae072a0721424a2&chksm=e8036fc2df74e6d489c4aa9b06f917ef7cee6027f13e150fca53cf79d5d188d4ccc1af49e098&scene=21#wechat_redirect
[Spring Boot]: https://mp.weixin.qq.com/s?__biz=MzIyNTI3NDQ4NQ==&mid=2247487798&idx=2&sn=ac0293b996521b872a9dba5fbb3e65e6&chksm=e8036e2cdf74e73aba104a9a994a5b2e31483e8dcbe0f1d9936f6d5173b887e1560f59d2819c&scene=21#wechat_redirect
[Java_296_-]: https://mp.weixin.qq.com/s?__biz=MzIyNTI3NDQ4NQ==&mid=2247487674&idx=1&sn=7aff0bdf2bb727303f3d3618995aef21&chksm=e8036fa0df74e6b6d872c7e6ece179c524ed463a4a6b74c96875475c9a3d5ddb903427dd993b&scene=21#wechat_redirect
[Java_357_-]: https://mp.weixin.qq.com/s?__biz=MzIyNTI3NDQ4NQ==&mid=2247486376&idx=1&sn=d1fef270c463ea8ac663f6fbfedd70a0&chksm=e80374b2df74fda4d3bafba878a106a19e18c5fcda266008f4f37975847a21bc612ffcd5ff39&scene=21#wechat_redirect
[-]: https://mp.weixin.qq.com/s?__biz=MzIyNTI3NDQ4NQ==&mid=2247487750&idx=1&sn=747bccbb5f5ea6b58915198de40da777&chksm=e8036e1cdf74e70ae97a5e8e265b49d7236d904d291203309159d07ba1724033062c0e370843&scene=21#wechat_redirect
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQwNTg3NTc1_size_16_color_FFFFFF_t_70_pic_center]: /images/20220525/86551f87ecae4af2b0bff51c2a77a779.png