
1.用party包構(gòu)建決策樹
以iris數(shù)據(jù)集為例。
用ctree()建立決策樹,用predict()對(duì)新數(shù)據(jù)進(jìn)行預(yù)測(cè)。
訓(xùn)練集與測(cè)試集劃分:
[ruby] view plain copy
> str(iris)
'data.frame': 150 obs. of 5 variables:
$ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
$ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
$ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
$ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
$ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
> set.seed(1234)
> ind <- sample(2, nrow(iris), replace=TRUE, prob=c(0.7, 0.3))
> trainData <- iris[ind==1,]
> testData <- iris[ind==2,]
用默認(rèn)參數(shù)來建立決策樹:
[ruby] view plain copy
> library(party)
> myFormula <- Species ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width
> iris_ctree <- ctree(myFormula, data=trainData)
> # check the prediction
> table(predict(iris_ctree), trainData$Species)
setosa versicolor virginica
setosa 40 0 0
versicolor 0 37 3
virginica 0 1 31
輸出規(guī)則并繪制已構(gòu)建好的決策樹以便查看。
[ruby] view plain copy
> print(iris_ctree)
Conditional inference tree with 4 terminal nodes
Response: Species
Inputs: Sepal.Length, Sepal.Width, Petal.Length, Petal.Width
Number of observations: 112
1) Petal.Length <= 1.9; criterion = 1, statistic = 104.643
2)* weights = 40
1) Petal.Length > 1.9
3) Petal.Width <= 1.7; criterion = 1, statistic = 48.939
4) Petal.Length <= 4.4; criterion = 0.974, statistic = 7.397
5)* weights = 21
4) Petal.Length > 4.4
6)* weights = 19
3) Petal.Width > 1.7
7)* weights = 32
> plot(iris_ctree)
> # 圖略
[ruby] view plain copy
> plot(iris_ctree, type="simple")
[ruby] view plain copy
> #圖略
用測(cè)試集對(duì)構(gòu)建好的決策樹進(jìn)行測(cè)試:
[ruby] view plain copy
> # predict on test data
> testPred <- predict(iris_ctree, newdata = testData)
> table(testPred, testData$Species)
testPred setosa versicolor virginica
setosa 10 0 0
versicolor 0 12 2
virginica 0 0 14
幾點(diǎn)值得注意的地方:
① ctree()不能很好地處理缺失值,含有缺失值的觀測(cè)有時(shí)被劃分到左子樹,有時(shí)劃到右子樹,這是由缺失值的替代規(guī)則決定的。
② 訓(xùn)練集和測(cè)試集需出自同一個(gè)數(shù)據(jù)集,即它們的表結(jié)構(gòu)、含有的變量要一致,無論決策樹最終是否用到了全部的變量。
③ 如果訓(xùn)練集和測(cè)試集的分類變量的水平值不一致,對(duì)測(cè)試集的預(yù)測(cè)會(huì)識(shí)別。解決此問題的方法是根據(jù)測(cè)試集中的分類變量的水平值顯式地設(shè)置訓(xùn)練數(shù)據(jù)。
2.用rpar包構(gòu)建決策樹
以bodyfat數(shù)據(jù)集為例。用rpart()構(gòu)建決策樹,允許選擇具有最小預(yù)測(cè)誤差的決策樹,再使用predict()對(duì)新數(shù)據(jù)進(jìn)行預(yù)測(cè)。
首先查看數(shù)據(jù):
[ruby] view plain copy
> data("bodyfat", package = "TH.data")
> dim(bodyfat)
[1] 71 10
> attributes(bodyfat)
$names
[1] "age" "DEXfat" "waistcirc" "hipcirc" "elbowbreadth"
[6] "kneebreadth" "anthro3a" "anthro3b" "anthro3c" "anthro4"
$row.names
[1] "47" "48" "49" "50" "51" "52" "53" "54" "55" "56" "57" "58" "59" "60"
[15] "61" "62" "63" "64" "65" "66" "67" "68" "69" "70" "71" "72" "73" "74"
[29] "75" "76" "77" "78" "79" "80" "81" "82" "83" "84" "85" "86" "87" "88"
[43] "89" "90" "91" "92" "93" "94" "95" "96" "97" "98" "99" "100" "101" "102"
[57] "103" "104" "105" "106" "107" "108" "109" "110" "111" "112" "113" "114" "115" "116"
[71] "117"
$class
[1] "data.frame"
> bodyfat[1:5,]
age DEXfat waistcirc hipcirc elbowbreadth kneebreadth anthro3a anthro3b anthro3c
47 57 41.68 100.0 112.0 7.1 9.4 4.42 4.95 4.50
48 65 43.29 99.5 116.5 6.5 8.9 4.63 5.01 4.48
49 59 35.41 96.0 108.5 6.2 8.9 4.12 4.74 4.60
50 58 22.79 72.0 96.5 6.1 9.2 4.03 4.48 3.91
51 60 36.42 89.5 100.5 7.1 10.0 4.24 4.68 4.15
anthro4
47 6.13
48 6.37
49 5.82
50 5.66
51 5.91
訓(xùn)練集與測(cè)試集劃分,和模型訓(xùn)練:
[ruby] view plain copy
> set.seed(1234)
> ind <- sample(2, nrow(bodyfat), replace=TRUE, prob=c(0.7, 0.3))
> bodyfat.train <- bodyfat[ind==1,]
> bodyfat.test <- bodyfat[ind==2,]
> # train a decision tree
> library(rpart)
> myFormula <- DEXfat ~ age + waistcirc + hipcirc + elbowbreadth + kneebreadth
> bodyfat_rpart <- rpart(myFormula, data = bodyfat.train,
+ control = rpart.control(minsplit = 10))
> attributes(bodyfat_rpart)
$names
[1] "frame" "where" "call"
[4] "terms" "cptable" "method"
[7] "parms" "control" "functions"
[10] "numresp" "splits" "variable.importance"
[13] "y" "ordered"
$xlevels
named list()
$class
[1] "rpart"
> print(bodyfat_rpart$cptable)
CP nsplit rel error xerror xstd
1 0.67272638 0 1.00000000 1.0194546 0.18724382
2 0.09390665 1 0.32727362 0.4415438 0.10853044
3 0.06037503 2 0.23336696 0.4271241 0.09362895
4 0.03420446 3 0.17299193 0.3842206 0.09030539
5 0.01708278 4 0.13878747 0.3038187 0.07295556
6 0.01695763 5 0.12170469 0.2739808 0.06599642
7 0.01007079 6 0.10474706 0.2693702 0.06613618
8 0.01000000 7 0.09467627 0.2695358 0.06620732
> print(bodyfat_rpart)
n= 56
node), split, n, deviance, yval
* denotes terminal node
1) root 56 7265.0290000 30.94589
2) waistcirc< 88.4 31 960.5381000 22.55645
4) hipcirc< 96.25 14 222.2648000 18.41143
8) age< 60.5 9 66.8809600 16.19222 *
9) age>=60.5 5 31.2769200 22.40600 *
5) hipcirc>=96.25 17 299.6470000 25.97000
10) waistcirc< 77.75 6 30.7345500 22.32500 *
11) waistcirc>=77.75 11 145.7148000 27.95818
22) hipcirc< 99.5 3 0.2568667 23.74667 *
23) hipcirc>=99.5 8 72.2933500 29.53750 *
3) waistcirc>=88.4 25 1417.1140000 41.34880
6) waistcirc< 104.75 18 330.5792000 38.09111
12) hipcirc< 109.9 9 68.9996200 34.37556 *
13) hipcirc>=109.9 9 13.0832000 41.80667 *
7) waistcirc>=104.75 7 404.3004000 49.72571 *
繪制決策樹圖形:
[ruby] view plain copy
> plot(bodyfat_rpart)
> text(bodyfat_rpart, use.n=T)
> #圖略
選擇具有最小預(yù)測(cè)誤差的決策樹:
[ruby] view plain copy
> opt <- which.min(bodyfat_rpart$cptable[,"xerror"])
> cp <- bodyfat_rpart$cptable[opt, "CP"]
> bodyfat_prune <- prune(bodyfat_rpart, cp = cp)
> print(bodyfat_prune)
n= 56
node), split, n, deviance, yval
* denotes terminal node
1) root 56 7265.02900 30.94589
2) waistcirc< 88.4 31 960.53810 22.55645
4) hipcirc< 96.25 14 222.26480 18.41143
8) age< 60.5 9 66.88096 16.19222 *
9) age>=60.5 5 31.27692 22.40600 *
5) hipcirc>=96.25 17 299.64700 25.97000
10) waistcirc< 77.75 6 30.73455 22.32500 *
11) waistcirc>=77.75 11 145.71480 27.95818 *
3) waistcirc>=88.4 25 1417.11400 41.34880
6) waistcirc< 104.75 18 330.57920 38.09111
12) hipcirc< 109.9 9 68.99962 34.37556 *
13) hipcirc>=109.9 9 13.08320 41.80667 *
7) waistcirc>=104.75 7 404.30040 49.72571 *
> plot(bodyfat_prune)
> text(bodyfat_prune, use.n=T)
> #圖略
用決策樹模型進(jìn)行預(yù)測(cè),并與實(shí)際值進(jìn)行對(duì)比。圖中abline()繪制了一條對(duì)角線。一個(gè)好的預(yù)測(cè)模型,絕大多數(shù)的點(diǎn)應(yīng)該落在對(duì)角線上或者越接近對(duì)角線越好。
[ruby] view plain copy
> DEXfat_pred <- predict(bodyfat_prune, newdata=bodyfat.test)
> xlim <- range(bodyfat$DEXfat)
> plot(DEXfat_pred ~ DEXfat, data=bodyfat.test, xlab="Observed",
+ ylab="Predicted", ylim=xlim, xlim=xlim)
> abline(a=0, b=1)
[ruby] view plain copy
> #圖略
3.隨機(jī)森林
以iris數(shù)據(jù)集為例。
使用randomForest()存在兩個(gè)限制:第一個(gè)是該函數(shù)不能處理帶有缺失值的數(shù)據(jù),要事先對(duì)缺失值進(jìn)行處理;第二是分類屬性的水平劃分?jǐn)?shù)量最大值為32,大于32的分類屬性需要事先轉(zhuǎn)換。
另一種是使用party包中的cforest(),該函數(shù)沒有限定分類屬性的水平劃分?jǐn)?shù)。
訓(xùn)練集和測(cè)試集劃分:
[ruby] view plain copy
> ind <- sample(2, nrow(iris), replace=TRUE, prob=c(0.7, 0.3))
> trainData <- iris[ind==1,]
> testData <- iris[ind==2,]
訓(xùn)練隨機(jī)森林模型:
[ruby] view plain copy
> library(randomForest)
> rf <- randomForest(Species ~ ., data=trainData, ntree=100, proximity=TRUE)
> table(predict(rf), trainData$Species)
setosa versicolor virginica
setosa 36 0 0
versicolor 0 31 1
virginica 0 1 35
> print(rf)
Call:
randomForest(formula = Species ~ ., data = trainData, ntree = 100, proximity = TRUE)
Type of random forest: classification
Number of trees: 100
No. of variables tried at each split: 2
OOB estimate of error rate: 1.92%
Confusion matrix:
setosa versicolor virginica class.error
setosa 36 0 0 0.00000000
versicolor 0 31 1 0.03125000
virginica 0 1 35 0.02777778
> attributes(rf)
$names
[1] "call" "type" "predicted" "err.rate"
[5] "confusion" "votes" "oob.times" "classes"
[9] "importance" "importanceSD" "localImportance" "proximity"
[13] "ntree" "mtry" "forest" "y"
[17] "test" "inbag" "terms"
$class
[1] "randomForest.formula" "randomForest"
根據(jù)生成的隨機(jī)森林中不同的樹來繪制誤差率:
[ruby] view plain copy
> plot(rf)
> #圖略
查看變量重要性:
[ruby] view plain copy
> importance(rf)
MeanDecreaseGini
Sepal.Length 6.485090
Sepal.Width 1.380624
Petal.Length 32.498074
Petal.Width 28.250058
> varImpPlot(rf)
> #圖略
最后使用測(cè)試集進(jìn)行測(cè)試,用table()和margin()查看結(jié)果。圖中數(shù)據(jù)點(diǎn)的邊距為正確分類的比例減去被歸到其他類別的最大比例。一般來說,邊距為正數(shù)說明該數(shù)據(jù)點(diǎn)劃分正確。
[ruby] view plain copy
> irisPred <- predict(rf, newdata=testData)
> table(irisPred, testData$Species)
irisPred setosa versicolor virginica
setosa 14 0 0
versicolor 0 17 3
virginica 0 1 11
> plot(margin(rf, testData$Species))
[ruby] view plain copy
> #圖略
數(shù)據(jù)分析咨詢請(qǐng)掃描二維碼
若不方便掃碼,搜微信號(hào):CDAshujufenxi
LSTM 模型輸入長度選擇技巧:提升序列建模效能的關(guān)鍵? 在循環(huán)神經(jīng)網(wǎng)絡(luò)(RNN)家族中,長短期記憶網(wǎng)絡(luò)(LSTM)憑借其解決長序列 ...
2025-07-11CDA 數(shù)據(jù)分析師報(bào)考條件詳解與準(zhǔn)備指南? ? 在數(shù)據(jù)驅(qū)動(dòng)決策的時(shí)代浪潮下,CDA 數(shù)據(jù)分析師認(rèn)證愈發(fā)受到矚目,成為眾多有志投身數(shù) ...
2025-07-11數(shù)據(jù)透視表中兩列相乘合計(jì)的實(shí)用指南? 在數(shù)據(jù)分析的日常工作中,數(shù)據(jù)透視表憑借其強(qiáng)大的數(shù)據(jù)匯總和分析功能,成為了 Excel 用戶 ...
2025-07-11尊敬的考生: 您好! 我們誠摯通知您,CDA Level I和 Level II考試大綱將于 2025年7月25日 實(shí)施重大更新。 此次更新旨在確保認(rèn) ...
2025-07-10BI 大數(shù)據(jù)分析師:連接數(shù)據(jù)與業(yè)務(wù)的價(jià)值轉(zhuǎn)化者? ? 在大數(shù)據(jù)與商業(yè)智能(Business Intelligence,簡稱 BI)深度融合的時(shí)代,BI ...
2025-07-10SQL 在預(yù)測(cè)分析中的應(yīng)用:從數(shù)據(jù)查詢到趨勢(shì)預(yù)判? ? 在數(shù)據(jù)驅(qū)動(dòng)決策的時(shí)代,預(yù)測(cè)分析作為挖掘數(shù)據(jù)潛在價(jià)值的核心手段,正被廣泛 ...
2025-07-10數(shù)據(jù)查詢結(jié)束后:分析師的收尾工作與價(jià)值深化? ? 在數(shù)據(jù)分析的全流程中,“query end”(查詢結(jié)束)并非工作的終點(diǎn),而是將數(shù) ...
2025-07-10CDA 數(shù)據(jù)分析師考試:從報(bào)考到取證的全攻略? 在數(shù)字經(jīng)濟(jì)蓬勃發(fā)展的今天,數(shù)據(jù)分析師已成為各行業(yè)爭搶的核心人才,而 CDA(Certi ...
2025-07-09【CDA干貨】單樣本趨勢(shì)性檢驗(yàn):捕捉數(shù)據(jù)背后的時(shí)間軌跡? 在數(shù)據(jù)分析的版圖中,單樣本趨勢(shì)性檢驗(yàn)如同一位耐心的偵探,專注于從單 ...
2025-07-09year_month數(shù)據(jù)類型:時(shí)間維度的精準(zhǔn)切片? ? 在數(shù)據(jù)的世界里,時(shí)間是最不可或缺的維度之一,而year_month數(shù)據(jù)類型就像一把精準(zhǔn) ...
2025-07-09CDA 備考干貨:Python 在數(shù)據(jù)分析中的核心應(yīng)用與實(shí)戰(zhàn)技巧? ? 在 CDA 數(shù)據(jù)分析師認(rèn)證考試中,Python 作為數(shù)據(jù)處理與分析的核心 ...
2025-07-08SPSS 中的 Mann-Kendall 檢驗(yàn):數(shù)據(jù)趨勢(shì)與突變分析的有力工具? ? ? 在數(shù)據(jù)分析的廣袤領(lǐng)域中,準(zhǔn)確捕捉數(shù)據(jù)的趨勢(shì)變化以及識(shí)別 ...
2025-07-08備戰(zhàn) CDA 數(shù)據(jù)分析師考試:需要多久?如何規(guī)劃? CDA(Certified Data Analyst)數(shù)據(jù)分析師認(rèn)證作為國內(nèi)權(quán)威的數(shù)據(jù)分析能力認(rèn)證 ...
2025-07-08LSTM 輸出不確定的成因、影響與應(yīng)對(duì)策略? 長短期記憶網(wǎng)絡(luò)(LSTM)作為循環(huán)神經(jīng)網(wǎng)絡(luò)(RNN)的一種變體,憑借獨(dú)特的門控機(jī)制,在 ...
2025-07-07統(tǒng)計(jì)學(xué)方法在市場(chǎng)調(diào)研數(shù)據(jù)中的深度應(yīng)用? 市場(chǎng)調(diào)研是企業(yè)洞察市場(chǎng)動(dòng)態(tài)、了解消費(fèi)者需求的重要途徑,而統(tǒng)計(jì)學(xué)方法則是市場(chǎng)調(diào)研數(shù) ...
2025-07-07CDA數(shù)據(jù)分析師證書考試全攻略? 在數(shù)字化浪潮席卷全球的當(dāng)下,數(shù)據(jù)已成為企業(yè)決策、行業(yè)發(fā)展的核心驅(qū)動(dòng)力,數(shù)據(jù)分析師也因此成為 ...
2025-07-07剖析 CDA 數(shù)據(jù)分析師考試題型:解鎖高效備考與答題策略? CDA(Certified Data Analyst)數(shù)據(jù)分析師考試作為衡量數(shù)據(jù)專業(yè)能力的 ...
2025-07-04SQL Server 字符串截取轉(zhuǎn)日期:解鎖數(shù)據(jù)處理的關(guān)鍵技能? 在數(shù)據(jù)處理與分析工作中,數(shù)據(jù)格式的規(guī)范性是保證后續(xù)分析準(zhǔn)確性的基礎(chǔ) ...
2025-07-04CDA 數(shù)據(jù)分析師視角:從數(shù)據(jù)迷霧中探尋商業(yè)真相? 在數(shù)字化浪潮席卷全球的今天,數(shù)據(jù)已成為企業(yè)決策的核心驅(qū)動(dòng)力,CDA(Certifie ...
2025-07-04CDA 數(shù)據(jù)分析師:開啟數(shù)據(jù)職業(yè)發(fā)展新征程? ? 在數(shù)據(jù)成為核心生產(chǎn)要素的今天,數(shù)據(jù)分析師的職業(yè)價(jià)值愈發(fā)凸顯。CDA(Certified D ...
2025-07-03