1
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
packageurl <- "http://cran.r-project.org/src/contrib/Archive/knitr/knitr_1.12.tar.gz"
install.packages(packageurl, repos=NULL, type="source")## Installing package into 'C:/Users/koval/Documents/R/win-library/3.2'
## (as 'lib' is unspecified)wine <- read.csv ("C:/whitewines.csv") #загрузка данных в R
str (wine) #отображение внутренней структуры объекта wine## 'data.frame': 4898 obs. of 12 variables:
## $ fixed.acidity : num 7 6.3 8.1 7.2 7.2 8.1 6.2 7 6.3 8.1 ...
## $ volatile.acidity : num 0.27 0.3 0.28 0.23 0.23 0.28 0.32 0.27 0.3 0.22 ...
## $ citric.acid : num 0.36 0.34 0.4 0.32 0.32 0.4 0.16 0.36 0.34 0.43 ...
## $ residual.sugar : num 20.7 1.6 6.9 8.5 8.5 6.9 7 20.7 1.6 1.5 ...
## $ chlorides : num 0.045 0.049 0.05 0.058 0.058 0.05 0.045 0.045 0.049 0.044 ...
## $ free.sulfur.dioxide : num 45 14 30 47 47 30 30 45 14 28 ...
## $ total.sulfur.dioxide: num 170 132 97 186 186 97 136 170 132 129 ...
## $ density : num 1.001 0.994 0.995 0.996 0.996 ...
## $ pH : num 3 3.3 3.26 3.19 3.19 3.26 3.18 3 3.3 3.22 ...
## $ sulphates : num 0.45 0.49 0.44 0.4 0.4 0.44 0.47 0.45 0.49 0.45 ...
## $ alcohol : num 8.8 9.5 10.1 9.9 9.9 10.1 9.6 8.8 9.5 11 ...
## $ quality : int 6 6 6 6 6 6 6 6 6 6 ...hist(wine$quality) #строим гистограмму для оценок дегустаторов
wine_train <- wine[1:3750, ] #формируем данные для обучения путём деления исходных данных
wine_test <- wine[3751:4898, ] #формируем данные для тестирования путём деления исходных данных
#3
library (rpart) # подключаем библиотеку rpart## Warning: package 'rpart' was built under R version 3.2.5m.rpart<-rpart (quality ~ ., data = wine_train) #создаём модель m.rpart с quality как переменной результата и данными из wine_train
m.rpart #смотрим базовую информацию о дереве## n= 3750
##
## node), split, n, deviance, yval
## * denotes terminal node
##
## 1) root 3750 3140.06000 5.886933
## 2) alcohol< 10.85 2473 1510.66200 5.609381
## 4) volatile.acidity>=0.2425 1406 740.15080 5.402560
## 8) volatile.acidity>=0.4225 182 92.99451 4.994505 *
## 9) volatile.acidity< 0.4225 1224 612.34560 5.463235 *
## 5) volatile.acidity< 0.2425 1067 631.12090 5.881912 *
## 3) alcohol>=10.85 1277 1069.95800 6.424432
## 6) free.sulfur.dioxide< 11.5 93 99.18280 5.473118 *
## 7) free.sulfur.dioxide>=11.5 1184 879.99920 6.499155
## 14) alcohol< 11.85 611 447.38130 6.296236 *
## 15) alcohol>=11.85 573 380.63180 6.715532 *summary (m.rpart) #смотрим подробную информацию о дереве## Call:
## rpart(formula = quality ~ ., data = wine_train)
## n= 3750
##
## CP nsplit rel error xerror xstd
## 1 0.17816211 0 1.0000000 1.0004571 0.02388743
## 2 0.04439109 1 0.8218379 0.8228358 0.02238039
## 3 0.02890893 2 0.7774468 0.7851283 0.02202864
## 4 0.01655575 3 0.7485379 0.7582200 0.02088449
## 5 0.01108600 4 0.7319821 0.7466331 0.02050013
## 6 0.01000000 5 0.7208961 0.7437313 0.02042172
##
## Variable importance
## alcohol density chlorides
## 38 23 12
## volatile.acidity total.sulfur.dioxide free.sulfur.dioxide
## 12 7 6
## sulphates pH residual.sugar
## 1 1 1
##
## Node number 1: 3750 observations, complexity param=0.1781621
## mean=5.886933, MSE=0.8373493
## left son=2 (2473 obs) right son=3 (1277 obs)
## Primary splits:
## alcohol < 10.85 to the left, improve=0.17816210, (0 missing)
## density < 0.992385 to the right, improve=0.11980970, (0 missing)
## chlorides < 0.0395 to the right, improve=0.08199995, (0 missing)
## total.sulfur.dioxide < 153.5 to the right, improve=0.03875440, (0 missing)
## free.sulfur.dioxide < 11.75 to the left, improve=0.03632119, (0 missing)
## Surrogate splits:
## density < 0.99201 to the right, agree=0.869, adj=0.614, (0 split)
## chlorides < 0.0375 to the right, agree=0.773, adj=0.334, (0 split)
## total.sulfur.dioxide < 102.5 to the right, agree=0.705, adj=0.132, (0 split)
## sulphates < 0.345 to the right, agree=0.670, adj=0.031, (0 split)
## fixed.acidity < 5.25 to the right, agree=0.662, adj=0.009, (0 split)
##
## Node number 2: 2473 observations, complexity param=0.04439109
## mean=5.609381, MSE=0.6108623
## left son=4 (1406 obs) right son=5 (1067 obs)
## Primary splits:
## volatile.acidity < 0.2425 to the right, improve=0.09227123, (0 missing)
## free.sulfur.dioxide < 13.5 to the left, improve=0.04177240, (0 missing)
## alcohol < 10.15 to the left, improve=0.03313802, (0 missing)
## citric.acid < 0.205 to the left, improve=0.02721200, (0 missing)
## pH < 3.325 to the left, improve=0.01860335, (0 missing)
## Surrogate splits:
## total.sulfur.dioxide < 111.5 to the right, agree=0.610, adj=0.097, (0 split)
## pH < 3.295 to the left, agree=0.598, adj=0.067, (0 split)
## alcohol < 10.05 to the left, agree=0.590, adj=0.049, (0 split)
## sulphates < 0.715 to the left, agree=0.584, adj=0.037, (0 split)
## residual.sugar < 1.85 to the right, agree=0.581, adj=0.029, (0 split)
##
## Node number 3: 1277 observations, complexity param=0.02890893
## mean=6.424432, MSE=0.8378682
## left son=6 (93 obs) right son=7 (1184 obs)
## Primary splits:
## free.sulfur.dioxide < 11.5 to the left, improve=0.08484051, (0 missing)
## alcohol < 11.85 to the left, improve=0.06149941, (0 missing)
## fixed.acidity < 7.35 to the right, improve=0.04259695, (0 missing)
## residual.sugar < 1.275 to the left, improve=0.02795662, (0 missing)
## total.sulfur.dioxide < 67.5 to the left, improve=0.02541719, (0 missing)
## Surrogate splits:
## total.sulfur.dioxide < 48.5 to the left, agree=0.937, adj=0.14, (0 split)
##
## Node number 4: 1406 observations, complexity param=0.011086
## mean=5.40256, MSE=0.526423
## left son=8 (182 obs) right son=9 (1224 obs)
## Primary splits:
## volatile.acidity < 0.4225 to the right, improve=0.04703189, (0 missing)
## free.sulfur.dioxide < 17.5 to the left, improve=0.04607770, (0 missing)
## total.sulfur.dioxide < 86.5 to the left, improve=0.02894310, (0 missing)
## alcohol < 10.25 to the left, improve=0.02890077, (0 missing)
## chlorides < 0.0455 to the right, improve=0.02096635, (0 missing)
## Surrogate splits:
## density < 0.99107 to the left, agree=0.874, adj=0.027, (0 split)
## citric.acid < 0.11 to the left, agree=0.873, adj=0.022, (0 split)
## fixed.acidity < 9.85 to the right, agree=0.873, adj=0.016, (0 split)
## chlorides < 0.206 to the right, agree=0.871, adj=0.005, (0 split)
##
## Node number 5: 1067 observations
## mean=5.881912, MSE=0.591491
##
## Node number 6: 93 observations
## mean=5.473118, MSE=1.066482
##
## Node number 7: 1184 observations, complexity param=0.01655575
## mean=6.499155, MSE=0.7432425
## left son=14 (611 obs) right son=15 (573 obs)
## Primary splits:
## alcohol < 11.85 to the left, improve=0.05907511, (0 missing)
## fixed.acidity < 7.35 to the right, improve=0.04400660, (0 missing)
## density < 0.991395 to the right, improve=0.02522410, (0 missing)
## residual.sugar < 1.225 to the left, improve=0.02503936, (0 missing)
## pH < 3.245 to the left, improve=0.02417936, (0 missing)
## Surrogate splits:
## density < 0.991115 to the right, agree=0.710, adj=0.401, (0 split)
## volatile.acidity < 0.2675 to the left, agree=0.665, adj=0.307, (0 split)
## chlorides < 0.0365 to the right, agree=0.631, adj=0.237, (0 split)
## total.sulfur.dioxide < 126.5 to the right, agree=0.566, adj=0.103, (0 split)
## residual.sugar < 1.525 to the left, agree=0.560, adj=0.091, (0 split)
##
## Node number 8: 182 observations
## mean=4.994505, MSE=0.5109588
##
## Node number 9: 1224 observations
## mean=5.463235, MSE=0.5002823
##
## Node number 14: 611 observations
## mean=6.296236, MSE=0.7322117
##
## Node number 15: 573 observations
## mean=6.715532, MSE=0.6642788library(rpart.plot) #подключаем библиотеку rpart plot## Warning: package 'rpart.plot' was built under R version 3.2.5rpart.plot(m.rpart, digits = 3) #строим регрессионое дерево по модели m.rpart разррядностью 3
rpart.plot(m.rpart, digits = 4, fallen.leaves = TRUE, type = 3, extra = 101) #строим регрессионное дерево по модели m.rpart с разрядностью 4, с выровненными нижними узлами, изменённым способом решения, с подписями узлов (прописано соответственно)
#4 оценка эффективности модели
p.rpart <- predict(m.rpart, wine_test) #используем прогнозирующую функцию
summary(p.rpart)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.995 5.463 5.882 5.999 6.296 6.716summary(wine_test$quality)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.000 5.000 6.000 5.848 6.000 8.000cor(p.rpart, wine_test$quality) #смотрим корреляцию между реальными данными и прогнозируемыми## [1] 0.4931608MAE <- function(actual, predicted) {
mean(abs(actual - predicted))
}
MAE(p.rpart, wine_test$quality)#средняя абсолютная погрешность## [1] 0.5732104#5 повышение эффективности модели
library(rJava) #подключаем библиотеку rJava ## Warning: package 'rJava' was built under R version 3.2.3library(RWeka) #подключаем библиотеку RWeka## Warning: package 'RWeka' was built under R version 3.2.5
m.m5p <- M5P(quality ~ ., data = wine_train) #строим модельное дерево
m.m5p #выводим модельное дерево## M5 pruned model tree:
## (using smoothed linear models)
##
## alcohol <= 10.85 : LM1 (2473/77.476%)
## alcohol > 10.85 :
## | free.sulfur.dioxide <= 20.5 :
## | | free.sulfur.dioxide <= 10.5 : LM2 (81/104.574%)
## | | free.sulfur.dioxide > 10.5 : LM3 (224/87.002%)
## | free.sulfur.dioxide > 20.5 : LM4 (972/84.073%)
##
## LM num: 1
## quality =
## 0.0777 * fixed.acidity
## - 2.3087 * volatile.acidity
## + 0.0732 * residual.sugar
## + 0.0022 * free.sulfur.dioxide
## - 155.0175 * density
## + 0.6462 * pH
## + 0.7923 * sulphates
## + 0.0758 * alcohol
## + 156.2102
##
## LM num: 2
## quality =
## -0.0314 * fixed.acidity
## - 0.3415 * volatile.acidity
## + 1.7929 * citric.acid
## + 0.1316 * residual.sugar
## - 0.2456 * chlorides
## + 0.1212 * free.sulfur.dioxide
## - 178.6281 * density
## + 0.054 * pH
## + 0.1392 * sulphates
## + 0.0108 * alcohol
## + 180.6069
##
## LM num: 3
## quality =
## -0.2019 * fixed.acidity
## - 2.3804 * volatile.acidity
## - 1.0851 * citric.acid
## + 0.0905 * residual.sugar
## - 0.2456 * chlorides
## + 0.0041 * free.sulfur.dioxide
## - 177.078 * density
## + 0.054 * pH
## + 0.0868 * sulphates
## + 0.0108 * alcohol
## + 183.5076
##
## LM num: 4
## quality =
## 0.0004 * fixed.acidity
## - 0.0325 * volatile.acidity
## + 0.0957 * residual.sugar
## - 5.9702 * chlorides
## + 0.0002 * free.sulfur.dioxide
## - 172.3931 * density
## + 1.0123 * pH
## + 1.1653 * sulphates
## + 0.1542 * alcohol
## + 171.6842
##
## Number of Rules : 4summary(m.m5p) #смотрим подробную информацию о модельном дереве##
## === Summary ===
##
## Correlation coefficient 0.5932
## Mean absolute error 0.5804
## Root mean squared error 0.7367
## Relative absolute error 83.3671 %
## Root relative squared error 80.507 %
## Total Number of Instances 3750p.m5p <- predict(m.m5p, wine_test) #используем прогнозирующую функцию
summary(p.m5p) #смотрим подробную информацию о модельном дереве## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.170 5.646 6.032 6.079 6.501 7.913cor(p.m5p, wine_test$quality) #смотрим корреляцию между реальными данными и прогнозируемыми## [1] 0.531723MAE(wine_test$quality, p.m5p) #средняя абсолютная погрешность## [1] 0.5660352You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.