library(e1071)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(lattice)
library(ggplot2)
library(caret)
data =CO2%>%as.data.frame()
plot(data)
###首先繪製以種類為底的散布圖
ggplot(data=CO2) +
geom_point(aes(x=conc,y=uptake,color=Type))
###再來是盒鬚圖
qplot(x=conc,y=uptake,data=CO2,geom="boxplot",color=Type)
###anova分析 測定
model1<-lm(conc~Type,data=CO2)
anova(model1)
## Analysis of Variance Table
##
## Response: conc
## Df Sum Sq Mean Sq F value Pr(>F)
## Type 1 0 0 0 1
## Residuals 82 7268400 88639
model2<- lm(uptake~Type,data=CO2)
anova(model2)
## Analysis of Variance Table
##
## Response: uptake
## Df Sum Sq Mean Sq F value Pr(>F)
## Type 1 3365.5 3365.5 43.519 3.835e-09 ***
## Residuals 82 6341.4 77.3
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
###資料有約莫98筆 我們拆半TRAINING 效果可能會較好
test=sample(nrow(CO2),52, replace=FALSE)
x <- subset(CO2[test,], select = -Type)
y <- CO2$Type[test]
training = CO2[-test,]
svm_model1 =
svmfit = svm(Type ~ ., data = CO2[-test,])
pred = predict(svm_model1,x)
confusionMatrix(pred,y)
## Confusion Matrix and Statistics
##
## Reference
## Prediction Quebec Mississippi
## Quebec 21 1
## Mississippi 4 26
##
## Accuracy : 0.9038
## 95% CI : (0.7897, 0.968)
## No Information Rate : 0.5192
## P-Value [Acc > NIR] : 3.139e-09
##
## Kappa : 0.8065
## Mcnemar's Test P-Value : 0.3711
##
## Sensitivity : 0.8400
## Specificity : 0.9630
## Pos Pred Value : 0.9545
## Neg Pred Value : 0.8667
## Prevalence : 0.4808
## Detection Rate : 0.4038
## Detection Prevalence : 0.4231
## Balanced Accuracy : 0.9015
##
## 'Positive' Class : Quebec
##