vlambda博客
学习文章列表

library(readr)Enzyme <- read_csv("~/Desktop/主成分分析/Enzyme.csv")#导入View(Enzyme)

>df1<-Enzyme[,2:10]#预处理,选取Enzyme数据框中2到10列的数据形成新的矩阵df1.> df1# A tibble: 36 x 9 Time MDA LOX APX PAL CAT POD PPO TPC <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> 1 40 41 19 58 80 186. 40 20 965 2 40 42 20 55 155 172. 34 37 955 3 40 43 17 51 92 166. 30 36 937 4 40 30 23 57 208 163. 85 23 1261 5 40 34 24 58 180 146. 89 26 1249 6 40 38 24 52 99 167. 81 21 1269 7 40 40 27 55 150 70.7 81 16 1322 8 40 30 30 54 104 56.7 81 16 1312 9 40 43 29 55 167 73.7 82 22 135710 40 46 27 58 96 66.7 64 22 1080# … with 26 more rows>Enzyme1.pca <- prcomp(df1,scale. = TRUE)#对给定的数据矩阵进行主成分分析，并将结果作为类prcomp的对象返回。> Enzyme1.pcaStandard deviations (1, .., p=9):[1] 2.0909293 1.1638511 1.0689045 0.9458037 0.7227202 0.6075112 0.5181985 0.2353166 0.1451410
Rotation (n x k) = (9 x 9): PC1 PC2 PC3 PC4 PC5 PC6 PC7Time 0.46315503 -0.04916147 0.03637764 0.162115952 0.09831722 -0.05605495 0.15384446MDA 0.43051775 -0.04773755 -0.14795093 -0.069491134 -0.36795168 -0.34716366 -0.30304858LOX -0.09369929 0.32940027 -0.72371726 -0.441381496 -0.08318472 -0.00732021 0.37465711APX -0.08716532 -0.75858481 -0.10162202 -0.059575764 -0.45541633 0.34852207 0.26596939PAL 0.18847050 -0.30570836 0.24096297 -0.784312315 0.43453792 -0.08163434 -0.03770386CAT -0.37539362 -0.03778714 0.33391251 -0.026114784 -0.18066354 -0.69437542 0.46568301POD 0.41870137 0.00242730 0.02591931 0.254736824 0.31195985 0.10630817 0.65436944PPO 0.44279023 -0.08209132 -0.12802074 -0.008043973 -0.27235413 -0.34781106 -0.01258019TPC -0.18960223 -0.45795031 -0.50603522 0.299564950 0.49765782 -0.36567563 -0.16354171 PC8 PC9Time -0.423321246 0.73470281MDA -0.488029855 -0.44691662LOX -0.086060923 0.09687049APX -0.054174793 0.02299334PAL 0.013325895 -0.02694037CAT -0.113141408 0.03184374POD 0.038176838 -0.46993978PPO 0.746837400 0.16634344TPC -0.009080942 -0.01764606

> library(ggbiplot)>ggbiplot(Enzyme1.pca,obs.scale = 1,var.scale = 1,groups =Enzyme$Treament,ellipse = TRUE,circle = TRUE)+scale_color_discrete(name="")+theme(legend.direction = 'horizontal',legend.position = 'top')

df<-Enzyme[c(2,3,4,5,6,7,8,9,10)]View(df)

> Enzyme.pca<-PCA(df,graph=FALSE)> Enzyme.pca**Results for the Principal Component Analysis (PCA)**The analysis was performed on 36 individuals, described by 9 variables*The results are available in the following objects:

 name description 1 "$eig" "eigenvalues" 2 "$var" "results for the variables" 3 "$var$coord" "coord. for the variables" 4 "$var$cor" "correlations variables - dimensions"5 "$var$cos2" "cos2 for the variables" 6 "$var$contrib" "contributions of the variables" 7 "$ind" "results for the individuals" 8 "$ind$coord" "coord. for the individuals" 9 "$ind$cos2" "cos2 for the individuals" 10 "$ind$contrib" "contributions of the individuals" 11 "$call" "summary statistics" 12 "$call$centre" "mean of the variables" 13 "$call$ecart.type" "standard error of the variables" 14 "$call$row.w" "weights for the individuals" 15 "$call$col.w" "weights for the variables" 

> library(factoextra)> library(FactoMineR)> fviz_pca_ind(Enzyme.pca,geom.ind="point",pointsize=3,pointshape=21,fill.ind=Enzyme$Treament,palette=c("#00AFBB","#E7B800","#FC4E07","blue"),addEllipses=TRUE,legend.titl="Groups",title="")+theme_grey()

>fviz_pca_ind(Enzyme2.pca,geom.ind="point",pointsize=4,pointshape=21,fill.ind=Enzyme$Time,palette=c("#00AFBB","#E7B800","#FC4E07"),addEllipses=TRUE,legend.titl="Groups",title="")+theme_grey()错误: Continuous value supplied to discrete scale

>str(Enzyme$Time)num [1:36] 40 40 40 40 40 40 40 40 40 40 ...#查看数据框中某列的数值类型，你会发现是num数值型，而fill.ind=Enzyme$Time这列数据需要因子向量型。>as.character(Enzyme$Time) [1] "40" "40" "40" "40" "40" "40" "40" "40" "40" "40" "40" "40" "80" "80" "80" [16] "80" "80" "80" "80" "80" "80" "80" "80" "80" "120" "120" "120" "120" "120" "120"[31] "120" "120" "120" "120" "120" "120"#将Time所在列的数据转换为字符型的因子向量。>Enzyme$Time<-as.character(Enzyme$Time)#将数据框中的某列的数值转换为因子向量，变量名仍为Time>str(Enzyme$Time) chr [1:36] "40" "40" "40" "40" "40" "40" "40" "40" "40" "40" "40" "40" "80" "80" "80" "80" ...#再次查看，Time的类型，发现修改成功，变成字符型chr了。

> library(factoextra)> library(FactoMineR)> df2<-Enzyme[,3:10]> df2# A tibble: 36 x 8 MDA LOX APX PAL CAT POD PPO TPC <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> 1 41 19 58 80 186. 40 20 965 2 42 20 55 155 172. 34 37 955 3 43 17 51 92 166. 30 36 937 4 30 23 57 208 163. 85 23 1261 5 34 24 58 180 146. 89 26 1249 6 38 24 52 99 167. 81 21 1269 7 40 27 55 150 70.7 81 16 1322 8 30 30 54 104 56.7 81 16 1312 9 43 29 55 167 73.7 82 22 135710 46 27 58 96 66.7 64 22 1080# … with 26 more rows> Enzyme2.pca<-PCA(df2,graph=FALSE)
> Enzyme2.pca**Results for the Principal Component Analysis (PCA)**The analysis was performed on 36 individuals, described by 8 variables*The results are available in the following objects:
 name description 1 "$eig" "eigenvalues" 2 "$var" "results for the variables" 3 "$var$coord" "coord. for the variables" 4 "$var$cor" "correlations variables - dimensions"5 "$var$cos2" "cos2 for the variables" 6 "$var$contrib" "contributions of the variables" 7 "$ind" "results for the individuals" 8 "$ind$coord" "coord. for the individuals" 9 "$ind$cos2" "cos2 for the individuals" 10 "$ind$contrib" "contributions of the individuals" 11 "$call" "summary statistics" 12 "$call$centre" "mean of the variables" 13 "$call$ecart.type" "standard error of the variables" 14 "$call$row.w" "weights for the individuals" 15 "$call$col.w" "weights for the variables" > fviz_pca_ind(Enzyme2.pca,geom.ind="point",pointsize=4,pointshape=21,fill.ind=Enzyme$Time,palette=c("#00AFBB","#E7B800","#FC4E07"),addEllipses=TRUE,legend.titl="Groups",title="")+theme_grey()