R语言-生成频数表和列联表crosstable函数介绍

Total Observations in Table:  143 
 
             | test_cancer$diagnosis 
   lda.class |         0 |         1 | Row Total | 
-------------|-----------|-----------|-----------|
           0 |        82 |        11 |        93 | 
             |     0.882 |     0.118 |     0.650 | 
             |     0.988 |     0.183 |           | 
             |     0.573 |     0.077 |           | 
-------------|-----------|-----------|-----------|
           1 |         1 |        49 |        50 | 
             |     0.020 |     0.980 |     0.350 | 
             |     0.012 |     0.817 |           | 
             |     0.007 |     0.343 |           | 
-------------|-----------|-----------|-----------|
Column Total |        83 |        60 |       143 | 
             |     0.580 |     0.420 |           | 
-------------|-----------|-----------|-----------|

## 使用knn模型做预测
knn_pred_1 = knn(train_cancer[,2:4], test_cancer[,2:4], train_cancer$diagnosis, k=1)
## 创建列联表看预测效果
CrossTable(x = knn_pred_1, y = test_cancer$diagnosis, prop.chisq = FALSE)
>
   Cell Contents
|-------------------------|
|                       N |
|           N / Row Total |
|           N / Col Total |
|         N / Table Total |
|-------------------------|
 
Total Observations in Table:  143 
 
             | test_cancer$diagnosis 
  knn_pred_1 |         0 |         1 | Row Total | 
-------------|-----------|-----------|-----------|
           0 |        77 |         8 |        85 | 
             |     0.906 |     0.094 |     0.594 | 
             |     0.928 |     0.133 |           | 
             |     0.538 |     0.056 |           | 
-------------|-----------|-----------|-----------|
           1 |         6 |        52 |        58 | 
             |     0.103 |     0.897 |     0.406 | 
             |     0.072 |     0.867 |           | 
             |     0.042 |     0.364 |           | 
-------------|-----------|-----------|-----------|
Column Total |        83 |        60 |       143 | 
             |     0.580 |     0.420 |           | 
-------------|-----------|-----------|-----------|

CrossTable(x, y, digits=3, max.width = 5, expected=FALSE, prop.r=TRUE, prop.c=TRUE,
           prop.t=TRUE, prop.chisq=TRUE, chisq = FALSE, fisher=FALSE, mcnemar=FALSE,
           resid=FALSE, sresid=FALSE, asresid=FALSE,
           missing.include=FALSE,
           fORMat=c("SAS","SPSS"), dnn = NULL, ...)

head(CO2)
#得到“conc”特征的频数表
table(CO2$conc)

library(vcd)
head(Arthritis)
 
table(Arthritis$Treatment,Arthritis$Improved)
with(Arthritis,table(Treatment,Improved))
mytable <- xtabs(~Treatment+Improved,data = Arthritis)
with(Arthritis,xtabs(~Treatment+Improved,data = Arthritis))
 
margin.table(mytable,2) # sum by row
prop.table(mytable,2)  #proportion by column
prop.table(mytable)  #proportion by total
 
addmargins(mytable)
addmargins(mytable,1)
addmargins(prop.table(mytable,2),1)
  
library(gmodels)
CrossTable(Arthritis$Treatment,Arthritis$Improved) ##SAS format