r - Predict() R 函数插入符包错误 : "newdata" rows different, "type"不接受

Question

• 我正在使用插入符包运行逻辑回归分析。

• 数据以 18x6 矩阵的形式输入

• 到目前为止，除了 predict() 函数之外，一切都很好。

• R 告诉我 type 参数应该是 raw 或 prob 但 raw只是输出最后一列(二项式变量的值)的精确副本。 prob 给我以下错误:

"Error in dimnames(out)[[2]] <- modelFit$obsLevels : length of 'dimnames' [2] not equal to array extent In addition: Warning message: 'newdata' had 7 rows but variables found have 18 rows"

install.packages("pbkrtest")
install.packages("caret")
install.packages('e1071', dependencies=TRUE)
#install.packages('caret', dependencies = TRUE)
require(caret)
library(caret)

A=matrix(
  c(
    64830,18213,4677,24761,9845,17504,22137,12531,5842,28827,51840,4079,1000,2069,969,9173,11646,946,66161,18852,5581,27219,10159,17527,23402,11409,8115,31425,55993,0,0,1890,1430,7873,12779,627,68426,18274,5513,25687,10971,14104,19604,13438,6011,30055,57242,0,0,2190,1509,8434,10492,755,69716,18366,5735,26556,11733,16605,20644,15516,5750,31116,64330,0,0,1850,1679,9233,12000,500,73128,18906,5759,28555,11951,19810,22086,17425,6152,28469,72020,0,0,1400,1750,8599,12000,500,1,1,1,0,1,0,0,0,0,1,0,1,1,1,1,1,1,1
  ),

  nrow = 18,
  ncol = 6,
  byrow = FALSE)  #"bycol" does NOT exist
################### data set as vectors
a<-c(64830,18213,4677,24761,9845,17504,22137,12531,5842,28827,51840,4079,1000,2069,969,9173,11646,946)
b<-c(66161,18852,5581,27219,10159,17527,23402,11409,8115,31425,55993,0,0,1890,1430,7873,12779,627)
c<-c(68426,18274,5513,25687,10971,14104,19604,13438,6011,30055,57242,0,0,2190,1509,8434,10492,755)
d<-c(69716,18366,5735,26556,11733,16605,20644,15516,5750,31116,64330,0,0,1850,1679,9233,12000,500)
e<-c(73128,18906,5759,28555,11951,19810,22086,17425,6152,28469,72020,0,0,1400,1750,8599,12000,500)
f<-c(1,1,1,0,1,0,0,0,0,1,0,1,1,1,1,1,1,1)
######################

n<-nrow(A);
K<-ncol(A)-1;

Train <- createDataPartition(f, p=0.6, list=FALSE)  #60% of data set is used as training.
training <- A[ Train, ]
testing <- A[ -Train, ]
nrow(training)

#this is the logistic formula:
#estimates from logistic regression characterize the relationship between the predictor and response variable on a log-odds scale
mod_fit <- train(f ~ a + b + c + d +e,  data=training, method="glm", family="binomial")
mod_fit

#this isthe exponential function to calculate the odds ratios for each preditor:
exp(coef(mod_fit$finalModel))

predict(mod_fit, newdata=training)
predict(mod_fit, newdata=testing, type="prob")

Answer 1

我不太确定理解，但 A 是 (a,b,c,d,e,f) 的矩阵。因此您不需要创建两个对象。

install.packages("pbkrtest")
install.packages("caret")
install.packages('e1071', dependencies=TRUE)
#install.packages('caret', dependencies = TRUE)
require(caret)
library(caret)

A=matrix(
  c(
        64830,18213,4677,24761,9845,17504,22137,12531,5842,28827,51840,4079,1000,2069,969,9173,11646,946,66161,18852,5581,27219,10159,17527,23402,11409,8115,31425,55993,0,0,1890,1430,7873,12779,627,68426,18274,5513,25687,10971,14104,19604,13438,6011,30055,57242,0,0,2190,1509,8434,10492,755,69716,18366,5735,26556,11733,16605,20644,15516,5750,31116,64330,0,0,1850,1679,9233,12000,500,73128,18906,5759,28555,11951,19810,22086,17425,6152,28469,72020,0,0,1400,1750,8599,12000,500,1,1,1,0,1,0,0,0,0,1,0,1,1,1,1,1,1,1
  ),
  nrow = 18,
  ncol = 6,
  byrow = FALSE)  #"bycol" does NOT exist

A <- data.frame(A)
colnames(A) <- c('a','b','c','d','e','f')
A$f <- as.factor(A$f)

Train <- createDataPartition(A$f, p=0.6, list=FALSE)  #60% of data set is used as training.
training <- A[ Train, ]
testing <- A[ -Train, ]
nrow(training)

要预测变量，您必须输入解释变量而不是要预测的变量

mod_fit <- train(f ~ a + b + c + d +e,  data=training, method="glm", family="binomial")
mod_fit

#this isthe exponential function to calculate the odds ratios for each preditor:
exp(coef(mod_fit$finalModel))

predict(mod_fit, newdata=training[,-which(colnames(training)=="f")])
predict(mod_fit, newdata=testing[,-which(colnames(testing)=="f")])