Question

我正在学习使用glmnet和brnn个软件包。请考虑以下代码：

library(RODBC)
library(brnn)
library(glmnet)
memory.limit(size = 4000)
z <-odbcConnect("mydb") # database with Access queries and tables

# import the data
f5 <- sqlFetch(z,"my_qry")

# head(f5)

# check for 'NA'
sum(is.na(f5))

# choose a 'locn', up to 16 of variable 'locn' are present
f6 <- subset(f5, locn == "mm")
# dim(f6)

# use glmnet to identify possible iv's

training_xnm <- f6[,1:52] # training data
xnm <- as.matrix(training_xnm)
y <- f6[,54] # response

fit.nm <- glmnet(xnm,y, family="binomial", alpha=0.6, nlambda=1000,standardize=TRUE,maxit=100000)
# print(fit.nm)

# cross validation for glmnet to determine a good lambda value
cv.fit.nm <- cv.glmnet(xnm, y)

# have a look at the 'min' and '1se' lambda values
cv.fit.nm$lambda.min
cv.fit.nm$lambda.1se
# returned $lambda.min of 0.002906279, $lambda.1se of 2.587214

# for testing purposes I choose a value between 'min' and '1se'
mid.lambda.nm = (cv.fit.nm$lambda.min + cv.fit.nm$lambda.1se)/2

print(coef(fit.nm, s = mid.lambda.nm)) # 8 iv's retained

# I then manually inspect the data frame and enter the column index for each of the iv's
# these iv's will be the input to my 'brnn' neural nets

cols <- c(1, 3, 6, 8, 11, 20, 25, 38) # column indices of useful iv's

# brnn creation: only one shown but this step will be repeated
# take a 85% sample from data frame
ridxs <- sample(1:nrow(f6), floor(0.85*nrow(f6)) ) # row id's
f6train <- f6[ridxs,] # the resultant data frame of 85%
f6train <-f6train[,cols] # 'cols' as chosen above

# For the 'brnn' phase response is a binary value, 'fin'
# and predictors are the 8 iv's found earlier
out = brnn( fin ~ x1 + x2 + x3 + x4 + x5 + x6 + x7 + x8, data=f6train, neurons=3,normalize=TRUE, epochs=500, verbose=FALSE)
#summary(out)

# see how well the net predicts the training cases
pred <- predict(out)

上面的脚本运行正常。

我的问题是：如何自动运行上述脚本以针对locn的不同值运行，这实质上是如何推广步骤：cols <- c(1, 3, 6, 8, 11, 20, 25, 38) # column indices of useful iv's。目前我可以手动执行此操作但无法查看如何以locn的不同值以一般方式执行此操作，例如

locn.list <- c("am", "bm", "cm", "dm", "em")  
for(j in 1:5) {
this.locn <- locn.list[j]
# run the above script
}

Answer 1

自从发表我的问题以来，我找到了Simon，Friedman，Hastie和Tibshirani的论文：Coxnet：Regularized Cox Regression，它解决了如何提取我想要的东西。

本文的一些相关细节，并根据我的数据进行了调整（lambda符号除外）：我们可以检查我们的模型选择哪个协变量处于活动状态，并查看这些协变量的系数。

coef(fit.nm, s = cv.fit.nm$lambda.min) # returns the p length coefficient vector

对应于lambda = cv.fit $ lambda.min。

的解决方案的

Coefficients <- coef(fit.nm, s = cv.fit.nm$lambda.min)
Active.Index <- which(Coefficients != 0)
Active.Coefficients <- Coefficients[Active.Index]

Active.Index # identifies the covariates that are active in the model and
Active.Coefficients # shows the coefficients of those covariates

希望这对其他人有用！

如何在glmnet和交叉验证中自动化变量选择

1 个答案: