我想为我想,以适应泊松模型的数据集做交叉验证。然而,我注意到,当我使用lambda = 0
时,我得到的功能cv.glm
和cv.glmnet
的输出非常不同。下面是我的基本泊松模型代码(第一部分是数据集的设置):输出与cv.glmnet
game_soon <- function(game_type, hour){
ret_vec <- c()
len_game_type <- length(game_type)
for(i in 1:len_game_type){
if(game_type[i] == 'N' && hour[i] >= 16){
ret_vec <- c(ret_vec, 1)
}
else if(game_type[i] == 'D' && hour[i] >= 10 && hour[i] <= 17){
ret_vec <- c(ret_vec, 1)
}
else{
ret_vec <- c(ret_vec, 0)
}
}
return(ret_vec)
}
wrigley_agg <- read.csv("/Users/eweine/Desktop/myDivvy/export/EWEINE/WR/WRIGLEY_DIVVY/data", header=FALSE)
colnames(wrigley_agg) <- c("Checkouts", "Temp", "Humidity", "Rain_Intensity",
"Rain_Total", "Hour", "DOY", "Weekday", "Cubs_Game")
game_vec <- wrigley_agg$Cubs_Game
hour_vec <- wrigley_agg$Hour
new_column <- game_soon(game_vec, hour_vec)
wrigley_agg$Game_Soon <- new_column
require(glm)
require(boot)
basic_poisson <- glm(Checkouts ~ Weekday + Game_Soon + poly(Hour, 6) +
poly(Temp, 4) + poly(Rain_Intensity, 4), data=wrigley_agg, family=poisson)
cv_possion <- cv.glm(wrigley_agg, basic_poisson, K=10)
print(cv_possion)
我的输出是:
[1] 958.9232 958.5509
下面是我为cv.glmnet
型号代码:
x_pois <- model.matrix(Checkouts ~ Weekday + Game_Soon + poly(Hour, 6) + poly(Temp, 4) +
poly(Rain_Intensity, 4), data=wrigley_agg)
y_pois <- wrigley_agg$Checkouts
cv_lasso_pois <- cv.glmnet(x_pois, y_pois, family="poisson", alpha=1, lambda=seq(1, 0, -1))
no_penalty_cv <- cv_lasso_pois$cvm[cv_lasso_pois$lambda == 0]
print(no_penalty_cv)
而且我的输出是:
[1] 13.41691
可以找到数据here。
为什么这些价值观如此不同?
> cv.glm ...# 错误:对象 'cv.glm' 未找到 –
你能否就此展开? –
您没有包含库调用来加载可能包含所有函数和数据的包......但我的猜测是数据集可能不在那里。请阅读[MCVE]。 –