Reputation: 103
I am getting undefined columns error in R. Here is a description of tran_data
train_data <- train[c("DURATION","HOURLY_WAGE", "WAGE_RATE_OF_PAY_FROM_HOUR", "OCCUPATION_NUM","CASE_STATUS_1.0","AGENT_PRESENT_1.0")]
> str(train_data)
data.frame: 70000 obs. of 6 variables:
$ DURATION : num 0.0674 0.0674 0.0449 0.0562 0.0674 ...
$ HOURLY_WAGE : num 0.378 0.298 0.387 0.333 0.34 ...
$ WAGE_RATE_OF_PAY_FROM_HOUR: num 0.396 0.302 0.391 0.333 0.354 ...
$ OCCUPATION_NUM : num 0.3 0.3 0.3 0.3 0.3 0.3 0.1 0.1 0.1 0.3 ...
$ CASE_STATUS_1.0 : Factor w/ 2 levels "0","1": 2 2 2 2 2 2 2 2 2 2 ...
$ AGENT_PRESENT_1.0 : Factor w/ 2 levels "0","1": 2 1 1 2 2 1 2 2 2 1 ...
Code that is throwing an error
n <- neuralnet(train_data$AGENT_PRESENT_1.0~train_data$HOURLY_WAGE+
train_data$DURATION+
train_data$WAGE_RATE_OF_PAY_FROM_HOUR+
train_data$CASE_STATUS_1.0+
train_data$OCCUPATION_NUM,
data=train_data,hidden = 1)
ERROR:
Error in [.data.frame
(data, , model.list$variables) :
undefined columns selected
I tried unlist function but I am getting the same error. Any help on how to solve this?
Upvotes: 1
Views: 9344
Reputation: 887158
The issue would be the formula
needs the unquoted column names and not the values
library(neuralnet)
n <- neuralnet(`AGENT_PRESENT_1.0` ~ HOURLY_WAGE+
DURATION+
WAGE_RATE_OF_PAY_FROM_HOUR+
`CASE_STATUS_1.0`+
OCCUPATION_NUM,
data=train_data, hidden = 1)
Using a reproducible example
data(iris)
this works
n1 <- neuralnet(Species ~ Petal.Length + Petal.Width, iris, hidden = 1)
this results in error
n1 <- neuralnet(iris$Species ~ iris$Petal.Length + iris$Petal.Width, iris, hidden = 1)
Error in
[.data.frame
(data, , model.list$variables) : undefined columns selected
Upvotes: 1