Created
June 21, 2019 21:22
-
-
Save benlistyg/8dbc65987dc46f2420d3e55c12da702f to your computer and use it in GitHub Desktop.
Messing around with predicting college major from vocational interest data.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Multinomial Logit Model vs Random Forest | |
# Predicting College Major from Items | |
library(data.table) # For fread function (v fast!) | |
library(dplyr) # For pre-processing | |
library(tm) # For cleaning text / pre-processing | |
library(nnet) #for MNL | |
library(randomForest) #For rf | |
# Helper function for making training / testing sets. | |
outersect <- function(x, y) { | |
sort(c(setdiff(x, y), | |
setdiff(y, x))) | |
} | |
# Normalizing majors (entered as free response data) | |
majors <- data.table::fread(input = paste(getwd(),'/data.csv',sep=''), sep = '\t',stringsAsFactors = F)$major %>% | |
toupper() %>% | |
trimws() %>% | |
removePunctuation() %>% | |
removeNumbers() %>% | |
table() %>% | |
melt() %>% | |
arrange(-value) %>% | |
.[-1,] | |
# Final data set | |
vi_data <- data.table::fread(input = paste(getwd(),'/data.csv',sep=''), sep = '\t',stringsAsFactors = F) %>% | |
mutate(MAJOR = toupper(major)) %>% | |
select(-major) %>% | |
filter(MAJOR %in% as.character(majors$.[2:10])) %>% | |
filter(!is.na(MAJOR)) %>% | |
select(R1:C8, MAJOR) %>% | |
mutate(R = rowSums(select(., grep("R[0-9]", names(.)))), | |
I = rowSums(select(., grep("I[0-9]", names(.)))), | |
A = rowSums(select(., grep("A[0-9]", names(.)))), | |
S = rowSums(select(., grep("S[0-9]", names(.)))), | |
E = rowSums(select(., grep("E[0-9]", names(.)))), | |
C = rowSums(select(., grep("C[0-9]", names(.))))) %>% | |
mutate(MAJOR = as.factor(MAJOR)) %>% | |
select(R,I,A,S,E,C,MAJOR) | |
test_rows <- sample(1:nrow(vi_data), size = 5000, replace = F) | |
train_rows <- outersect(x = 1:nrow(vi_data), y = test_rows) | |
mnl_vi <- multinom(MAJOR ~ R+I+A+S+E+C, data=vi_data[train_rows,]) | |
rf_vi <- randomForest::randomForest(MAJOR ~ ., data=vi_data[train_rows,]) | |
list( | |
`Multi-Nomial Logit` = data.frame(vi_data[test_rows,], | |
prediction = predict(mnl_vi, vi_data[test_rows,-ncol(vi_data)])) %>% | |
select(MAJOR, prediction) %>% | |
table(.) | |
, | |
`Random Forest` = data.frame(vi_data[test_rows,], | |
prediction = predict(rf_vi, vi_data[test_rows,-ncol(vi_data)])) %>% | |
select(MAJOR, prediction) %>% | |
table(.) | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment