In this task, I run my first machine learning prediction model and submit my work to a Kagle competition.
# load necessary packages
library(skimr)
library(tree)
library(gridExtra)
library(randomForest)
library(caret)
library(MLmetrics)
library(dplyr)
library(forcats)
library(rpart)
library(rattle)
library(readr)
# Import training and testing data:
train_raw <- read.csv2("/Users/godwinnutsugah/Dropbox/AAEE-UGA/AAEC 8610/Project_Data/data/train.csv", sep = ",",
stringsAsFactors = TRUE)
test_raw <- read.csv2("/Users/godwinnutsugah/Dropbox/AAEE-UGA/AAEC 8610/Project_Data/data/test.csv", sep = ",",
stringsAsFactors = TRUE)
# Functions to replace NAs with most frequent level or median
replace_na_most <- function(x){
fct_explicit_na(x, na_level = names(which.max(table(x))))
}
replace_na_med <- function(x){
x[is.na(x)] <- median(x,na.rm = TRUE)
x
}
# Minimal cleaning
cleanup_minimal <- function(data){
nomis <- data %>%
mutate_if(is.factor, replace_na_most) %>%
mutate_if(is.numeric, replace_na_med)
nomis
}
# cleaned data
train_minclean <- cleanup_minimal(train_raw)
test_minclean <- cleanup_minimal(test_raw)
# run the simplest tree algorithm
mod_rpart <- rpart(SalePrice~., data=train_minclean)
# Try this command to make a nice tree plot!
fancyRpartPlot(mod_rpart, caption = NULL)
# code to export the predictions in the appropriate format
pred_rpart <- predict(mod_rpart, newdata = test_minclean)
submission_rpart <- tibble(Id=test_raw$Id, SalePrice=pred_rpart)
head(submission_rpart)
## # A tibble: 6 × 2
## Id SalePrice
## <int> <dbl>
## 1 1461 118199.
## 2 1462 151246.
## 3 1463 185210.
## 4 1464 185210.
## 5 1465 249392.
## 6 1466 185210.
#export output into .csv file
write_csv(submission_rpart, file="/Users/godwinnutsugah/Dropbox/AAEE-UGA/AAEC 8610/Project_Data/data/submission_rpart.csv")
My score and position