Homework #11

library(tidyverse)
library(rpart)
library(rattle)

#Import training and testing data:
#(Obviously, your file paths might be different here ):

train_raw <- read.csv2("train.csv", sep = ",", stringsAsFactors = TRUE)

test_raw <- read.csv2("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
}
cleanup_minimal <- function(data){
  nomis <- data %>%
    mutate_if(is.factor, replace_na_most) %>%
    mutate_if(is.numeric, replace_na_med)
  nomis
}
train_minclean <- cleanup_minimal(train_raw)
test_minclean <- cleanup_minimal(test_raw)

mod_rpart <- rpart(SalePrice~., data=train_minclean)
# Try this command to make a nice tree plot!
fancyRpartPlot(mod_rpart, caption = NULL)

pred_rpart <- predict(mod_rpart, newdata = test_minclean)
submission_rpart <- tibble(Id=test_raw$Id, SalePrice=pred_rpart)
head(submission_rpart)

## # A tibble: 6 x 2
##      Id SalePrice
##   <int>     <dbl>
## 1  1461   118199.
## 2  1462   151246.
## 3  1463   185210.
## 4  1464   185210.
## 5  1465   249392.
## 6  1466   185210.

# Obviously, your file path might be different here:
write_csv(submission_rpart, file="submission_rpart.csv")