HW11: Machine Learning & Kaggle

Task 1

#Load libraries
library(tidyverse)
library(tree)
library(randomForest)
library(caret)
library(MLmetrics)
library(skimr)
library(rpart)
library(rattle)

Load and clean the data

# Import training and testing data:
train_raw <- read.csv2("train.csv", sep = ",",
                       stringsAsFactors = TRUE)
test_raw <- read.csv2("test.csv", sep = ",",
                      stringsAsFactors = TRUE)
dim(train_raw)

## [1] 1460   81

dim(test_raw)

## [1] 1459   80

#skim(train_raw)

# 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)

Run the simplest tree algorithm there is

mod_rpart <- rpart(SalePrice~., data=train_minclean)
# Tree plot
fancyRpartPlot(mod_rpart, caption = NULL)

# Export predictions
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.

write_csv(submission_rpart, file="submission_rpart.csv")

Submit to kaggle

Task 2

# Training a random forest
mod_rf <- randomForest(SalePrice ~ ., data = train_minclean)

trainX <- select(train_minclean, -SalePrice)
test_minclean <- rbind(trainX[1, ] , test_minclean)
test_minclean <- test_minclean[-1,]
# Get predictions:
pred_rf <-predict(mod_rf, newdata = test_minclean)
submission_rf <- tibble(Id=test_raw$Id, SalePrice=pred_rf)
write_csv(submission_rf, file="submission_rf.csv")