R

[henryliangt]

https://bookdown.org/xiao/RAnalysisBook/r-markdown.html

https://www.jianshu.com/p/503877661a57

https://bookdown.org/zbw2101211203/bookdown/appendix_1.html

https://www.runoob.com/r/r-string.html

` getwd()

library(readr)

install.packages("tidyverse")

install.packages("dplyr")

install.packages("knitr")

install.packages("ggplot2") install.packages("") install.packages("")

install.packages("") install.packages("") install.packages("")

install.packages("") install.packages("") install.packages("")

install.packages("") install.packages("") install.packages("")

`

library(ggplot2)
library(reader)
library()

[henryliangt]

knitr::opts_chunk$set(echo = TRUE)

[henryliangt]

melbdata <- read.csv("https://raw.githubusercontent.com/henryliangt/usyd/main/Melbourne_housing_FULL.csv", header = TRUE)
melbdata <- read.csv("Melbourne_housing_FULL.csv", header = TRUE)
dim(melbdata)
colnames(melbdata)

[henryliangt]

---

title: "Regression and smoothing" author: " " output: html_document: fig_caption: yes include: after_body: css/stylesDD.js number_sections: yes self_contained: yes theme: flatly css:

• css/styles.css

• https://use.fontawesome.com/releases/v5.0.6/css/all.css toc: true toc_depth: 2 toc_float: true code_folding: hide

knitr::opts_chunk$set(echo = TRUE)

Load the data

We will be using a dataset of Melbourne house prices. Let's first load the data and see what is in the table. This dataset was downloaded from Kaggle and the data was released under the CC BY-NC-SA 4.0 license.

melbdata <- read.csv("Melbourne_housing_FULL.csv", header = TRUE)
dim(melbdata)
colnames(melbdata)

Now let's subset to only look at house prices in St. Kilda (and remove cases that have the price variable missing).

st.kilda <- subset(melbdata, Suburb == "St Kilda")
dim(st.kilda)
sum(is.na(st.kilda$Price))
st.kilda <- st.kilda[!is.na(st.kilda$Price), ]
dim(st.kilda)

Let's plot this using the ggplot2 package.

install.packages("ggplot2")

library(ggplot2)
ggplot(st.kilda, aes(x = BuildingArea, y = Price/1000)) + geom_point()

First regression model

lmfit <- lm(Price ~ BuildingArea, data = st.kilda)
summary(lmfit)
new <- data.frame(BuildingArea = 100)
predict(lmfit, new, interval = "confidence")

Remove outliers

To improve our regression model, let's try to remove the two points that look like outliers (and expensive places) and do the lm() fit again.

# Below the | operator does elementwise OR to check either of two conditions
outliers <- which(st.kilda$BuildingArea < 40 | st.kilda$Price > 1000000)
st.kilda.sub <- st.kilda[-outliers,]
lmfit2 <- lm(Price ~ BuildingArea, data = st.kilda.sub)
summary(lmfit2)

Multivariate regression

Now let's add building type as a predictor in our model and see if it improves the prediction.

lmfit3 <- lm(Price ~ Type + BuildingArea, data = st.kilda.sub) 
summary(lmfit3)
new <- data.frame(BuildingArea = c(100,100), Type = c("u", "h")) # Cant predict townhouse since none exist in original data after filtering. 
predict(lmfit3, new) 

Spline smoothing

st.kilda.noNA <- subset(st.kilda.sub, !is.na(BuildingArea) & !is.na(Price))
dim(st.kilda.noNA)

spline.fit <- smooth.spline(x=st.kilda.noNA$BuildingArea, y = st.kilda.noNA$Price)
# Or use with
spline.fit2 <- with(st.kilda.noNA, smooth.spline(x = BuildingArea, y = Price))

Loess smoothing

lo1.fit <- loess(Price ~ BuildingArea, data = st.kilda.noNA)

plot(st.kilda.noNA$BuildingArea, st.kilda.noNA$Price)
lines(spline.fit, col = "purple", lwd =2)
lines(sort(st.kilda.noNA$BuildingArea), predict(lo1.fit, sort(st.kilda.noNA$BuildingArea)), col = "red", lwd =2)
legend("bottomright",c("Spline","Loess"),
      lty=c(1,1), col=c("purple", "red"))

# We can also use the loess fit to do prediction 
predict(lo1.fit, 100)

[henryliangt]

getwd()
setwd('C:/Users/HenryLiang/Desktop/GIA File/StudyUSYD/5003/w3')
list.files()

[henryliangt]

data = read.csv("PTSD.csv", header = TRUE)
# data = read.table("height.txt",  header = TRUE)
class(data)
dim(data)
nrow(data)
ncol(data)
colnames(data) 
object.size(data)
print(paste('Rows= ', nrow(data), '  and  Cols = ',ncol(data), sep = ":"))
names(data)

head(data, 6)
tail(data, 6)
summary(data)
str(data)