20151201Demo.Rmd

---
title: "20151201Demo"
author: "David Chiu"
date: "2015年12月1日"
output: html_document
---

## RDemo
```
install.packages("car")
library("car")
data()
data(Quartet)

plot(Quartet$x, Quartet$y1)
fit = lm(Quartet$y1 ~ Quartet$x)
abline(fit, col="red")
fit

```
## GDP
```
gdp = read.csv("gdp.csv",header=TRUE)

gdp = gdp[1:15,]
gdp$GDP = as.numeric(sub(",", "", gdp$GDP))
gdp$Export = as.numeric(sub(",", "", gdp$Export))
cor(gdp$Export, gdp$GDP)
plot(gdp$Export ~ gdp$GDP)
fit = lm(gdp$Export ~ gdp$GDP)
abline(fit, col="red")
fit
summary(fit)

```

## RBasic
```
help.search(“sum”)
demo()
demo("graphics")
rm(a)


3+8
3-8
3*8
3/8
1/0
10/3
11%%2

a = 3
a <- 5
fit = lm(y1 ~ x, data =Quartet)
fit <- lm(y1 ~ x, data =Quartet)

numer = 17.8
chr = "hello"
logic1 = TRUE
class(numer)
class(chr)
class(logic1)
card_length = 3
card_width = "5 inches"
card_length * card_width
```
## Vector
```
getwd()
gdp = read.csv("C:/Users/BigData/Desktop/gdp.csv",header=TRUE)
setwd("C:/Users/BigData/Desktop")

x = c(1,2,3,7)
y= c(2,3,5,1)
x+y
x*y
x - y
x/y

x + 10
x + c(10)
x + c(10,10,10,10)

x + c(1,2)
x + c(1,2,1,2)

x = c(1,2,3,7)
sum(x)

?sum
help(sum)

x = c(1,2,3,4, NA)
sum(x)
sum(x, na.rm=TRUE)

height_vec = c(180,169,173)
height_vec
names(height_vec) = c("Brian", "Toby", "Sherry")
height_vec

name_vec = c("Brian", "Toby", "Sherry")
names(height_vec) = name_vec
height_vec > 175
height_vec / 100
height_vec > 175 | height_vec < 170
height_vec < 175 & height_vec > 170

```

## Vector Example
```
height_vec = c(180,169,173)
names(height_vec) = c("Brian", "Toby", "Sherry")
height_vec
weight_vec = c(73,87,43)
bmi_vec = weight_vec/(height_vec / 100)^2
bmi_vec < 18.5 | bmi_vec >= 24
names(bmi_vec[bmi_vec < 18.5 | bmi_vec >= 24])

a = c(1,2,3,4)
b = c(FALSE, FALSE, TRUE, FALSE)
a[b]
a[!b]

```
## Matrix

```
1:10
sum(1:10)
seq(1,10,2)

1:9
matrix(1:9, nrow = 3)
matrix(1:9, nrow = 3, byrow=TRUE)

a = c(1,2)
b = c(3,4)
c(a,b)

kevin = c(85,73)
marry = c(72,64)
jerry = c(59,66)

mat = matrix(c(kevin,marry,jerry), nrow=3, byrow=TRUE)
rownames(mat) = c("kevin", "marry", "jerry")
colnames(mat) = c("first", "second")
mat

mat2 = matrix(c(kevin, marry, jerry), nrow=3, byrow=TRUE, dimnames=list(c('kevin', 'marry', 'jerry'),c('first', 'second')))

install.packages("swirl")
library("swirl")
dim(mat)
nrow(mat)
ncol(mat)

mat[2:3,2]
mat[2:3,]
mat[,]
mat[1,]
 mat[2,2] =64
 mat3 = rbind(mat2, c(78,63))
 rownames(mat3)[nrow(mat3)] = 'sam'
mat3

mat4 = cbind(mat2,c(82,77,70))
colnames(mat4)[ncol(mat4)] = 'third'
mat4

rowSums(mat2)
colSums(mat2)

m1 = matrix(1:4, byrow=TRUE, nrow=2)
m2 = matrix(5:8, byrow=TRUE, nrow=2)

m1 + m2
m1 - m2
m1 * m2
m1 / m2

m1 %*% m2

mat[,1] * 0.4 + mat[,2] * 0.6
mat %*% c(0.4,0.6)
```

## Factor

```
a = c(0,0,0,1,1,1,1,1,0,0)
plot(a)
a = as.factor(a)
a
plot(a)
weather= c("sunny","rainy"
, "cloudy", "rainy",
"cloudy")
class(weather)

weather = factor(weather)
weather = as.factor(weather)
class(weather)

weather_category = factor(weather)
weather_category

temperature = c("Low", "High", "High", "Medium", "Low",
"Medium")
temperature
temperature_category =factor(temperature) 
temperature_category
temperature_category[2]
temperature_category[1]
temperature_category[2] > temperature_category[1]

temperature_category = factor(temperature, order = TRUE,
levels = c("Low",
"Medium", "High"))
temperature_category[2] > temperature_category[1]
levels(temperature_category)

weather= c("s","r", "c", "r", "c")
weather_factor = factor(weather)
weather_factor
levels(weather_factor) = c("cloudy","rainy","sunny")
weather_factor
```

## DataFrame
```
data(iris)
class(iris)
df = data.frame(a=c(1,2,3,4,5),b=c(2,3,4,5,6))
head(iris)
?head
head(iris, 10)
head(iris, n = 10)
tail(iris, 10)
tail(iris, n = 10)
str(iris)
iris$Sepal.Length


iris[1:3,]
iris[1:3,1]
iris[1:3,"Sepal.Length"]
head(iris[,1:2])
iris$"Sepal.Length"

#取前五筆包含length 及 width 的資料
Five.Sepal.iris = iris[1:5, c("Sepal.Length","Sepal.Width")]
#可以用條件做篩選
setosa.data = iris[iris$Species=="setosa",1:5]
str(setosa.data)

#使用which 做資料篩選
which(iris$Species=="setosa")
a = c(1,8,2,9,3)
which(a < 5)

df = data.frame(a=c(1,2,3,4,5),b=c(2,3,4,5,6))
df2 = data.frame(b=c(2,5,6,8,3),c=c(1,1,1,0,0))
merge(df,df2, by="b")

a = c(1,8,2,9,3)
sort(a)
sort(a, decreasing = TRUE)
order(a)
order(a, decreasing = TRUE)

order(df2$b)
df2[order(df2$b),]
iris[order(iris$Sepal.Length, decreasing = TRUE),]
weather= c("sunny","rainy", "cloudy", "rainy","cloudy")
table(weather)
table.iris = table(iris$Species)
pie(table.iris)
hist(iris$Sepal.Length)

boxplot(Petal.Width ~ Species, data = iris)
plot(x=iris$Petal.Length, y=iris$Petal.Width, col=iris$Species)
```

## stock example
```
tw2330 = read.csv("table.csv", header=TRUE)
str(tw2330)
max(tw2330$Close)
min(tw2330$Close)
summary(tw2330$Close)

hist(tw2330$Close)
boxplot(tw2330$Close)

tw2330$Date = as.Date(tw2330$Date)
plot(tw2330$Date, tw2330$Close)

stock2 = tw2330[tw2330$Date >= '2015-01-01',]
str(stock2)
summary(stock2$Close)
ordered_stock = stock2[order(stock2$Close),]
ordered_stock[1,]
ordered_stock[nrow(ordered_stock),]
stock2[1,] - ordered_stock[1,]

```


## List

```
item = list(thing="hat", size="8.25")
item

test = list(name="Toby", score = c(87,57,72))
test$score
test$score[2]

flower= list(title="iris dataset", data= iris)
class(flower)
class(flower$data)
flower$data[1,"Sepal.Width"]

```
## File read and write
```
test.data = read.table(“match.txt" ,header = TRUE, sep=“|”)
```