5+5
2*2
5-7
(5+5)/2
2^2
28%%6

> getwd() # 获取当前路径
> setwd("~/") # 设置工作路径
> .libPaths() # 获取R包的位置
> library() # 所有软件包的列表
> search()# 当前环境加载的包

数值型 numerics (1, 2.5)
逻辑判断 logical (TRUE or FALSE)
字符型 characters
因子 factors
判断数据类型 class(变量名）

a <- c(1, 2, 5, 3, 6, -2, 4)
b <- c("apple", "pear", "orange")
c <- c(TRUE, FALSE, TRUE, FALSE, TRUE, FALSE)

myymatrix <- matrix(vector, nrow=number_of_rows, ncol=number_of_columns,
                    byrow=logical_value)
> myMatrix <- matrix(1:15, nrow=3, ncol=5) 
> y <- matrix(1:18, nrow=2)

# Elements are arranged sequentially by row.
M <- matrix(c(3:14), nrow = 4, byrow = TRUE)
print(M)

# Elements are arranged sequentially by column.
N <- matrix(c(3:14), nrow = 4, byrow = FALSE)
print(N)

# Define the column and row names.
rownames = c("row1", "row2", "row3", "row4")
colnames = c("col1", "col2", "col3")

P <- matrix(c(3:14), nrow = 4, byrow = TRUE, dimnames = list(rownames, colnames))
print(P[1,3]) # 按行列取值
print(M+N)
print(M*N)
print(M/N)

students <- c("A", "B", "C", "D")
math_score<-c(100, 80, 70, 95)
english_score<-c(96, 86, 77, 99)
students_scores<-data.frame(students, math_score,english_score)
students_scores[,2]
students_scores[2,2]

# Create the data frame.
emp.data <- data.frame(
  emp_id = c (1:5), 
  emp_name = c("Rick","Dan","Michelle","Ryan","Gary"),
  salary = c(623.3,515.2,611.0,729.0,843.25), 
  
  start_date = as.Date(c("2017-01-01", "2017-09-23", "2017-11-15", "2017-05-11",
                         "2018-03-27")),
  stringsAsFactors = FALSE)
# Print the data frame.            
print(emp.data)
print(str(emp.data))
print(summary(emp.data))

excellence<- c("excellent", "bad", "good", "okay", "bad")
excellence<- factor(excellence)

excellence <- factor(excellence, order=TRUE,levels=c("bad", "okay","good","excellent"))
excellence

# Create a vector as input.
data <- c("East","West","East","North","North","East","West","West","West","East","North")

print(data)
print(is.factor(data))

# Apply the factor function.
factor_data <- factor(data)

print(factor_data)
print(is.factor(factor_data))

a <- "My First List"
b <- c(25, 26, 18, 39)
c <- matrix(1:10, nrow=5)
d <- c("one", "two", "three")
mylist <- list(title=a ,b,c,d)

# 列表
list_data = list("Red", "Green", c(21,32,11), TRUE, 51.23, 119.1);
print(list_data[2])
list_2 = list(1,2,3)
list_3 = c(list_2,list_data)
print(list_3)

a <- c(2,3,4,5);
b <- c(1,3,5,7);
print(a+b);
print(a-b);
print(a*b);
print(a/b);
print(a%%b);
print(a^b);

print(a>b);
print(a==b);
print(a>=b);
print(a!=b);

print(a&b)
print(a|b)

v1 <- c(3,1,TRUE,2+3i);
v2 <<- c(3,1,TRUE,2+3i);
v3 = c(3,1,TRUE,2+3i);
print(v1);
print(v2);
print(v3);

c(3,1,TRUE,2+3i) -> v1;
c(3,1,TRUE,2+3i) ->> v2;
print(v1);
print(v2);

function_name <- function(arg_1, arg_2, ...) {
   Function body 
}

a = 'Hello'
b <- 'How'
c <- "are you? "

print(paste(a,b,c))
print(paste(a,b,c, sep = "-"))
print(paste(a,b,c, sep = " ", collapse = " "))

data <- read.csv('input.csv')
print(data)
print(is.data.frame(data))
print(ncol(data))
print(nrow(data))
print(max(data$score))
person = subset(data,score == min(score))
print(person)
write.csv(person,"output.csv")

any(grepl('xlsx',installed.packages()));
library('xlsx')
data = read.xlsx('input.xlsx',sheetIndex = 1)
print(data)
write.xlsx(data,'test.xlsx')

pie(x, labels, radius, main, col, clockwise)
x - 是包含饼图中使用的数值的向量。
labels - 用于描述切片的标签。
radius - 用来表示饼图圆的半径(-1和+1之间的值)。
main - 用来表示图表的标题。
col - 表示调色板。
clockwise - 是一个逻辑值，指示片是顺时针还是逆时针绘制。

# Create data for the graph.
x <- c(11, 30, 39, 20)
labels <- c("70后", "80后", "90后", "00后")

piepercent<- paste(round(100*x/sum(x), 2), "%")
# Give the chart file a name.
png(file = "birth_of_age1.jpg")

# Plot the chart.
pie(x, labels = piepercent, main = "出生年龄段 - 饼状图",col = rainbow(length(x)))
legend("topright", c("70后","80后","90后","00后"), cex = 0.8,
       fill = rainbow(length(x)))

# Save the file.
dev.off()

barplot(H,xlab,ylab,main,names.arg,col)
H - 是包含条形图中使用的数值的向量或矩阵。
xlab - 是x轴的标签。
ylab - 是y轴的标签。
main - 是条形图的标题。
names.arg - 是在每个栏下显示的名称向量。
col - 用于给图中的图条给出颜色。

colors <- c("green","orange","brown")
months <- c("一月","二月","三月","四月","五月")
regions <- c("东部地区","西部地区","南部地区")

# Create the matrix of the values.
Values <- matrix(c(2,9,3,11,9,4,8,7,3,12,5,2,8,10,11),nrow = 3,ncol = 5,byrow = TRUE)

# Give the chart file a name.
png(file = "barchart_stacked.png")

# Create the bar chart.
barplot(Values,main = "总收入",names.arg = months,xlab = "月份",ylab = "收入",
        col = colors)

# Add the legend to the chart.
legend("topleft", regions, cex = 1.3, fill = colors)

# Save the file.
dev.off()

library(vcd)
counts <- table(Arthritis$Improved,Arthritis$Treatment)
print(counts)
png(file = "./result/barchart_stacked1.png")
barplot(counts,main='Stacked Bar Plot',xlab='Treatment',ylab='Frequency',col=c('red','yellow','green'),legend=rownames(counts))
dev.off()

png(file = "./result/barchart_stacked2.png")
barplot(counts,main='Grouped Bar Plot',xlab='Treatment',ylab='Frequency',col=c('red','yellow','green'),legend=rownames(counts),beside=TRUE) # 分组
dev.off()

plot(x, y, main, xlab, ylab, xlim, ylim, axes)
x - 是数据集，其值是水平坐标。
y - 是数据集，其值是垂直坐标。
main - 是图表的标题。
xlab - 是水平轴(y轴)上的标签。
ylab - 是垂直轴(y轴)上的标签。
xlim - 是用于绘制的x的值的极限。
ylim - 是用于绘制的y值的极限。
axes - 指示是否应在绘图上绘制两个轴。

png(file = './result/test1.png')
attach(mtcars)
plot(wt,mpg)
abline(lm(mpg~wt))
title('Regression of mpg on weight')
detach(mtcars)
# Save the file.
dev.off()

leadership$age[leadership$age ==99] <- NA # 任何等于99的年龄都被修改为NA

mydate <- as.Date(c('2007-06-22','2004-02-13'))
print(mydate)
print(class(mydate))

strDdte = c('01/05/1987','08/16/1975')
dates = as.Date(strDdte,'%m/%d/%Y')
print(dates)


strDate = as.character(dates)
print(strDate)
print(class(strDate))

# 类型转换
a <- c(1,2,3)
b <- as.numeric(a)
c = as.character(a)
d = as.vector(a)
e = as.matrix(a)
f = as.matrix(a)
g = as.data.frame(a)
h = as.factor(a)
i = as.logical(a)
print(is.numeric(a))
print(is.character(c))
print(is.vector(d))
print(is.matrix(e))
print(is.data.frame(g))
print(is.logical(i))

total <- merge(dataframeA,dataframeB,by='ID')

total <- rbind(dataframeA,dataframeB)

a = c(1,2,3)
d = matrix(a)
print(d)
e = t(d)
print(e)

newdata <- subset(leadership,age >= 35 | age < 24,select=c(q1,q2,q3,q4))

library(sqldf)
newdf <- sqldf('select * from mtcars where carb=1 order by mpg',row.names = TRUE)
print(newdf)

library(reshape)
md <- melt(mydata,id=(c('id','time')))

a = 3.1415
print(floor(a))
print(ceiling(a))
print(round(a,digits = 2))
print(signif(a,digits = 2))
print(cos(a))
print(sin(a))
print(tan(a))
print(log(a,base = 2))
print(log10(x))
print(exp(e))

# 统计函数
print(mean(c(1,2,3,4)))
print(median(c(1,2,3,4)))
print(sd(c(1,2,3,4)))
print(var(c(1,2,3,4)))
print(mad(c(1,2,3,4)))
print(range(c(1,2,3,4,5)))

mean(x, trim = 0, na.rm = FALSE, ...)
x - 是输入向量。
trim - 用于从排序的向量的两端删除一些观测值。
na.rm - 用于从输入向量中删除缺少的值。

x <- c(17,8,6,4.12,11,8,54,-11,18,-7)
# Find Mean.
result.mean <- mean(x)
print(result.mean)

median(x,na.rm=FALSE)
x - 是输入向量
na.rm - 是用于输入向量中删除缺少的值。

# Find the median.
median.result <- median(x)
print(median.result)

# 众数
# Create the function.
getmode <- function(v) {
  uniqv <- unique(v)
  uniqv[which.max(tabulate(match(v, uniqv)))]
}

# Create the vector with numbers.
v <- c(2,1,2,3,1,2,3,4,1,5,5,3,2,3)

# Calculate the mode using the user function.
result <- getmode(v)
print(result)

# Create the vector with characters.
charv <- c("baidu.com","tmall.com","yiibai.com","qq.com","yiibai.com")

# Calculate the mode using the user function.
result <- getmode(charv)
print(result)

y = ax+b
y 响应变量
x 预测变量
a与b是系统参数

x <- c(151, 174, 138, 186, 128, 136, 179, 163, 152, 131)
y <- c(63, 81, 56, 91, 47, 57, 76, 72, 62, 48)

# Apply the lm() function.
relation <- lm(y~x)

# Give the chart file a name.
png(file = "linearregression.png")

# Plot the chart.
plot(y,x,col = "blue",main = "身高和体重回归",
     abline(lm(x~y)),cex = 1.3,pch = 16,xlab = "体重(Kg)",ylab = "身高(cm)")

# Save the file.
dev.off()


print(summary(relation))

# Find weight of a person with height 170.
a <- data.frame(x = 170)
result <-  predict(relation,a)
print(result)

lm(y ~ x1+x2+x3...,data)
ormula - 即：y ~ x1+x2+x3...是呈现响应变量和预测变量之间关系的符号。
data - 是应用公式的向量。

# Create the relationship model.
model <- lm(mpg~disp+hp+wt, data = input)

# Show the model.
print(model)

# Get the Intercept and coefficients as vector elements.
cat("# # # # The Coefficient Values # # # ","\n")

a <- coef(model)[1]
print(a)

Xdisp <- coef(model)[2]
Xhp <- coef(model)[3]
Xwt <- coef(model)[4]

glm(formula,data,family)

formula - 是呈现变量之间关系的符号。
data - 是给出这些变量值的数据集。
family - 是R对象来指定模型的概述，对于逻辑回归，它的值是二项式。

# Select some columns form mtcars.
input <- mtcars[,c("am","cyl","hp","wt")]
print(head(input))

input <- mtcars[,c("am","cyl","hp","wt")]

am.data = glm(formula = am ~ cyl + hp + wt, data = input, family = binomial)

print(summary(am.data))

# Create a sequence of numbers between -10 and 10 incrementing by 0.1.
x <- seq(-10, 10, by = .1)

# Choose the mean as 2.5 and standard deviation as 0.5.
y <- dnorm(x, mean = 2.5, sd = 0.5)

# Give the chart file a name.
png(file = "dnorm.png")

plot(x,y)

# Save the file.
dev.off()

library(party)

# Create the input data frame.
input.dat <- readingSkills[c(1:105),]

# Give the chart file a name.
png(file = "decision_tree.png")

# Create the tree.
  output.tree <- ctree(
  nativeSpeaker ~ age + shoeSize + score, 
  data = input.dat)

# Plot the tree.
plot(output.tree)

# Save the file.
dev.off()

randomForest(formula, data)
formula - 是描述预测变量和响应变量的公式。
data - 是使用的数据集的名称。

library("party")
library("randomForest")

# Create the forest.
output.forest <- randomForest(nativeSpeaker ~ age + shoeSize + score, 
           data = readingSkills)

# View the forest results.
print(output.forest) 

# Importance of each predictor.
print(importance(output.forest,type = 2))

Surv(time,event)
survfit(formula)
time - 是直到事件发生的后续时间。
event - 表示预期事件发生的状态。
formula - 是预测变量之间的关系。

# Load the library.
library("survival")

# Create the survival object. 
survfit(Surv(pbc$time,pbc$status == 2)~1)

# Give the chart file a name.
png(file = "survival.png")

# Plot the graph. 
plot(survfit(Surv(pbc$time,pbc$status == 2)~1))

# Save the file.
dev.off()

# Load the library.
library("MASS")

# Create a data frame from the main data set.
car.data <- data.frame(Cars93$AirBags, Cars93$Type)

# Create a table with the needed variables.
car.data = table(Cars93$AirBags, Cars93$Type) 
print(car.data)

# Perform the Chi-Square test.
print(chisq.test(car.data))

for (i in 1:10) print('hello')

i <- 10
while (i>0) {print('hello'};i <- i-1}

if (cond) statement1 else statement2

feeling <- c('sad','afraid')
for (i in feeling)
    print(
        switch(i,happy = 'I am glad you  are happy',
        afraid = 'there is nothing to fear',
        sad = 'cheer up',
        angry = 'calm down now'
        )
    )

vars = c('wt','hp','mpg')
datasets = mtcars[vars]
print(datasets)
print(summary(datasets))#最小值、最大值、四分位数和数值型变量的均值，以及因子向量和逻 辑型向量的频数统计

# 通过Hmisc包中的describe()函数计算描述性统计量
print('通过Hmisc包中的describe()函数计算描述性统计量')
library(Hmisc)
print(describe(mtcars[vars]))#若basic=TRUE(默认值)，则计算其中所有值、空值、缺失 值的数量，以及最小值、最大值、值域，还有总和。若desc=TRUE(同样也是默认值)，则计算 中位数、平均数、平均数的标准误、平均数置信度为95%的置信区间、方差、标准差以及变异系 数。

# 通过pastecs包中的stat.desc()函数计算描述性统计量
print('通过pastecs包中的stat.desc()函数计算描述性统计量')
library(pastecs)
print(stat.desc(mtcars[vars]))#计算非缺失值的数量、 平均数、标准差、中位数、截尾均值、绝对中位差、最小值、最大值、值域、偏度、峰度和平均 值的标准误

library(gmodels)
print(CrossTable(Arthritis$Treatment,Arthritis$Improved))