R语言统计知识以及常用方法实例

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))