R学习——霍普金斯大学week4

##week4
"str 函数"
#返回参数
# > str(str)
# function (object, ...)  
#  > str(lm)
# function (formula, data, subset, weights, na.action, method = "qr", 
#           model = TRUE, x = FALSE, y = FALSE, qr = TRUE, singular.ok = TRUE, 
#           contrasts = NULL, offset, ...)  
# > str(ls)
# function (name, pos = -1L, envir = as.environment(pos), 
#           all.names = FALSE, pattern, sorted = TRUE)  
# 
# > x <- rnorm(100,2,4)
# > summary(x)
# Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
# -7.6173 -0.5374  2.1654  2.1999  4.8181 12.2632 
# > str(x)
# num [1:100] 5.25 -3.75 4.06 8.18 -0.28 ...

# > f <- gl(40,10)
# > str(f) 输出会更加紧凑
# Factor w/ 40 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...

# > library(datasets)
# > head(airquality)
# Ozone Solar.R Wind Temp Month Day
# 1    41     190  7.4   67     5   1
# 2    36     118  8.0   72     5   2
# 3    12     149 12.6   74     5   3
# 4    18     313 11.5   62     5   4
# 5    NA      NA 14.3   56     5   5
# 6    28      NA 14.9   66     5   6
# > str(airquality)
# 'data.frame':	153 obs. of  6 variables:
#     $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
# $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
# $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
# $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ...
# $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
# $ Day    : int  1 2 3 4 5 6 7 8 9 10 ...



# > library(datasets)
# > head(airquality)
# Ozone Solar.R Wind Temp Month Day
# 1    41     190  7.4   67     5   1
# 2    36     118  8.0   72     5   2
# 3    12     149 12.6   74     5   3
# 4    18     313 11.5   62     5   4
# 5    NA      NA 14.3   56     5   5
# 6    28      NA 14.9   66     5   6
# > str(airquality)
# 'data.frame':	153 obs. of  6 variables:
#     $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
# $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
# $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
# $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ...
# $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
# $ Day    : int  1 2 3 4 5 6 7 8 9 10 ...


"总结:str相当于一个概括的函数"


"simulation"

# 四中随机数
dnorm(x, mean = 0,sd= 1, log = FALSE)
pnorm(q, mean = 0,sd = 1, lower.tail = TRUE, log.p = FALSE)
qnorm(p, mean = 0,sd = 1, lower.tail = TRUE, log.p = FALSE)
rnorm(n, mean = 0,sd = 1)



# > x <- rnorm(10)
# > x
# [1]  0.6655806 -0.4015949 -2.7861818 -1.5521880  1.9839463
# [6] -0.8560313  0.8182983 -0.2929819  1.4166468 -1.7064836
# > x <- rnorm(10, 20, 2)
# > x
# [1] 18.15547 17.62154 17.20510 17.75022 17.79313 18.99929
# [7] 21.45195 20.91455 22.81174 20.40405
# > summary(x)
# Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
# 17.21   17.76   18.58   19.31   20.79   22.81 

# R中生成的数字并不是完全随机的,设置seed方便追溯结果

# > set.seed(1)
# > rnorm(5)
# [1] -0.6264538  0.1836433 -0.8356286  1.5952808  0.3295078
# > rnorm(5)
# [1] -0.8204684  0.4874291  0.7383247  0.5757814 -0.3053884
# > set.seed(1)
# > rnorm(1)
# [1] -0.6264538


# > rpois(10,1)
# [1] 1 2 0 2 3 1 1 0 0 0
# > rpois(10,2)
# [1] 3 1 3 2 3 6 1 3 4 1
# > rpois(10,20)
# [1] 21 17 18 18 21 16 23 22 24 23
# > 
# > ppois(2,2)
# [1] 0.6766764
# > ppois(4,2)
# [1] 0.947347
# > ppois(6,2)
# [1] 0.9954662



# > rpois(10,1)
# [1] 1 2 0 2 3 1 1 0 0 0
# > rpois(10,2)
# [1] 3 1 3 2 3 6 1 3 4 1
# > rpois(10,20)
# [1] 21 17 18 18 21 16 23 22 24 23
# > 

# > ppois(2,2) cumulative distribution
# [1] 0.6766764 ##Pr(x <= 2)
# > ppois(4,2) 
# [1] 0.947347 ## Pr(x <= 4)
# > ppois(6,2)
# [1] 0.9954662 ## Pr(x <= 6)


"画图 生成一个随机函数"
set.seed(20)
x <- rnorm(100)
e <- rnorm(100,0, 2)
y <- 0.5 + 2 * x + e
summary(y)
plot(x, y)

# > set.seed(20)
# > x <- rnorm(100)
# > e <- rnorm(100,0, 2)
# > y <- 0.5 + 2 * x + e
# > summary(y)
# Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
# -6.4084 -1.5402  0.6789  0.6893  2.9303  6.5052 
# > plot(x, y)


# 如果是两元的函数
set.seed(10)
x <- rbinom(100, 1, 0.5)
e <- rnorm(100, 0, 2)
y <- 0.5 + 2 * x + e
summary(y)
plot(x,y)

# > set.seed(10)
# > x <- rbinom(100, 1, 0.5)
# > e <- rnorm(100, 0, 2)
# > y <- 0.5 + 2 * x + e
# > summary(y)
# Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
# -3.4936 -0.1409  1.5767  1.4322  2.8397  6.9410 
# > plot(x,y)


set.seed(1)
x <- rnorm(100)
log.mu <- 0.5 +0.3 * x
y <- rpois(100, exp(log.mu))
summary(y)
plot(x,y)

# > set.seed(1)
# > x <- rnorm(100)
# > log.mu <- 0.5 +0.3 * x
# > y <- rpois(100, exp(log.mu))
# > summary(y)
# Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
# 0.00    1.00    1.00    1.55    2.00    6.00 
# > plot(x,y)


# sample 随机取出四个数字且不放回
# 除了对数字取样还能对字母取样


# > set.seed(1)
# > sample(1:10, 4)
# [1] 9 4 7 1
# > sample(1:10, 4)
# [1] 2 7 3 6
# > sample(letters, 5)
# [1] "r" "s" "a" "u" "w"
# > sample(1:10)
# [1] 10  6  9  2  1  5  8  4  3  7
# > sample(1:10)
# [1]  5 10  2  8  6  1  4  3  9  7
# > sample(1:10,replace= TRUE)
# [1]  3  6 10 10  6  4  4 10  9  7



"profiler 分析为什么时间过程的工具"

# user time = cpu + system time
# elapsed time = user time + 加载时间



system.time({
    n <- 1000
    r <- numeric(n)
    for (i in 1:n){
        x<- rnorm(n)
        r[i] <- mean(x)
    }
})

"R profiler"