R foundation for, while, the custom function (proof of the central limit theorem)

Later proved the Central Limit Theorem custom fun not get to know ,,, 
### 6.R language and Statistics #### 

### 7. cycling with a custom function #### 
# 7.1 for ### cycles # 

Example ( "for") 

for (I in. 1:. 5) Print (. 1: I) # number of loops through each, each taken a number, is printed a vector 

for (n in c (2,5,10,20 , 50)) {# vectors not loop through a number 
  x <- stats :: rnorm (n ) # n to generate a normal distribution having a number, n being the number of that loop through the above 
  cat (n, ":" , sum (x ^ 2), "\ n") # corresponding to each number n, the normal distribution of the square array and generating 
} 
#cat serving as the connection, the embodiment: number: squares of x and line 

f <- factor (sample (letters [1: 5], 10, replace = TRUE)); f # samples, generating a sequence of letters 

for (i in unique (f) ) print (i) # sequentially an extraction sequence in each of a value unique to 

# 7.2 while statement #### 
V <- C ( "the Hello", "the while Loop") 
CNT <- 2 

the while (CNT <. 7) { 
  Print (V) 
  CNT = CNT +. 1 
} 

a <- c (1:5)
i<-15)
while(a[i]<5){
  Print (A [I]) 
  I = I +. 1 
} 
the last element of the amount of orientation # 
B [length (B)] 
tail (B,. 1) 
# 7.3 custom function #### 

myfun_cv <-function (X) { function in R # is an object 
  cv <-sd (x) / mean (x) # function used to calculate the coefficient of variation thereof statement 
  return (cv) # cv return value function execution is completed, the value is the coefficient of variation 
} 

# test the function 
a <-c (1,2,5,8,9,6) # generates a vector   
myfun_cv (a) # call a custom function to calculate the coefficient of variation 

# 7.4 by circulating and custom function to verify the central limit Theorem #### 
myfun <-function (a) { 
  X <-1: Mr # 100 as a sequence of 1 to 100, these values can be changed later, corresponds to overwrite the original value 
  x <-data.frame (x ) 
  a <-data.frame (a) 
  
  for (I in. 1: 100) {# set loop that 100 samples extracted, and assign the calculated mean of the data frame to the variables x 
    c <-a [sample ( nrow (A), 1000),] 
    m = Mean (C)
    X $ X [I] <- m 
  } 
  
  Windows (1280,720); PAR (mfrow = C (1,2)) 
  Plot (Density (A $ A), main = "This is the original distribution") 
  Plot (Density (x $ x), main = " this is the mean distribution of the extracted sample")    
} 
### 7.4 .1 normal #### 
a <-rnorm (10000,0,1) 
myfun (a) 
7.4.2 exponential distribution ### #### 
B <-rexp (100000,1) 
myfun (B) 
### 7.4.3t distribution #### 
C <-rt (1000,3) 
myfun (C) 
# ## 7.4.4F distribution #### 
D <-rchisq (100000,1) 
myfun (D)