R 简明教程

$ R

> myString <- "Hello, World!"
> print ( myString)
[1] "Hello, World!"

# My first program in R Programming
myString <- "Hello, World!"

print ( myString)

$ Rscript test.R

[1] "Hello, World!"

# My first program in R Programming

if(FALSE) {
   "This is a demo for multi-line comments and it should be put inside either a
      single OR double quote"
}

myString <- "Hello, World!"
print ( myString)

[1] "Hello, World!"

# Create a vector.
apple <- c('red','green',"yellow")
print(apple)

# Get the class of the vector.
print(class(apple))

[1] "red"    "green"  "yellow"
[1] "character"

# Create a list.
list1 <- list(c(2,5,3),21.3,sin)

# Print the list.
print(list1)

[[1]]
[1] 2 5 3

[[2]]
[1] 21.3

[[3]]
function (x)  .Primitive("sin")

# Create a matrix.
M = matrix( c('a','a','b','c','b','a'), nrow = 2, ncol = 3, byrow = TRUE)
print(M)

     [,1] [,2] [,3]
[1,] "a"  "a"  "b"
[2,] "c"  "b"  "a"

# Create an array.
a <- array(c('green','yellow'),dim = c(3,3,2))
print(a)

, , 1

     [,1]     [,2]     [,3]
[1,] "green"  "yellow" "green"
[2,] "yellow" "green"  "yellow"
[3,] "green"  "yellow" "green"

, , 2

     [,1]     [,2]     [,3]
[1,] "yellow" "green"  "yellow"
[2,] "green"  "yellow" "green"
[3,] "yellow" "green"  "yellow"

# Create a vector.
apple_colors <- c('green','green','yellow','red','red','red','green')

# Create a factor object.
factor_apple <- factor(apple_colors)

# Print the factor.
print(factor_apple)
print(nlevels(factor_apple))

[1] green  green  yellow red    red    red    green
Levels: green red yellow
[1] 3

# Create the data frame.
BMI <- 	data.frame(
   gender = c("Male", "Male","Female"),
   height = c(152, 171.5, 165),
   weight = c(81,93, 78),
   Age = c(42,38,26)
)
print(BMI)

  gender height weight Age
1   Male  152.0     81  42
2   Male  171.5     93  38
3 Female  165.0     78  26

# Assignment using equal operator.
var.1 = c(0,1,2,3)

# Assignment using leftward operator.
var.2 <- c("learn","R")

# Assignment using rightward operator.
c(TRUE,1) -> var.3

print(var.1)
cat ("var.1 is ", var.1 ,"\n")
cat ("var.2 is ", var.2 ,"\n")
cat ("var.3 is ", var.3 ,"\n")

[1] 0 1 2 3
var.1 is  0 1 2 3
var.2 is  learn R
var.3 is  1 1

var_x <- "Hello"
cat("The class of var_x is ",class(var_x),"\n")

var_x <- 34.5
cat("  Now the class of var_x is ",class(var_x),"\n")

var_x <- 27L
cat("   Next the class of var_x becomes ",class(var_x),"\n")

The class of var_x is  character
   Now the class of var_x is  numeric
      Next the class of var_x becomes  integer

print(ls())

[1] "my var"     "my_new_var" "my_var"     "var.1"
[5] "var.2"      "var.3"      "var.name"   "var_name2."
[9] "var_x"      "varname"

# List the variables starting with the pattern "var".
print(ls(pattern = "var"))

[1] "my var"     "my_new_var" "my_var"     "var.1"
[5] "var.2"      "var.3"      "var.name"   "var_name2."
[9] "var_x"      "varname"

print(ls(all.name = TRUE))

[1] ".cars"        ".Random.seed" ".var_name"    ".varname"     ".varname2"
[6] "my var"       "my_new_var"   "my_var"       "var.1"        "var.2"
[11]"var.3"        "var.name"     "var_name2."   "var_x"

rm(var.3)
print(var.3)

[1] "var.3"
Error in print(var.3) : object 'var.3' not found

rm(list = ls())
print(ls())

character(0)

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

# Create a sequence of numbers from 32 to 44.
print(seq(32,44))

# Find mean of numbers from 25 to 82.
print(mean(25:82))

# Find sum of numbers frm 41 to 68.
print(sum(41:68))

[1] 32 33 34 35 36 37 38 39 40 41 42 43 44
[1] 53.5
[1] 1526

# Create a function to print squares of numbers in sequence.
new.function <- function(a) {
   for(i in 1:a) {
      b <- i^2
      print(b)
   }
}

# Create a function to print squares of numbers in sequence.
new.function <- function(a) {
   for(i in 1:a) {
      b <- i^2
      print(b)
   }
}

# Call the function new.function supplying 6 as an argument.
new.function(6)

[1] 1
[1] 4
[1] 9
[1] 16
[1] 25
[1] 36

# Create a function with arguments.
new.function <- function(a, b) {
   print(a^2)
   print(a)
   print(b)
}

# Evaluate the function without supplying one of the arguments.
new.function(6)

[1] 36
[1] 6
Error in print(b) : argument "b" is missing, with no default

# Accessing vector elements using position.
t <- c("Sun","Mon","Tue","Wed","Thurs","Fri","Sat")
u <- t[c(2,3,6)]
print(u)

# Accessing vector elements using logical indexing.
v <- t[c(TRUE,FALSE,FALSE,FALSE,FALSE,TRUE,FALSE)]
print(v)

# Accessing vector elements using negative indexing.
x <- t[c(-2,-5)]
print(x)

# Accessing vector elements using 0/1 indexing.
y <- t[c(0,0,0,0,0,0,1)]
print(y)

[1] "Mon" "Tue" "Fri"
[1] "Sun" "Fri"
[1] "Sun" "Tue" "Wed" "Fri" "Sat"
[1] "Sun"

# Create a list containing strings, numbers, vectors and a logical
# values.
list_data <- list("Red", "Green", c(21,32,11), TRUE, 51.23, 119.1)
print(list_data)

[[1]]
[1] "Red"

[[2]]
[1] "Green"

[[3]]
[1] 21 32 11

[[4]]
[1] TRUE

[[5]]
[1] 51.23

[[6]]
[1] 119.1

# Create a list containing a vector, a matrix and a list.
list_data <- list(c("Jan","Feb","Mar"), matrix(c(3,9,5,1,-2,8), nrow = 2),
   list("green",12.3))

# Give names to the elements in the list.
names(list_data) <- c("1st Quarter", "A_Matrix", "A Inner list")

# Show the list.
print(list_data)

$`1st_Quarter`
[1] "Jan" "Feb" "Mar"

$A_Matrix
     [,1] [,2] [,3]
[1,]    3    5   -2
[2,]    9    1    8

$A_Inner_list
$A_Inner_list[[1]]
[1] "green"

$A_Inner_list[[2]]
[1] 12.3

# Create a list containing a vector, a matrix and a list.
list_data <- list(c("Jan","Feb","Mar"), matrix(c(3,9,5,1,-2,8), nrow = 2),
   list("green",12.3))

# Give names to the elements in the list.
names(list_data) <- c("1st Quarter", "A_Matrix", "A Inner list")

# Access the first element of the list.
print(list_data[1])

# Access the thrid element. As it is also a list, all its elements will be printed.
print(list_data[3])

# Access the list element using the name of the element.
print(list_data$A_Matrix)

$`1st_Quarter`
[1] "Jan" "Feb" "Mar"

$A_Inner_list
$A_Inner_list[[1]]
[1] "green"

$A_Inner_list[[2]]
[1] 12.3

     [,1] [,2] [,3]
[1,]    3    5   -2
[2,]    9    1    8

# Create a list containing a vector, a matrix and a list.
list_data <- list(c("Jan","Feb","Mar"), matrix(c(3,9,5,1,-2,8), nrow = 2),
   list("green",12.3))

# Give names to the elements in the list.
names(list_data) <- c("1st Quarter", "A_Matrix", "A Inner list")

# Add element at the end of the list.
list_data[4] <- "New element"
print(list_data[4])

# Remove the last element.
list_data[4] <- NULL

# Print the 4th Element.
print(list_data[4])

# Update the 3rd Element.
list_data[3] <- "updated element"
print(list_data[3])

[[1]]
[1] "New element"

$<NA>
NULL

$`A Inner list`
[1] "updated element"

# Create two lists.
list1 <- list(1,2,3)
list2 <- list("Sun","Mon","Tue")

# Merge the two lists.
merged.list <- c(list1,list2)

# Print the merged list.
print(merged.list)

[[1]]
[1] 1

[[2]]
[1] 2

[[3]]
[1] 3

[[4]]
[1] "Sun"

[[5]]
[1] "Mon"

[[6]]
[1] "Tue"

# Create lists.
list1 <- list(1:5)
print(list1)

list2 <-list(10:14)
print(list2)

# Convert the lists to vectors.
v1 <- unlist(list1)
v2 <- unlist(list2)

print(v1)
print(v2)

# Now add the vectors
result <- v1+v2
print(result)

[[1]]
[1] 1 2 3 4 5

[[1]]
[1] 10 11 12 13 14

[1] 1 2 3 4 5
[1] 10 11 12 13 14
[1] 11 13 15 17 19

matrix(data, nrow, ncol, byrow, dimnames)

# 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] [,2] [,3]
[1,]    3    4    5
[2,]    6    7    8
[3,]    9   10   11
[4,]   12   13   14
     [,1] [,2] [,3]
[1,]    3    7   11
[2,]    4    8   12
[3,]    5    9   13
[4,]    6   10   14
     col1 col2 col3
row1    3    4    5
row2    6    7    8
row3    9   10   11
row4   12   13   14

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

# Create the matrix.
P <- matrix(c(3:14), nrow = 4, byrow = TRUE, dimnames = list(rownames, colnames))

# Access the element at 3rd column and 1st row.
print(P[1,3])

# Access the element at 2nd column and 4th row.
print(P[4,2])

# Access only the  2nd row.
print(P[2,])

# Access only the 3rd column.
print(P[,3])

[1] 5
[1] 13
col1 col2 col3
   6    7    8
row1 row2 row3 row4
   5    8   11   14

# Create two vectors of different lengths.
vector1 <- c(5,9,3)
vector2 <- c(10,11,12,13,14,15)

# Take these vectors as input to the array.
result <- array(c(vector1,vector2),dim = c(3,3,2))
print(result)

, , 1

     [,1] [,2] [,3]
[1,]    5   10   13
[2,]    9   11   14
[3,]    3   12   15

, , 2

     [,1] [,2] [,3]
[1,]    5   10   13
[2,]    9   11   14
[3,]    3   12   15

# Create two vectors of different lengths.
vector1 <- c(5,9,3)
vector2 <- c(10,11,12,13,14,15)
column.names <- c("COL1","COL2","COL3")
row.names <- c("ROW1","ROW2","ROW3")
matrix.names <- c("Matrix1","Matrix2")

# Take these vectors as input to the array.
result <- array(c(vector1,vector2),dim = c(3,3,2),dimnames = list(row.names,column.names,
   matrix.names))
print(result)

, , Matrix1

     COL1 COL2 COL3
ROW1    5   10   13
ROW2    9   11   14
ROW3    3   12   15

, , Matrix2

     COL1 COL2 COL3
ROW1    5   10   13
ROW2    9   11   14
ROW3    3   12   15

# Create two vectors of different lengths.
vector1 <- c(5,9,3)
vector2 <- c(10,11,12,13,14,15)
column.names <- c("COL1","COL2","COL3")
row.names <- c("ROW1","ROW2","ROW3")
matrix.names <- c("Matrix1","Matrix2")

# Take these vectors as input to the array.
result <- array(c(vector1,vector2),dim = c(3,3,2),dimnames = list(row.names,
   column.names, matrix.names))

# Print the third row of the second matrix of the array.
print(result[3,,2])

# Print the element in the 1st row and 3rd column of the 1st matrix.
print(result[1,3,1])

# Print the 2nd Matrix.
print(result[,,2])

COL1 COL2 COL3
   3   12   15
[1] 13
     COL1 COL2 COL3
ROW1    5   10   13
ROW2    9   11   14
ROW3    3   12   15

# Create two vectors of different lengths.
vector1 <- c(5,9,3)
vector2 <- c(10,11,12,13,14,15)

# Take these vectors as input to the array.
array1 <- array(c(vector1,vector2),dim = c(3,3,2))

# Create two vectors of different lengths.
vector3 <- c(9,1,0)
vector4 <- c(6,0,11,3,14,1,2,6,9)
array2 <- array(c(vector1,vector2),dim = c(3,3,2))

# create matrices from these arrays.
matrix1 <- array1[,,2]
matrix2 <- array2[,,2]

# Add the matrices.
result <- matrix1+matrix2
print(result)

     [,1] [,2] [,3]
[1,]   10   20   26
[2,]   18   22   28
[3,]    6   24   30

# 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))

[1] "East"  "West"  "East"  "North" "North" "East"  "West"  "West"  "West"  "East" "North"
[1] FALSE
[1] East  West  East  North North East  West  West  West  East  North
Levels: East North West
[1] TRUE

# Create the vectors for data frame.
height <- c(132,151,162,139,166,147,122)
weight <- c(48,49,66,53,67,52,40)
gender <- c("male","male","female","female","male","female","male")

# Create the data frame.
input_data <- data.frame(height,weight,gender)
print(input_data)

# Test if the gender column is a factor.
print(is.factor(input_data$gender))

# Print the gender column so see the levels.
print(input_data$gender)

  height weight gender
1    132     48   male
2    151     49   male
3    162     66 female
4    139     53 female
5    166     67   male
6    147     52 female
7    122     40   male
[1] TRUE
[1] male   male   female female male   female male
Levels: female male

data <- c("East","West","East","North","North","East","West",
   "West","West","East","North")
# Create the factors
factor_data <- factor(data)
print(factor_data)

# Apply the factor function with required order of the level.
new_order_data <- factor(factor_data,levels = c("East","West","North"))
print(new_order_data)

 [1] East  West  East  North North East  West  West  West  East  North
Levels: East North West
 [1] East  West  East  North North East  West  West  West  East  North
Levels: East West North

# 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("2012-01-01", "2013-09-23", "2014-11-15", "2014-05-11",
      "2015-03-27")),
   stringsAsFactors = FALSE
)
# Print the data frame.
print(emp.data)

 emp_id    emp_name     salary     start_date
1     1     Rick        623.30     2012-01-01
2     2     Dan         515.20     2013-09-23
3     3     Michelle    611.00     2014-11-15
4     4     Ryan        729.00     2014-05-11
5     5     Gary        843.25     2015-03-27

# 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("2012-01-01", "2013-09-23", "2014-11-15", "2014-05-11",
      "2015-03-27")),
   stringsAsFactors = FALSE
)
# Get the structure of the data frame.
str(emp.data)

'data.frame':   5 obs. of  4 variables:
 $ emp_id    : int  1 2 3 4 5
 $ emp_name  : chr  "Rick" "Dan" "Michelle" "Ryan" ...
 $ salary    : num  623 515 611 729 843
 $ start_date: Date, format: "2012-01-01" "2013-09-23" "2014-11-15" "2014-05-11" ...

# 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("2012-01-01", "2013-09-23", "2014-11-15", "2014-05-11",
      "2015-03-27")),
   stringsAsFactors = FALSE
)
# Print the summary.
print(summary(emp.data))

     emp_id    emp_name             salary        start_date
 Min.   :1   Length:5           Min.   :515.2   Min.   :2012-01-01
 1st Qu.:2   Class :character   1st Qu.:611.0   1st Qu.:2013-09-23
 Median :3   Mode  :character   Median :623.3   Median :2014-05-11
 Mean   :3                      Mean   :664.4   Mean   :2014-01-14
 3rd Qu.:4                      3rd Qu.:729.0   3rd Qu.:2014-11-15
 Max.   :5                      Max.   :843.2   Max.   :2015-03-27

# 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("2012-01-01","2013-09-23","2014-11-15","2014-05-11",
      "2015-03-27")),
   stringsAsFactors = FALSE
)
# Extract Specific columns.
result <- data.frame(emp.data$emp_name,emp.data$salary)
print(result)

  emp.data.emp_name emp.data.salary
1              Rick          623.30
2               Dan          515.20
3          Michelle          611.00
4              Ryan          729.00
5              Gary          843.25

# 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("2012-01-01", "2013-09-23", "2014-11-15", "2014-05-11",
      "2015-03-27")),
   stringsAsFactors = FALSE
)
# Extract first two rows.
result <- emp.data[1:2,]
print(result)

  emp_id    emp_name   salary    start_date
1      1     Rick      623.3     2012-01-01
2      2     Dan       515.2     2013-09-23

# 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("2012-01-01", "2013-09-23", "2014-11-15", "2014-05-11",
      "2015-03-27")),
   stringsAsFactors = FALSE
)

# Extract 3rd and 5th row with 2nd and 4th column.
result <- emp.data[c(3,5),c(2,4)]
print(result)

  emp_name start_date
3 Michelle 2014-11-15
5     Gary 2015-03-27

.libPaths()

[2] "C:/Program Files/R/R-3.2.2/library"

library()

Packages in library ‘C:/Program Files/R/R-3.2.2/library’:

base                    The R Base Package
boot                    Bootstrap Functions (Originally by Angelo Canty
                        for S)
class                   Functions for Classification
cluster                 "Finding Groups in Data": Cluster Analysis
                        Extended Rousseeuw et al.
codetools               Code Analysis Tools for R
compiler                The R Compiler Package
datasets                The R Datasets Package
foreign                 Read Data Stored by 'Minitab', 'S', 'SAS',
                        'SPSS', 'Stata', 'Systat', 'Weka', 'dBase', ...
graphics                The R Graphics Package
grDevices               The R Graphics Devices and Support for Colours
                        and Fonts
grid                    The Grid Graphics Package
KernSmooth              Functions for Kernel Smoothing Supporting Wand
                        & Jones (1995)
lattice                 Trellis Graphics for R
MASS                    Support Functions and Datasets for Venables and
                        Ripley's MASS
Matrix                  Sparse and Dense Matrix Classes and Methods
methods                 Formal Methods and Classes
mgcv                    Mixed GAM Computation Vehicle with GCV/AIC/REML
                        Smoothness Estimation
nlme                    Linear and Nonlinear Mixed Effects Models
nnet                    Feed-Forward Neural Networks and Multinomial
                        Log-Linear Models
parallel                Support for Parallel computation in R
rpart                   Recursive Partitioning and Regression Trees
spatial                 Functions for Kriging and Point Pattern
                        Analysis
splines                 Regression Spline Functions and Classes
stats                   The R Stats Package
stats4                  Statistical Functions using S4 Classes
survival                Survival Analysis
tcltk                   Tcl/Tk Interface
tools                   Tools for Package Development
utils                   The R Utils Package

search()

[1] ".GlobalEnv"        "package:stats"     "package:graphics"
[4] "package:grDevices" "package:utils"     "package:datasets"
[7] "package:methods"   "Autoloads"         "package:base"

 install.packages("Package Name")

# Install the package named "XML".
 install.packages("XML")

install.packages(file_name_with_path, repos = NULL, type = "source")

# Install the package named "XML"
install.packages("E:/XML_3.98-1.3.zip", repos = NULL, type = "source")

library("package Name", lib.loc = "path to library")

# Load the package named "XML"
install.packages("E:/XML_3.98-1.3.zip", repos = NULL, type = "source")

# Create vector objects.
city <- c("Tampa","Seattle","Hartford","Denver")
state <- c("FL","WA","CT","CO")
zipcode <- c(33602,98104,06161,80294)

# Combine above three vectors into one data frame.
addresses <- cbind(city,state,zipcode)

# Print a header.
cat("# # # # The First data frame\n")

# Print the data frame.
print(addresses)

# Create another data frame with similar columns
new.address <- data.frame(
   city = c("Lowry","Charlotte"),
   state = c("CO","FL"),
   zipcode = c("80230","33949"),
   stringsAsFactors = FALSE
)

# Print a header.
cat("# # # The Second data frame\n")

# Print the data frame.
print(new.address)

# Combine rows form both the data frames.
all.addresses <- rbind(addresses,new.address)

# Print a header.
cat("# # # The combined data frame\n")

# Print the result.
print(all.addresses)

# # # # The First data frame
     city       state zipcode
[1,] "Tampa"    "FL"  "33602"
[2,] "Seattle"  "WA"  "98104"
[3,] "Hartford" "CT"   "6161"
[4,] "Denver"   "CO"  "80294"

# # # The Second data frame
       city       state   zipcode
1      Lowry      CO      80230
2      Charlotte  FL      33949

# # # The combined data frame
       city      state zipcode
1      Tampa     FL    33602
2      Seattle   WA    98104
3      Hartford  CT     6161
4      Denver    CO    80294
5      Lowry     CO    80230
6     Charlotte  FL    33949

library(MASS)
merged.Pima <- merge(x = Pima.te, y = Pima.tr,
   by.x = c("bp", "bmi"),
   by.y = c("bp", "bmi")
)
print(merged.Pima)
nrow(merged.Pima)

   bp  bmi npreg.x glu.x skin.x ped.x age.x type.x npreg.y glu.y skin.y ped.y
1  60 33.8       1   117     23 0.466    27     No       2   125     20 0.088
2  64 29.7       2    75     24 0.370    33     No       2   100     23 0.368
3  64 31.2       5   189     33 0.583    29    Yes       3   158     13 0.295
4  64 33.2       4   117     27 0.230    24     No       1    96     27 0.289
5  66 38.1       3   115     39 0.150    28     No       1   114     36 0.289
6  68 38.5       2   100     25 0.324    26     No       7   129     49 0.439
7  70 27.4       1   116     28 0.204    21     No       0   124     20 0.254
8  70 33.1       4    91     32 0.446    22     No       9   123     44 0.374
9  70 35.4       9   124     33 0.282    34     No       6   134     23 0.542
10 72 25.6       1   157     21 0.123    24     No       4    99     17 0.294
11 72 37.7       5    95     33 0.370    27     No       6   103     32 0.324
12 74 25.9       9   134     33 0.460    81     No       8   126     38 0.162
13 74 25.9       1    95     21 0.673    36     No       8   126     38 0.162
14 78 27.6       5    88     30 0.258    37     No       6   125     31 0.565
15 78 27.6      10   122     31 0.512    45     No       6   125     31 0.565
16 78 39.4       2   112     50 0.175    24     No       4   112     40 0.236
17 88 34.5       1   117     24 0.403    40    Yes       4   127     11 0.598
   age.y type.y
1     31     No
2     21     No
3     24     No
4     21     No
5     21     No
6     43    Yes
7     36    Yes
8     40     No
9     29    Yes
10    28     No
11    55     No
12    39     No
13    39     No
14    49    Yes
15    49    Yes
16    38     No
17    28     No
[1] 17

library(MASS)
print(ships)

     type year   period   service   incidents
1     A   60     60        127         0
2     A   60     75         63         0
3     A   65     60       1095         3
4     A   65     75       1095         4
5     A   70     60       1512         6
.............
.............
8     A   75     75       2244         11
9     B   60     60      44882         39
10    B   60     75      17176         29
11    B   65     60      28609         58
............
............
17    C   60     60      1179          1
18    C   60     75       552          1
19    C   65     60       781          0
............
............

molten.ships <- melt(ships, id = c("type","year"))
print(molten.ships)

      type year  variable  value
1      A   60    period      60
2      A   60    period      75
3      A   65    period      60
4      A   65    period      75
............
............
9      B   60    period      60
10     B   60    period      75
11     B   65    period      60
12     B   65    period      75
13     B   70    period      60
...........
...........
41     A   60    service    127
42     A   60    service     63
43     A   65    service   1095
...........
...........
70     D   70    service   1208
71     D   75    service      0
72     D   75    service   2051
73     E   60    service     45
74     E   60    service      0
75     E   65    service    789
...........
...........
101    C   70    incidents    6
102    C   70    incidents    2
103    C   75    incidents    0
104    C   75    incidents    1
105    D   60    incidents    0
106    D   60    incidents    0
...........
...........

recasted.ship <- cast(molten.ships, type+year~variable,sum)
print(recasted.ship)

     type year  period  service  incidents
1     A   60    135       190      0
2     A   65    135      2190      7
3     A   70    135      4865     24
4     A   75    135      2244     11
5     B   60    135     62058     68
6     B   65    135     48979    111
7     B   70    135     20163     56
8     B   75    135      7117     18
9     C   60    135      1731      2
10    C   65    135      1457      1
11    C   70    135      2731      8
12    C   75    135       274      1
13    D   60    135       356      0
14    D   65    135       480      0
15    D   70    135      1557     13
16    D   75    135      2051      4
17    E   60    135        45      0
18    E   65    135      1226     14
19    E   70    135      3318     17
20    E   75    135       542      1

# Get and print current working directory.
print(getwd())

# Set current working directory.
setwd("/web/com")

# Get and print current working directory.
print(getwd())

[1] "/web/com/1441086124_2016"
[1] "/web/com"

id,name,salary,start_date,dept
1,Rick,623.3,2012-01-01,IT
2,Dan,515.2,2013-09-23,Operations
3,Michelle,611,2014-11-15,IT
4,Ryan,729,2014-05-11,HR
5,Gary,843.25,2015-03-27,Finance
6,Nina,578,2013-05-21,IT
7,Simon,632.8,2013-07-30,Operations
8,Guru,722.5,2014-06-17,Finance

data <- read.csv("input.csv")
print(data)

      id,   name,    salary,   start_date,     dept
1      1    Rick     623.30    2012-01-01      IT
2      2    Dan      515.20    2013-09-23      Operations
3      3    Michelle 611.00    2014-11-15      IT
4      4    Ryan     729.00    2014-05-11      HR
5     NA    Gary     843.25    2015-03-27      Finance
6      6    Nina     578.00    2013-05-21      IT
7      7    Simon    632.80    2013-07-30      Operations
8      8    Guru     722.50    2014-06-17      Finance

data <- read.csv("input.csv")

print(is.data.frame(data))
print(ncol(data))
print(nrow(data))

[1] TRUE
[1] 5
[1] 8

# Create a data frame.
data <- read.csv("input.csv")
retval <- subset(data, as.Date(start_date) > as.Date("2014-01-01"))

# Write filtered data into a new file.
write.csv(retval,"output.csv")
newdata <- read.csv("output.csv")
print(newdata)

  X      id   name      salary   start_date    dept
1 3      3    Michelle  611.00   2014-11-15    IT
2 4      4    Ryan      729.00   2014-05-11    HR
3 5     NA    Gary      843.25   2015-03-27    Finance
4 8      8    Guru      722.50   2014-06-17    Finance

# Create a data frame.
data <- read.csv("input.csv")
retval <- subset(data, as.Date(start_date) > as.Date("2014-01-01"))

# Write filtered data into a new file.
write.csv(retval,"output.csv", row.names = FALSE)
newdata <- read.csv("output.csv")
print(newdata)

      id    name      salary   start_date    dept
1      3    Michelle  611.00   2014-11-15    IT
2      4    Ryan      729.00   2014-05-11    HR
3     NA    Gary      843.25   2015-03-27    Finance
4      8    Guru      722.50   2014-06-17    Finance

install.packages("xlsx")

# Verify the package is installed.
any(grepl("xlsx",installed.packages()))

# Load the library into R workspace.
library("xlsx")

[1] TRUE
Loading required package: rJava
Loading required package: methods
Loading required package: xlsxjars

id	name      salary    start_date	dept
1	Rick	    623.3	  1/1/2012	   IT
2	Dan       515.2     9/23/2013    Operations
3	Michelle  611	     11/15/2014	IT
4	Ryan	    729	     5/11/2014	   HR
5	Gary	    43.25     3/27/2015  	Finance
6	Nina	    578       5/21/2013	   IT
7	Simon	    632.8	  7/30/2013	   Operations
8	Guru	    722.5	  6/17/2014	   Finance

name	    city
Rick	    Seattle
Dan       Tampa
Michelle  Chicago
Ryan	    Seattle
Gary	    Houston
Nina	    Boston
Simon	    Mumbai
Guru	    Dallas

# Read the first worksheet in the file input.xlsx.
data <- read.xlsx("input.xlsx", sheetIndex = 1)
print(data)

      id,   name,     salary,   start_date,   dept
1      1    Rick      623.30    2012-01-01    IT
2      2    Dan       515.20    2013-09-23    Operations
3      3    Michelle  611.00    2014-11-15    IT
4      4    Ryan      729.00    2014-05-11    HR
5     NA    Gary      843.25    2015-03-27    Finance
6      6    Nina      578.00    2013-05-21    IT
7      7    Simon     632.80    2013-07-30    Operations
8      8    Guru      722.50    2014-06-17    Finance

writeBin(object, con)
readBin(con, what, n )

# Read the "mtcars" data frame as a csv file and store only the columns
   "cyl", "am" and "gear".
write.table(mtcars, file = "mtcars.csv",row.names = FALSE, na = "",
   col.names = TRUE, sep = ",")

# Store 5 records from the csv file as a new data frame.
new.mtcars <- read.table("mtcars.csv",sep = ",",header = TRUE,nrows = 5)

# Create a connection object to write the binary file using mode "wb".
write.filename = file("/web/com/binmtcars.dat", "wb")

# Write the column names of the data frame to the connection object.
writeBin(colnames(new.mtcars), write.filename)

# Write the records in each of the column to the file.
writeBin(c(new.mtcars$cyl,new.mtcars$am,new.mtcars$gear), write.filename)

# Close the file for writing so that it can be read by other program.
close(write.filename)

# Create a connection object to read the file in binary mode using "rb".
read.filename <- file("/web/com/binmtcars.dat", "rb")

# First read the column names. n = 3 as we have 3 columns.
column.names <- readBin(read.filename, character(),  n = 3)

# Next read the column values. n = 18 as we have 3 column names and 15 values.
read.filename <- file("/web/com/binmtcars.dat", "rb")
bindata <- readBin(read.filename, integer(),  n = 18)

# Print the data.
print(bindata)

# Read the values from 4th byte to 8th byte which represents "cyl".
cyldata = bindata[4:8]
print(cyldata)

# Read the values form 9th byte to 13th byte which represents "am".
amdata = bindata[9:13]
print(amdata)

# Read the values form 9th byte to 13th byte which represents "gear".
geardata = bindata[14:18]
print(geardata)

# Combine all the read values to a dat frame.
finaldata = cbind(cyldata, amdata, geardata)
colnames(finaldata) = column.names
print(finaldata)

 [1]    7108963 1728081249    7496037          6          6          4
 [7]          6          8          1          1          1          0
[13]          0          4          4          4          3          3

[1] 6 6 4 6 8

[1] 1 1 1 0 0

[1] 4 4 4 3 3

     cyl am gear
[1,]   6  1    4
[2,]   6  1    4
[3,]   4  1    4
[4,]   6  0    3
[5,]   8  0    3

<RECORDS>
   <EMPLOYEE>
      <ID>1</ID>
      <NAME>Rick</NAME>
      <SALARY>623.3</SALARY>
      <STARTDATE>1/1/2012</STARTDATE>
      <DEPT>IT</DEPT>
   </EMPLOYEE>

   <EMPLOYEE>
      <ID>2</ID>
      <NAME>Dan</NAME>
      <SALARY>515.2</SALARY>
      <STARTDATE>9/23/2013</STARTDATE>
      <DEPT>Operations</DEPT>
   </EMPLOYEE>

   <EMPLOYEE>
      <ID>3</ID>
      <NAME>Michelle</NAME>
      <SALARY>611</SALARY>
      <STARTDATE>11/15/2014</STARTDATE>
      <DEPT>IT</DEPT>
   </EMPLOYEE>

   <EMPLOYEE>
      <ID>4</ID>
      <NAME>Ryan</NAME>
      <SALARY>729</SALARY>
      <STARTDATE>5/11/2014</STARTDATE>
      <DEPT>HR</DEPT>
   </EMPLOYEE>

   <EMPLOYEE>
      <ID>5</ID>
      <NAME>Gary</NAME>
      <SALARY>843.25</SALARY>
      <STARTDATE>3/27/2015</STARTDATE>
      <DEPT>Finance</DEPT>
   </EMPLOYEE>

   <EMPLOYEE>
      <ID>6</ID>
      <NAME>Nina</NAME>
      <SALARY>578</SALARY>
      <STARTDATE>5/21/2013</STARTDATE>
      <DEPT>IT</DEPT>
   </EMPLOYEE>

   <EMPLOYEE>
      <ID>7</ID>
      <NAME>Simon</NAME>
      <SALARY>632.8</SALARY>
      <STARTDATE>7/30/2013</STARTDATE>
      <DEPT>Operations</DEPT>
   </EMPLOYEE>

   <EMPLOYEE>
      <ID>8</ID>
      <NAME>Guru</NAME>
      <SALARY>722.5</SALARY>
      <STARTDATE>6/17/2014</STARTDATE>
      <DEPT>Finance</DEPT>
   </EMPLOYEE>

</RECORDS>

# Load the package required to read XML files.
library("XML")

# Also load the other required package.
library("methods")

# Give the input file name to the function.
result <- xmlParse(file = "input.xml")

# Print the result.
print(result)

1
Rick
623.3
1/1/2012
IT

2
Dan
515.2
9/23/2013
Operations

3
Michelle
611
11/15/2014
IT

4
Ryan
729
5/11/2014
HR

5
Gary
843.25
3/27/2015
Finance

6
Nina
578
5/21/2013
IT

7
Simon
632.8
7/30/2013
Operations

8
Guru
722.5
6/17/2014
Finance

# Load the packages required to read XML files.
library("XML")
library("methods")

# Give the input file name to the function.
result <- xmlParse(file = "input.xml")

# Exract the root node form the xml file.
rootnode <- xmlRoot(result)

# Print the result.
print(rootnode[1])

$EMPLOYEE
   1
   Rick
   623.3
   1/1/2012
   IT


attr(,"class")
[1] "XMLInternalNodeList" "XMLNodeList"

# Load the packages required to read XML files.
library("XML")
library("methods")

# Convert the input xml file to a data frame.
xmldataframe <- xmlToDataFrame("input.xml")
print(xmldataframe)

      ID    NAME     SALARY    STARTDATE       DEPT
1      1    Rick     623.30    2012-01-01      IT
2      2    Dan      515.20    2013-09-23      Operations
3      3    Michelle 611.00    2014-11-15      IT
4      4    Ryan     729.00    2014-05-11      HR
5     NA    Gary     843.25    2015-03-27      Finance
6      6    Nina     578.00    2013-05-21      IT
7      7    Simon    632.80    2013-07-30      Operations
8      8    Guru     722.50    2014-06-17      Finance

install.packages("rjson")

{
   "ID":["1","2","3","4","5","6","7","8" ],
   "Name":["Rick","Dan","Michelle","Ryan","Gary","Nina","Simon","Guru" ],
   "Salary":["623.3","515.2","611","729","843.25","578","632.8","722.5" ],

   "StartDate":[ "1/1/2012","9/23/2013","11/15/2014","5/11/2014","3/27/2015","5/21/2013",
      "7/30/2013","6/17/2014"],
   "Dept":[ "IT","Operations","IT","HR","Finance","IT","Operations","Finance"]
}

# Load the package required to read JSON files.
library("rjson")

# Give the input file name to the function.
result <- fromJSON(file = "input.json")

# Print the result.
print(result)

$ID
[1] "1"   "2"   "3"   "4"   "5"   "6"   "7"   "8"

$Name
[1] "Rick"     "Dan"      "Michelle" "Ryan"     "Gary"     "Nina"     "Simon"    "Guru"

$Salary
[1] "623.3"  "515.2"  "611"    "729"    "843.25" "578"    "632.8"  "722.5"

$StartDate
[1] "1/1/2012"   "9/23/2013"  "11/15/2014" "5/11/2014"  "3/27/2015"  "5/21/2013"
   "7/30/2013"  "6/17/2014"

$Dept
[1] "IT"         "Operations" "IT"         "HR"         "Finance"    "IT"
   "Operations" "Finance"

# Load the package required to read JSON files.
library("rjson")

# Give the input file name to the function.
result <- fromJSON(file = "input.json")

# Convert JSON file to a data frame.
json_data_frame <- as.data.frame(result)

print(json_data_frame)

      id,   name,    salary,   start_date,     dept
1      1    Rick     623.30    2012-01-01      IT
2      2    Dan      515.20    2013-09-23      Operations
3      3    Michelle 611.00    2014-11-15      IT
4      4    Ryan     729.00    2014-05-11      HR
5     NA    Gary     843.25    2015-03-27      Finance
6      6    Nina     578.00    2013-05-21      IT
7      7    Simon    632.80    2013-07-30      Operations
8      8    Guru     722.50    2014-06-17      Finance

install.packages("RCurl")
install.packages("XML")
install.packages("stringr")
install.packages("plyr")

# Read the URL.
url <- "http://www.geos.ed.ac.uk/~weather/jcmb_ws/"

# Gather the html links present in the webpage.
links <- getHTMLLinks(url)

# Identify only the links which point to the JCMB 2015 files.
filenames <- links[str_detect(links, "JCMB_2015")]

# Store the file names as a list.
filenames_list <- as.list(filenames)

# Create a function to download the files by passing the URL and filename list.
downloadcsv <- function (mainurl,filename) {
   filedetails <- str_c(mainurl,filename)
   download.file(filedetails,filename)
}

# Now apply the l_ply function and save the files into the current R working directory.
l_ply(filenames,downloadcsv,mainurl = "http://www.geos.ed.ac.uk/~weather/jcmb_ws/")

"JCMB_2015.csv" "JCMB_2015_Apr.csv" "JCMB_2015_Feb.csv" "JCMB_2015_Jan.csv"
   "JCMB_2015_Mar.csv"

install.packages("RMySQL")

# Create a connection Object to MySQL database.
# We will connect to the sampel database named "sakila" that comes with MySql installation.
mysqlconnection = dbConnect(MySQL(), user = 'root', password = '', dbname = 'sakila',
   host = 'localhost')

# List the tables available in this database.
 dbListTables(mysqlconnection)

 [1] "actor"                      "actor_info"
 [3] "address"                    "category"
 [5] "city"                       "country"
 [7] "customer"                   "customer_list"
 [9] "film"                       "film_actor"
[11] "film_category"              "film_list"
[13] "film_text"                  "inventory"
[15] "language"                   "nicer_but_slower_film_list"
[17] "payment"                    "rental"
[19] "sales_by_film_category"     "sales_by_store"
[21] "staff"                      "staff_list"
[23] "store"

# Query the "actor" tables to get all the rows.
result = dbSendQuery(mysqlconnection, "select * from actor")

# Store the result in a R data frame object. n = 5 is used to fetch first 5 rows.
data.frame = fetch(result, n = 5)
print(data.fame)

        actor_id   first_name    last_name         last_update
1        1         PENELOPE      GUINESS           2006-02-15 04:34:33
2        2         NICK          WAHLBERG          2006-02-15 04:34:33
3        3         ED            CHASE             2006-02-15 04:34:33
4        4         JENNIFER      DAVIS             2006-02-15 04:34:33
5        5         JOHNNY        LOLLOBRIGIDA      2006-02-15 04:34:33

result = dbSendQuery(mysqlconnection, "select * from actor where last_name = 'TORN'")

# Fetch all the records(with n = -1) and store it as a data frame.
data.frame = fetch(result, n = -1)
print(data)

        actor_id    first_name     last_name         last_update
1        18         DAN            TORN              2006-02-15 04:34:33
2        94         KENNETH        TORN              2006-02-15 04:34:33
3       102         WALTER         TORN              2006-02-15 04:34:33

dbSendQuery(mysqlconnection, "update mtcars set disp = 168.5 where hp = 110")

dbSendQuery(mysqlconnection,
   "insert into mtcars(row_names, mpg, cyl, disp, hp, drat, wt, qsec, vs, am, gear, carb)
   values('New Mazda RX4 Wag', 21, 6, 168.5, 110, 3.9, 2.875, 17.02, 0, 1, 4, 4)"
)

# Create the connection object to the database where we want to create the table.
mysqlconnection = dbConnect(MySQL(), user = 'root', password = '', dbname = 'sakila',
   host = 'localhost')

# Use the R data frame "mtcars" to create the table in MySql.
# All the rows of mtcars are taken inot MySql.
dbWriteTable(mysqlconnection, "mtcars", mtcars[, ], overwrite = TRUE)

dbSendQuery(mysqlconnection, 'drop table if exists mtcars')

pie(x, labels, radius, main, col, clockwise)

# Create data for the graph.
x <- c(21, 62, 10, 53)
labels <- c("London", "New York", "Singapore", "Mumbai")

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

# Plot the chart.
pie(x,labels)

# Save the file.
dev.off()

# Create data for the graph.
x <-  c(21, 62, 10,53)
labels <-  c("London","New York","Singapore","Mumbai")

piepercent<- round(100*x/sum(x), 1)

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

# Plot the chart.
pie(x, labels = piepercent, main = "City pie chart",col = rainbow(length(x)))
legend("topright", c("London","New York","Singapore","Mumbai"), cex = 0.8,
   fill = rainbow(length(x)))

# Save the file.
dev.off()

# Get the library.
library(plotrix)

# Create data for the graph.
x <-  c(21, 62, 10,53)
lbl <-  c("London","New York","Singapore","Mumbai")

# Give the chart file a name.
png(file = "3d_pie_chart.jpg")

# Plot the chart.
pie3D(x,labels = lbl,explode = 0.1, main = "Pie Chart of Countries ")

# Save the file.
dev.off()

barplot(H,xlab,ylab,main, names.arg,col)

# Create the data for the chart
H <- c(7,12,28,3,41)

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

# Plot the bar chart
barplot(H)

# Save the file
dev.off()

# Create the input vectors.
colors = c("green","orange","brown")
months <- c("Mar","Apr","May","Jun","Jul")
regions <- c("East","West","North")

# 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 = "total revenue", names.arg = months, xlab = "month", ylab = "revenue", col = colors)

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

# Save the file
dev.off()

boxplot(x, data, notch, varwidth, names, main)

input <- mtcars[,c('mpg','cyl')]
print(head(input))

                   mpg  cyl
Mazda RX4         21.0   6
Mazda RX4 Wag     21.0   6
Datsun 710        22.8   4
Hornet 4 Drive    21.4   6
Hornet Sportabout 18.7   8
Valiant           18.1   6

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

# Plot the chart.
boxplot(mpg ~ cyl, data = mtcars, xlab = "Number of Cylinders",
   ylab = "Miles Per Gallon", main = "Mileage Data")

# Save the file.
dev.off()

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

# Plot the chart.
boxplot(mpg ~ cyl, data = mtcars,
   xlab = "Number of Cylinders",
   ylab = "Miles Per Gallon",
   main = "Mileage Data",
   notch = TRUE,
   varwidth = TRUE,
   col = c("green","yellow","purple"),
   names = c("High","Medium","Low")
)
# Save the file.
dev.off()

hist(v,main,xlab,xlim,ylim,breaks,col,border)

# Create data for the graph.
v <-  c(9,13,21,8,36,22,12,41,31,33,19)

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

# Create the histogram.
hist(v,xlab = "Weight",col = "yellow",border = "blue")

# Save the file.
dev.off()

# Create data for the graph.
v <- c(9,13,21,8,36,22,12,41,31,33,19)

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

# Create the histogram.
hist(v,xlab = "Weight",col = "green",border = "red", xlim = c(0,40), ylim = c(0,5),
   breaks = 5)

# Save the file.
dev.off()

plot(v,type,col,xlab,ylab)

# Create the data for the chart.
v <- c(7,12,28,3,41)

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

# Plot the bar chart.
plot(v,type = "o")

# Save the file.
dev.off()

# Create the data for the chart.
v <- c(7,12,28,3,41)
t <- c(14,7,6,19,3)

# Give the chart file a name.
png(file = "line_chart_2_lines.jpg")

# Plot the bar chart.
plot(v,type = "o",col = "red", xlab = "Month", ylab = "Rain fall",
   main = "Rain fall chart")

lines(t, type = "o", col = "blue")

# Save the file.
dev.off()

plot(x, y, main, xlab, ylab, xlim, ylim, axes)

input <- mtcars[,c('wt','mpg')]
print(head(input))

                    wt      mpg
Mazda RX4           2.620   21.0
Mazda RX4 Wag       2.875   21.0
Datsun 710          2.320   22.8
Hornet 4 Drive      3.215   21.4
Hornet Sportabout   3.440   18.7
Valiant             3.460   18.1

# Get the input values.
input <- mtcars[,c('wt','mpg')]

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

# Plot the chart for cars with weight between 2.5 to 5 and mileage between 15 and 30.
plot(x = input$wt,y = input$mpg,
   xlab = "Weight",
   ylab = "Milage",
   xlim = c(2.5,5),
   ylim = c(15,30),
   main = "Weight vs Milage"
)

# Save the file.
dev.off()

# Create a vector.
x <- c(12,7,3,4.2,18,2,54,-21,8,-5)

# Find Mean.
result.mean <-  mean(x,trim = 0.3)
print(result.mean)

[1] 5.55

# Create a vector.
x <- c(12,7,3,4.2,18,2,54,-21,8,-5,NA)

# Find mean.
result.mean <-  mean(x)
print(result.mean)

# Find mean dropping NA values.
result.mean <-  mean(x,na.rm = TRUE)
print(result.mean)

[1] NA
[1] 8.22

glm(formula,data,family)

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

print(head(input))

                  am   cyl  hp    wt
Mazda RX4          1   6    110   2.620
Mazda RX4 Wag      1   6    110   2.875
Datsun 710         1   4     93   2.320
Hornet 4 Drive     0   6    110   3.215
Hornet Sportabout  0   8    175   3.440
Valiant            0   6    105   3.460

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

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

print(summary(am.data))

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

Deviance Residuals:
     Min        1Q      Median        3Q       Max
-2.17272     -0.14907  -0.01464     0.14116   1.27641

Coefficients:
            Estimate Std. Error z value Pr(>|z|)
(Intercept) 19.70288    8.11637   2.428   0.0152 *
cyl          0.48760    1.07162   0.455   0.6491
hp           0.03259    0.01886   1.728   0.0840 .
wt          -9.14947    4.15332  -2.203   0.0276 *
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 43.2297  on 31  degrees of freedom
Residual deviance:  9.8415  on 28  degrees of freedom
AIC: 17.841

Number of Fisher Scoring iterations: 8

# 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()

# Create a sequence of numbers between -10 and 10 incrementing by 0.2.
x <- seq(-10,10,by = .2)

# Choose the mean as 2.5 and standard deviation as 2.
y <- pnorm(x, mean = 2.5, sd = 2)

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

# Plot the graph.
plot(x,y)

# Save the file.
dev.off()

# Create a sequence of probability values incrementing by 0.02.
x <- seq(0, 1, by = 0.02)

# Choose the mean as 2 and standard deviation as 3.
y <- qnorm(x, mean = 2, sd = 1)

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

# Plot the graph.
plot(x,y)

# Save the file.
dev.off()

# Create a sample of 50 numbers which are normally distributed.
y <- rnorm(50)

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

# Plot the histogram for this sample.
hist(y, main = "Normal DIstribution")

# Save the file.
dev.off()

# Create a sample of 50 numbers which are incremented by 1.
x <- seq(0,50,by = 1)

# Create the binomial distribution.
y <- dbinom(x,50,0.5)

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

# Plot the graph for this sample.
plot(x,y)

# Save the file.
dev.off()

# Probability of getting 26 or less heads from a 51 tosses of a coin.
x <- pbinom(26,51,0.5)

print(x)

[1] 0.610116

# How many heads will have a probability of 0.25 will come out when a coin
# is tossed 51 times.
x <- qbinom(0.25,51,1/2)

print(x)

[1] 23

# Find 8 random values from a sample of 150 with probability of 0.4.
x <- rbinom(8,150,.4)

print(x)

[1] 58 61 59 66 55 60 61 67

glm(formula,data,family)

input <- warpbreaks
print(head(input))

      breaks   wool  tension
1     26       A     L
2     30       A     L
3     54       A     L
4     25       A     L
5     70       A     L
6     52       A     L

output <-glm(formula = breaks ~ wool+tension, data = warpbreaks,
   family = poisson)
print(summary(output))

Call:
glm(formula = breaks ~ wool + tension, family = poisson, data = warpbreaks)

Deviance Residuals:
    Min       1Q     Median       3Q      Max
  -3.6871  -1.6503  -0.4269     1.1902   4.2616

Coefficients:
            Estimate Std. Error z value Pr(>|z|)
(Intercept)  3.69196    0.04541  81.302  < 2e-16 ***
woolB       -0.20599    0.05157  -3.994 6.49e-05 ***
tensionM    -0.32132    0.06027  -5.332 9.73e-08 ***
tensionH    -0.51849    0.06396  -8.107 5.21e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 297.37  on 53  degrees of freedom
Residual deviance: 210.39  on 50  degrees of freedom
AIC: 493.06

Number of Fisher Scoring iterations: 4

input <- mtcars[,c("am","mpg","hp")]
print(head(input))

                   am   mpg   hp
Mazda RX4          1    21.0  110
Mazda RX4 Wag      1    21.0  110
Datsun 710         1    22.8   93
Hornet 4 Drive     0    21.4  110
Hornet Sportabout  0    18.7  175
Valiant            0    18.1  105

# Get the dataset.
input <- mtcars

# Create the regression models.
result1 <- aov(mpg~hp*am,data = input)
result2 <- aov(mpg~hp+am,data = input)

# Compare the two models.
print(anova(result1,result2))

Model 1: mpg ~ hp * am
Model 2: mpg ~ hp + am
  Res.Df    RSS Df  Sum of Sq     F Pr(>F)
1     28 245.43
2     29 245.44 -1 -0.0052515 6e-04 0.9806

timeseries.object.name <-  ts(data, start, end, frequency)

# Get the data points in form of a R vector.
rainfall <- c(799,1174.8,865.1,1334.6,635.4,918.5,685.5,998.6,784.2,985,882.8,1071)

# Convert it to a time series object.
rainfall.timeseries <- ts(rainfall,start = c(2012,1),frequency = 12)

# Print the timeseries data.
print(rainfall.timeseries)

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

# Plot a graph of the time series.
plot(rainfall.timeseries)

# Save the file.
dev.off()

Jan    Feb    Mar    Apr    May     Jun    Jul    Aug    Sep
2012  799.0  1174.8  865.1  1334.6  635.4  918.5  685.5  998.6  784.2
        Oct    Nov    Dec
2012  985.0  882.8 1071.0

# Get the data points in form of a R vector.
rainfall1 <- c(799,1174.8,865.1,1334.6,635.4,918.5,685.5,998.6,784.2,985,882.8,1071)
rainfall2 <-
           c(655,1306.9,1323.4,1172.2,562.2,824,822.4,1265.5,799.6,1105.6,1106.7,1337.8)

# Convert them to a matrix.
combined.rainfall <-  matrix(c(rainfall1,rainfall2),nrow = 12)

# Convert it to a time series object.
rainfall.timeseries <- ts(combined.rainfall,start = c(2012,1),frequency = 12)

# Print the timeseries data.
print(rainfall.timeseries)

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

# Plot a graph of the time series.
plot(rainfall.timeseries, main = "Multiple Time Series")

# Save the file.
dev.off()

           Series 1  Series 2
Jan 2012    799.0    655.0
Feb 2012   1174.8   1306.9
Mar 2012    865.1   1323.4
Apr 2012   1334.6   1172.2
May 2012    635.4    562.2
Jun 2012    918.5    824.0
Jul 2012    685.5    822.4
Aug 2012    998.6   1265.5
Sep 2012    784.2    799.6
Oct 2012    985.0   1105.6
Nov 2012    882.8   1106.7
Dec 2012   1071.0   1337.8

nls(formula, data, start)

a = b1*x^2+b2

xvalues <- c(1.6,2.1,2,2.23,3.71,3.25,3.4,3.86,1.19,2.21)
yvalues <- c(5.19,7.43,6.94,8.11,18.75,14.88,16.06,19.12,3.21,7.58)

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


# Plot these values.
plot(xvalues,yvalues)


# Take the assumed values and fit into the model.
model <- nls(yvalues ~ b1*xvalues^2+b2,start = list(b1 = 1,b2 = 3))

# Plot the chart with new data by fitting it to a prediction from 100 data points.
new.data <- data.frame(xvalues = seq(min(xvalues),max(xvalues),len = 100))
lines(new.data$xvalues,predict(model,newdata = new.data))

# Save the file.
dev.off()

# Get the sum of the squared residuals.
print(sum(resid(model)^2))

# Get the confidence intervals on the chosen values of the coefficients.
print(confint(model))

[1] 1.081935
Waiting for profiling to be done...
       2.5%    97.5%
b1 1.137708 1.253135
b2 1.497364 2.496484

install.packages("party")

install.packages("randomForest)

install.packages("survival")

chisq.test(data)

library("MASS")
print(str(Cars93))

'data.frame':   93 obs. of  27 variables:
 $ Manufacturer      : Factor w/ 32 levels "Acura","Audi",..: 1 1 2 2 3 4 4 4 4 5 ...
 $ Model             : Factor w/ 93 levels "100","190E","240",..: 49 56 9 1 6 24 54 74 73 35 ...
 $ Type              : Factor w/ 6 levels "Compact","Large",..: 4 3 1 3 3 3 2 2 3 2 ...
 $ Min.Price         : num  12.9 29.2 25.9 30.8 23.7 14.2 19.9 22.6 26.3 33 ...
 $ Price             : num  15.9 33.9 29.1 37.7 30 15.7 20.8 23.7 26.3 34.7 ...
 $ Max.Price         : num  18.8 38.7 32.3 44.6 36.2 17.3 21.7 24.9 26.3 36.3 ...
 $ MPG.city          : int  25 18 20 19 22 22 19 16 19 16 ...
 $ MPG.highway       : int  31 25 26 26 30 31 28 25 27 25 ...
 $ AirBags           : Factor w/ 3 levels "Driver & Passenger",..: 3 1 2 1 2 2 2 2 2 2 ...
 $ DriveTrain        : Factor w/ 3 levels "4WD","Front",..: 2 2 2 2 3 2 2 3 2 2 ...
 $ Cylinders         : Factor w/ 6 levels "3","4","5","6",..: 2 4 4 4 2 2 4 4 4 5 ...
 $ EngineSize        : num  1.8 3.2 2.8 2.8 3.5 2.2 3.8 5.7 3.8 4.9 ...
 $ Horsepower        : int  140 200 172 172 208 110 170 180 170 200 ...
 $ RPM               : int  6300 5500 5500 5500 5700 5200 4800 4000 4800 4100 ...
 $ Rev.per.mile      : int  2890 2335 2280 2535 2545 2565 1570 1320 1690 1510 ...
 $ Man.trans.avail   : Factor w/ 2 levels "No","Yes": 2 2 2 2 2 1 1 1 1 1 ...
 $ Fuel.tank.capacity: num  13.2 18 16.9 21.1 21.1 16.4 18 23 18.8 18 ...
 $ Passengers        : int  5 5 5 6 4 6 6 6 5 6 ...
 $ Length            : int  177 195 180 193 186 189 200 216 198 206 ...
 $ Wheelbase         : int  102 115 102 106 109 105 111 116 108 114 ...
 $ Width             : int  68 71 67 70 69 69 74 78 73 73 ...
 $ Turn.circle       : int  37 38 37 37 39 41 42 45 41 43 ...
 $ Rear.seat.room    : num  26.5 30 28 31 27 28 30.5 30.5 26.5 35 ...
 $ Luggage.room      : int  11 15 14 17 13 16 17 21 14 18 ...
 $ Weight            : int  2705 3560 3375 3405 3640 2880 3470 4105 3495 3620 ...
 $ Origin            : Factor w/ 2 levels "USA","non-USA": 2 2 2 2 2 1 1 1 1 1 ...
 $ Make              : Factor w/ 93 levels "Acura Integra",..: 1 2 4 3 5 6 7 9 8 10 ...

# 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))

                     Compact Large Midsize Small Sporty Van
  Driver & Passenger       2     4       7     0      3   0
  Driver only              9     7      11     5      8   3
  None                     5     0       4    16      3   6

         Pearson's Chi-squared test

data:  car.data
X-squared = 33.001, df = 10, p-value = 0.0002723

Warning message:
In chisq.test(car.data) : Chi-squared approximation may be incorrect