Chapter 2 and 3 Computing with R and R Command Patters

Loading Data Sets

1. install package

install.packages("nycflights13")
#or go to packages in rstudio

2. load package

library(nycflights13)
#or go to packages and check box next to nycflights13

3. read data table into R

data("flights",package="nycflights13")

Chap 3 Chaining Syntax

suppressMessages(library(dplyr))
data("BabyNames",package="DataComputing")

The general chaining syntax:

#Object_Name <- 
#Data_Table %>%
#function_name(arguments) %>%
#function_name(arguments)

example 1:

MyBabies<-
  BabyNames %>% 
  head(3)
MyBabies

##   name sex count year
## 1 Mary   F  7065 1880
## 2 Anna   F  2604 1880
## 3 Emma   F  2003 1880

this is equivalent to:

MyBabies <-
  head(BabyNames,3)  
MyBabies

##   name sex count year
## 1 Mary   F  7065 1880
## 2 Anna   F  2604 1880
## 3 Emma   F  2003 1880

example 2:

Princes <- 
  BabyNames %>%
  filter(name=="Prince") %>%
  group_by(year,sex) %>%
  summarise(sum(count))
Princes

## Source: local data frame [194 x 3]
## Groups: year [?]
## 
##     year   sex sum(count)
##    (int) (chr)      (int)
## 1   1880     M         16
## 2   1881     M         17
## 3   1882     M         18
## 4   1883     M         18
## 5   1884     M         17
## 6   1885     M         21
## 7   1886     M         22
## 8   1887     M         18
## 9   1888     M         19
## 10  1889     M         14
## ..   ...   ...        ...

equivalent to:

Princes <- summarise(group_by(filter(BabyNames,name=="Prince"),year,sex),sum(count))
Princes

## Source: local data frame [194 x 3]
## Groups: year [?]
## 
##     year   sex sum(count)
##    (int) (chr)      (int)
## 1   1880     M         16
## 2   1881     M         17
## 3   1882     M         18
## 4   1883     M         18
## 5   1884     M         17
## 6   1885     M         21
## 7   1886     M         22
## 8   1887     M         18
## 9   1888     M         19
## 10  1889     M         14
## ..   ...   ...        ...

Data Frames

You can make data frames as follows:

a <- c(10,30,15)
b <- c("Bob","John","Ben")
df <- data.frame(a,b, stringsAsFactors = FALSE)  #want strings to be characters not factors
df

##    a    b
## 1 10  Bob
## 2 30 John
## 3 15  Ben

You can name your data frame as follows:

names(df) <- c("age","friend")
 df

##   age friend
## 1  10    Bob
## 2  30   John
## 3  15    Ben

You can look at elements of your data frame as follows:

df[1,2] #first case, second variable

## [1] "Bob"

 df[,2] #second variable

## [1] "Bob"  "John" "Ben"

 df[,1] #first variable

## [1] 10 30 15

How do you select last two cases of the friend variable?

df[2:3,2]

## [1] "John" "Ben"

df[2:3,"friend"]

## [1] "John" "Ben"

df[-1,"friend"]

## [1] "John" "Ben"

How do you select case with “Bob” as friend?

bob_friend <- c(TRUE,FALSE,FALSE)
df[bob_friend,]

##   age friend
## 1  10    Bob

#subset(my_data_frame, subset = some_condition)
subset(df, subset= friend=="Bob")

##   age friend
## 1  10    Bob

Lists

You can make a list as follows:

x <- df
y <- 7
z <- c(1,2)
my_list <- list(x,y,z)
my_list

## [[1]]
##   age friend
## 1  10    Bob
## 2  30   John
## 3  15    Ben
## 
## [[2]]
## [1] 7
## 
## [[3]]
## [1] 1 2

you can create a named list as follows

names(my_list) <- c("data_frame", "num", "vec")
my_list

## $data_frame
##   age friend
## 1  10    Bob
## 2  30   John
## 3  15    Ben
## 
## $num
## [1] 7
## 
## $vec
## [1] 1 2

You can select the “data frame” element of your list as follows:

my_list[[1]]

##   age friend
## 1  10    Bob
## 2  30   John
## 3  15    Ben

my_list[["data_frame"]]

##   age friend
## 1  10    Bob
## 2  30   John
## 3  15    Ben

You can select the second element of “vec” as follows:

my_list[["vec"]][2]

## [1] 2