# Data entry/ Import to R directly

infant_data<-data.frame(Age=numeric(0),gender=character(0),weight=numeric(0))

mydata<-edit(infant_data)

mydata

# Age gender weight

# 2 m 3.4

# 3 f 2.8

# 2 m 4.0

# 5 m 3.8

# 4 f 3.0

# 6 f 2.5

# to edit or enter additional data

mydata<-edit(mydata)

## embeding data

#(1)

mydatatxt <-"age gender weight

2 m 3.4

3 f 2.8

2 m 4.0"

mydata1<-read.table(header = TRUE, text = mydatatxt )

# read.table: reads data from a file or a character vector

#(2)

studentgrades<- "StudentID, First, Last, Math, Science, Social

011, Bob, Smith, 90, 80, 67

012, Jane, Weary, 75, , 80 "

grade <-read.table(header = TRUE, text = studentgrades )

# DETECTION OF MISSING VALUES

airquality[!complete.cases(airquality),] # show each row with NA

any(is.na(airquality$Ozone)) # whether there is a missing under the column or not

colSums(is.na(airquality)) # sum of missing observation under each column

# importing Data from excel, spss and stata

install.packages("xlsx")

install.packages("haven")

install.packages("foriegn")

library(xlsx)

library(haven)

library(foreign)

# stata

practice <- read_dta("practice.dta")

View(practice)

#SPSS

Rain <- read_sav("Rain.sav")

View(Rain)

install.packages("Hmisc")

library(Hmisc)

Rain1 <- spss.get("Rain.sav",use.value.labels=TRUE)

Rain1

#EXCEL

EastHar <- read_excel("EastHar.xlsx")

View(EastHar)
# CSV file

exceldata <- read_csv("exceldata.csv")

View(exceldata)

# Import excel data from the nth sheet

install.packages("readxl")

library(readxl)

data <- read_excel("EastHar.xlsx", sheet = 2)

## Exporting data

df

write.table(df, file = "exported1.txt", col.names=TRUE, row.names=FALSE, sep = "")

write.table(df, file = "exported2.csv", col.names=TRUE, row.names=FALSE, sep = ",")

write.table(Rain, file = "exported3.csv", col.names=TRUE, row.names=FALSE, sep = ",")

##DATA WRAGLING

# create a new variable

quiz<- data.frame(x1 = c(2, 2, 6, 4), x2 = c(3, 4, 2, 8))

quiz

quiz$SUM <- quiz$x1 + quiz$x2 # assigned to a new column named "SUM" within the quiz data frame

quiz

#EXTRACTING

str(USArrests)

USArrests[3,2]

USArrests$Assault[3]

Assault[3]
str(USArrests)

USArrests[USArrests$Assault >= 200, ]

USArrests[USArrests$UrbanPop == 80, ]

attach(USArrests)

USArrests[Assault >= 200, ]

USArrests[UrbanPop == 80, ]

detach(USArrests)

#BOOLEAN AND& , OR/

USArrests[USArrests$Assault > 50 & USArrests$UrbanPop < 70, ]

USArrests[USArrests$UrbanPop > 50 | USArrests$UrbanPop < 60, ]

attach(USArrests)

USArrests[Assault > 50 & UrbanPop < 70, ]

USArrests[UrbanPop > 50 | UrbanPop < 60, ]

detach(USArrests)

# order() function to sort a data frame

USArrests[order(USArrests$Murder), ] #Ascending

USArrests[order(-USArrests$Murder), ] #Descending OR

USArrests[order(USArrests$Murder, decreasing = TRUE), ]

attach(USArrests)

USArrests[order(Murder), ] #Ascending

USArrests[order(-Murder), ] #Descending OR

USArrests[order(Murder, decreasing = TRUE), ]

detach(USArrests)

# subset() function to to select parts of a data frame.

subset(USArrests, UrbanPop > 50& UrbanPop < 60)

DF1<- data.frame(ID=1:3, course1=c("A","B", "C"), course2=c("B", "C", "A"))

DF2<- data.frame(ID=1:4, course3=c("A","A", "B", "C"), course4=c("A", "A", "A", "B"))

total <- merge(DF1, DF2, by="ID") #by ID

## total <- merge(DF1, DF2, by=c("ID", "Region") # by Region

total <- merge(DF1, DF2, all = TRUE) # include all data from both data frames.

##

str(cars)

colSums(is.na(cars)) # sum of missing values under each column

force(cars)# to disply the data in the console

## RECODING VARIABLES

cars$dist[cars$dist == 999] <- NA

cars$distcat[cars$dist < 50] <- "Small"

cars$distcat[cars$dist >= 50 & cars$dist < 80] <- "Medium"

cars$distcat[cars$dist >= 80] <- "Long"

str(cars)

attach(cars)

cars$dist[dist == 999] <- NA

cars$distcat[dist < 50] <- "Small"

cars$distcat[dist >= 50 & cars$dist < 80] <- "Medium"

cars$distcat[dist >= 80] <- "Long"

str(cars)

detach(cars)