R program(8) Data

rm(list=Is())

 

setwd("c:/data")

write.csv(iris,"a.csv")

df <- read.csv("a.csv")

str(df)

df <- read.csv("a.csv", header=F)

str(df)

df <- read.csv("a.csv", header=F, stringsAsFactors=T)

str(df)

 

# subset: 데이터 추출

sub_df <- subset(df,subset=(Sepal.Length<5.5))

sub2_df <- subset(df,subset=(Sepal.Length<5.5 & Species=="setosa"))

 

sub3_df <- subset(df,select=-Sepal.Length)

 

# 데이터 병합

# 행 병합

r_df <- rbind(sub_df,sub2_df)

r_df

 

# 열로 병합

sub_df <- df[,1:3]

sub2_df <- df[,4:6]

 

c_df <- cbind(sub_df,sub2_df)

 

# 변수명 변경

colnames(c_df)

colnames(c_df) <- c("a","b",3,4,5,6)

str(c_df)

 

# merge: 데이터 병합

x <- data.frame(name=c("a","b","c"),a=c(1,2,3))

x

y <- data.frame(name=c("a","b","c"),b=c(4,5,6))

y

 

z <- merge(x,y, by="name")

z

 

·install.packages("dplyr")

library(dplyr)

df <- iris

str(df)

head(df)

 

# filter: 행 선택

sub_df <- df %>% filter(Species=="setosa")

head(sub_df)

sub2_df <- df %>% filter(Species=="setosa" & Sepal.Length > 5)

head(sub2_df)

 

# select: 열(변수) 선택

sub3_df <- df %>% select(c(Sepal.Length,Sepal.width))

str(sub3_df)

str(df)

 

# f, s 조합

sub3_df <- df %>% filter(Species=="setosa") %>% select(c(Sepal.Length,Sepal.Width))

str(sub5_df)

 

# arrange: 정렬

sort_df <- df %>% arrange(Sepal.Length)

head(sort_df)

sort_df <- df %>% arrange(desc(Sepal.Length))

head(sort_df)

 

# summarise, group_by

 

df %>% summarise(Sep_leh_mean=mean(Sepal.Length))

df %>% group_by(Species) %>%

summarise(Sep_leh_mean=mean(Sepal.Length),

Sep_wid_mean=mean(Sepal.Width),

Pet_len_mean=mean(petal.Length),

Pet_wid_mean=mean(Petal.Width))

 

# reshape 패키지

# install.packages("reshape2")

library(reshape2)

 

airquality

head(airquality)

str(airquality)

df <- airquality

 

# melt: 기준으로 재정렬

melt_df <- melt(df,id=c("Month","Day))

head(melt_df)

 

# cast 재형태화

cast_df <- dcast(melt_df,Day=month+variable)

cast_df

 

a <- NA

is.na(a)

is.na(1)

airquality

is.na(airquality)

df <- airquality

na.omit(df)

complete.cases(df)

a <- df[complete.cases(df),]

a

omit_df <- na.omit(df)

 

names(mtcars)[1] <- c("MPG")

names(mtcars)

 

names(mtcars)[which[names(mtcars) == "cyl")] <- c("CYL")

 

mtcars <- rename(mtcars, mpg = MPG, cyl = CYL)

 

names(mtcars)

str(mtcars)

 

# 일정 이상

data()
library(dplyr)
data("starwars")
str(starwars)
names(starwars)
starwars %>%
  filter(height > 191) %>%
  select(name, hair_color)

starwars[starwars$height > 191, c("name", "hair_color")]