R语言上课代码记录3

# import data
# import csv file
data1 <- read.csv("C:/Users/烟雨潇潇/Desktop/大学作业/R语言数据分析/data/co2.csv")
# path <- scan("clipboard", what="string")
#read.csv(path)
# 效果 "C:\\Users\\烟雨潇潇\\Desktop\\大学作业\\R语言数据分析\\data\\co2.csv"
# CSDN搜到

# import Stata data
library("readstata13")
data2 <- read.dta13(path)
# library("foreign") # for a Stata version 5-12
# read.dta()

# import Excel data
library("readxl")
data3 <- read_excel("C:/Users/烟雨潇潇/Desktop/大学作业/R语言数据分析/data/市场化指数2000-2019.xlsx")

# list all variables in the dataset
names(data1)

# select the variables we need
selvar <- c("Entity", "Year", "Annual.CO2.emissions")
# keep the selected variables
data1_new <- data1[names(data1) %in% selvar]
# or,simply do
data1_new2 <- data1[selvar]

# To drop the selected variables
data1_new3 <- data1[!c(names(data1) %in% selvar)]

# logical operators: and (&), or (|), not(!)

# Another way to subset data
names(data2)
data2_new <- data2[,c(1:4,9)]

# show the first/last 8th rows of data
head(data1_new2, 8) # first 8 rows
tail(data1_new2, 8)