6주차 과제

6주차 과제

과제 1 _ mlu파일 분석해보기

1번.

library(readxl)

getwd()

## [1] "C:/Users/admin/Desktop/R"

setwd("C:/Users/admin/Desktop/R")
mlu <- read_excel("mlu (1).xls", sheet=2)

2번.

library(dplyr)

## 
## 다음의 패키지를 부착합니다: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

mlu %>% filter(utterances_mlu<= 500) -> mlu1
dim(mlu1)

## [1] 5 9

3번.

df <- mlu %>% select (File, age, utterances_mlu, words_mlu, Types_freq, Token_freq)

4번.

mlu$MLU <- mlu$words_mlu / mlu$utterances_mlu
mlu %>% group_by(age) %>% summarise(MLU_mean = mean(MLU))

## # A tibble: 3 × 2
##   age   MLU_mean
##   <chr>    <dbl>
## 1 A0        2.50
## 2 A1        2.59
## 3 A2        2.99

5번.

mlu$token_type <- mlu$Token_freq / mlu$Types_freq
mean(mlu$token_type)

## [1] 2.653726

과제 2 _ 혼자서해보기

1번.

mpg<-as.data.frame(ggplot2::mpg) 
mpg1 <- mpg %>% filter(displ <= 4)
mpg2 <- mpg %>% filter(displ >= 5)
mean(mpg1$hwy)

## [1] 25.96319

mean(mpg2$hwy)

## [1] 18.07895

2번.

audi <- mpg %>% filter(manufacturer=="audi")
toyota <- mpg %>% filter(manufacturer=="toyota")
mean(audi$cty)

## [1] 17.61111

mean(toyota$cty)

## [1] 18.52941

3번.

a1 <- mpg %>% filter(manufacturer %in% c("chevrolet", "ford", "honda"))
mean(a1$hwy)

## [1] 22.50943