ProblemaN5

library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.6     v dplyr   1.0.7
## v tidyr   1.1.4     v stringr 1.4.0
## v readr   2.1.1     v forcats 0.5.1

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.6     v dplyr   1.0.7
## v tidyr   1.1.4     v stringr 1.4.0
## v readr   2.1.0     v forcats 0.5.1

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

url="https://raw.githubusercontent.com/mcfrank/tidyverse-tutorial/master/data/ws.csv"
df<-read.csv(url)
head(df)

##   data_id age comprehension production language form birth_order ethnicity
## 1   51699  27           497        497  English   WS      Fourth  Hispanic
## 2   51700  21           369        369  English   WS      Second     White
## 3   51701  26           190        190  English   WS      Fourth     White
## 4   51702  27           264        264  English   WS      Second     White
## 5   51703  19           159        159  English   WS      Second     Other
## 6   51704  30           513        513  English   WS      Second     Other
##      sex zygosity norming longitudinal source_name         mom_ed
## 1 Female       NA    TRUE        FALSE    Marchman Some Secondary
## 2 Female       NA    TRUE        FALSE    Marchman      Secondary
## 3 Female       NA    TRUE        FALSE    Marchman        College
## 4   Male       NA    TRUE        FALSE    Marchman      Secondary
## 5 Female       NA    TRUE        FALSE    Marchman      Secondary
## 6 Female       NA    TRUE        FALSE    Marchman      Secondary

Promedio de la comprensión para cada etnia

df%>%group_by(ethnicity)%>%summarize(promedio=mean(comprehension)) 

## # A tibble: 6 x 2
##   ethnicity promedio
##   <chr>        <dbl>
## 1 Asian         273.
## 2 Black         289.
## 3 Hispanic      221.
## 4 Other         223.
## 5 White         281.
## 6 <NA>          256.

Promedio de la producción para cada sexo

df%>%group_by(sex)%>%summarize(promedio=mean(production))

## # A tibble: 3 x 2
##   sex    promedio
##   <chr>     <dbl>
## 1 Female     297.
## 2 Male       260.
## 3 <NA>       233.

hist(df$age,col="blue", main="Histograma de la distribución por edad de los participantes",xlab="Age",freq = FALSE)