DF 2 con dplyr: como crear y modificar variables

###installar paquetes: install.packages("gapminder"), install.packages("dplyr"), install.packages("ggplot2")

### cargar paquetes
library(gapminder)
library(dplyr)

## 
## Attaching package: 'dplyr'

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

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

library(ggplot2)


###DATAFRAME
gapminder

## # A tibble: 1,704 × 6
##    country     continent  year lifeExp      pop gdpPercap
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
##  1 Afghanistan Asia       1952    28.8  8425333      779.
##  2 Afghanistan Asia       1957    30.3  9240934      821.
##  3 Afghanistan Asia       1962    32.0 10267083      853.
##  4 Afghanistan Asia       1967    34.0 11537966      836.
##  5 Afghanistan Asia       1972    36.1 13079460      740.
##  6 Afghanistan Asia       1977    38.4 14880372      786.
##  7 Afghanistan Asia       1982    39.9 12881816      978.
##  8 Afghanistan Asia       1987    40.8 13867957      852.
##  9 Afghanistan Asia       1992    41.7 16317921      649.
## 10 Afghanistan Asia       1997    41.8 22227415      635.
## # … with 1,694 more rows

##Mutar variable lifeExp de años a meses
gapminder<-gapminder%>%
  mutate(lifeExp=lifeExp*12)%>%
  print()

## # A tibble: 1,704 × 6
##    country     continent  year lifeExp      pop gdpPercap
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
##  1 Afghanistan Asia       1952    346.  8425333      779.
##  2 Afghanistan Asia       1957    364.  9240934      821.
##  3 Afghanistan Asia       1962    384. 10267083      853.
##  4 Afghanistan Asia       1967    408. 11537966      836.
##  5 Afghanistan Asia       1972    433. 13079460      740.
##  6 Afghanistan Asia       1977    461. 14880372      786.
##  7 Afghanistan Asia       1982    478. 12881816      978.
##  8 Afghanistan Asia       1987    490. 13867957      852.
##  9 Afghanistan Asia       1992    500. 16317921      649.
## 10 Afghanistan Asia       1997    501. 22227415      635.
## # … with 1,694 more rows

##crea nueva variable llamada ID2 
gapminder<-gapminder%>%
  mutate(ID2= c(1:1704))%>%
  print()

## # A tibble: 1,704 × 7
##    country     continent  year lifeExp      pop gdpPercap   ID2
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl> <int>
##  1 Afghanistan Asia       1952    346.  8425333      779.     1
##  2 Afghanistan Asia       1957    364.  9240934      821.     2
##  3 Afghanistan Asia       1962    384. 10267083      853.     3
##  4 Afghanistan Asia       1967    408. 11537966      836.     4
##  5 Afghanistan Asia       1972    433. 13079460      740.     5
##  6 Afghanistan Asia       1977    461. 14880372      786.     6
##  7 Afghanistan Asia       1982    478. 12881816      978.     7
##  8 Afghanistan Asia       1987    490. 13867957      852.     8
##  9 Afghanistan Asia       1992    500. 16317921      649.     9
## 10 Afghanistan Asia       1997    501. 22227415      635.    10
## # … with 1,694 more rows

##crear una nueva variable derivada de variables disponibles
gapminder<-gapminder%>%
  mutate(gdp=gdpPercap*pop)%>%
  print()

## # A tibble: 1,704 × 8
##    country     continent  year lifeExp      pop gdpPercap   ID2          gdp
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl> <int>        <dbl>
##  1 Afghanistan Asia       1952    346.  8425333      779.     1  6567086330.
##  2 Afghanistan Asia       1957    364.  9240934      821.     2  7585448670.
##  3 Afghanistan Asia       1962    384. 10267083      853.     3  8758855797.
##  4 Afghanistan Asia       1967    408. 11537966      836.     4  9648014150.
##  5 Afghanistan Asia       1972    433. 13079460      740.     5  9678553274.
##  6 Afghanistan Asia       1977    461. 14880372      786.     6 11697659231.
##  7 Afghanistan Asia       1982    478. 12881816      978.     7 12598563401.
##  8 Afghanistan Asia       1987    490. 13867957      852.     8 11820990309.
##  9 Afghanistan Asia       1992    500. 16317921      649.     9 10595901589.
## 10 Afghanistan Asia       1997    501. 22227415      635.    10 14121995875.
## # … with 1,694 more rows

##quien tiene el GDP mas alto?
gapminder%>%
  filter(year==2007)%>%
  arrange(desc(gdp))%>%
  print()

## # A tibble: 142 × 8
##    country        continent  year lifeExp        pop gdpPercap   ID2     gdp
##    <fct>          <fct>     <int>   <dbl>      <int>     <dbl> <int>   <dbl>
##  1 United States  Americas   2007    939.  301139947    42952.  1620 1.29e13
##  2 China          Asia       2007    876. 1318683096     4959.   300 6.54e12
##  3 Japan          Asia       2007    991.  127467972    31656.   804 4.04e12
##  4 India          Asia       2007    776. 1110396331     2452.   708 2.72e12
##  5 Germany        Europe     2007    953.   82400996    32170.   576 2.65e12
##  6 United Kingdom Europe     2007    953.   60776238    33203.  1608 2.02e12
##  7 France         Europe     2007    968.   61083916    30470.   540 1.86e12
##  8 Brazil         Americas   2007    869.  190010647     9066.   180 1.72e12
##  9 Italy          Europe     2007    967.   58147733    28570.   780 1.66e12
## 10 Mexico         Americas   2007    914.  108700891    11978.   996 1.30e12
## # … with 132 more rows

## Plot
gapminder%>%
  filter(year==2007)%>%
  ggplot( aes(x= pop, y=gdp))+
  geom_point()+
  scale_x_log10()+
  scale_y_log10()+
  geom_smooth()

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'