Cargar paquete

library(readr)

Cargar CSV

read_csv("data/gapminder_comas.csv")
## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   country = col_character(),
##   continent = col_character(),
##   year = col_double(),
##   lifeExp = col_double(),
##   pop = col_double(),
##   gdpPercap = col_double()
## )
## # A tibble: 1,704 x 6
##    country     continent  year lifeExp      pop gdpPercap
##    <chr>       <chr>     <dbl>   <dbl>    <dbl>     <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

Asignar nombre a datos

datos_obtenidos_csv <- read_csv("data/gapminder_comas.csv")
## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   country = col_character(),
##   continent = col_character(),
##   year = col_double(),
##   lifeExp = col_double(),
##   pop = col_double(),
##   gdpPercap = col_double()
## )

Cargar datos csv

datos_obtenidos_csv
## # A tibble: 1,704 x 6
##    country     continent  year lifeExp      pop gdpPercap
##    <chr>       <chr>     <dbl>   <dbl>    <dbl>     <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

Cargar datos TSV

datos_obtenidos_tsv <- read_tsv("data/gapminder_tabs.tsv")
## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   country = col_character(),
##   continent = col_character(),
##   year = col_double(),
##   lifeExp = col_double(),
##   pop = col_double(),
##   gdpPercap = col_double()
## )
datos_obtenidos_tsv
## # A tibble: 1,704 x 6
##    country     continent  year lifeExp      pop gdpPercap
##    <chr>       <chr>     <dbl>   <dbl>    <dbl>     <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

Leer delimitar arbitrario

datos_obtenidos_michi <- read_delim("data/gapminder_michi.txt", delim = "#")
## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   country = col_character(),
##   continent = col_character(),
##   year = col_double(),
##   lifeExp = col_double(),
##   pop = col_double(),
##   gdpPercap = col_double()
## )
datos_obtenidos_michi
## # A tibble: 1,704 x 6
##    country     continent  year lifeExp      pop gdpPercap
##    <chr>       <chr>     <dbl>   <dbl>    <dbl>     <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

Leer delimitar arbitrario

datos_obtenidos_punto_y_coma <- read_delim("data/gapminder_comas2.txt", delim = ";")
## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   country = col_character(),
##   continent = col_character(),
##   year = col_double(),
##   lifeExp = col_double(),
##   pop = col_double(),
##   gdpPercap = col_double()
## )

datos_obtenidos_punto_y_coma

Lee delimitar arbitrario

datos_obtenidos_slash<- read_delim("data/gapminder_slash.txt", delim = "/")
## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   country = col_character(),
##   continent = col_character(),
##   year = col_double(),
##   lifeExp = col_double(),
##   pop = col_double(),
##   gdpPercap = col_double()
## )

datos_obtenidos_slash

Lee delimitar arbitario

datos_obtenidos_guiones<- read_delim("data/gapminder_guiones.txt", delim = "_")
## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   `country-continent-year-lifeExp-pop-gdpPercap` = col_character()
## )
## Warning: 24 parsing failures.
## row                                          col           expected actual                         file
## 625 country-continent-year-lifeExp-pop-gdpPercap delimiter or quote      - 'data/gapminder_guiones.txt'
## 625 country-continent-year-lifeExp-pop-gdpPercap delimiter or quote      G 'data/gapminder_guiones.txt'
## 625 country-continent-year-lifeExp-pop-gdpPercap delimiter or quote      - 'data/gapminder_guiones.txt'
## 625 country-continent-year-lifeExp-pop-gdpPercap delimiter or quote      G 'data/gapminder_guiones.txt'
## 625 country-continent-year-lifeExp-pop-gdpPercap delimiter or quote      - 'data/gapminder_guiones.txt'
## ... ............................................ .................. ...... ............................
## See problems(...) for more details.

datos_obtenidos_guiones

Leer excel

library(readxl)

Leer “gapminder_excel.xlsx”

 gapminder_excel <- read_xlsx("data/gapminder_excel.xlsx")
gapminder_excel
## # A tibble: 1,704 x 6
##    country     continent  year lifeExp      pop gdpPercap
##    <chr>       <chr>     <dbl>   <dbl>    <dbl>     <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

Manera alternativa

gapminder_excel2 <- read_excel("data/gapminder_excel.xlsx")

gapminder_excel2

Leer SPSS

library(haven)

Leer “09_UNIVERSIDADES_CARATULA.SAV”

read_sav ("data/09_UNIVERSIDADES_CARATULA.SAV")
## # A tibble: 122 x 8
##    SELECT UC0DD_CD UC0DD_DPTO UC0PP_CD UC0PP_PROV UC0DI_CD UC0DI_DIST   UC0P_OBS
##    <chr>  <chr>    <chr>      <chr>    <chr>      <chr>    <chr>        <chr>   
##  1 U0001  16       LORETO     01       MAYNAS     13       SAN JUAN BA… ""      
##  2 U0002  14       LAMBAYEQUE 03       LAMBAYEQUE 01       LAMBAYEQUE   ""      
##  3 U0003  15       LIMA       01       LIMA       40       SANTIAGO DE… ""      
##  4 U0004  15       LIMA       01       LIMA       13       JESUS MARIA  ""      
##  5 U0005  15       LIMA       01       LIMA       35       SAN MARTIN … ""      
##  6 U0006  15       LIMA       01       LIMA       40       SANTIAGO DE… ""      
##  7 U0007  15       LIMA       01       LIMA       21       PUEBLO LIBRE ""      
##  8 U0008  23       TACNA      01       TACNA      01       TACNA        ""      
##  9 U0009  10       HUANUCO    01       HUANUCO    01       HUANUCO      ""      
## 10 U0010  15       LIMA       01       LIMA       13       JESUS MARIA  ""      
## # … with 112 more rows
datos_spss <- read_sav("data/09_UNIVERSIDADES_CARATULA.SAV")
datos_spss
## # A tibble: 122 x 8
##    SELECT UC0DD_CD UC0DD_DPTO UC0PP_CD UC0PP_PROV UC0DI_CD UC0DI_DIST   UC0P_OBS
##    <chr>  <chr>    <chr>      <chr>    <chr>      <chr>    <chr>        <chr>   
##  1 U0001  16       LORETO     01       MAYNAS     13       SAN JUAN BA… ""      
##  2 U0002  14       LAMBAYEQUE 03       LAMBAYEQUE 01       LAMBAYEQUE   ""      
##  3 U0003  15       LIMA       01       LIMA       40       SANTIAGO DE… ""      
##  4 U0004  15       LIMA       01       LIMA       13       JESUS MARIA  ""      
##  5 U0005  15       LIMA       01       LIMA       35       SAN MARTIN … ""      
##  6 U0006  15       LIMA       01       LIMA       40       SANTIAGO DE… ""      
##  7 U0007  15       LIMA       01       LIMA       21       PUEBLO LIBRE ""      
##  8 U0008  23       TACNA      01       TACNA      01       TACNA        ""      
##  9 U0009  10       HUANUCO    01       HUANUCO    01       HUANUCO      ""      
## 10 U0010  15       LIMA       01       LIMA       13       JESUS MARIA  ""      
## # … with 112 more rows

Manera alternativa de leer spss con read_spss()

datos_spss2 <- read_spss("data/09_UNIVERSIDADES_CARATULA.SAV")
datos_spss2
## # A tibble: 122 x 8
##    SELECT UC0DD_CD UC0DD_DPTO UC0PP_CD UC0PP_PROV UC0DI_CD UC0DI_DIST   UC0P_OBS
##    <chr>  <chr>    <chr>      <chr>    <chr>      <chr>    <chr>        <chr>   
##  1 U0001  16       LORETO     01       MAYNAS     13       SAN JUAN BA… ""      
##  2 U0002  14       LAMBAYEQUE 03       LAMBAYEQUE 01       LAMBAYEQUE   ""      
##  3 U0003  15       LIMA       01       LIMA       40       SANTIAGO DE… ""      
##  4 U0004  15       LIMA       01       LIMA       13       JESUS MARIA  ""      
##  5 U0005  15       LIMA       01       LIMA       35       SAN MARTIN … ""      
##  6 U0006  15       LIMA       01       LIMA       40       SANTIAGO DE… ""      
##  7 U0007  15       LIMA       01       LIMA       21       PUEBLO LIBRE ""      
##  8 U0008  23       TACNA      01       TACNA      01       TACNA        ""      
##  9 U0009  10       HUANUCO    01       HUANUCO    01       HUANUCO      ""      
## 10 U0010  15       LIMA       01       LIMA       13       JESUS MARIA  ""      
## # … with 112 more rows

Leer datos con otros argumentos

sheet

library(readxl)
read_xlsx("data/gapminder_excel_sheet.xlsx",sheet = 2)
## # A tibble: 1,704 x 6
##    country     continent  year lifeExp      pop gdpPercap
##    <chr>       <chr>     <dbl>   <dbl>    <dbl>     <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
gap_excel_sheet1<- read_xlsx("data/gapminder_excel_sheet.xlsx",sheet = "Hoja 2")
gap_excel_sheet2<- read_xlsx("data/gapminder_excel_sheet.xlsx",sheet = 2)

col_names

read_xlsx("data/gapminder_excel_col_names.xlsx")
## # A tibble: 1,703 x 6
##    Afghanistan Asia  `1952` `28.800999999999998` `8425333` `779.44531449999999`
##    <chr>       <chr>  <dbl>                <dbl>     <dbl>                <dbl>
##  1 Afghanistan Asia    1957                 30.3   9240934                 821.
##  2 Afghanistan Asia    1962                 32.0  10267083                 853.
##  3 Afghanistan Asia    1967                 34.0  11537966                 836.
##  4 Afghanistan Asia    1972                 36.1  13079460                 740.
##  5 Afghanistan Asia    1977                 38.4  14880372                 786.
##  6 Afghanistan Asia    1982                 39.9  12881816                 978.
##  7 Afghanistan Asia    1987                 40.8  13867957                 852.
##  8 Afghanistan Asia    1992                 41.7  16317921                 649.
##  9 Afghanistan Asia    1997                 41.8  22227415                 635.
## 10 Afghanistan Asia    2002                 42.1  25268405                 727.
## # … with 1,693 more rows
gap_excel_col_names <- read_xlsx("data/gapminder_excel_col_names.xlsx",col_names=FALSE)
## New names:
## * `` -> ...1
## * `` -> ...2
## * `` -> ...3
## * `` -> ...4
## * `` -> ...5
## * ...
read_xlsx("data/gapminder_excel_sheet.xlsx", 2)
## # A tibble: 1,704 x 6
##    country     continent  year lifeExp      pop gdpPercap
##    <chr>       <chr>     <dbl>   <dbl>    <dbl>     <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
gap_excel_col_names <- read_xlsx("data/gapminder_excel_col_names.xlsx",col_names=FALSE)
## New names:
## * `` -> ...1
## * `` -> ...2
## * `` -> ...3
## * `` -> ...4
## * `` -> ...5
## * ...

Leer datos de paquetes

library(vcdExtra)
## Loading required package: vcd
## Loading required package: grid
## Loading required package: gnm
library(datasets)
datasets("ggplot2")
## Loading package: ggplot2
##              Item      class      dim
## 1        diamonds data.frame 53940x10
## 2       economics data.frame    574x6
## 3  economics_long data.frame   2870x4
## 4       faithfuld data.frame   5625x3
## 5     luv_colours data.frame    657x4
## 6         midwest data.frame   437x28
## 7             mpg data.frame   234x11
## 8          msleep data.frame    83x11
## 9    presidential data.frame     11x4
## 10          seals data.frame   1155x4
## 11      txhousing data.frame   8602x9
##                                                                Title
## 1                           Prices of over 50,000 round cut diamonds
## 2                                            US economic time series
## 3                                            US economic time series
## 4                           2d density estimate of Old Faithful data
## 5                                            'colors()' in Luv space
## 6                                               Midwest demographics
## 7  Fuel economy data from 1999 to 2008 for 38 popular models of cars
## 8       An updated and expanded version of the mammals sleep dataset
## 9                    Terms of 11 presidents from Eisenhower to Obama
## 10                                    Vector field of seal movements
## 11                                               Housing sales in TX