R Notebook

library(rio)
library(htmltab)
link='https://github.com/JoseManuelMagallanes/Estadistica_Para_AnalisisPolitico/raw/master/lapop17.dta'
lapop17=import(link)

library(stringr)
names(lapop17)=str_split(names(lapop17)," ",simplify = T)[,1]
names(lapop17)=str_replace_all(names(lapop17), "[^[:ascii:]]", "")
lapop17[,]=lapply(lapop17[,], str_replace_all,"[^[:ascii:]]","")
names(lapop17)

  [1] "pais"         "sobremuestra" "idnum"        "uniq_id"      "upm"          "prov"         "municipio"    "cluster"     
  [9] "ur"           "tamano"       "idiomaq"      "fecha"        "wt"           "estratopri"   "estratosec"   "q2"          
 [17] "q1"           "perprov"      "ls3"          "a4"           "soct2"        "idio2"        "np1"          "sgl1"        
 [25] "cp6"          "cp7"          "cp8"          "cp13"         "cp20"         "it1"          "l1"           "prot3"       
 [33] "jc10"         "jc13"         "jc15a"        "vic1ext"      "vic1exta"     "vic2new"      "aoj11"        "aoj12"       
 [41] "b1"           "b2"           "b3"           "b4"           "b6"           "b43"          "b12"          "b13"         
 [49] "b18"          "b21"          "b21a"         "b32"          "b37"          "b47a"         "m1"           "m2"          
 [57] "sd2new2"      "sd3new2"      "sd6new2"      "infrax"       "infra3"       "ros1"         "ros4"         "ing4"        
 [65] "eff1"         "eff2"         "aoj22new"     "media3"       "media4"       "exp_a"        "dst1b"        "drk1"        
 [73] "env1c"        "env2b"        "envp3l"       "envp3l_o"     "envp3n"       "envp3n_o"     "envp41"       "envp42"      
 [81] "pn4"          "w14a"         "e5"           "e15"          "e16"          "d1"           "d2"           "d3"          
 [89] "d4"           "d5"           "d6"           "ivv3"         "lib1"         "lib2b"        "lib2c"        "lib4"        
 [97] "exc2"         "exc6"         "exc20"        "exc11"        "exc13"        "exc14"        "exc15"        "exc16"       
[105] "exc18"        "exc7"         "exc7new"      "vb1"          "vb2"          "vb3n"         "vb10"         "vb11"        
[113] "pol1"         "vb20"         "dis7a"        "dis8a"        "dis9a"        "dis10a"       "dis11a"       "for5"        
[121] "mil10a"       "mil10e"       "ccq1"         "ccq2"         "ccq3"         "ccq4"         "ie1"          "ie2"         
[129] "ie3"          "ie6"          "ie9"          "ie10"         "envp8"        "wf1"          "cct1b"        "ed"          
[137] "ed2"          "q5a"          "q5b"          "q3c"          "ocup4a"       "ocup1a"       "q10g"         "q10new"      
[145] "q14"          "q10d"         "q10e"         "q11n"         "q12c"         "q12bn"        "q12"          "q12m"        
[153] "q12f"         "vac1"         "etid"         "iiet1"        "iiet2"        "iiet3"        "www1"         "gi0"         
[161] "pr1"          "r3"           "r4"           "r4a"          "r5"           "r6"           "r7"           "r8"          
[169] "r12"          "r14"          "r15"          "r18"          "r1"           "r16"          "colorr"       "conocim"     
[177] "iarea1"       "iarea2"       "iarea3"       "iarea4"       "iarea6"       "iarea7"       "sexi"         "colori"      
[185] "srvyrid"      "nationality"  "formatq"      "sex"         

library(htmltab)
links=list(web="https://es.wikipedia.org/wiki/%C3%8Dndice_global_de_felicidad",
           xpath ='//*[@id="mw-content-text"]/div/table')
feli<- htmltab(doc = links$web, which =links$xpath)

str(feli)

'data.frame':   156 obs. of  9 variables:
 $ №                                     : chr  "1" "2" "3" "4" ...
 $ País                                  : chr  "Finlandia" "Noruega" "Dinamarca" "Islandia" ...
 $ Puntuación                            : chr  "7.633" "7.594" "7.555" "7.495" ...
 $ PIB per cápita                        : chr  "1.305" "1.456" "1.351" "1.343" ...
 $ Apoyo social                          : chr  "1.592" "1.582" "1.590" "1.644" ...
 $ Esperanza de años de vida saludable   : chr  "0.874" "0.861" "0.868" "0.914" ...
 $ Libertad para tomar decisiones vitales: chr  "0.681" "0.686" "0.683" "0.677" ...
 $ Generosidad                           : chr  "0.192" "0.286" "0.284" "0.353" ...
 $ Percepción de la corrupción           : chr  "0.393" "0.340" "0.408" "0.138" ...

names(feli)

[1] "№"                                      "País"                                   "Puntuación"                            
[4] "PIB per cápita"                         "Apoyo social"                           "Esperanza de años de vida saludable"   
[7] "Libertad para tomar decisiones vitales" "Generosidad"                            "Percepción de la corrupción"           

library(stringr)
names(feli)=str_split(names(feli)," ",simplify = T)[,1]

names(feli)=str_replace_all(names(feli), "[^[:ascii:]]", "")
feli[,]=lapply(feli[,], str_replace_all,"[^[:ascii:]]","")
feli$Rank=NULL
str(feli)

'data.frame':   156 obs. of  9 variables:
 $            : chr  "1" "2" "3" "4" ...
 $ Pas        : chr  "Finlandia" "Noruega" "Dinamarca" "Islandia" ...
 $ Puntuacin  : chr  "7.633" "7.594" "7.555" "7.495" ...
 $ PIB        : chr  "1.305" "1.456" "1.351" "1.343" ...
 $ Apoyo      : chr  "1.592" "1.582" "1.590" "1.644" ...
 $ Esperanza  : chr  "0.874" "0.861" "0.868" "0.914" ...
 $ Libertad   : chr  "0.681" "0.686" "0.683" "0.677" ...
 $ Generosidad: chr  "0.192" "0.286" "0.284" "0.353" ...
 $ Percepcin  : chr  "0.393" "0.340" "0.408" "0.138" ...

feli[,c(3:9)]=lapply(feli[,c(3:9)],parse_number)

1.La puntuación de la felicidad se distribuye asimetricamente?

str(demo)

'data.frame':   167 obs. of  9 variables:
 $ Country               : chr  "Norway" "Iceland" "Sweden" "New Zealand" ...
 $ Score                 : num  9.87 9.58 9.39 9.26 9.22 9.15 9.15 9.14 9.09 9.03 ...
 $ Electoral             : num  10 10 9.58 10 10 9.58 9.58 10 10 9.58 ...
 $ Functioning           : num  9.64 9.29 9.64 9.29 9.29 7.86 9.64 8.93 8.93 9.29 ...
 $ Politicalparticipation: num  10 8.89 8.33 8.89 8.33 8.33 7.78 8.33 7.78 7.78 ...
 $ Politicalculture      : num  10 10 10 8.13 9.38 10 8.75 8.75 8.75 9.38 ...
 $ Civilliberties        : num  9.71 9.71 9.41 10 9.12 10 10 9.71 10 9.12 ...
 $ Regimetype            : Ord.factor w/ 4 levels "Authoritarian"<..: 4 4 4 4 4 4 4 4 4 4 ...
 $ Continent             : Factor w/ 6 levels "Africa","Asia",..: 3 3 3 5 3 3 4 3 5 3 ...

library(ggplot2)
histNum=ggplot(feli,aes(x=Puntuacin))+ geom_histogram(bins=5) 
histNum

Podemos decir del gráfico anterior que la distribución no es simétrica

2.¿El valor representativo de indice de felicidad es robusto?

summary(feli$Puntuacin)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  2.905   4.454   5.378   5.376   6.168   7.633 

basen=ggplot(data=feli,aes(x=Puntuacin))
basen + geom_histogram(bins=10)

Skew(feli$Puntuacin,conf.level = 0.05)

      skew     lwr.ci     upr.ci 
0.01494113 0.00845982 0.02190004 

Gini(feli$Puntuacin)

[1] 0.1196207

La desigualdad es cuando se acerca a 1

library(ggplot2)
library(gglorenz)
ggplot(feli,aes(x=Puntuacin))+ gglorenz::stat_lorenz(color='red') +
    geom_abline(linetype = "dashed") + coord_fixed() +
    labs(x = "% Paises ordenados por Indice de felicidad",
         y = "% Acumulado de Puntuacin de IF",
         title = "Relación pais/Indice de Felicidad",
         caption = "Astor, Maggie (14 de marzo de 2018)") + 
     scale_y_continuous(breaks=seq(0,1,0.15)) +
     scale_x_continuous(breaks=seq(0,1,0.2))

library(ggplot2)
basep=ggplot(data=feli, aes(y=as.numeric(Puntuacin))) 
basep +  geom_boxplot() + coord_flip()

y clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.

plot(cars)

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.