# Folder de trabajo
setwd("~/pye1pm")
## Asignacion 3 Utilizando conjuntos de datos R
## Para un analisis exploratorio de datos
#Para este ejemplo en particular seran datos de castores
# Paquete
library(fdth)
##
## Attaching package: 'fdth'
## The following objects are masked from 'package:stats':
##
## sd, var
library(modeest)
##
## Attaching package: 'modeest'
## The following object is masked from 'package:fdth':
##
## mfv
library(pacman) #package manager
p_load("datasets")
#datos acerca de castores
castores <-beaver1
#conociendo los datos
head(castores) #Esto nos dara las primeras 6 filas
## day time temp activ
## 1 346 840 36.33 0
## 2 346 850 36.34 0
## 3 346 900 36.35 0
## 4 346 910 36.42 0
## 5 346 920 36.55 0
## 6 346 930 36.69 0
dim(castores) # me da el numero de columnas
## [1] 114 4
## Medidas de tendencia central
summary(castores)
## day time temp activ
## Min. :346.0 Min. : 0.0 Min. :36.33 Min. :0.00000
## 1st Qu.:346.0 1st Qu.: 932.5 1st Qu.:36.76 1st Qu.:0.00000
## Median :346.0 Median :1415.0 Median :36.87 Median :0.00000
## Mean :346.2 Mean :1312.0 Mean :36.86 Mean :0.05263
## 3rd Qu.:346.0 3rd Qu.:1887.5 3rd Qu.:36.96 3rd Qu.:0.00000
## Max. :347.0 Max. :2350.0 Max. :37.53 Max. :1.00000
# Valor minimo, primer cuartil, mediana, tercer cuartil, valor maximo
boxplot(castores)
boxplot(castores$temp)
## Medidas de dispersion
#Varianza
var(castores$temp)
## [1] 0.03741196
#desviacion estandar
sd(castores$temp)
## [1] 0.1934217
#grafico de dispersion
plot(castores)
#tarea añadir analisis de distribucion de frecuencias
#tablas e histogramas
tabla <- fdt(castores, breaks = "Sturges")
tabla
## day
## Class limits f rf rf(%) cf cf(%)
## [342.54,343.531) 0 0.0 0.00 0 0.00
## [343.531,344.523) 0 0.0 0.00 0 0.00
## [344.523,345.514) 0 0.0 0.00 0 0.00
## [345.514,346.505) 91 0.8 79.82 91 79.82
## [346.505,347.496) 23 0.2 20.18 114 100.00
## [347.496,348.488) 0 0.0 0.00 114 100.00
## [348.488,349.479) 0 0.0 0.00 114 100.00
## [349.479,350.47) 0 0.0 0.00 114 100.00
##
## time
## Class limits f rf rf(%) cf cf(%)
## [0,296.688) 18 0.16 15.79 18 15.79
## [296.688,593.375) 5 0.04 4.39 23 20.18
## [593.375,890.062) 2 0.02 1.75 25 21.93
## [890.062,1186.75) 18 0.16 15.79 43 37.72
## [1186.75,1483.44) 18 0.16 15.79 61 53.51
## [1483.44,1780.12) 18 0.16 15.79 79 69.30
## [1780.12,2076.81) 18 0.16 15.79 97 85.09
## [2076.81,2373.5) 17 0.15 14.91 114 100.00
##
## temp
## Class limits f rf rf(%) cf cf(%)
## [35.967,36.209) 0 0.00 0.00 0 0.00
## [36.209,36.451) 4 0.04 3.51 4 3.51
## [36.451,36.694) 14 0.12 12.28 18 15.79
## [36.694,36.936) 61 0.54 53.51 79 69.30
## [36.936,37.178) 26 0.23 22.81 105 92.11
## [37.178,37.421) 8 0.07 7.02 113 99.12
## [37.421,37.663) 1 0.01 0.88 114 100.00
## [37.663,37.905) 0 0.00 0.00 114 100.00
##
## activ
## Class limits f rf rf(%) cf cf(%)
## [0,0.1263) 108 0.95 94.74 108 94.74
## [0.1263,0.2525) 0 0.00 0.00 108 94.74
## [0.2525,0.3788) 0 0.00 0.00 108 94.74
## [0.3788,0.505) 0 0.00 0.00 108 94.74
## [0.505,0.6312) 0 0.00 0.00 108 94.74
## [0.6312,0.7575) 0 0.00 0.00 108 94.74
## [0.7575,0.8838) 0 0.00 0.00 108 94.74
## [0.8838,1.01) 6 0.05 5.26 114 100.00
# Histograma de frecuencia absoluta
plot(tabla, type="fh")
# Histograma de frecuencia acumulada
plot(tabla, type="cfh")
# Histograma de frecuencia relativa
plot(tabla, type="rfh")
# Poligono de frecuencia absoluta
plot(tabla, type="fp")
# Poligono de frecuencia acumulada
plot(tabla, type="cfp")
# Poligono de frecuencia relativa
plot(tabla, type="rfp")
