tarea 2 proba

set.seed(356) 

data("diamonds")

muestra <- diamonds %>% sample_n(120)

head(muestra)

## # A tibble: 6 × 10
##   carat cut       color clarity depth table price     x     y     z
##   <dbl> <ord>     <ord> <ord>   <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1  0.74 Ideal     D     SI1      61.8    56  3517  5.84  5.88  3.62
## 2  0.36 Very Good D     SI1      63.1    55   851  4.59  4.54  2.88
## 3  0.59 Very Good E     VS2      60.6    60  2094  5.44  5.49  3.31
## 4  0.77 Premium   I     VS1      62.6    55  2524  5.9   5.85  3.68
## 5  0.23 Very Good F     VVS2     61.2    58   530  3.96  3.98  2.43
## 6  0.51 Very Good G     VS2      62.9    57  1438  5.06  5.12  3.2

mean(muestra$carat)   

## [1] 0.8471667

median(muestra$carat) 

## [1] 0.77

mode_carat <- as.numeric(names(sort(table(muestra$carat), decreasing = TRUE)[1]))

mode_carat 

## [1] 0.71

var(muestra$depth)  

## [1] 1.959639

sd(muestra$depth)    

## [1] 1.399871

range(muestra$depth) 

## [1] 57.8 65.1

IQR(muestra$depth)   

## [1] 1.75

quantile(muestra$table, probs = c(0.25, 0.75)) # Q1 y Q3

## 25% 75% 
##  56  59

quantile(muestra$table, probs = c(0.30, 0.78, 0.90)) # percentiles 30, 78, 90

## 30% 78% 90% 
##  57  59  60

library(psych)

describe(muestra$x)[c("skew", "kurtosis")]

##    skew kurtosis
## X1 0.14    -0.77

tabla_y <- table(muestra$y)

tabla_y

## 
## 3.78 3.98 4.17  4.2 4.28 4.32 4.33 4.35  4.4 4.42 4.43 4.46 4.47 4.49 4.54 4.55 
##    1    1    1    1    2    1    1    1    1    2    1    1    1    1    1    1 
## 4.57 4.58 4.67  4.7 4.72 4.73 4.77 4.78 4.81 4.93 5.05 5.06  5.1 5.12 5.15 5.18 
##    1    1    2    1    1    1    1    1    1    1    1    1    1    1    1    1 
## 5.19 5.25 5.27 5.29 5.31  5.4 5.46 5.49 5.57 5.67 5.68  5.7 5.74 5.75 5.77  5.8 
##    1    1    2    2    1    1    1    1    1    1    2    1    2    2    1    1 
## 5.84 5.85 5.88  5.9 5.93 5.97    6 6.07 6.15 6.19 6.23 6.26 6.27  6.3 6.32 6.33 
##    2    2    1    1    1    1    1    1    1    1    3    1    1    1    1    1 
## 6.36 6.37 6.38 6.41 6.44 6.45 6.46 6.47 6.52 6.54 6.55 6.57 6.58 6.59 6.61 6.63 
##    1    1    1    1    1    1    1    1    3    2    1    1    1    1    1    1 
## 6.69 6.78  6.8 6.83 6.84  6.9 6.91 7.27 7.28 7.33 7.35  7.4 7.45 7.58  7.6 7.61 
##    1    1    1    1    1    1    1    3    2    1    1    1    2    2    1    1 
## 8.01  8.2 8.26 8.48 
##    1    1    1    1

hist(muestra$y, main = "Histograma de Y", xlab = "y", col = "skyblue", border = "white")

tabla_corte <- table(muestra$cut)

tabla_corte

## 
##      Fair      Good Very Good   Premium     Ideal 
##         2        12        24        30        52

barplot(tabla_corte, col = "lightgreen", main = "Distribución de Corte")

prop <- round(tabla_corte/sum(tabla_corte)*100,1)

pie(tabla_corte, labels = paste0(names(tabla_corte)," (",prop,"%)"),
    
    col = rainbow(length(tabla_corte)), main = "Distribución de Corte (Dona)")