Analisis descriptivo

1. Cargue de datos

library(readxl)
df<- read_excel("C:/Users/lufca/OneDrive/Escritorio/Tesis/consolidad_filtrados.xlsx", 
    col_types = c("numeric", "text", "text", 
        "text", "text", "text", "numeric", 
        "numeric", "numeric", "numeric", 
        "numeric", "numeric", "numeric"))

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

2. Estadistica descriptica

df %>%
  group_by(Familia) %>% 
  summarise(
    media = mean(P_Fresco, na.rm = TRUE),
    mediana= median(P_Fresco, na.rm = TRUE),
    desviacion = sd(P_Fresco, na.rm = TRUE),
    min_P = min(P_Fresco, na.rm = TRUE),
    max_P = max(P_Fresco, na.rm = TRUE)
  )

## # A tibble: 15 × 6
##    Familia media mediana desviacion min_P max_P
##      <dbl> <dbl>   <dbl>      <dbl> <dbl> <dbl>
##  1       1  73.4    66.8       57.6  0.75  364.
##  2       2  94.1    98.2       52.9  0.8   194.
##  3       3  90.9    81.2       60.1  2.7   236.
##  4       4  80.2    74         53.8  1.65  217.
##  5       5  83.1    86.2       44.3  0.6   195.
##  6       6 123.    119.        68.3  3.35  386.
##  7       7  91.2    87.8       44.4  1.85  211.
##  8       8 200.    194.        92.7  6.6   478 
##  9       9  83.5    82.2       48.9  2.05  232.
## 10      10  81.0    83.9       44.7  1.75  180 
## 11      11  81.0    73.1       62.6  1.2   240.
## 12      12  74.5    73.6       58.7  0.9   200.
## 13      13 153.    149.        84.5  5.5   430.
## 14      14 131.    134.        78.6  3     331.
## 15      15 132.    139.        63.0 21.1   268.

3. Histogramas

#install.packages("ggplot2")
library(ggplot2)

ggplot(data = df, aes(x = P_Fresco)) +
  geom_histogram(binwidth = 4) +  # Puedes ajustar el ancho de las barras según tus preferencias
  facet_wrap(~ Familia, scales = "free")  # Esto creará un histograma por cada familia

4. Analisis de la dependencia espacial

#install.packages("spdep")
library(spdep)

## Loading required package: spData

## The legacy packages maptools, rgdal, and rgeos, underpinning this package
## will retire shortly. Please refer to R-spatial evolution reports on
## https://r-spatial.org/r/2023/05/15/evolution4.html for details.
## This package is now running under evolution status 0

## To access larger datasets in this package, install the spDataLarge
## package with: `install.packages('spDataLarge',
## repos='https://nowosad.github.io/drat/', type='source')`

## Loading required package: sf

## Linking to GEOS 3.11.2, GDAL 3.7.2, PROJ 9.3.0; sf_use_s2() is TRUE

Revisando que no hayan duplicados

any(duplicated(df$ID))

## [1] FALSE

1. Construyendo la matriz de pesos espaciales

coordinates <- cbind(df$X, df$Y)
listw <- knn2nb(knearneigh(coordinates, k = 3), row.names = df$ID)
listw <- nb2listw(listw)

2. Calcular el índice de Moran

(moran <- moran.test(df$P_Fresco, listw, alternative="greater"))

## 
##  Moran I test under randomisation
## 
## data:  df$P_Fresco  
## weights: listw    
## 
## Moran I statistic standard deviate = 10.499, p-value < 2.2e-16
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic       Expectation          Variance 
##      0.2408509658     -0.0008710801      0.0005300609