Datos hurtos de Ganado 2019

library(janitor)
## Warning: package 'janitor' was built under R version 4.0.3
## 
## Attaching package: 'janitor'
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test
library(tidyverse)
## -- Attaching packages --------------------------------------------------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.2     v purrr   0.3.4
## v tibble  3.0.3     v dplyr   1.0.2
## v tidyr   1.1.2     v stringr 1.4.0
## v readr   1.4.0     v forcats 0.5.0
## -- Conflicts ------------------------------------------------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(Hmisc)
## Warning: package 'Hmisc' was built under R version 4.0.3
## Loading required package: lattice
## Loading required package: survival
## Loading required package: Formula
## Warning: package 'Formula' was built under R version 4.0.3
## 
## Attaching package: 'Hmisc'
## The following objects are masked from 'package:dplyr':
## 
##     src, summarize
## The following objects are masked from 'package:base':
## 
##     format.pval, units
data_hurtos <- read_csv(
  file = "HURTO_A_CABEZAS_DE_GANADO_PER_ODO_DEL_01_DE_ENERO__AL_31_DE_DICIEMBRE_A_O_2019.csv"
) %>% 
  clean_names() %>% 
  filter(cantidad == 1) %>% 
  mutate_if(is.character, tolower) %>% 
  mutate_if(is.character, capitalize) %>% 
  mutate_if(is.character, as.factor) %>% 
  mutate(dia = factor(dia,
                      levels = c("Lunes", "Martes", "Miércoles", "Jueves",
                                 "Viernes", "Sábado", "Domingo"))) %>% 
  select(-codigo_dane)
## 
## -- Column specification --------------------------------------------------------------------------------------------------
## cols(
##   Departamento = col_character(),
##   Municipio = col_character(),
##   Día = col_character(),
##   Barrio = col_character(),
##   Zona = col_character(),
##   `Clase de sitio` = col_character(),
##   `Arma empleada` = col_character(),
##   `Móvil Agresor` = col_character(),
##   `Móvil Victima` = col_character(),
##   Sexo = col_character(),
##   `Estado civil` = col_character(),
##   `País de nacimiento` = col_character(),
##   `Clase de empleado` = col_character(),
##   Escolaridad = col_character(),
##   `Código DANE` = col_double(),
##   Cantidad = col_double()
## )
head(data_hurtos)

grafico 1

  • Hurtos por dia de la semana y zona
library(ggplot2)
library(dplyr)


data_hurtos %>%
  group_by(dia, zona) %>% 
  summarise(cantidad  = n()) %>% 
  ggplot( aes(x = dia, y = cantidad, color= zona, group = zona))+
  geom_point()+
  geom_line()
## `summarise()` regrouping output by 'dia' (override with `.groups` argument)

## Gráfico 2

  • hurto por dia de la semana y zona, comportamiento departamental.
data_hurtos %>% 
   group_by(dia, zona, departamento) %>% 
  summarise(cantidad  = n()) %>% 
  ggplot(mapping = aes(x = dia,
                       y = cantidad, color = zona, group = zona))+
  facet_wrap(facets = ~departamento, scales = "free", ncol = 4)+
  geom_point()+
  geom_line()+
  theme(legend.position = "toc", axis.text = element_text(angle = 45, hjust = 1))
## `summarise()` regrouping output by 'dia', 'zona' (override with `.groups` argument)
## geom_path: Each group consists of only one observation. Do you need to adjust
## the group aesthetic?

grafico 3

-Hurto por clase de empleado, comportamiento por zonas.

data_hurtos %>% 
 group_by(clase_de_empleado, zona) %>% 
  summarise(total = sum(cantidad)) %>% 
  ggplot(mapping =  aes(x = reorder(clase_de_empleado, total),
                        y = total))+
  facet_wrap(facets = ~zona, scales = "free", ncol = 2)+
  
  geom_point()+
  coord_flip()
## `summarise()` regrouping output by 'clase_de_empleado' (override with `.groups` argument)

grafico 4

  • Distribucion de hurtos por departamento, comportamiento semanal.
data_hurtos %>% 
 group_by(departamento, dia) %>% 
  summarise(total = sum(cantidad)) %>% 
  ggplot(mapping = aes(x = total ))+
    facet_wrap(facets = ~departamento, scales = "free", ncol= 4)+
    geom_density(alpha = 0.5)
## `summarise()` regrouping output by 'departamento' (override with `.groups` argument)