The aim of the project is to compare the crime rate in the neighbouring postcodes for each of the five previous years: Postcode selected are 5000 and 5006 and offence_level_1 description: ACTS INTENDED TO CAUSE INJURY.
knitr::opts_chunk$set(echo = FALSE, message = FALSE, warning = FALSE) library(devtools) devtools::install_github("Sonal28/prfasonalv") library(knitr) library(prfasonalv) library(data.table) library(readxl) library(ggplot2)
The result of this code is to display cowplot for 5 year data and show the correlation in neightbuoring postcodes. The below knit table generates 20 rows markdown table for crime data set for year 2012-2013.
options(knitr.table.format = "html") offence_des <- "ACTS INTENDED TO CAUSE INJURY" postcode_vec <- c(5000, 5006) data1 <- setDT(read_xlsx("data/crime-statistics-2012-13.xlsx")) setnames(data1, c("date", "suburb", "postcode", "offence_level_1", "offence_level_2", "offence_level_3", "offence_count")) knitr::kable(data1[1:20])
Generates cowplot for 5 year crime dataset.
offence_des <- "ACTS INTENDED TO CAUSE INJURY" postcode_vec <- c(5000, 5006) data1 <- setDT(read_xlsx("data/crime-statistics-2012-13.xlsx")) data1 <- setnames(data1, c("date", "suburb", "postcode", "offence_level_1", "offence_level_2", "offence_level_3", "offence_count")) plot_2012 <- crime_file(data1, offence_des, postcode_vec) data2 <- setDT(read_xlsx("data/crime-statistics-2013-14.xlsx")) data2 <- setnames(data2, c("date", "suburb", "postcode", "offence_level_1", "offence_level_2", "offence_level_3", "offence_count")) plot_2013 <- crime_file(data2, offence_des, postcode_vec) data3 <- setDT(read_xlsx("data/crime-statistics-2014-15.xlsx")) data3 <- setnames(data3, c("date", "suburb", "postcode", "offence_level_1", "offence_level_2", "offence_level_3", "offence_count")) plot_2014 <- crime_file(data3, offence_des, postcode_vec) data4 <- setDT(read_xlsx("data/crime-statistics-2015-16.xlsx")) data4 <- setnames(data4, c("date", "suburb", "postcode", "offence_level_1", "offence_level_2", "offence_level_3", "offence_count")) plot_2015 <- crime_file(data4, offence_des, postcode_vec) data5 <- setDT(read_xlsx("data/crime-statistics-2016-17.xlsx")) data5 <- setnames(data5, c("date", "suburb", "postcode", "offence_level_1", "offence_level_2", "offence_level_3", "offence_count")) plot_2016 <- crime_file(data5, offence_des, postcode_vec) cowplot::plot_grid(plot_2012, plot_2013, plot_2014, plot_2015, plot_2016, labels=c("2012-2013", "2013-2014", "2014-2015", "2015-2016", "2016-2017"), label_size = 8)
The above cowplot shows 5 different geom_count() plot grouping on basis of monthly occurance of crime at postcodes 5000 (x-axis) and postcodes 5006 (y-axis). Each geom plot shows the correlation within the neighbouring postcodes for different year(2012 to 2017). As we can see the plots, the co-occurance of postcodes are more concentrated when the value of x and y axis is near 0 (count), whereas less when it moves farther. So, the two postcodes are more co-related when the number of crime count is less.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.