I. Exposition

This report begins analytic inquiry of the data stored in the data transfer object (dto) prepared by the ./manipulation/0-greeter.R script.

# Attach these packages so their functions don't need to be qualified
library(magrittr)          # pipes
library(ggplot2)           # graphing
# for other packages, please use qualifiers (e.g. dplyr::select() )
requireNamespace("dplyr")    # data wrangling
requireNamespace("ggpubr")   # documents

# import custom functions and scripts
base::source("./scripts/common-functions.R")

# path to the data source
path_file_input_dto <- "./data-unshared/derived/0-dto.rds"

I. Data

dto <- readRDS(path_file_input_dto)
dto %>% pryr::object_size(); dto %>% class(); dto %>% names()

82.4 MB

[1] "list"

[1] "sentence" "codebook" "inmate"

# assign aliases for this report
ds          <- dto$sentence
ds_codebook <- dto$codebook

# adjust column names
ds <- ds %>% 
  dplyr::mutate(
    offense_group = substr(offense_arrest_cd,1,1)  # less granular category 
    ,begin_date   = lubridate::as_date(begin_date) # ensure proper data format
  ) %>% 
  dplyr::select(c(
    "person_id"          # idnumbercomb, manually checked to represent a unique person 
    ,"begin_date"        # date the person began serving the aggregate sentence
    ,"offense_group"     # one-letter code (we need "C" - drug-related fellonies)
    ,"offense_arrest_cd" # code for the offense committed   
    ,"offense_count"     # count of offenses in inmate's sentence
    ,"offense_arrest"    # standardized description of the offense committed
  ))
ds %>% dplyr::glimpse(50)

Observations: 120,381
Variables: 6
$ person_id         <dbl> 1, 1, 2, 2, 3, 5, 6...
$ begin_date        <date> 1974-09-24, 1974-0...
$ offense_group     <chr> "E", "E", "D", "D",...
$ offense_arrest_cd <chr> "E01", "E01", "D21"...
$ offense_count     <dbl> 1, 2, 1, 2, 1, 1, 1...
$ offense_arrest    <chr> "FORGERY 1ST DEGREE...

# view the contents of the codebook for these variables
ds_codebook %>% 
  dplyr::filter(field_name %in% c(
    "begin_date"
    ,"offense_arrest_cd"
    ,"offense_arrest"
  )) %>% 
  neat()

field_name	description	sample_data
offense_arrest_cd	code for the offense committed	E01
offense_arrest	standardized description of the offense committed	FORGERY 1ST DEGREE
begin_date	date the person began serving the aggregate sentence	27296

  # knitr::kable(format = "pandoc")

II. Development

1

# compute the number of convictions and offenses for each person
ds <- ds %>% 
  dplyr::group_by(person_id) %>% 
  dplyr::mutate(
    n_convictions       = dplyr::n()         # convictions
    ,n_offense_counts   = sum(offense_count)                        # offenses, counts of
  ) %>% 
  dplyr::ungroup()
ds %>% dplyr::glimpse(50)

Observations: 120,381
Variables: 8
$ person_id         <dbl> 1, 1, 2, 2, 3, 5, 6...
$ begin_date        <date> 1974-09-24, 1974-0...
$ offense_group     <chr> "E", "E", "D", "D",...
$ offense_arrest_cd <chr> "E01", "E01", "D21"...
$ offense_count     <dbl> 1, 2, 1, 2, 1, 1, 1...
$ offense_arrest    <chr> "FORGERY 1ST DEGREE...
$ n_convictions     <int> 2, 2, 2, 2, 1, 1, 1...
$ n_offense_counts  <dbl> 3, 3, 3, 3, 1, 1, 1...

# frequency distribution of recedivism / how many people for each level?
# anything > 1 = recedivism
t2 <- ds %>% 
  dplyr::group_by(n_convictions) %>% 
  dplyr::summarize(
    n_people   = length(unique(person_id)) # number of people with that many convictions
  )

t2 %>% 
  ggplot2::ggplot(aes(x = n_convictions, y = n_people))+
  geom_bar(stat = "identity", fill = 'salmon', alpha = .5, color = "black")+
  theme_minimal() +
  labs(title = "Frequency distribution of conviction count")

# obsevation: most people are first time offenders

2

# Q. Distribution of offenses for people with a single conviction:
# For those who have a single convictions, how many people have 1,2,3,... offenses? 
d1 <- ds %>% 
  dplyr::filter(n_convictions == 1) %>% 
  dplyr::group_by(n_offense_counts) %>% 
  dplyr::summarise(
    n_people = n()
  ) %>% 
  dplyr::ungroup() 

d1 %>% 
  ggplot2::ggplot(aes(x = n_offense_counts, y = n_people))+
  geom_bar(stat = "identity",fill = 'aquamarine3', alpha = .5, color = "black")+
  theme_minimal() +
  labs(title = "Frequency distribution of offense count for people with 1 conviction" )

d1 %>% 
  dplyr::filter(! n_offense_counts == 1) %>% # remove convictions with a single offense count
  ggplot2::ggplot(aes(x = n_offense_counts, y = n_people))+
  geom_bar(stat = "identity",fill = 'aquamarine3', alpha = .5, color = "black")+
  theme_minimal() + 
  labs(title = "Frequency distribution of offense count for people with 2+ conviction" )

3

# Q.  Among the people with a single conviction
# For each offense group, how many unique persons were registered
# For each offense group, how many distinct convictions were registered
t3 <- ds %>% 
  dplyr::filter(n_convictions == 1) %>%
  dplyr::group_by(offense_group) %>% 
  dplyr::summarize(
    # WARNING: people will be double counted because 
    # a single conviction may contain multiple offenses from various offense groups
    n_people = length(unique(person_id)) # ! WARNING 
    ,n_offenses = sum(offense_count)
  ) %>% 
  dplyr::ungroup()


t3 %>% 
  ggplot2::ggplot(aes(x = offense_group  ) ) +
  geom_bar(aes(y = n_offenses),fill = "yellow",color = "black", stat = "identity", alpha = .3)+
  geom_bar(aes(y = n_people),  fill = "blue", stat = "identity", alpha = .6)+
  theme_minimal() +
  labs(title = "Offense count by offense group for people with 1 conviction")

4

# Q.  For every offense group, 
# how many individuals had at least one conviction with at leasT one offence in this offense group
t4 <- ds %>% 
  dplyr::mutate(
    year = lubridate::year(begin_date)
  ) %>% 
  dplyr::group_by(offense_group, year) %>% 
  dplyr::summarize(
    n_people = length(unique(person_id))
  )  %>% 
  dplyr::ungroup()
  
t4 %>% 
  dplyr::filter(year  %in% 1970:2014) %>% 
  dplyr::filter(offense_group %in% c("A","B","C","D")) %>% 
  ggplot2::ggplot(aes(x = year, y = n_people, color = offense_group))+
  geom_point()+
  geom_line(aes(group = offense_group))+
  geom_vline(xintercept = 1996)+
  theme_minimal() +
  labs(title = "Number of people with at least 1 conviction")

Session Information

For the sake of documentation and reproducibility, the current report was rendered in the following environment. Click the line below to expand.

Environment

- Session info -------------------------------------------------------------------------------------------------------
 setting  value                       
 version  R version 3.5.2 (2018-12-20)
 os       Windows >= 8 x64            
 system   x86_64, mingw32             
 ui       RStudio                     
 language (EN)                        
 collate  English_United States.1252  
 ctype    English_United States.1252  
 tz       America/Los_Angeles         
 date     2019-05-15                  

- Packages -----------------------------------------------------------------------------------------------------------
 package     * version date       lib source        
 assertthat    0.2.1   2019-03-21 [1] CRAN (R 3.5.3)
 backports     1.1.4   2019-04-10 [1] CRAN (R 3.5.3)
 callr         3.2.0   2019-03-15 [1] CRAN (R 3.5.3)
 cellranger    1.1.0   2016-07-27 [1] CRAN (R 3.5.3)
 cli           1.1.0   2019-03-19 [1] CRAN (R 3.5.3)
 codetools     0.2-15  2016-10-05 [2] CRAN (R 3.5.2)
 colorspace    1.4-1   2019-03-18 [1] CRAN (R 3.5.3)
 crayon        1.3.4   2017-09-16 [1] CRAN (R 3.5.3)
 crosstalk     1.0.0   2016-12-21 [1] CRAN (R 3.5.3)
 desc          1.2.0   2018-05-01 [1] CRAN (R 3.5.3)
 devtools      2.0.2   2019-04-08 [1] CRAN (R 3.5.3)
 digest        0.6.18  2018-10-10 [1] CRAN (R 3.5.3)
 dplyr         0.8.0.1 2019-02-15 [1] CRAN (R 3.5.3)
 DT            0.6     2019-05-09 [1] CRAN (R 3.5.3)
 evaluate      0.13    2019-02-12 [1] CRAN (R 3.5.3)
 fansi         0.4.0   2018-10-05 [1] CRAN (R 3.5.3)
 fs            1.3.1   2019-05-06 [1] CRAN (R 3.5.3)
 ggplot2     * 3.1.1   2019-04-07 [1] CRAN (R 3.5.3)
 ggpubr        0.2     2018-11-15 [1] CRAN (R 3.5.3)
 glue          1.3.1   2019-03-12 [1] CRAN (R 3.5.3)
 gtable        0.3.0   2019-03-25 [1] CRAN (R 3.5.3)
 highr         0.8     2019-03-20 [1] CRAN (R 3.5.3)
 hms           0.4.2   2018-03-10 [1] CRAN (R 3.5.3)
 htmltools     0.3.6   2017-04-28 [1] CRAN (R 3.5.3)
 htmlwidgets   1.3     2018-09-30 [1] CRAN (R 3.5.3)
 httpuv        1.5.1   2019-04-05 [1] CRAN (R 3.5.3)
 httr          1.4.0   2018-12-11 [1] CRAN (R 3.5.3)
 jsonlite      1.6     2018-12-07 [1] CRAN (R 3.5.3)
 kableExtra    1.1.0   2019-03-16 [1] CRAN (R 3.5.3)
 knitr       * 1.22    2019-03-08 [1] CRAN (R 3.5.3)
 labeling      0.3     2014-08-23 [1] CRAN (R 3.5.2)
 later         0.8.0   2019-02-11 [1] CRAN (R 3.5.3)
 lazyeval      0.2.2   2019-03-15 [1] CRAN (R 3.5.3)
 lubridate     1.7.4   2018-04-11 [1] CRAN (R 3.5.3)
 magrittr    * 1.5     2014-11-22 [1] CRAN (R 3.5.3)
 memoise       1.1.0   2017-04-21 [1] CRAN (R 3.5.3)
 mime          0.6     2018-10-05 [1] CRAN (R 3.5.2)
 munsell       0.5.0   2018-06-12 [1] CRAN (R 3.5.3)
 pillar        1.3.1   2018-12-15 [1] CRAN (R 3.5.3)
 pkgbuild      1.0.3   2019-03-20 [1] CRAN (R 3.5.3)
 pkgconfig     2.0.2   2018-08-16 [1] CRAN (R 3.5.3)
 pkgload       1.0.2   2018-10-29 [1] CRAN (R 3.5.3)
 plyr          1.8.4   2016-06-08 [1] CRAN (R 3.5.3)
 prettyunits   1.0.2   2015-07-13 [1] CRAN (R 3.5.3)
 processx      3.3.1   2019-05-08 [1] CRAN (R 3.5.2)
 promises      1.0.1   2018-04-13 [1] CRAN (R 3.5.3)
 pryr          0.1.4   2018-02-18 [1] CRAN (R 3.5.3)
 ps            1.3.0   2018-12-21 [1] CRAN (R 3.5.3)
 purrr         0.3.2   2019-03-15 [1] CRAN (R 3.5.3)
 R6            2.4.0   2019-02-14 [1] CRAN (R 3.5.3)
 Rcpp          1.0.1   2019-03-17 [1] CRAN (R 3.5.3)
 readr         1.3.1   2018-12-21 [1] CRAN (R 3.5.3)
 readxl        1.3.1   2019-03-13 [1] CRAN (R 3.5.3)
 remotes       2.0.4   2019-04-10 [1] CRAN (R 3.5.3)
 rlang         0.3.4   2019-04-07 [1] CRAN (R 3.5.3)
 rmarkdown     1.12    2019-03-14 [1] CRAN (R 3.5.3)
 rprojroot     1.3-2   2018-01-03 [1] CRAN (R 3.5.3)
 rstudioapi    0.10    2019-03-19 [1] CRAN (R 3.5.3)
 rvest         0.3.3   2019-04-11 [1] CRAN (R 3.5.3)
 scales        1.0.0   2018-08-09 [1] CRAN (R 3.5.3)
 sessioninfo   1.1.1   2018-11-05 [1] CRAN (R 3.5.3)
 shiny         1.3.2   2019-04-22 [1] CRAN (R 3.5.2)
 stringi       1.4.3   2019-03-12 [1] CRAN (R 3.5.3)
 stringr       1.4.0   2019-02-10 [1] CRAN (R 3.5.3)
 tibble        2.1.1   2019-03-16 [1] CRAN (R 3.5.3)
 tidyselect    0.2.5   2018-10-11 [1] CRAN (R 3.5.3)
 usethis       1.5.0   2019-04-07 [1] CRAN (R 3.5.3)
 utf8          1.1.4   2018-05-24 [1] CRAN (R 3.5.3)
 viridisLite   0.3.0   2018-02-01 [1] CRAN (R 3.5.3)
 webshot       0.5.1   2018-09-28 [1] CRAN (R 3.5.3)
 withr         2.1.2   2018-03-15 [1] CRAN (R 3.5.3)
 xfun          0.6     2019-04-02 [1] CRAN (R 3.5.3)
 xml2          1.2.0   2018-01-24 [1] CRAN (R 3.5.3)
 xtable        1.8-4   2019-04-21 [1] CRAN (R 3.5.3)
 yaml          2.2.0   2018-07-25 [1] CRAN (R 3.5.2)

[1] C:/Users/an499583/Documents/R/win-library/3.5
[2] C:/Program Files/R/R-3.5.2/library

Report rendered by an499583 at 2019-05-15, 17:40 -0700 in 9 seconds.

EDA 1: Basic Questions

I. Exposition

I. Data

II. Development

1

2

3

4

Session Information