Goal is to predict Spam Emails from key words

library(tidyverse)
## Warning: package 'ggplot2' was built under R version 4.3.3
## Warning: package 'forcats' was built under R version 4.3.3
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(correlationfunnel)
## Warning: package 'correlationfunnel' was built under R version 4.3.3
## ══ correlationfunnel Tip #1 ════════════════════════════════════════════════════
## Make sure your data is not overly imbalanced prior to using `correlate()`.
## If less than 5% imbalance, consider sampling. :)
spam <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2023/2023-08-15/spam.csv')
## Rows: 4601 Columns: 7
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): yesno
## dbl (6): crl.tot, dollar, bang, money, n000, make
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Clean data

skimr::skim(spam)
Data summary
Name spam
Number of rows 4601
Number of columns 7
_______________________
Column type frequency:
character 1
numeric 6
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
yesno 0 1 1 1 0 2 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
crl.tot 0 1 283.29 606.35 1 35 95 266.00 15841.00 ▇▁▁▁▁
dollar 0 1 0.08 0.25 0 0 0 0.05 6.00 ▇▁▁▁▁
bang 0 1 0.27 0.82 0 0 0 0.32 32.48 ▇▁▁▁▁
money 0 1 0.09 0.44 0 0 0 0.00 12.50 ▇▁▁▁▁
n000 0 1 0.10 0.35 0 0 0 0.00 5.45 ▇▁▁▁▁
make 0 1 0.10 0.31 0 0 0 0.00 4.54 ▇▁▁▁▁ 
factors_vec <- spam %>% select(crl.tot,dollar, bang, money, n000, make, yesno) %>% names()

data_clean <- spam %>%
    # address factors imported as numeric
    mutate(across(all_of(factors_vec), as.factor))

Explore Data

data_clean %>% count(yesno)
## # A tibble: 2 × 2
##   yesno     n
##   <fct> <int>
## 1 n      2788
## 2 y      1813
data_clean %>% 
    ggplot(aes(yesno)) +
    geom_bar()

Correlation plot

# step one: Binarize
data_binarized <- data_clean %>%
    binarize()

data_binarized %>% glimpse()
## Rows: 4,601
## Columns: 19
## $ crl.tot__4        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ crl.tot__5        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ crl.tot__6        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ crl.tot__7        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ crl.tot__9        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ `crl.tot__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ dollar__0         <dbl> 1, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0…
## $ `dollar__-OTHER`  <dbl> 0, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1…
## $ bang__0           <dbl> 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0…
## $ `bang__-OTHER`    <dbl> 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1…
## $ money__0          <dbl> 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1…
## $ `money__-OTHER`   <dbl> 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0…
## $ n000__0           <dbl> 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 0…
## $ `n000__-OTHER`    <dbl> 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1…
## $ make__0           <dbl> 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1…
## $ make__0.1         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ `make__-OTHER`    <dbl> 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0…
## $ yesno__n          <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
## $ yesno__y          <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
# Step two: Correlation
data_correlation <- data_binarized %>%
    correlate(yesno__y)

data_correlation
## # A tibble: 19 × 3
##    feature bin    correlation
##    <fct>   <chr>        <dbl>
##  1 yesno   n          -1     
##  2 yesno   y           1     
##  3 bang    0          -0.553 
##  4 bang    -OTHER      0.553 
##  5 dollar  0          -0.539 
##  6 dollar  -OTHER      0.539 
##  7 money   -OTHER      0.475 
##  8 money   0          -0.475 
##  9 n000    0          -0.419 
## 10 n000    -OTHER      0.419 
## 11 make    0          -0.239 
## 12 make    -OTHER      0.223 
## 13 crl.tot -OTHER      0.212 
## 14 crl.tot 5          -0.126 
## 15 crl.tot 9          -0.0906
## 16 make    0.1         0.0803
## 17 crl.tot 6          -0.0802
## 18 crl.tot 4          -0.0775
## 19 crl.tot 7          -0.0769
# Step three: plot
data_correlation %>%
    correlationfunnel::plot_correlation_funnel()