Setting up analytics environment

Notes: Setting up my R environment by loading tidyverse and palmerpenguins packages after their installation via renv.

library(tidyverse)
## ── 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   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4     
## ── 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(ggplot2)
library(palmerpenguins)
## 
## Attaching package: 'palmerpenguins'
## 
## The following objects are masked from 'package:datasets':
## 
##     penguins, penguins_raw
library(here)
## here() starts at C:/workspace/da-with-r
library(skimr)
library(janitor)
## 
## Attaching package: 'janitor'
## 
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test
library(dplyr)
library(SimDesign)

Simple EDA

Conducting basic EDA for penguins dataset:

head(penguins)
## # A tibble: 6 × 8
##   species island    bill_length_mm bill_depth_mm flipper_length_mm body_mass_g
##   <fct>   <fct>              <dbl>         <dbl>             <int>       <int>
## 1 Adelie  Torgersen           39.1          18.7               181        3750
## 2 Adelie  Torgersen           39.5          17.4               186        3800
## 3 Adelie  Torgersen           40.3          18                 195        3250
## 4 Adelie  Torgersen           NA            NA                  NA          NA
## 5 Adelie  Torgersen           36.7          19.3               193        3450
## 6 Adelie  Torgersen           39.3          20.6               190        3650
## # ℹ 2 more variables: sex <fct>, year <int>
tail(penguins)
## # A tibble: 6 × 8
##   species   island bill_length_mm bill_depth_mm flipper_length_mm body_mass_g
##   <fct>     <fct>           <dbl>         <dbl>             <int>       <int>
## 1 Chinstrap Dream            45.7          17                 195        3650
## 2 Chinstrap Dream            55.8          19.8               207        4000
## 3 Chinstrap Dream            43.5          18.1               202        3400
## 4 Chinstrap Dream            49.6          18.2               193        3775
## 5 Chinstrap Dream            50.8          19                 210        4100
## 6 Chinstrap Dream            50.2          18.7               198        3775
## # ℹ 2 more variables: sex <fct>, year <int>
colnames(penguins)
## [1] "species"           "island"            "bill_length_mm"   
## [4] "bill_depth_mm"     "flipper_length_mm" "body_mass_g"      
## [7] "sex"               "year"
skim_without_charts(penguins)
Data summary
Name penguins
Number of rows 344
Number of columns 8
_______________________
Column type frequency:
factor 3
numeric 5
________________________
Group variables None

Variable type: factor

skim_variable n_missing complete_rate ordered n_unique top_counts
species 0 1.00 FALSE 3 Ade: 152, Gen: 124, Chi: 68
island 0 1.00 FALSE 3 Bis: 168, Dre: 124, Tor: 52
sex 11 0.97 FALSE 2 mal: 168, fem: 165

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100
bill_length_mm 2 0.99 43.92 5.46 32.1 39.23 44.45 48.5 59.6
bill_depth_mm 2 0.99 17.15 1.97 13.1 15.60 17.30 18.7 21.5
flipper_length_mm 2 0.99 200.92 14.06 172.0 190.00 197.00 213.0 231.0
body_mass_g 2 0.99 4201.75 801.95 2700.0 3550.00 4050.00 4750.0 6300.0
year 0 1.00 2008.03 0.82 2007.0 2007.00 2008.00 2009.0 2009.0 
glimpse(penguins)
## Rows: 344
## Columns: 8
## $ species           <fct> Adelie, Adelie, Adelie, Adelie, Adelie, Adelie, Adel…
## $ island            <fct> Torgersen, Torgersen, Torgersen, Torgersen, Torgerse…
## $ bill_length_mm    <dbl> 39.1, 39.5, 40.3, NA, 36.7, 39.3, 38.9, 39.2, 34.1, …
## $ bill_depth_mm     <dbl> 18.7, 17.4, 18.0, NA, 19.3, 20.6, 17.8, 19.6, 18.1, …
## $ flipper_length_mm <int> 181, 186, 195, NA, 193, 190, 181, 195, 193, 190, 186…
## $ body_mass_g       <int> 3750, 3800, 3250, NA, 3450, 3650, 3625, 4675, 3475, …
## $ sex               <fct> male, female, female, NA, female, male, female, male…
## $ year              <int> 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007…

Data Cleaning

clean_names(penguins)
## # A tibble: 344 × 8
##    species island    bill_length_mm bill_depth_mm flipper_length_mm body_mass_g
##    <fct>   <fct>              <dbl>         <dbl>             <int>       <int>
##  1 Adelie  Torgersen           39.1          18.7               181        3750
##  2 Adelie  Torgersen           39.5          17.4               186        3800
##  3 Adelie  Torgersen           40.3          18                 195        3250
##  4 Adelie  Torgersen           NA            NA                  NA          NA
##  5 Adelie  Torgersen           36.7          19.3               193        3450
##  6 Adelie  Torgersen           39.3          20.6               190        3650
##  7 Adelie  Torgersen           38.9          17.8               181        3625
##  8 Adelie  Torgersen           39.2          19.6               195        4675
##  9 Adelie  Torgersen           34.1          18.1               193        3475
## 10 Adelie  Torgersen           42            20.2               190        4250
## # ℹ 334 more rows
## # ℹ 2 more variables: sex <fct>, year <int>
bias(penguins$flipper_length_mm, penguins_raw$`Flipper Length (mm)`)
## [1] NA

Data Viz

base <- ggplot(data = penguins) +
  geom_point(mapping = aes(x=flipper_length_mm, y=body_mass_g, color=species)) +
  labs(title = 'Palmer Penguins: Body Mass vs. Flipper Length', subtitle = 'Sample of Three Penguins Species',
       caption = 'Data collected by Dr. Kristen Gorman in 2007-2009')

base + annotate('text', x=220, y=3500, label='The Gentoos are the largest', color='medium blue',
             fontface='bold', size=4.5, angle=25)
## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).