Cleaning and Exploring Data from the 2024 Men’s VNL Scoring Statistics

VNL Match - Canada vs. Cuba

Introduction

This dataset is by Jonathan Moyer on the 2024 Volleyball National League (VNL) statistics. There are multiple datasets by Moyer on the 2024 VNL, but I will be focusing on the Men’s VNL scorers dataset that displays all points scored by attacking, blocking, and serving, along with the team name and player for each statistic.

Links to R Package and Dataset

• Janitor Package
• Kaggle - VNL 2024 Men’s Volleyball Stats

Exploring Janitor Package

The Janitor Package in R allows for quicker and easier data exploration and cleaning. The functions I will be exploring in this package are:

• cleaning_names()
• describe_class()
• taybl()

Cleaning

Using clean_names() function to clean dataframe names.

Cleaning Column Names

VNL2024Men_Scorers[1,]

##    Name Team Tot_Pts Tot_Atk Tot_Block Tot_Serve
## 1 Conte  ARG     121     101        11         9

Here are the names of the columns before cleaning.

VNL2024Men_Scorers <- clean_names(VNL2024Men_Scorers)
VNL2024Men_Scorers[1,]

##    name team tot_pts tot_atk tot_block tot_serve
## 1 Conte  ARG     121     101        11         9

This dataset is quite clean, however, the original column names contained capitals. Using the clean_names() function, it took away the capitals to allow for easier coding and consistency.

Cleaning

Using describe_class() to check the class of specific variables in the dataset.

Describing Class

describe_class(VNL2024Men_Scorers$tot_pts)

## [1] "integer"

describe_class(VNL2024Men_Scorers$team)

## [1] "character"

This features allows me to look into the class of the variable, which can be a quick and useful method for verifying.

Exploring

Using tabyl() function with adorn_ functions to enhance table.

Bottom 10 Points Scored

head(VNL2024Men_Scorers %>% tabyl(tot_pts, show_na = FALSE) %>% adorn_totals() %>% adorn_pct_formatting() %>% adorn_title(placement = "top"), 11)

##                <NA>
##  tot_pts  n percent
##        0 61   20.7%
##        1 13    4.4%
##        2  6    2.0%
##        3  5    1.7%
##        4  4    1.4%
##        5  4    1.4%
##        6  4    1.4%
##        7  6    2.0%
##        8  5    1.7%
##        9  2    0.7%

Top 10 Points Scored

tail(VNL2024Men_Scorers %>% tabyl(tot_pts, show_na = FALSE) %>% adorn_totals() %>% adorn_pct_formatting() %>% adorn_title(), 11)

##              <NA>
##    170   2   0.7%
##    178   2   0.7%
##    180   1   0.3%
##    185   2   0.7%
##    195   2   0.7%
##    196   1   0.3%
##    218   1   0.3%
##    225   1   0.3%
##    284   1   0.3%
##    320   1   0.3%
##  Total 294 100.0%

Using head() and tail() to make it easier to display as an example, using the tabyl() function allows for me to see the top and bottom amount of points scored with the proportion of players achieveing those scores. A decent percentage of players did not score any points during the VNL.

Top VNL Scorer

##         name team tot_pts tot_atk tot_block tot_serve
## 233 T. Stern  SLO     320     265        24        31

Volleybox - T. Stern Page

Using the information from the tabyl() function, I found that Tonek Stern of Slovenia scored the highest amount of points in the VNL. Though they did not make it onto the podium (placed fourth), Stern made a huge impact on get them that high in the rankings.

Reflection

Final Thoughts

Exploring this package with this dataset was very informational and came with its challenges. Finding messy data was challenging for me, and is something I want to focus on in the future. Because this data was quite clean, it made it challenging to find functions in the package that would produce interesting outcomes.

The name cleaning function makes it easy to create clean variable names quickly, which I think will be very useful in future projects. This goes along with the class describing function, where it may be very useful for large datasets with many columns. The tabyl() function along with the adorn_ add ons makes it extremely easy to make a clean table. Next time, it will be extremely useful for categorical variables, as the function is not quite meant for quantitative variables. I do, however, find the percentages of people who got those amount of points interesting because it revealed that a good amount of people did not score any points in the VNL.

I enjoyed the challenge of figuring out funtions to use on my own and will use what I have learned from this min-project for all my future projects.