Data set 2 - Pokemon

library(dplyr)
## Warning: package 'dplyr' was built under R version 4.4.2
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(stringr)
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.4.2
library(tidyr)
library(forcats)

url <- "https://raw.githubusercontent.com/j-song-npc/607-Project-2-/refs/heads/main/pokemon_competitive_analysis(1).csv"
pokemon_df <- read.csv(url) 
View(pokemon_df)

Split columns

pokemon <- pokemon_df %>%
  mutate(
    Smogon_VGC_Use_2022 = ifelse(Smogon_VGC_Usage_2022 == "NoUsage" | Smogon_VGC_Usage_2022 == 0, "NoUsage", NA),
    Smogon_VGC_Usage_Rate_2022 = ifelse(Smogon_VGC_Usage_2022 != "NoUsage" &  Smogon_VGC_Usage_2022 !=0, Smogon_VGC_Usage_2022, NA),
     Smogon_VGC_Use_2023 = ifelse(Smogon_VGC_Usage_2023 == "NoUsage" | Smogon_VGC_Usage_2023 == 0, "NoUsage", NA),
    Smogon_VGC_Usage_Rate_2023 = ifelse(Smogon_VGC_Usage_2023 != "NoUsage" &  Smogon_VGC_Usage_2023 !=0, Smogon_VGC_Usage_2023, NA), 
     Smogon_VGC_Use_2024 = ifelse(Smogon_VGC_Usage_2024 == "NoUsage" | Smogon_VGC_Usage_2024 == 0, "NoUsage", NA),
    Smogon_VGC_Usage_Rate_2024 = ifelse(Smogon_VGC_Usage_2024 != "NoUsage" &  Smogon_VGC_Usage_2024 !=0, Smogon_VGC_Usage_2024, NA),
    Worlds_VGC_Use_2022 = ifelse(Worlds_VGC_Usage_2022 == "NoUsage" | Worlds_VGC_Usage_2022 == 0, "NoUsage", NA),
    Worlds_VGC_Usage_Rate_2022 = ifelse(Worlds_VGC_Usage_2022 != "NoUsage" &  Worlds_VGC_Usage_2022 !=0, Worlds_VGC_Usage_2022, NA),
    Worlds_VGC_Use_2023 = ifelse(Worlds_VGC_Usage_2023 == "NoUsage" | Worlds_VGC_Usage_2023 == 0, "NoUsage", NA),
    Worlds_VGC_Usage_Rate_2023 = ifelse(Worlds_VGC_Usage_2023 != "NoUsage" &  Worlds_VGC_Usage_2023 !=0, Worlds_VGC_Usage_2023, NA),
    Worlds_VGC_Use_2024 = ifelse(Worlds_VGC_Usage_2024 == "NoUsage" | Worlds_VGC_Usage_2024 == 0, "NoUsage", NA),
    Worlds_VGC_Usage_Rate_2024 = ifelse(Worlds_VGC_Usage_2024 != "NoUsage" &  Worlds_VGC_Usage_2024 !=0, Worlds_VGC_Usage_2024, NA))

Clean table

pokemon <- pokemon %>%
  mutate(
    Smogon_VGC_Use_2022 = ifelse(is.na(Smogon_VGC_Use_2022), "Yes", Smogon_VGC_Use_2022),
    Smogon_VGC_Use_2023 = ifelse(is.na(Smogon_VGC_Use_2023), "Yes", Smogon_VGC_Use_2023),
    Smogon_VGC_Use_2024 = ifelse(is.na(Smogon_VGC_Use_2024), "Yes", Smogon_VGC_Use_2024),
    Worlds_VGC_Use_2022 = ifelse(is.na(Worlds_VGC_Use_2022), "Yes", Worlds_VGC_Use_2022),
    Worlds_VGC_Use_2023 = ifelse(is.na(Worlds_VGC_Use_2023), "Yes", Worlds_VGC_Use_2023),
    Worlds_VGC_Use_2024 = ifelse(is.na(Worlds_VGC_Use_2024), "Yes", Worlds_VGC_Use_2024),
  )

pokemon <- pokemon %>%
  select(-Smogon_VGC_Usage_2022, -Smogon_VGC_Usage_2023, -Smogon_VGC_Usage_2024, -Worlds_VGC_Usage_2022, -Worlds_VGC_Usage_2023, -Worlds_VGC_Usage_2024)

Analysis

My analysis is aimed to see if there is a relationship between type of pokemon vs usage in game.

pokemon_long <- pokemon %>%
  pivot_longer(cols=c(Smogon_VGC_Usage_Rate_2022, Smogon_VGC_Usage_Rate_2023, Smogon_VGC_Usage_Rate_2024, Worlds_VGC_Usage_Rate_2022, Worlds_VGC_Usage_Rate_2023, Worlds_VGC_Usage_Rate_2024), 
               names_to="Tournament",
               values_to= "usage",
               values_drop_na = TRUE) %>%

  pivot_longer(cols = c("type1", "type2"),  
               names_to = "TypeLabel",      
               values_to = "Type",
               values_drop_na = TRUE) %>%
  filter(Type != "No_type")

ggplot(pokemon_long, aes(x = fct_infreq(Type), fill = Tournament)) + 
  geom_bar(position="stack") +
  labs(title = "Pokemon type vs usage",
x = "Pokemon Type",
y = "Usage in tournament") + 
  coord_flip()

Conclusion

Water pokemon were used most frequently and ice pokemon used the least when looking across all tournaments.