Pokemon Scraping

Author

Brian J

Data background

The data I have chosen to scrape for assignment 7 is a Pokemon database. The goal of scraping this database is to gather information about each of the Pokemon and create graphs to compare the different typings and other interesting information like attack and HP. With the link provided, you can see a Pokemon database with all stats of the Pokemon listed. Link: https://pokemondb.net/pokedex/all

Data Visualization

In the first graph, the goal is to show the attack variable by how much HP a Pokemon has. I am guessing that the higher HP a Pokemon has, the lower attack it has. This can be attributed to the idea in Pokemon that larger Pokemon have a higher hp level.

The next thing I wanted to look at is the relationship between defense and attack. My theory behind this is that if a Pokemon has an extraordinary amount of one, than the other must be low to even the stats out.

Looking at this graph, the correlation shows that my hypothesis was wrong. There is a direct correlation between defense and offense. This must show that with stronger pokemon, both defense and offense improve.

A common occurrence when people play Pokemon video games is the tough decision of what starter to choose out of the types fire, water, and grass. The graph below shows the attacks of all grass type Pokemon on a box plot. As you can see below, when observing the typing through attack, fire and water appear ahead of grass. Additionally, there are two outliers which are very strong Pokemon with high attack levels, these could by legendary Pokemon which skew the data.

A belief I have seen in Pokemon players is that higher HP leads to slower speed. The goal of this visualization is identify any correlation between the two and determine if this belief is based on truth. Below, it shows a smaller correlation between the two. An element I decided to add is color based on attack to show how strong the attacks are for the Pokemon being plotted.

The Final analysis I wanted to perform is the Pokemon with highest combined stats. The visualization shows that all of the Pokemon with the highest totals are legendary or mythic Pokemon.

--- title: "Pokemon Scraping" author: "Brian J" editor: visual toc: true # Generates an automatic table of contents. format: # Options related to formatting. html: # Options related to HTML output. code-tools: TRUE # Allow the code tools option showing in the output. embed-resources: TRUE # Embeds all components into a single HTML file. execute: # Options related to the execution of code chunks. warning: FALSE # FALSE: Code chunk sarnings are hidden by default. message: FALSE # FALSE: Code chunk messages are hidden by default. echo: FALSE # TRUE: Show all code in the output. --- ## Data background The data I have chosen to scrape for assignment 7 is a Pokemon database. The goal of scraping this database is to gather information about each of the Pokemon and create graphs to compare the different typings and other interesting information like attack and HP. With the link provided, you can see a Pokemon database with all stats of the Pokemon listed. Link: <https://pokemondb.net/pokedex/all> ## Data Visualization ```{r} library(tidyverse) library(httr) library(rvest) library(polite) library(lubridate) library(magrittr) library(dplyr) library(jsonlite) library(tidyr) library(writexl) library(readxl) ``` ```{r} pokemon_table <- read_csv("https://myxavier-my.sharepoint.com/:x:/g/personal/janishefskib_xavier_edu/ESvu9ZrYeilHoW76r7fUsIcB7JAQ3WWUQ0i1BvyNXrcjHw?download=1") ``` In the first graph, the goal is to show the attack variable by how much HP a Pokemon has. I am guessing that the higher HP a Pokemon has, the lower attack it has. This can be attributed to the idea in Pokemon that larger Pokemon have a higher hp level. ```{r} ggplot(pokemon_table, aes(x = HP, y = Attack)) + geom_point(aes(), size = 2, alpha = 0.7) + labs(title = "Scatter Plot of HP vs Attack", x = "HP", y = "Attack") + geom_smooth(method = "lm", se = FALSE, color = "blue") ``` The next thing I wanted to look at is the relationship between defense and attack. My theory behind this is that if a Pokemon has an extraordinary amount of one, than the other must be low to even the stats out. ```{r} ggplot(pokemon_table, aes(x = Defense, y = Attack)) + geom_point(aes(), size = 2, alpha = 0.7) + labs(title = "Scatter Plot of Defense vs Attack", x = "Defense", y = "Attack") + geom_smooth(method = "lm", se = FALSE, color = "blue") ``` Looking at this graph, the correlation shows that my hypothesis was wrong. There is a direct correlation between defense and offense. This must show that with stronger pokemon, both defense and offense improve. A common occurrence when people play Pokemon video games is the tough decision of what starter to choose out of the types fire, water, and grass. The graph below shows the attacks of all grass type Pokemon on a box plot. As you can see below, when observing the typing through attack, fire and water appear ahead of grass. Additionally, there are two outliers which are very strong Pokemon with high attack levels, these could by legendary Pokemon which skew the data. ```{r} attack_pokemon <- pokemon_table %>% filter(Type %in% c("Water", "Fire", "Grass")) ggplot(attack_pokemon, aes(x = Type, y = Attack, fill = Type)) + geom_boxplot(alpha = 0.7) + labs(title = "Attack strengths of Water, Fire, and Grass Types", x = "Type", y = "Attack Strength") + theme_minimal() ``` A belief I have seen in Pokemon players is that higher HP leads to slower speed. The goal of this visualization is identify any correlation between the two and determine if this belief is based on truth. Below, it shows a smaller correlation between the two. An element I decided to add is color based on attack to show how strong the attacks are for the Pokemon being plotted. ```{r} ggplot(pokemon_table, aes(x = HP, y = Speed)) + geom_point(aes(color = Attack), size = 2, alpha = 0.7) + labs(title = "Scatter Plot of HP vs Speed by Pokémon Type", x = "HP", y = "Speed") + theme_minimal() + theme(legend.position = "right")+ geom_smooth(method = "lm") ``` The Final analysis I wanted to perform is the Pokemon with highest combined stats. The visualization shows that all of the Pokemon with the highest totals are legendary or mythic Pokemon. ```{r} top_10 <- pokemon_table %>% arrange(desc(Total)) %>% slice_head(n = 10) ggplot(top_10, aes(x = reorder(Name, Total), y = Total)) + geom_bar(stat = "identity", fill = "pink") + labs(title = "Top 10 Pokémon by Total Stats", x = "Pokémon", y = "Total Stats") + theme_minimal() + coord_flip() ```