R_Activity_4

library(dplyr)
library(stringr)

#Loading the CSV fike
pokemon_data <- read.csv("pokemon-go-raw-data-form.csv")

#remove duplicate rows
pokemon_data <- pokemon_data%>%
  distinct()

#Unification of Weather
pokemon_data$Weather <- gsub("cloudy","Cloudy",pokemon_data$Weather)
 
#Unifing the type of pokeball from duplicit names
pokemon_data$Type.of.Pokeball <- gsub("pokeball","regular",pokemon_data$Type.of.Pokeball)

#renames the type of catch to have same results
pokemon_data <- pokemon_data %>%
  mutate(Type.of.catch = case_when(
    Type.of.catch %in% c("regular", "reg") ~ "regular",
    Type.of.catch %in% c("nice", "n") ~ "nice",
    Type.of.catch %in% c("great", "g") ~ "great",
    Type.of.catch %in% c("excellent", "ex") ~ "excellent",
    TRUE ~ Type.of.catch 
  ))

#Removes the row with missing value in the type of catch
pokemon_data <- pokemon_data %>%
  filter(!is.na(Type.of.catch) & Type.of.catch != "")

#Mutation of names so for duplicates pokemon they are the same
pokemon_data <- pokemon_data %>%
  mutate(Name = str_to_title(Name),
         Weather = str_to_title(Weather),
         Type.A = str_to_title(Type.A),
         Type.B = str_to_title(Type.B),
         Type.of.Pokeball = str_to_title(Type.of.Pokeball),
         Type.of.catch = str_to_title(Type.of.catch)
         )

#Removes the N/A rows
pokemon_data <- pokemon_data %>%
  drop_na()

View(pokemon_data)

ggplot(pokemon_data, aes(x = Name)) +
  geom_bar(fill = "steelblue") +
  labs(title = "Frequency of Pokémon Caught", x = "Pokémon", y = "Count") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))

ggplot(pokemon_data, aes(x = Type.A, y = CP, fill = Type.A)) +
  geom_boxplot() +
  labs(title = "Combat Power Distribution by Pokémon Type", x = "Type", y = "CP")

regular_pokeball_data <- pokemon_data %>%
  filter(Type.of.Pokeball == "Regular")

# Create the plot
ggplot(regular_pokeball_data, aes(x = Type.A, y = CP, fill = Type.A)) +
  geom_boxplot() +
  labs(title = "Combat Power Distribution for Regular Pokéball by Pokémon Type", x = "Type", y = "CP")

ggplot(pokemon_data, aes(x = Location, y = CP, color = Type.A)) +
  geom_point(size = 3, alpha = 0.7) + # Adjust size and transparency of points
  labs(title = "Combat Power (CP) by Location", x = "Location", y = "Combat Power (CP)") 

pokeball_data <- pokemon_data %>%
  group_by(Type.of.Pokeball) %>%
  summarise(Count = n(), .groups = 'drop')

ggplot(pokeball_data, aes(x = "", y = Count, fill = Type.of.Pokeball)) +
  geom_bar(stat = "identity", width = 1) +
  coord_polar("y") +
  labs(title = "Distribution of Pokéball Types", fill = "Type of Pokéball")

ggplot(pokemon_data, aes(x = CP)) +
  geom_histogram(binwidth = 50, fill = "blue", color = "black", alpha = 0.7) +
  labs(title = "Distribution of Combat Power (CP)", x = "Combat Power (CP)", y = "Frequency")