R Notebook

library(readr)
fraudTest <- read_csv("fraudTest.csv")

New names:
• `` -> `...1`
Rows: 555719 Columns: 23
── Column specification ───────────────────────────────────────────────────────────────
Delimiter: ","
chr (12): trans_date_trans_time, merchant, category, first, last, gender, street, c...
dbl (11): ...1, cc_num, amt, zip, lat, long, city_pop, unix_time, merch_lat, merch_...

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

View(fraudTest)

library(tidyverse)
library(dplyr)
library(ggthemes)

Warning: package ‘ggthemes’ was built under R version 4.4.2

library(ggplot2)

#Histogram

fraudTest %>% filter(is_fraud == 1) %>% ggplot(aes(x=amt)) + 
geom_histogram(bins=30, fill="blue", color="black") +
  ggtitle("Transaction Amount Distribution for is Fraud")

#Fraud Transactions by Cat

#Anova Test

# Summary of the ANOVA results
summary(anova_result)

              Df    Sum Sq  Mean Sq F value Pr(>F)    
time_of_day    3  35533019 11844340   85.91 <2e-16 ***
Residuals   2141 295180423   137870                   
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

#Map Vis

state_abbreviations <- data.frame(
  abbr = state.abb,         
  name = tolower(state.name)  
)

# Step 2: Convert abbreviations in fraudTest to full state names

fraud_data <- fraudTest %>%
  filter(is_fraud == 1) %>%                    
  group_by(state) %>%                         
  summarize(is_fraud = n()) %>%             
  left_join(state_abbreviations, by = c("state" = "abbr")) %>% 
  rename(state_full = name)                    

# Step 3: Prepare the US states spatial data

us_states <- us_states %>%
  mutate(state = tolower(ID)) %>%              
  left_join(fraud_data, by = c("state" = "state_full")) 

# Step 4: Create the 

us_mp <- ggplot(data = us_states) +
  geom_sf(aes(fill = is_fraud), color = "white") + 
  scale_fill_gradient(
    low = "lightblue", high = "red",
    name = "Fraud Count"
  ) +
  theme_minimal() +
  labs(
    title = "Fraud Incidents by State",
    subtitle = "Highlighting states with the highest number of fraud incidents"
  )


us_mp