library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.0
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(completejourney)
## Welcome to the completejourney package! Learn more about these data
## sets at http://bit.ly/completejourney.
library(dplyr)
library(ggplot2)

transactions = transactions_sample
view(transactions)






#1 amount of Cerealsales by day of week

products_day <- products %>%
  filter(str_detect(product_category, regex("(COLD CEREAL)|(HOT CEREAL)"))) %>%
  inner_join(transactions, by = "product_id") %>%
  group_by(wday1 = wday(transaction_timestamp, label = TRUE)) %>%
  summarise(total_sales = sum(sales_value, na.rm = TRUE))
barplot_sales <- ggplot(products_day, aes(x = wday1, y = total_sales, fill = wday1)) +
  geom_bar(stat = "identity") +
  labs(x = "Day of Week", y = "Total Sales", title = "Total Sales of Cereals by Day of Week") +
  scale_fill_brewer(palette = "Set3")


print(barplot_sales)

#2 amount of coupons used by household income 

coupon_counts <- coupon_redemptions %>%
  group_by(household_id) %>%
  summarise(total_coupons = n_distinct(coupon_upc)) %>%
  inner_join(demographics, by = "household_id") %>%
  filter(!(income %in% c("200-249K", "250K+"))) %>%
  select(total_coupons, income)



boxplot <- ggplot(coupon_counts, aes(x = as.factor(income), y = total_coupons, fill = as.factor(income))) +
  geom_boxplot() +
  scale_fill_brewer(palette = "Set3") +  
  labs(x = "Household Income", y = "Total Coupons Used", title = "Distribution of Total Coupons Used by Household Income")


print(boxplot)

#3 Vegetables and kids 
  
merged_data <- inner_join(transactions, demographics, by = "household_id")
vegetables_data <- inner_join(merged_data, products, by = "product_id") %>%
    filter(str_detect(product_category, "VEGETABLES")) %>%
    group_by(kids_count, household_id, product_id) %>%
    summarise(total_vegetable_sales = sum(sales_value, na.rm = TRUE))
## `summarise()` has grouped output by 'kids_count', 'household_id'. You can
## override using the `.groups` argument.
  scatter_plot <- ggplot(vegetables_data, aes(x = household_id, y = total_vegetable_sales, color = factor(kids_count))) +
    geom_point() +
    scale_color_brewer(palette = "Set3") +
    labs(x = "Household ID", y = "Total Vegetable Sales", title = "Amount of vegetebles bought by Households with a differnt number of kids
         ") +
    labs(color = "Number of Kids") +  
    theme(legend.position = "bottom")  
  

  print(scatter_plot)