Module 5 Visualization Lab

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6     ✔ purrr   0.3.4
## ✔ tibble  3.1.8     ✔ dplyr   1.0.9
## ✔ tidyr   1.2.0     ✔ stringr 1.4.1
## ✔ readr   2.1.2     ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(completejourney)

## Welcome to the completejourney package! Learn more about these data
## sets at http://bit.ly/completejourney.

library(dplyr)
library(lubridate)

## 
## Attaching package: 'lubridate'
## 
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

transactions <- get_transactions()
transactions

promotions <- get_promotions()
promotions

#plot 1, total sales for fruits and vegetables based on income and age
transactions %>%
  inner_join (demographics) %>%
  inner_join(products)%>%
  filter(str_detect(product_category, "FRUIT|VEGETABLE"))%>%
  group_by(income, age)%>%
  summarize(total = sum(sales_value, na.rm = TRUE))%>%
  mutate(label_y = cumsum(total))%>%
  ggplot(aes(x = income, y = total, fill = age)) +
  geom_histogram(stat="identity") +
  scale_y_continuous(name = "Total Cost", labels = scales::dollar) +
  theme(axis.text.x=element_text(size=5))+
  labs(x = "Income Range")+
  ggtitle("Total Cost of Fruits and Vegetables Based on Income and Age")

## Joining, by = "household_id"
## Joining, by = "product_id"
## `summarise()` has grouped output by 'income'. You can override using the
## `.groups` argument.

## Warning: Ignoring unknown parameters: binwidth, bins, pad

#plot 2, monthly total sales for just food items
products %>%
  filter(str_detect(department,"DELI|FROZEN GROCERY|GROCERY|MEAT|MEAT-PCKGD|NUTRITION|PASTRY|PROD-WHS SALES|PRODUCE|SALAD BAR|SEAFOOD| SEAFOOD-PCKGD"))%>%
  inner_join(transactions)%>%
  mutate(month = month(transaction_timestamp, label = TRUE)) %>%
  group_by(month, department)%>%
  summarize(total = sum(sales_value, na.rm = TRUE))%>%
  ggplot(aes(x=month,y=total, color = department))+
  geom_point()+
  scale_y_log10(name = "Total Cost", labels = scales::dollar)+
  labs(x = "Month")+
  ggtitle("Total Cost of Food Per Month Based on Department")

## Joining, by = "product_id"
## `summarise()` has grouped output by 'month'. You can override using the
## `.groups` argument.

#plot 3, savings amount each day for frozen items
transactions %>%
  mutate(Weekday = wday(transaction_timestamp, label = TRUE))%>%
  inner_join(products)%>%
  filter(str_detect(product_category, "FROZEN|FRZN"))%>%
  group_by(Weekday, coupon_disc, product_category)%>%
  summarize(totals = sum(coupon_disc, na.rm = TRUE))%>%
  ggplot(aes(y=totals,x=Weekday))+
  geom_boxplot() +
  labs(x = "Weekday", y = "Total Savings")+
  ggtitle("Range of Total Amount Saved Each Day on Frozen Items")

## Joining, by = "product_id"
## `summarise()` has grouped output by 'Weekday', 'coupon_disc'. You can override
## using the `.groups` argument.