module 5 lab Wade Burke

``` r
library(ggplot2)
library(dplyr)   

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1
## ✔ readr     2.1.5

## ── 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.

#plot one 
transactions <- transactions_sample

transactions %>% 
  inner_join(demographics) %>%
  group_by(age) %>%
  summarize(average_sales = mean(sales_value)) %>%
  ggplot(aes(x = age, y = average_sales)) + 
  geom_col(color = 'blue') +
  ggtitle('Age Ranges vs Average Sales Value') + 
  labs(x = 'Age Ranges', y = 'Average Sales Value') +
  scale_y_continuous(breaks = seq(0, 4, by = .1))

## Joining with `by = join_by(household_id)`

transactions %>%
  inner_join(demographics) %>%
  group_by(income) %>%
  summarize(average_quantity = mean(quantity)) %>%
  ggplot(aes(x = income, y = average_quantity)) +
  geom_point(color = 'red') +
  ggtitle('Income Levels vs Average Quantity of Goods') +
  labs(x = 'income level', y = 'Average Quantity')

## Joining with `by = join_by(household_id)`

transactions %>%
  inner_join(demographics) %>%
  group_by(income) %>%
  summarize(total_sales_value = sum(sales_value)) %>%
  ggplot(aes(x = total_sales_value, y = income)) +
  geom_col(color = 'green') +
  ggtitle('Total Sales Value vs Income Range') +
  labs(x = 'Total Sales Value', y = 'Income Ranges')

## Joining with `by = join_by(household_id)`