Midterm

library(ggplot2)
library(esquisse)
library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✓ tibble  3.1.6     ✓ dplyr   1.0.7
## ✓ tidyr   1.1.4     ✓ stringr 1.4.0
## ✓ readr   2.1.0     ✓ forcats 0.5.1
## ✓ purrr   0.3.4

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(lubridate)

## 
## Attaching package: 'lubridate'

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

library(readxl)
library(dplyr)
library(scales)

## 
## Attaching package: 'scales'

## The following object is masked from 'package:purrr':
## 
##     discard

## The following object is masked from 'package:readr':
## 
##     col_factor

bike_orderlines <- read_excel("bike_orderlines.xlsx")
bike_orderlines$order_date<-factor(format(bike_orderlines$order_date, '%Y'))
year <- unique(bike_orderlines$order_date)
TP <- unique(bike_orderlines$category_2)
revenue <- c()
order_date <- c()
category_2 <- c()
for (i in 1:length(year))
{
  for (j in 1:length(TP))
  {
    result <- 0
    bike_orderlines2 <- dplyr::filter(bike_orderlines, year[i]==order_date, TP[j]==category_2)
    for (z in 1:length(bike_orderlines2$total_price))
      result <- result+bike_orderlines2$total_price[z]
    revenue <- c(revenue, result)
    category_2 <- c(category_2, TP[j])
  }
}
order_date <- c(year[1], year[1], year[1], year[1], year[1], year[1], year[1], year[1], year[1])
for (i in 2:length(year))
{
  for (j in 1:length(TP))
  {
    order_date <- c(order_date, year[i])
  }
}
bike_orderline <- data.frame(order_date, category_2, revenue)

#1,
ggplot(data = bike_orderline, aes(x = order_date, y = revenue, fill = category_2)) +
  scale_fill_hue(direction = 1) +
  labs(y = "Revenue", title = "Revenue By Year") +
  theme_linedraw() +
  theme(legend.position = "bottom")+
  facet_wrap(vars(category_2), scales = "free_y") +
  geom_col() +
  geom_smooth(aes(group=1), method = "lm", se = FALSE)+
  scale_y_continuous(labels = comma)+
  scale_y_continuous(labels=scales::dollar_format())+
  theme(axis.title.x = element_text(size = 1))+
  scale_size_continuous(order_date)

## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.

## `geom_smooth()` using formula 'y ~ x'

#2,
ggplot(data = bike_orderline, aes(x = order_date, y = revenue, fill = category_2)) +
  scale_fill_hue(direction = 1) +
  labs(y = "Revenue", title = "Revenue By Year") +
  theme_linedraw() +
  theme(legend.position = "bottom")+
  facet_wrap(vars(category_2), scales = "free_y") +
  geom_col() +
  geom_smooth(aes(group=1), method = "lm", se = FALSE)+
  scale_y_continuous(labels = comma)+
  scale_y_continuous(labels=scales::dollar_format())+
  theme(axis.title.x = element_text(size = 1))+
  scale_size_continuous(order_date)

## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.
## `geom_smooth()` using formula 'y ~ x'

#3,
bike_orderline$order_date <- as.numeric(as.character(bike_orderline$order_date))
ggplot(bike_orderline) +
  aes(x = order_date, y = revenue, fill = category_2) +
  geom_area(size = 1.5) +
  scale_fill_hue(direction = 1) +
  labs(y = "Revenue",title = "Sales Over Year by Category 2",subtitle = "Sales Trending up",fill = "2nd Category") +
  theme_minimal() + 
  scale_y_continuous(labels = comma)+
  scale_y_continuous(labels=scales::dollar_format())

## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.