Amazon books Visualization

---
title: "Amazon books Final"
author: "Jeff Fossi"
date: "2022-10-14"
output: html_document
---
```{r}
# Importing libraries
library(flexdashboard)
library(tidyverse)
library(highcharter)
library(gt)
library(htmltools)
library(viridis)
library(readr)
library(dplyr)
```

```{r}
# Importing data
df2 <- read_csv('C:/Users/jmf_a/OneDrive/BDAT 630 Data Visualization/final/AmazonBestSellers2013-2022Books.csv', show_col_types = FALSE)
```

```{r}
head(df2)
```
```{r}
df2 <- select(df2, 'rank', 'title', 'author', 'customerranking', 'customerrankingcount', 'format', 'price', 'year')

```

```{r}
# Removing duplicates
df2 <- df2 %>% 
  distinct(title, .keep_all = TRUE) %>% 
  rename(rank = 'rank')
```

```{r}
# remove #, "out of 5 stars"  and $ from columns rank customerranking, and price respectively. 

df2$rank <- as.numeric(gsub("\\#", "", df2$rank))
#df$customerranking <- gsub(" out of 5 stars", "", as.character((df$customerranking)))

df2$customerranking <- as.numeric(gsub(" out of 5 stars", "", df2$customerranking))

df2$price <- as.numeric(gsub("\\$", "", df2$price))
```

```{r}
# Remove null values. 

df2 <- na.omit(df2)
```

```{r}
head(df2)

```

```{r}
# Colors
custom_colors <- viridis::mako(n = 5)

# Most common genre
df2 %>% 
  group_by(format) %>% 
  summarise(count = n()) %>% 
  hchart('pie', hcaes(x = format, y = count, color = custom_colors)) %>% 
  hc_add_theme(hc_theme_google()) %>% 
  hc_tooltip(pointFormat='<b>Proportion: </b> {point.percentage:,.2f}%') %>% 
  hc_title(text = 'Most Common format from 2013 to 2022',
           style = list(fontSize = '15px', fontWeight = 'bold')) %>% 
  hc_credits(enabled = FALSE, text = '@jefffossi')
  
```
```{r}
# Colors
custom_colors <- viridis::mako(n = 15)

# Most popular authors by reviews
df2 %>% 
  group_by(author) %>% 
  summarise(Reviews = mean(customerranking)) %>% 
  arrange(desc(Reviews)) %>% 
  head(15) %>% 
  hchart('column', hcaes(x = author, y = Reviews,color = custom_colors)) %>%   hc_add_theme(hc_theme_google()) %>% 
  hc_tooltip(pointFormat = '<b>Average of Reviews: </b> {point.y} <br>') %>% 
  hc_title(text = 'Most Popular Authors from 2013 to 2022',
           style = list(fontSize = '15px', fontWeight = 'bold')) %>% 
  hc_subtitle(text = 'By Average of Reviews on Amazon',
              style = list(fontSize = '16px')) %>% 
  hc_credits(enabled = FALSE, text = '@jefffossi')
```
```{r}
# Colors
custom_colors <- viridis::mako(n = 15)

# Most popular authors by reviews
df2 %>% 
  group_by(author) %>% 
  summarise(Reviews = sum(customerranking)) %>% 
  arrange(desc(Reviews)) %>% 
  head(15) %>% 
  hchart('column', hcaes(x = author, y = Reviews,color = custom_colors)) %>%   hc_add_theme(hc_theme_google()) %>% 
  hc_tooltip(pointFormat = '<b>Total of Reviews: </b> {point.y} <br>') %>% 
  hc_title(text = 'Most Popular Authors from 2013 to 2022',
           style = list(fontSize = '15px', fontWeight = 'bold')) %>% 
  hc_subtitle(text = 'By Sum of Reviews on Amazon',
              style = list(fontSize = '16px')) %>% 
  hc_credits(enabled = FALSE, text = '@jefffossi')
```
```{r}
# Colors
custom_colors <- viridis::plasma(n = 15)

# Most popular books by reviews
df2 %>% 
  arrange(desc(customerrankingcount)) %>% 
  head(15) %>% 
  hchart('bar', hcaes(x = title, y = customerrankingcount, color = custom_colors)) %>% 
  hc_add_theme(hc_theme_google()) %>% 
  hc_tooltip(pointFormat = '<b>Number of Reviews: </b> {point.y} <br>') %>% 
  hc_title(text = 'Most Popular Books from 2013 to 2022',
           style = list(fontSize = '25px', fontWeight = 'bold')) %>% 
  hc_subtitle(text = 'By Number of Reviews',
              style = list(fontSize = '16px')) %>% 
  hc_credits(enabled = TRUE, text = '@jefffossi')
```
```{r}
# This is going to be a datatable
df3 <- df2 %>% 
  filter(customerranking >= 4.9) %>% 
  arrange(desc(customerrankingcount)) %>% 
  select(title, author)

# HTML table
div(style = 'height:600px; overflow-y:scroll', gt(df3) %>% 
      tab_header(title = md('Best Books from 2013 to 2022'),
                 subtitle = md('By Users Rating')) %>% 
      opt_table_font(font = list(google_font('Chivo'), default_fonts())) %>% 
      tab_style(location = cells_column_labels(columns = everything()),
                style = list(cell_borders(sides = 'bottom', 
                                          weight = px(2)), 
                             cell_text(weight = 'bold'))) %>% 
      tab_options(table.font.size = px(12L),
                  table.border.top.style = 'none',
                  column_labels.border.bottom.width = 2,
                  table_body.border.top.style = 'none',
                  data_row.padding = px(3))
    )
```