Take Home Exercise 3

This article is about creating a visualisation showing average rating and proportion of cocoa percent(% chocolate) greather than or equal to 70% by top 15 company locaton.

Assumptions

1. I have assumed that the visualisation excludes all chocolate products with cocoa percent less than 70%
2. I have assumed that “average rating” refers to the mean rating of all chocolate rating of companies in each location
3. I have also assumed that the “top 15 company location” is determined by ranking all company locations’ by average rating then average cocoa percent from greater to smallest and selecting the top 15

Installing and loading the required packages

packages = c('tidyverse', 'readxl', 'knitr')
for(p in packages){
  if(!require(p, character.only = T)){
    install.packages(p)
  }
  library(p, character.only = T)
}

Data import

cho<- read_csv("data/chocolate.csv")

Data cleaning

remove percentage sign in column cocoa_percent to change data format from string to numeric

cho$cocoa_percent = as.numeric(gsub("[\\%,]", "", cho$cocoa_percent))

remove chocolate with cocoa percentage smaller than 70%

cho_mod <-subset(cho, cocoa_percent >= 70)

Data Wrangling

get the average rating of product containing cocoa percentage greater or equal to 70% by company location

cho_mod_avg <-cho_mod %>% 
   group_by(company_location) %>%
   summarize(avg_rating = mean(rating, na.rm=TRUE)) %>%
   ungroup()

get the average cocoa percentage of product containing cocoa percentage greater or equal to 70% by company location

cho_mod_percent <- cho_mod %>% 
  group_by(company_location) %>%
  summarize(avg_cocoa_percent = mean(cocoa_percent, na.rm=TRUE)) %>%
  ungroup()

merging cho_mod_avg and cho_mod_percent with company location

cho_new = merge(cho_mod_avg,cho_mod_percent, by= "company_location")

get the top 15 company loctaion by arranging cho_new in descending order by average rating then by average cocoa percentage

cho_new_desc <- cho_new[order(-cho_new$avg_rating, -cho_new$avg_cocoa_percent),]
cho_top15 <- cho_new_desc[1:15, ]

find the cocoa percenatge of top 15 company

cho_top15_coco_percent <-cho_mod[cho_mod$company_location %in% c("Chile","Fiji","Denmark","Switzerland","Poland","Vietnam","Colombia",
  "Guatemala","Australia","U.A.E","Argentina","Amsterdam","Thailand",
  "Canada","Scotland"),]

merg cho_top15_coco_percent with cho_mod_avg to get average rating as well as cocoa percentage of top 15 company locations

cho_final = merge(cho_top15,cho_top15_coco_percent, by= "company_location")

Visualisation- scatterplot

Scatterplot was chosen becasue the goal to visualize the relationship between two continous variables cocoa percentage and cocao rating.

graphing the scatterplot