Week 2 Data Dive - Summaries
2024-01-23
Data Dive Week 2: Yuritzi Avila-Robledo
Directions:
Your RMarkdown notebook for this data dive should contain the following:
A numeric summary of data for at least 2 columns of data
For categorical columns, this should include unique values and counts
For numeric columns, this includes min/max, central tendency, and some notion of distribution (e.g., quantiles)
These summaries can be combined
A set of at least 3 novel questions to investigate informed by the following:
column summaries (i.e., the above bullet)
data documentation
your project’s goals/purpose
Address at least one of the above questions using an aggregation function
Visual summaries (i.e., visualizations) of 2 or more columns of your data
This should include distributions at least
In addition, you should consider trends, correlations, and interactions between variables
Use different channels (e.g., color) to show how categorical variables interact with continuous variables
1) Summary of data for at least 2 columns of data
Numeric
For my data dive assignment I will be looking at the chocolate.csv. I started off by importing my data and loading in the tidyverse package.
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── 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 errorschocolate <- read.csv("~/Desktop/chocolate.csv")library(readr)
summary(chocolate)## ref company_manufacturer company_location review_date
## Min. : 5 Length:2530 Length:2530 Min. :2006
## 1st Qu.: 802 Class :character Class :character 1st Qu.:2012
## Median :1454 Mode :character Mode :character Median :2015
## Mean :1430 Mean :2014
## 3rd Qu.:2079 3rd Qu.:2018
## Max. :2712 Max. :2021
## country_of_bean_origin specific_bean_origin_or_bar_name cocoa_percent
## Length:2530 Length:2530 Min. :0.4200
## Class :character Class :character 1st Qu.:0.7000
## Mode :character Mode :character Median :0.7000
## Mean :0.7164
## 3rd Qu.:0.7400
## Max. :1.0000
## ingredients most_memorable_characteristics rating
## Length:2530 Length:2530 Min. :1.000
## Class :character Class :character 1st Qu.:3.000
## Mode :character Mode :character Median :3.250
## Mean :3.196
## 3rd Qu.:3.500
## Max. :4.000From the summary listed above we are able to see that the average percent of cocoa in the cocoa beans used to produce chocolate was 70% , while the minimum was 42%. The earliest rating was in the year 2006 while the latest year was 2021, that gives us a range of 15 years of reviews. The highest rating was a 4, the lowest a 1, and the average rating was a 3.196. From this summary, we received only insight into the numerical data, now I will move onto taking a look at what the categorical data provides.
Categorical
For the categorical data I wanted to take a look at how many countries the cocoa beans originated from.
library(tidyverse)
chocolate |>
distinct(country_of_bean_origin) |>
count()## n
## 1 62I thought it would be interesting to see the different ingredients used in the chocolates so I decided to use the distinct function:
chocolate |>
distinct(ingredients)## ingredients
## 1 3- B,S,C
## 2 4- B,S,C,L
## 3 2- B,S
## 4 4- B,S,C,V
## 5 5- B,S,C,V,L
## 6 6-B,S,C,V,L,Sa
## 7 5-B,S,C,V,Sa
## 8
## 9 4- B,S,V,L
## 10 2- B,S*
## 11 1- B
## 12 3- B,S*,C
## 13 3- B,S,L
## 14 3- B,S,V
## 15 4- B,S*,C,L
## 16 4- B,S*,C,Sa
## 17 3- B,S*,Sa
## 18 4- B,S,C,Sa
## 19 4- B,S*,V,L
## 20 2- B,C
## 21 4- B,S*,C,V
## 22 5- B,S,C,L,Sa2) A set of at least 3 novel questions to investigate
Question 1: Does the percent of cocoa affect the rating of the chocolate?
Question 2: Does the country the cocoa bean originates from affect the percentage of cocoa?
Question 3: What affect does the manufacturer have on the rating of the chocolate?
3) Address at least one of the above questions using an aggregation function/Visual summaries (i.e., visualizations) of 2 or more columns of your data
Question 1: Does the percent of cocoa affect the rating of the chocolate?
I thought it would be interesting to see how having the max percentage of cocoa affects the rating of the chocolate which turned out to have a rating of 2 and 3.25 which is lower than expected. I’d assume the richer the chocolate is in cocoa the higher the rating.
chocolate|>
group_by(rating)|>
filter(cocoa_percent=="0.99")## # A tibble: 2 × 10
## # Groups: rating [2]
## ref company_manufacturer company_location review_date country_of_bean_origin
## <int> <chr> <chr> <int> <chr>
## 1 81 Michel Cluizel France 2006 Blend
## 2 915 TCHO U.S.A. 2012 Blend
## # ℹ 5 more variables: specific_bean_origin_or_bar_name <chr>,
## # cocoa_percent <dbl>, ingredients <chr>,
## # most_memorable_characteristics <chr>, rating <dbl>After the last results I wanted to created a visualization and try to find a linear trend on all the percentages of cocoa versus their ratings.
ggplot(chocolate,aes(x=cocoa_percent, y=rating))+geom_point(color="red")+labs(x="Cocoa Percentage",y="Rating", title="Cocoa Percentage vs Rating")+geom_smooth(method="lm",se=FALSE)## `geom_smooth()` using formula = 'y ~ x'
From this plot of cocoa percentage versus rating we are able to see that there is a decreasing linear trend where as cocoa percentage increases the rating decreases. This was a surprise as I’d assume the richer in cocoa the chocolate is the better the chocolate.
Question 2: Does the country the cocoa bean originates from affect the percentage of cocoa?
I thought it would be interesting to find the average cocoa percentage per country of bean origin in order to see which country’s land is richer in cocoa. If there were more data available it would be really interesting to see if the countries weather affects the percentage of cocoa which also affects the rating.
library(dplyr)
average_cocoa_per_country <- chocolate |>
group_by(country_of_bean_origin) |>
summarize(avg_cocoa_percentage = mean(cocoa_percent,na.rm = TRUE))ggplot(average_cocoa_per_country,aes(x=country_of_bean_origin, y=avg_cocoa_percentage))+geom_bar(stat="identity",fill="red")+labs(x="Country",y="Avg Cocoa Percentage", title="Average Cocoa Percentage per Country")+ theme(axis.text.x = element_text(angle = 90, vjust = 1, hjust=1))
Question 3: What affect does the manufacturer have on the rating of the chocolate?
Following along the same lines as the second question, I thought it would be interesting to see how the manufacturer’s company location affects the average rating of the chocolate. My interest for this may not be fulled answered by the data available but I was interested in seeing if the further away the company’s manufacturers location is from where the cocoa bean originated, maybe the rating decreases for their chocolate because of the distance the cocoa beans have to travel. This is what I gathered with what I had available:
rating_based_on_manufacturer <- chocolate |>
group_by(company_location)|>
summarize(avg_rating = mean(rating,na.rm = TRUE))ggplot(rating_based_on_manufacturer,aes(x=company_location,y=avg_rating))+geom_bar(stat="identity",fill="red")+labs(x="Manufacturer",y="Avg Rating", title="Manufacturers Average Rating")+ theme(axis.text.x = element_text(angle = 90, vjust = 1, hjust=1))
It looks like I have to get my hands on some chocolate manufactured from Canada!