Visualizing Data in the Tidyverse course project
Jirapanakorn Sutham
2022-05-18
This is a part of Visualizing Data in the Tidyverse course project.
Setting Environment
Load tidyverse package
library(tidyverse)Load provided dataset, which were downloaded in working directory,into R.
fast_food_sale <- read.csv(here::here('data_fastfood_sales.csv'))
fast_food_sale <- fast_food_sale %>%
rename('restaurant'="X.ปฟrestaurant") ##rename the first column.
fast_food_cal <- read.csv(here::here('data_fastfood_calories.csv'))Problem 1
Task 1 : Create a scatter plot with column us_sales along the x-axis and the column unit_count along the y-axis.
project_plot1 <- ggplot(data = fast_food_sale)+
geom_point(aes(x= us_sales,
y= unit_count),shape = 16)
project_plot1
Task 2 : Each axis should be transformed to a `log10` scale and should be appropriately labeled.project_plot1 <- ggplot(data = fast_food_sale)+
geom_point(aes(x= us_sales,
y= unit_count),shape = 16)+
scale_y_continuous(trans = 'log10')+
scale_x_continuous(trans = 'log10')
project_plot1
Task 3 : Color each point by the proportion of franchised stores (i.e. `num_franchised_stores` divided by `unit_count`). fast_food_sale <- fast_food_sale %>%
mutate(franchised_prop = num_franchised_stores/unit_count)
project_plot1 <- ggplot(data = fast_food_sale)+
geom_point(aes(x= us_sales,
y= unit_count,
color = franchised_prop),shape = 16) +
scale_y_continuous(trans = 'log10')+
scale_x_continuous(trans = 'log10')
project_plot1
Task 4 : Label each point with the name of the fast food restaurant using the `ggrepel` package. library(ggrepel)
project_plot1 <- ggplot(data = fast_food_sale)+
geom_text_repel(aes(x= us_sales,
y= unit_count,
label= restaurant))+
geom_point(aes(x= us_sales,
y= unit_count,
color = franchised_prop),shape = 16) +
scale_y_continuous(trans = 'log10')+
scale_x_continuous(trans = 'log10')
project_plot1
Task 5 : Use the classic dark-on-light ggplot2 theme. library(ggrepel)
project_plot1 <- ggplot(data = fast_food_sale)+
geom_text_repel(aes(x= us_sales,
y= unit_count,
label= restaurant))+
geom_point(aes(x= us_sales,
y= unit_count,
color = franchised_prop),shape = 16) +
scale_y_continuous(trans = 'log10')+
scale_x_continuous(trans = 'log10')+
theme_bw()
project_plot1
Task 6 : Rename the legend appropriately. library(ggrepel)
project_plot1 <- ggplot(data = fast_food_sale)+
geom_text_repel(aes(x= us_sales,
y= unit_count,
label= restaurant))+
geom_point(aes(x= us_sales,
y= unit_count,
color = franchised_prop),shape = 16) +
scale_y_continuous(trans = 'log10')+
scale_x_continuous(trans = 'log10')+
theme_bw()+
labs(x='U.S. sales in millions(log10 scale)',
y='Total number of stores(log10 scale)',
color='Proportion of stores franchised')
project_plot1
Problem 2
Task1 : Create a bar plot with the average_sales on the x-axis and restaurant on the y-axis (Hint: consider using the coord_flip() function).
project_plot2 <-ggplot(data = fast_food_sale)+
geom_col(aes(x=restaurant,y= average_sales))+
coord_flip()
project_plot2
Task2 : The order of restaurants on the y-axis should be in decreasing order of average sales with the restaurant with the largest average sales at the top and the restaurant with the smallest average sales at the bottom.
project_plot2 <-ggplot(data = fast_food_sale)+
geom_col(aes(x=reorder(restaurant,average_sales),
y= average_sales))+
coord_flip()
project_plot2
Task3 : Add text to each bar on the plot with the average sales (in the thousands) for each restaurant.
library(ggrepel)
project_plot2 <-ggplot(data = fast_food_sale)+
geom_col(aes(x=reorder(restaurant,average_sales),
y= average_sales))+
coord_flip()+
geom_text_repel(aes(x=reorder(restaurant,average_sales),
y= average_sales,
label=paste("$",round(average_sales,0))),
hjust=0.8,
nudge_y = 3,
direction = "x",
size=3)
project_plot2
Task4 : Each axis should be appropriately labeled.
library(ggrepel)
project_plot2 <-ggplot(data = fast_food_sale)+
geom_col(aes(x=reorder(restaurant,average_sales),
y= average_sales))+
coord_flip()+
geom_text_repel(aes(x=reorder(restaurant,average_sales),
y= average_sales,
label=paste("$",round(average_sales,0))),
hjust=0.8,
nudge_y = 3,
direction = "x",
size=3)+
labs(x='Restaurant',
y='Average sals per unite store (in thousands)')
project_plot2
Task5 : Along the x-axis, transform the text labels to include a dollar sign in front of each number.
library(ggrepel)
project_plot2 <-ggplot(data = fast_food_sale)+
geom_col(aes(x=reorder(restaurant,average_sales),
y= average_sales))+
coord_flip()+
geom_text_repel(aes(x=reorder(restaurant,average_sales),
y= average_sales,
label=paste("$",round(average_sales,0))),
hjust=0.8,
nudge_y = 3,
direction = "x",
size=3)+
labs(x='Restaurant',
y='Average sals per unite store (in thousands)')+
scale_y_continuous(labels = scales::label_dollar())
project_plot2
Task6 : Use the classic ggplot2 theme.
library(ggrepel)
project_plot2 <-ggplot(data = fast_food_sale)+
geom_col(aes(x=reorder(restaurant,average_sales),
y= average_sales))+
coord_flip()+
geom_text_repel(aes(x=reorder(restaurant,average_sales),
y= average_sales,
label=paste("$",round(average_sales,0))),
hjust=0.8,
nudge_y = 3,
direction = "x",
size=3)+
labs(x='Restaurant',
y='Average sals per unite store (in thousands)')+
scale_y_continuous(labels = scales::label_dollar())+
theme_classic()
project_plot2
Problem3
Task1 : Create a scatter plot with the column calories along the x-axis and the column sodium along the y-axis.
project_plot3 <-ggplot(data = fast_food_cal)+
geom_point(aes(x=calories,y= sodium),shape = 16)
project_plot3
Task2 : Each restaurant should have its own scatter plot (Hint: consider the facet functions).
project_plot3 <-ggplot(data = fast_food_cal)+
geom_point(aes(x=calories,y= sodium),shape = 16)+
facet_wrap(~restaurant)
project_plot3
Task3 : Add a horizontal line at y=2300 in each scatter plot.
project_plot3 <-ggplot(data = fast_food_cal)+
geom_point(aes(x=calories,y= sodium),shape = 16)+
facet_wrap(~restaurant)+
geom_hline(yintercept =2300)
project_plot3
Task4 : Each axis of the scatter plot should have an appropriately labeled x-axis and y-axis.
project_plot3 <-ggplot(data = fast_food_cal)+
geom_point(aes(x=calories,y= sodium),shape = 16)+
facet_wrap(~restaurant)+
geom_hline(yintercept =2300)+
labs(x="Calories",
y="Sodium (mg)")
project_plot3
Task5 : For all food items with a sodium level of greater than 2300 (mg) (the maximum daily intake from the Centers for Disease Control), add a text label each point with the name of the entree food item using the ggrepel package.
library(ggrepel)
project_plot3 <-ggplot(data = fast_food_cal)+
geom_point(aes(x=calories,
y= sodium),shape = 16)+
facet_wrap(~restaurant)+
geom_hline(yintercept =2300)+
labs(x="Calories",
y="Sodium (mg)")+
geom_text_repel(data = filter(fast_food_cal, sodium>2300),
aes(x=calories,
y= sodium,
label= item),
nudge_y = 1000,
nudge_x = 500,
Vjust = 50,
direction = 'y',
size=2)
project_plot3
Task6 : Use the classic dark-on-light ggplot2 theme.
library(ggrepel)
project_plot3 <-ggplot(data = fast_food_cal)+
geom_point(aes(x=calories,
y= sodium),shape = 16)+
facet_wrap(~restaurant)+
geom_hline(yintercept =2300)+
labs(x="Calories",
y="Sodium (mg)")+
geom_text_repel(data = filter(fast_food_cal, sodium>2300),
aes(x=calories,
y= sodium,
label= item),
nudge_y = 1000,
nudge_x = 500,
Vjust = 50,
direction = 'y',
size=2)+
theme_bw()+
theme(plot.margin = margin(.5,1,.5,1),aspect.ratio = 0.5)
project_plot3
Problem4
Task1 : Create a new column titled is_salad that contains a TRUE or FALSE value of whether or not the name of entree food item contains the character string “salad” in it.
fast_food_cal <-fast_food_cal %>%
mutate('is_salad' = str_detect(tolower(item),'salad'))
fast_food_cal %>%
select(restaurant,item,is_salad)%>%
filter(is_salad == TRUE)%>%
head() ##Show some result## restaurant item is_salad
## 1 Mcdonalds Premium Asian Salad w/o Chicken TRUE
## 2 Mcdonalds Premium Asian Salad w/ Grilled Chicken TRUE
## 3 Mcdonalds Premium Asian Salad w/ Crispy Chicken TRUE
## 4 Mcdonalds Premium Bacon Ranch Salad w/o Chicken TRUE
## 5 Mcdonalds Premium Bacon Ranch Salad w/ Grilled Chicken TRUE
## 6 Mcdonalds Premium Bacon Ranch Salad w/ Crispy Chicken TRUETask2 : Create boxplots with calories on the x-axis and restaurant on the y-axis.
project_plot4 <-ggplot(data = fast_food_cal)+
geom_boxplot(aes(x=calories,y= restaurant))
project_plot4
Task3 : The order of restaurants on the y-axis should be in decreasing order of calories with the restaurant with the median calories at the top and the restaurant with the smallest median calories at the bottom.
fast_food_cal<-fast_food_cal%>%
group_by(restaurant)%>%
mutate(med_cal_by_restaurant = median(calories))
##Create new column of median each restaurant's items calories.
project_plot4 <-ggplot(data = fast_food_cal)+
geom_boxplot(aes(x=calories,
y=reorder(restaurant,med_cal_by_restaurant)))
project_plot4
Task4 : Hide any outliers in the boxplots.
project_plot4 <-ggplot(data = fast_food_cal)+
geom_boxplot(aes(x=calories,
y=reorder(restaurant,med_cal_by_restaurant)),
outlier.shape = NA)
project_plot4
Task5 : On top of the boxplots add a set of jittered points representing each food item.
project_plot4 <-ggplot(data = fast_food_cal)+
geom_boxplot(aes(x=calories,
y=reorder(restaurant,med_cal_by_restaurant)),
outlier.shape = NA)+
geom_jitter(aes(x=calories,
y=restaurant))
project_plot4
Task6 : Each point should be colored based on whether it is an item with the word “salad” in it or not.
project_plot4 <-ggplot(data = fast_food_cal)+
geom_boxplot(aes(x=calories,
y=reorder(restaurant,med_cal_by_restaurant)),
outlier.shape = NA)+
geom_jitter(aes(x=calories,
y=restaurant,
color=is_salad))
project_plot4
Task7 : Each axis should be appropriately labeled, the legend should be appropriately labeled, and the x-axis should be transformed to a log10 scale.
project_plot4 <-ggplot(data = fast_food_cal)+
geom_boxplot(aes(x=calories,
y=reorder(restaurant,med_cal_by_restaurant)),
outlier.shape = NA)+
geom_jitter(aes(x=calories,
y=restaurant,
color=is_salad))+
labs(x='Calories (log10 scale)',
y='Restaurant')+
scale_x_continuous(trans = 'log10')+
scale_color_discrete(name = "Is the entree \na salad?",
labels= c("Is not a salad","salad"))
project_plot4
Task8 : Use the classic dark-on-light ggplot2 theme.
project_plot4 <-ggplot(data = fast_food_cal)+
geom_boxplot(aes(x=calories,
y=reorder(restaurant,med_cal_by_restaurant)),
outlier.shape = NA)+
geom_jitter(aes(x=calories,
y=restaurant,
color=is_salad))+
labs(x='Calories (log10 scale)',
y='Restaurant')+
scale_x_continuous(trans = 'log10')+
scale_color_discrete(name = "Is the entree \na salad?",
labels= c("Is not a salad","salad"))+
theme_bw()
project_plot4
Problem5
Task1: For each restaurant calculate the median amount of sugar in each entree item.
median_sugar<-fast_food_cal %>%
group_by(restaurant)%>%
summarize('sugar_median'=median(sugar))
median_sugar## # A tibble: 8 x 2
## restaurant sugar_median
## <chr> <dbl>
## 1 Arbys 6
## 2 Burger King 7.5
## 3 Chick Fil-A 4
## 4 Dairy Queen 6
## 5 Mcdonalds 9
## 6 Sonic 7
## 7 Subway 8
## 8 Taco Bell 4Task2 : Using this summarized dataset, combine this summarized dataset with the data_fastfood_sales.csv dataset. The combined dataset should only include restaurants that are included in both datasets.
sale_join_sugar <- fast_food_sale %>%
inner_join(median_sugar, by= 'restaurant')
sale_join_sugar%>%
select(restaurant,us_sales,sugar_median)## restaurant us_sales sugar_median
## 1 Subway 10800.00 8.0
## 2 Mcdonalds 37480.67 9.0
## 3 Burger King 10028.32 7.5
## 4 Taco Bell 9790.15 4.0
## 5 Sonic 4408.16 7.0
## 6 Arbys 3634.00 6.0Task3 : Using this new dataset, create a bar plot with restaurant on the x-axis and on the us_sales y-axis.
project_plot5 <- ggplot(data= sale_join_sugar)+
geom_col(aes(x=restaurant,
y=us_sales))
project_plot5 
Task4 : The order of restaurants on the x-axis should be in increasing order of US sales with the restaurant with the largest average sales on the right and the restaurant with the smallest US sales on the left.
project_plot5 <- ggplot(data= sale_join_sugar)+
geom_col(aes(x=reorder(restaurant,us_sales),
y=us_sales))
project_plot5 
Task5 : Color the bars by the median amount of sugar in the entree items from that restaurant.
library(viridis)
project_plot5 <- ggplot(data= sale_join_sugar)+
geom_col(aes(x=reorder(restaurant,us_sales),
y=us_sales,
fill = sugar_median))+
scale_fill_gradientn(colors=viridis(6))
project_plot5 
Task6 : Each axis should be appropriately labeled.
library(viridis)
project_plot5 <- ggplot(data= sale_join_sugar)+
geom_col(aes(x=reorder(restaurant,us_sales),
y=us_sales,
fill = sugar_median))+
scale_fill_gradientn(colors=viridis(6))+
labs(x="Restaurant",
y="U.S. sales(in millions)",
fill ="Median sugar (grams) \nin fast food entrees")
project_plot5 
Task7 : Use the classic ggplot2 theme.
library(viridis)
project_plot5 <- ggplot(data= sale_join_sugar)+
geom_col(aes(x=reorder(restaurant,us_sales),
y=us_sales,
fill = sugar_median))+
scale_fill_gradientn(colors=viridis(6))+
labs(x="Restaurant",
y="U.S. sales(in millions)",
fill ="Median sugar (grams) \nin fast food entrees")+
theme_classic()
project_plot5 