SGV Milk Tea Analysis
Kim Santos
Introduction
Milk tea is simply tea with milk added. It can come hot or cold and enjoyed with a variety of topping such as boba, jelly, red bean, egg pudding and even more! It has been widely popular through many parts of the world- even more so in certain regions. One of those regions is the San Gabriel Valley located in Southern California.
Investigation
This project investigates fives subjects and their experience with milk tea in the San Gabriel Valley, where their starting point is in El Monte, CA. Subjects input their own data into one data set altogether and frequently update it as they get their drinks.
Information subjects provide are:
- Shop - name of store
- City - city Shop is located
- Distance - how far Reviewers travel from El Monte, CA to the destination in miles
- Reviewer - indicate subjects’ name
- Price - how much the drink cost
- Drink Name - what drink did Reviewers get
- Boba - toppings added
- Rating - how reviewers rate their drink
- Rank - what ranking do reviewers consider the drink
- Comments - notes made about the drink
The experiences and preferences will be observed for each subjects by exploring the data and answering the following research questions.
Research Questions
- Which Cities were the most to least visited? How frequent did each Reviewer visit each city?
- What is the average Distance Reviewers travel to each city? What is the average distance each Reviewer will drive?
- What is the correlation between how far Reviewers travel and the cost of milk tea drinks they spend? is the correlation between Reviewers travel and how they rate milk teas?
- How are the Ratings in each City?
- Which City has the most Boba topping consumption? Which Reviewers get Boba toppings in their drink?
- How much do Reviewers Pay for their drinks?
Setup
# loading necessary libraries
library(readr) #read rectangular text data
library(ggplot2) # create visualizations
library(tidyverse) # transform and present data## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.0 ✔ stringr 1.5.0
## ✔ forcats 1.0.0 ✔ tibble 3.2.0
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errorslibrary(patchwork) # simple and powerful plot usage# The working directory is set to where the .csv file is stored in the computer
# The file is loaded and read with the variable name 'boba'.
setwd("~/Excel Documents")
boba <- read_csv("SGV Boba.csv") ## Rows: 97 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (7): Shop, City, Reviewer, Drink Name, Boba, Rank, Comments
## dbl (3): Distance, Price, Rating
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.Data Wrangling
This section loads and cleans the ‘boba’ data set. An overview of the data will display general info and identify values not applicable to their corresponding variables or irrelevant observations for analysis.This will allow the exploration of the data accurate results for the responses to the research questions.
This section loads and cleans the ‘boba’ data set.An overview of the data will display its general info and identify values not applicable to their corresponding…
Information to wrangle:
1. Check data types of variables
2. Remove columns: Rank and Comments
#view of the whole data set
as.data.frame(boba)## Shop City Distance Reviewer Price
## 1 85 Degrees Alhambra 7.1 Reviewer C 3.00
## 2 Wushiland San Gabriel 3.8 Reviewer E 4.74
## 3 Wushiland San Gabriel 3.8 Reviewer E 3.99
## 4 Wushiland San Gabriel 3.8 Reviewer E 3.99
## 5 Wushiland San Gabriel 5.7 Reviewer A 5.74
## 6 Wushiland San Gabriel 3.3 Reviewer B 3.99
## 7 OinkMoo Pasadena 7.1 Reviewer B 4.75
## 8 Nobibi Ice cream & Tea Chino Hills 18.0 Reviewer B 5.10
## 9 Vita Cane Rosemead 2.9 Reviewer C 7.50
## 10 Chakaa Arcadia 5.2 Reviewer D 4.25
## 11 Chakaa Arcadia 4.2 Reviewer B 4.75
## 12 Chakaa Arcadia 6.1 Reviewer C 4.75
## 13 Gotcha Rosemead 1.5 Reviewer B 5.25
## 14 Tenju Rowland Heights 13.0 Reviewer A 5.00
## 15 A+ tea house San Gabriel 4.5 Reviewer C 5.00
## 16 Hello Boba El Monte 1.3 Reviewer E 4.75
## 17 4 Season Tea House Rosemead 3.2 Reviewer C 5.00
## 18 Unique Tea Bar Hacienda Heights 8.5 Reviewer D 4.45
## 19 Sunright Tea Studio Diamond Bar 13.0 Reviewer D 4.75
## 20 Sunright Tea Studio Diamond Bar 14.0 Reviewer C 4.75
## 21 Ding Tea El Monte 0.9 Reviewer E 4.00
## 22 Tea Brick Monterey Park 5.2 Reviewer D 5.95
## 23 Chun Feng Sugar Koreatown 13.0 Reviewer B 4.95
## 24 Dragonfly tea bar Rowland Heights 12.0 Reviewer D 6.50
## 25 FTB San Gabriel 5.2 Reviewer C 4.25
## 26 FTB San Gabriel 5.5 Reviewer D 4.25
## 27 FTB San Gabriel 5.5 Reviewer D 4.25
## 28 FTB San Gabriel 5.5 Reviewer D 4.25
## 29 FTB San Gabriel 5.8 Reviewer E 4.25
## 30 FTB San Gabriel 4.2 Reviewer B 5.25
## 31 Wushiland San Gabriel 3.3 Reviewer B 5.49
## 32 Omomo Chino Hills 18.0 Reviewer B 5.00
## 33 Onezo Pasadena 12.0 Reviewer A 4.31
## 34 Onezo Pasadena 5.7 Reviewer E 5.75
## 35 Onezo Monterey Park 5.0 Reviewer B 5.75
## 36 Chi Cha San Gabriel 6.1 Reviewer A 6.25
## 37 Quickly Arcadia 3.3 Reviewer A 4.00
## 38 Yifang Rowland Heights 9.8 Reviewer B 5.75
## 39 Yifang Rowland Heights 11.2 Reviewer E 5.75
## 40 Mom's Bakery El Monte 1.9 Reviewer C 3.75
## 41 7Leaves Alhambra 6.9 Reviewer D 4.40
## 42 7Leaves Alhambra 11.0 Reviewer A 4.40
## 43 7Leaves Alhambra 11.0 Reviewer A 4.40
## 44 7Leaves Alhambra 6.9 Reviewer C 5.00
## 45 Happy Lemon Monterey Park 6.6 Reviewer D 5.50
## 46 Happy Lemon Monterey Park 6.3 Reviewer C 5.50
## 47 Tenju Rowland Heights 12.0 Reviewer E 5.00
## 48 Tenju Rowland Heights 9.6 Reviewer B 5.00
## 49 Hello Boba El Monte 1.6 Reviewer A 4.25
## 50 Happy Lemon Monterey Park 5.9 Reviewer E 5.50
## 51 Chakaa Arcadia 5.7 Reviewer A 5.50
## 52 OinkMoo Pasadena 9.6 Reviewer E 5.75
## 53 Feng Cha Costa Mesa 32.0 Reviewer E 5.00
## 54 Ono Tea House El Monte 0.6 Reviewer E 4.50
## 55 Twinkle Brown Sugar Alhambra 5.4 Reviewer C 5.45
## 56 Milk + T Little Tokyo 11.0 Reviewer B 5.50
## 57 Bubble Crush Monterey Park 4.1 Reviewer C 4.75
## 58 Bubble Crush Monterey Park 4.1 Reviewer C 5.00
## 59 4 Season Tea House Alhambra 3.2 Reviewer C 5.00
## 60 Ten Ren Monterey Park 6.2 Reviewer A 5.50
## 61 TanCha San Gabriel 3.4 Reviewer B 5.75
## 62 Miss Cheese Cafe Pasadena 7.8 Reviewer B 5.75
## 63 Neighbors Rosemead 3.1 Reviewer D 4.00
## 64 Neighbors Rosemead 3.1 Reviewer D 4.25
## 65 Neighbors Rosemead 2.8 Reviewer C 4.25
## 66 Dots Cafe Arcadia 5.8 Reviewer B 4.50
## 67 Lollicup Arcadia 6.7 Reviewer C 4.25
## 68 Yu Cake Rosemead 2.3 Reviewer B 5.25
## 69 Nest Tea House Arcadia 2.9 Reviewer B 4.15
## 70 Why Thirsty Arcadia 5.9 Reviewer C 4.50
## 71 Half & Half Monterey Park 8.0 Reviewer A 4.25
## 72 Tea Maru San Gabriel 6.5 Reviewer A 4.50
## 73 Boba Box Monrovia 8.6 Reviewer E 5.50
## 74 Feng Cha Costa Mesa 32.0 Reviewer E 4.75
## 75 Bobacraft Alhambra 8.6 Reviewer A 3.75
## 76 Bobacraft Alhambra 7.1 Reviewer D 4.50
## 77 Happy Lemon Monterey Park 5.0 Reviewer B 4.75
## 78 Twinkle Brown Sugar Alhambra 5.4 Reviewer C 5.75
## 79 Moo Tea Alhambra 3.8 Reviewer B 6.25
## 80 Tastea Alhambra 6.8 Reviewer D 5.50
## 81 Chami Tea Bar Whittier 7.8 Reviewer A 5.25
## 82 Chami Tea Bar Whittier 5.4 Reviewer D 4.00
## 83 Sunright Tea Studio Diamond Bar 13.0 Reviewer D 5.50
## 84 Sunright Tea Studio Diamond Bar 8.0 Reviewer A 5.50
## 85 Bon Appetea San Gabriel 6.3 Reviewer E 4.25
## 86 Oh My Pan San Gabriel 3.9 Reviewer D 3.05
## 87 Oh My Pan San Gabriel 3.9 Reviewer D 4.00
## 88 Boba Ave Arcadia 6.0 Reviewer D 4.25
## 89 Tancca Arcadia 5.5 Reviewer D 4.25
## 90 Tastea Alhambra 8.6 Reviewer A 5.50
## 91 Tenju Rowland Heights 11.0 Reviewer C 5.50
## 92 Ono Tea House El Monte 0.6 Reviewer C 5.50
## 93 Ono Tea House El Monte 0.5 Reviewer D 5.50
## 94 Uncle Tea West Covina 13.0 Reviewer C 4.25
## 95 Tenju Rowland Heights 12.0 Reviewer D 4.75
## 96 Wushiland San Gabriel 4.1 Reviewer C 4.74
## 97 Cafe Roule Alhambra 3.1 Reviewer B 4.75
## Drink Name Boba Rating Rank
## 1 Sea Salt Mountain Tea No 9.0 A
## 2 Red Bean Milk Tea No 10.0 A
## 3 Assam Black Tea Yes 10.0 A
## 4 Jasmine Green Milk Tea Yes 8.5 A
## 5 Ice Cream Green Milk Tea Yes 8.5 A
## 6 Jasmine Green Milk Tea Yes 9.0 A
## 7 Jasmine Milk Tea Yes 8.0 A
## 8 Ube Cloud Yes 8.0 A
## 9 Sugar Cane Juice No 10.0 A
## 10 Jasmine Milk Tea No 9.0 A
## 11 Jasmine Milk Tea Yes 8.0 A
## 12 White Peach Oolong w/o cheese foam No 9.0 A
## 13 Brown Sugar Fresh Milk Yes 8.5 A
## 14 Honey Green Tea Yes 10.0 A
## 15 Honey green tea No 10.0 A
## 16 Jasmine Milk Tea Yes 9.0 A
## 17 Jasmine Green Milk Tea No 10.0 A
## 18 Jasmine Green Milk Tea No 10.0 A
## 19 Jasmine Green Milk Tea No 9.0 A
## 20 Ceylon Milk Tea No 9.0 A
## 21 Wintermelon MT Yes 10.0 A
## 22 Mango Snow Milk No 10.0 A
## 23 Brown Sugar Fresh Milk Yes 8.0 A
## 24 Rainbow tea Yes 9.0 A
## 25 Rose Green Tea No 7.0 B
## 26 Almond Milk Tea Yes 10.0 B
## 27 Nom Nom Green Tea Yes 10.0 B
## 28 Jasmine Milk Tea No 9.0 B
## 29 Brown Sugar Milk Yes 8.0 B
## 30 Dirty Nom Nom Yes 8.0 B
## 31 Yogurt Green Tea Yes 7.8 B
## 32 Omomo Matcha Yes 8.0 B
## 33 Honey Green Tea Yes 7.0 B
## 34 Brown Sugar Milk @ Pasadena Yes 3.0 B
## 35 Brown Sugar Milk Yes 8.0 B
## 36 Brown Sugar Milk Yes 11.0 B
## 37 Jasmine Milk Tea Yes 7.5 B
## 38 Brown Sugar Milk Yes 8.0 B
## 39 Brown Sugar Milk Yes 8.0 B
## 40 Jasmine Milk Tea No 10.0 B
## 41 Jasmine Milk Tea No 8.0 B
## 42 Mung Bean Drink No 8.0 B
## 43 Hibiscus Tea thing No 8.3 B
## 44 Love Cream No 7.5 B
## 45 Jasmine Milk Tea w/ Cheese Foam? No 8.0 B
## 46 Black Tea w/ Salted Cheese No 9.0 B
## 47 Jasmine Milk Tea Yes 8.0 B
## 48 Jasmine Milk Tea Yes 8.0 B
## 49 Jasmine Milk Tea Yes 7.5 B
## 50 Brown Sugar Milk Yes 7.5 B
## 51 Brown Sugar Milk Yes 7.7 B
## 52 Brown Sugar Milk Yes 8.5 B
## 53 Brown Sugar Milk Yes 9.0 B
## 54 Brown Sugar Milk Yes 6.5 B
## 55 Chrysanthemum Tea No 8.0 B
## 56 Guilt Trip Yes 8.0 B
## 57 White Peach Oolong Tea No 7.5 B
## 58 Ceylon Milk Tea No 7.5 B
## 59 Mango Green Tea No 8.0 B
## 60 Dirty Latte Yes 7.5 B
## 61 Tiramisu Foam Cocao No 7.0 C
## 62 Brown Sugar milk Yes 7.0 C
## 63 Green Tea No 3.5 C
## 64 Almond Milk Tea No 4.0 C
## 65 Jasmine Milk Tea No 6.0 C
## 66 Lychee Black Tea Yes 6.5 C
## 67 Honey Green Tea Yes 3.5 C
## 68 Fresh Fruit tea No 5.0 C
## 69 Mango Green Tea Yes 5.0 C
## 70 Jasmine milk tea Yes 4.0 C
## 71 Ice Milk Drink w/ pudding & honey boba Yes 8.0 C
## 72 Wintermelon milk tea No 7.5 C
## 73 Green Milk Tea Yes 5.5 C
## 74 Jasmine Green Tea No 5.0 C
## 75 Jasmine Green Tea Yes 3.0 C
## 76 Jasmine Milk Tea No 4.0 C
## 77 Yogurt Green Tea Yes 5.5 C
## 78 Jasmine Milk Tea Honey No 5.0 C
## 79 Purple Yam Fresh Milk Yes 6.0 C
## 80 Almond Milk Tea No 6.5 C
## 81 Chami Mixed Fruit Tea No 4.0 C
## 82 Chami Milk Tea No 3.0 C
## 83 Pudding Milk Tea No 6.0 C
## 84 Brown Sugar Milk Yes 6.5 C
## 85 Green Milk Tea No 5.0 C
## 86 Jasmine Milk Tea No 0.0 F
## 87 Lavender Milk Tea No 0.0 F
## 88 Jasmine Milk Tea Yes 0.0 F
## 89 King's Boba Yes 0.0 F
## 90 Brown Sugar Milk Yes 0.0 F
## 91 Lavender Milk Tea No 0.0 F
## 92 Honey Green Tea No 1.0 F
## 93 Green Milk Tea No 1.0 F
## 94 Almond Milk Tea No 0.0 F
## 95 Almond Milk Tea No 1.0 F
## 96 Ovaltine Milk Tea No 1.0 F
## 97 Matcha Green Tea Yes 1.0 F
## Comments
## 1 yummmmmmmmmmmmmyyyy They have BOGO sometimes.
## 2 only because I never had red bean anywhere else xD and its good
## 3 their black tea is yummers
## 4 pretty solid imo c: it's just that their boba can be hard sometimes
## 5 i really like it the ice cream makes the drink creamy; only downside is their boba aint that gud
## 6 solid drink with lots of boba
## 7 v niceee; top list of things I'd get from there
## 8 freakin gooood; boba is alright tho
## 9 yummmerssss no boba lol
## 10 it was yum c: ; i agree, it really is yumm - nm
## 11 yummies; the boba is nice and chewy
## 12 yummy!!! light, fresh peachy taste with strong oolong kick at the end
## 13 Always consistent with this drink! My go to
## 14 it slaps
## 15 yummmmmm
## 16 Very good! Just that the cup is very small :c not that we're trying to drink a lot >.<
## 17 the drinks are yummerz, i didnt try their boba but their snacks are good they give a lot.
## 18 SO GOOD; PERFECT, MILKY
## 19 Yummy!
## 20 Very good~ I've never had Ceylon tea before, but it's very yummy! Would recommend getting it a little less sweet though~
## 21 i live by this i swear by this my newest obsession no one has better wintermelon than ding tea
## 22 IT SLAPSSSS -priscilla and Reviewer D
## 23 Really good but you can tell a change in consistency
## 24 pretty good tea and it has BOGO happy hour 1.50 1-5 pm but its in rowland
## 25 their tea is good, they had some moments where they didn't treat me right and I don't ususally get their boba so idk. But the last time I tried their boba it was hard as a rock.
## 26 Reviewer D freaking loved it with boba yummy
## 27 for those days when you want something milky, it's yummy
## 28 yummyskis jasmine milk tea
## 29 drink was good 2x amazing it gets an extra 0.5 points
## 30 can get a bit too much sometimes but still a good noms
## 31 Lotssss of boba; the drink is a bit too sweet tho
## 32 Drink was good in the end; was a tad annoying to mix it
## 33 I usually just get their tea and its not bad. A little sweet or not too sweet. Kinda inconsistent but its okay. Their boba is kinda tasteless.
## 34 The Pasadena one tasted like a coffee drink :///// and their cup is narrower than usual...
## 35 Tastes how a brown sugar milk should
## 36 The only reason it's B-tier is because its $6 for a small :/
## 37 Their drink isn't bad and their boba is meh but its cheap and their fried combo is yummers. but gotta get a little extra sweet for the drink bc its kinda watered down sometimes.
## 38 Boba was small and it fulfills my need for a brown sugar milk drink
## 39 I like it but sometimes not good? Boba is small/different than usual, also can be expensive :c
## 40 Hella yummy, but don't know much about their other drinks or if their boba is good
## 41 Tastes more like Assam milk tea, but still good; don't know about their boba
## 42 Refreshing!!! PLUS for drive thru
## 43 Not bad for a non boba drink!! And it's low calorie and cheapish c:
## 44 pretty basic drink i think it's a JMT w/ caramel, but i usually get it if idk wat to get from here
## 45 I've never gotten their boba but idk if they even have boba. But their drink hasn't disappointed me yet. But sometimes I crave boba so its not a good "go to" place.
## 46 yummmmyyyyy (for those no boba days)
## 47 i like it and their boba is sweet imo
## 48 Nice texture; boba nice and chewy
## 49 pretty good? the boba is edible the drink tastes not flowery but more TEA- E
## 50 Drink is yummy i like it but the boba could be better.. more on the harder side
## 51 was gonna give it an 8, but their cup annoyed me so much with all the spilling >:( drink itself was not bad
## 52 drink very yum, but boba hard :c. i got it when they had the 20% off promo, but normally it'd prolly be close to 6 bucks
## 53 yummy but far so B-tier
## 54 inconsistent............ but cheap... would go if desparate and lazy
## 55 i like it. never had their boba but i got 10% off :) and their cups are cute
## 56 was a hot day and felt great to consume
## 57 quite yummy, but a litttttttttle watered down, so not a super strong oolong taste
## 58 not bad! Again, a little bland, but still p good
## 59 pretty good! Regular sweetness is a litttttle too sweet though
## 60 it could be a little sweeter, but i think overall not bad! their boba is chewy so i like (obvs boba isnt sweet but alas)
## 61 too expensive for a small cup; drink itself is just alright
## 62 Would be something I'd get if there wasn\x92t anything else I want
## 63 they use to be fine but they changed their tea and it sucks now. Can't remember their boba that well.
## 64 Gave them another chance, but they disappointed me. Helllllllaaalujah sweet and tasted like just powder mixed with water instead of milk after a while>:(
## 65 Used to be 10/10 for that strong yummy jasmine taste, but they changed. >:(
## 66 It was ok but don\x92t think I'll get again; they make boba at 10am LOL
## 67 hehe I made my own drink here and their tea wasn't bad. Boba was meh but they don't exist near us anymore so too bad.
## 68 Was super thirsty when I got it so it was really refreshing; Started to taste bitter in the end
## 69 Meh; just average
## 70 their drink for our first time was so good, even the boba was sweet but they got worse and worse everytime we went.
## 71 the only drink i get at here i quite like it tbh but never really craving it yafeel? it's just there
## 72 don't go for their boba but their wintermelon is pretty gud like ding tea
## 73 boba is kinda hard (too chewy) not that sweet, drink is nice but the place is farrr its in Monrovia
## 74 meh. i got this after the ice all melted so it was watered down and its quite far. strong tea taste, pretty cheap
## 75 oh boy. they gave me tea with no sugar so i had to go back and ask for a lot of sugar. the custard bread was good. Their cookies and cream one is just an oreo and chocolate cream. misleading. w.e. and their boba custard was alright but the boba had no taste.
## 76 idk.. it's a bit bland, more tea-y. also tastes like sip and that brings bad memoriez
## 77 was a bit yogurty
## 78 i don't rly hate it... but it's weird? idk i dont like it either.. but it's pretty cheap c:
## 79 Boba was tasteless and I didn\x92t enjoy the yam bits; if it was just the drink, it would be ok
## 80 Actually really super sweet
## 81 I probably just don't like mixed fruit teas >.< I don't know why I got it. It's very pineapple and passion fruit flavored
## 82 Kinda tastes like cereal like Ovaltine Milk Tea from Wushiland, but this one is actually sweet enough
## 83 Just very very sweet. The pudding was good though and not super sweet. But the liquid is very very sweet ;.;
## 84 tasted weird...
## 85 didn't really like it and they have me mini boba dont like that
## 86 the drink wasn't memorable but the pudding was TRASH. The pudding texture was like soaked-up sponge cake.
## 87 Reviewer Ds drink tasted like medicine, and was undrinkable after drinking 1/4 of it
## 88 Regular sugar tastes like water. Boba experiene was like chewing hard air.
## 89 it was like $6 when I got it, small AF cup, and it tasted like SOYSAUCE
## 90 just lol.
## 91 Just don't it tastes like medicine and herbs
## 92 tasted bland and had a bitter aftertaste. was BOGO but if i had to pay full price for that ill sharpen my pitchfork and stab em
## 93 so damn bland. tastes like straight up milk
## 94 god
## 95 tastes like they blended those chinese almond cookies with milk. no thanks
## 96 Very bland and it tastes like chinese cereal. Like the milk that is flavored with unsweetened corn flakes
## 97 No thank you1. Check data types of variables
# looking into the structure
str(boba)## spc_tbl_ [97 × 10] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ Shop : chr [1:97] "85 Degrees" "Wushiland" "Wushiland" "Wushiland" ...
## $ City : chr [1:97] "Alhambra" "San Gabriel" "San Gabriel" "San Gabriel" ...
## $ Distance : num [1:97] 7.1 3.8 3.8 3.8 5.7 3.3 7.1 18 2.9 5.2 ...
## $ Reviewer : chr [1:97] "Reviewer C" "Reviewer E" "Reviewer E" "Reviewer E" ...
## $ Price : num [1:97] 3 4.74 3.99 3.99 5.74 3.99 4.75 5.1 7.5 4.25 ...
## $ Drink Name: chr [1:97] "Sea Salt Mountain Tea" "Red Bean Milk Tea" "Assam Black Tea" "Jasmine Green Milk Tea" ...
## $ Boba : chr [1:97] "No" "No" "Yes" "Yes" ...
## $ Rating : num [1:97] 9 10 10 8.5 8.5 9 8 8 10 9 ...
## $ Rank : chr [1:97] "A" "A" "A" "A" ...
## $ Comments : chr [1:97] "yummmmmmmmmmmmmyyyy They have BOGO sometimes." "only because I never had red bean anywhere else xD and its good" "their black tea is yummers" "pretty solid imo c: it's just that their boba can be hard sometimes" ...
## - attr(*, "spec")=
## .. cols(
## .. Shop = col_character(),
## .. City = col_character(),
## .. Distance = col_double(),
## .. Reviewer = col_character(),
## .. Price = col_double(),
## .. `Drink Name` = col_character(),
## .. Boba = col_character(),
## .. Rating = col_double(),
## .. Rank = col_character(),
## .. Comments = col_character()
## .. )
## - attr(*, "problems")=<externalptr>The data type for each variable appears to be correctly identified. It would only be necessary to change the variables’ data type if the analysis required for a specific type.
2. Remove columns: Rank and Comments
# first removing Rank and Comments then running head() to see final results
boba <- select(boba, -c("Rank", "Comments"))
head(boba)## # A tibble: 6 × 8
## Shop City Distance Reviewer Price `Drink Name` Boba Rating
## <chr> <chr> <dbl> <chr> <dbl> <chr> <chr> <dbl>
## 1 85 Degrees Alhambra 7.1 Reviewer C 3 Sea Salt Mounta… No 9
## 2 Wushiland San Gabriel 3.8 Reviewer E 4.74 Red Bean Milk T… No 10
## 3 Wushiland San Gabriel 3.8 Reviewer E 3.99 Assam Black Tea Yes 10
## 4 Wushiland San Gabriel 3.8 Reviewer E 3.99 Jasmine Green M… Yes 8.5
## 5 Wushiland San Gabriel 5.7 Reviewer A 5.74 Ice Cream Green… Yes 8.5
## 6 Wushiland San Gabriel 3.3 Reviewer B 3.99 Jasmine Green M… Yes 9The Rank and Comments columns have been removed as they are not required in this analysis. Now we see the first few rows with the newly cleaned data set.
Exploratory Data Analysis
This section will cover answering the research
questions we encountered in the beginning of the project.
Which Cities were the most to least visited? How frequent did each
Reviewer visit each city?
# Group cities together and summarize the total amount of reviewers' frequency visiting each city. Then summarize each reviewers' frequency individually for each city.
city_freq <- boba %>%
group_by(City) %>%
summarise(reviews = length(Reviewer))
city_freq <- city_freq %>%
ggplot(aes(reorder(City, reviews) , y = reviews, fill = City)) +
geom_bar(stat = "identity") +
ggtitle("Frequency Distribution of Reviewers Visiting Each City") +
xlab("City") +
ylab("Reviewers Count") +
theme(plot.title = element_text(hjust = 0.5), legend.position = 'none') +
coord_flip()
reviewer_city_freq <- boba %>%
ggplot(aes(y = City, fill = Reviewer)) +
geom_bar(position = position_dodge()) +
ggtitle("Reviewers Frequency Visiting Each City") +
labs(x = "Cities", y = "Reviewers Frequency Visiting") +
theme(plot.title = element_text(hjust = 0.5)) +
scale_fill_brewer(palette = "Spectral")
city_freq / reviewer_city_freq
Combining all reviewers’ visits, we first see San
Gabriel is the most frequently visited city to get milk tea with 20
visits. There are also multiple cities that are only visited once among
the reviewers, which are West Covina, Monrovia, Little Tokyo, Koreatown,
and Hacienda Heights.
Looking further into each reviewer, we can see how frequent each
reviewer visited each city. It appears Reviewer D and E visted San
Gabriel the most and Reviewer visited Alhambra with 5 visits.
What is the average Distance Reviewers travel to each city? What is the average distance each Reviewer will drive?
#Graph the average distance reviewers traveled for each city. Then graph each indidivual reviewers travel.
city_avg_dist <- boba %>%
group_by(City) %>%
summarise(avg_dist = mean(Distance))
city_avg_dist <-city_avg_dist %>%
ggplot(aes(reorder(City, avg_dist), y = avg_dist, fill = City)) +
geom_bar(stat = "identity") +
ggtitle("Average Distance Reviewers Traveled to Each City") +
xlab("City") +
ylab("Average Distance") +
theme(plot.title = element_text(hjust = 0.5), legend.position = 'none') +
coord_flip()
reviewer_avg_dist <-boba %>%
ggplot(aes(x = Reviewer,fill = mean(Distance))) +
geom_bar(position = position_dodge()) +
ggtitle("Average Distance Reviewers Travel") +
ylab("Avg Distance") +
xlab("Reviewers") +
theme(legend.position = 'none', plot.title = element_text(hjust = 0.5), axis.text.x = element_text(angle = 0, vjust = 0.5, hjust=.5))
city_avg_dist / reviewer_avg_dist
We can see the longest average distances
Reviewers traveled was just over 30 miles towards Costa Mesa while El
Monte is the shortest distance. As for each individual reviewer, they
all average a travel distance of around 15 miles and over.
What is the correlation between how far Reviewers travel and the cost of milk tea drinks they spend? What is the correlation between Reviewers travel and how they rate milk teas?
# Create scatter plot between Distance and Price
# Create scatter plot between Distance and Rating
# Distance vs Price
dist_vs_price_scat <- boba %>%
ggplot(aes(Distance, Price)) +
geom_point() +
ggtitle("Relationship Between Distance vs. Price") +
theme(plot.title = element_text(hjust = 0.5), legend.position = "none") +
geom_smooth(method = 'lm', se = FALSE)
dist_vs_rat_scat <- boba %>%
ggplot(aes(Distance, Rating)) +
geom_point() +
ggtitle("Relationship Between Distance vs. Rating") +
theme(plot.title = element_text(hjust = 0.5), legend.position = "none") +
geom_smooth(method = 'lm', se = FALSE)
dist_vs_price_scat / dist_vs_rat_scat## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
Although it may first seem there is no
correlation between both Distance vs Price and Distance vs Rating, they
both have a positive correlation
How are the Ratings in each City?
# create boxplots for eac City based on Ratings
city_rat_box <-
ggplot(boba, aes(x=City,y=Rating)) +
geom_boxplot() +
ggtitle("City Ratings") +
theme(axis.text.x = element_text(angle=60, hjust=1), plot.title = element_text(hjust = 0.5))
city_rat_box
Some Cities do not have a complete boxplots due
to only having one data that has been inputted. We will only know how
well those specific Cities do in terms of rating set by one
Reviewer.
Cities that do have a complete boxplot informs how Reviewers rate their drinks for each city. We see how cities overall some outliers and have 3 types of distributions- symetrical, positively and negatively skewed.
Those with postive skews: Alhambra, Arcadia, El Monte, and Rowland Heights. Those with negative skews: Pasadena and Rosemead Those with symetrical skews: Costa Mesa, Diamond Bar, and Monterey Park
Which City has the most Boba topping consumption? Which Reviewers get Boba toppings in their drink?
# create a groupby side by sdie barplot with each city
boba_city <- boba %>%
ggplot(aes(x = City,fill = Boba)) +
geom_bar(position = position_dodge()) +
ggtitle("Boba Topping Consumption in Each City") +
theme(plot.title = element_text(hjust = 0.5), axis.text.x = element_text(angle = 60, vjust = 1, hjust=1)) +
scale_fill_manual(values = c("darkolivegreen", "darksalmon"))
rev_got_boba <- boba %>%
ggplot(aes(x = Boba, fill = Reviewer)) +
geom_bar(position = position_dodge()) +
ggtitle("Reviewers who get Toppings") +
labs(x = "Reviewers", y = "Topping Count") +
theme(plot.title = element_text(hjust = 0.5)) +
scale_fill_brewer(palette = "Spectral")
boba_city / rev_got_boba
The first graph shows which city has the most
boba topping consumption between reviewers. Alhambra being the most with
no toppings while San Gabriel is even with who gets toppings. For each
reviewers, we see Reviewer C rarely gets any while Reviewer B gets the
most.
How much do Reviewers Pay for their drinks?
# create histogram to view frequency of prices for each reviewer
par(mfrow = c(2,3))
a_price <- hist(boba$Price[boba$Reviewer == "Reviewer A"], main = "Reviewer A Price Frequency", xlab = "Price", col = 'lightcoral')
b_price <- hist(boba$Price[boba$Reviewer == "Reviewer B"], main = "Reviewer B Price Frequency", xlab = "Price", col = 'lightcyan')
c_price <- hist(boba$Price[boba$Reviewer == "Reviewer C"], main = "Reviewer C Price Frequency", xlab = "Price", col = 'khaki1')
d_price <- hist(boba$Price[boba$Reviewer == "Reviewer D"], main = "Reviewer D Price Frequency", xlab = "Price", col = 'moccasin')
e_price <- hist(boba$Price[boba$Reviewer == "Reviewer E"], main = "Reviewer E Price Frequency", xlab = "Price", col = 'lavenderblush')
# create boxplot for each reviewer based on price variable to compare between eachother
ggplot(boba, aes(x=Reviewer,y=Price, fill = Reviewer)) +
geom_boxplot() +
theme_classic() +
theme(axis.text.x = element_text(angle=60, hjust=1)) +
theme(legend.position = 'none', plot.title = element_text(hjust = 0.5)) +
scale_fill_manual(values = c("lightcoral", "lightcyan", "khaki1", "moccasin", "lavenderblush")) +
ggtitle("Reviewer's prices on milk tea drinks")
The histograms show a frequency how much each
reviewers pay for their drinks. It appears between reviewers, they have
their own preference in how much they buy drinks.
The boxplots show another visualization to show how much reviewers
pay, and they all show a symmetrical, postiive and negative skew
distribution. This allows another interpretation to compare payments and
whether they fall positively or negatively distributed.
Conclusion
This project we have explored the ‘boba’ data set. We observed where reviewers traveled to and analyzed their experiences and preferences they faced as they got milk tea drinks in the San Gabriel Valley.
Cities We will first talk about the cities overall. San Gabriel came out to be the most visited city among reviewers with a total of 20 visits while West Covina, Monrovia, Little Tokyo, Koreatown and Hacienda Heights only have 1 visit. Since San Gabriel has the most visits, reviewers traveld an average 4 miles as their starting point is in El Monte. As for the other cities that were least visited, they traveled an average 7 miles and more. These cities were one of the shortest distances, yet we see Costa Mesa is the only one with 30 miles. With all the traveling between cities, we observed the relationship between cities and how they rate/ pay for drinks. The relationship for both has all been positively, negatively and symmetrically skewed. Lastly, the amount of toppings consumed was also observed. Alhambra has the least topping consumptions while San Gabriel was equal in having the most and least amount of consumptions.
Reviewers Now we will take a look into each reviewer individually. Reviewers have driven an average of 15 miles and over. Despite the long distance, we noticed that an average of 5 miles was frequently made. Reviewer D and E visited San Gabriel the most while Reviewer C visited Alhambra the most- all with a total of 5 visits. We also took a look at which reviewer gets the most and least boba toppings in each city and how much they would frequently pay. The reviewer who gets the most boba toppings and Reviewer B and Reviewer C gets the least. With how much reviewers spend on milk tea, it appears they would pay from a range of $3-$6 with the exception of some paying over $6.
Overall Based on our analysis, we can make assumptions about reviewers and their experiences with each city. Reviewers may prefer a specific city to get milk tea based on the amount of visits they frequent and how much they are willing to spend and travel. From what it seems, San Gabriel is a top city to visit as it is the shortest distance and most visits.
Limitations
There have subjective preferences that occurred from the data set.
Milk tea preferences When getting milk tea, options are usually given in how reviewers prefer their drinks. This is from the amount of sugar, ice levels, and size. This shows a disparity on reviewers experiences.
Travel Distance The willingness reviewers will travel is also subjective. This may be due to a milk tea reviewers really enjoy and will travel more to get it. However, it may also be the case reviewers may really like a drink but will not go such a distance just to get it.