Did you know? That Instant Noodle invented by Momofuku Ando of Nissin Foods with the brand name Chikin Ramen. Ando establishing the entire process and make this product ready to eat just in two-minutes by adding boiling water. And this inovation became an instant populer. Now many food industry from each country have various taste and become favourite many people around the world. which one do you like?
The data used in this analysis is The big list data from The Ramen Rater guide to the world of instant noodle, since 2002. This data consist of all varioes instant noodle around the world, and the rating based on ramen rater preferences not on sales popularity.
library(dplyr)
library(ggplot2)
library(plotly)
library(glue)
library(highcharter)
library(wordcloud2)please make sure that dataset in the same working directory as this file RMD
library(readxl)
main_ramen <- read_excel("data_input/Ramen_rating_3950.xlsx", sheet = "Reviewed")this step will inspect and prepare the dataset before analysis.
main_ramenfrom information above show that data consist of 3950 rows and 7 columns
main_ramen <- subset(main_ramen, select = -c(T))
names(main_ramen)[names(main_ramen) == "Review #"] <- "Review_ID"str(main_ramen)## tibble [3,950 × 6] (S3: tbl_df/tbl/data.frame)
## $ Review_ID: num [1:3950] 3950 3949 3948 3947 3946 ...
## $ Brand : chr [1:3950] "Nissin" "Liitle Couples" "Yamasa" "Nissin" ...
## $ Variety : chr [1:3950] "Mocchi Cchi Hello Kitty Yakisoba" "Fish Head Casserole" "Artisanal Ramen Broth - Miso / Jongga Ramen Sari" "Cup Noodles Roasted Duck w/Sweet Onion Soup" ...
## $ Style : chr [1:3950] "Cup" "Pack" "Pack" "Cup" ...
## $ Country : chr [1:3950] "Japan" "Taiwan" "South Korea" "Germany" ...
## $ Stars : chr [1:3950] "3.75" "5" "3.5" "3.25" ...there are several columns that have a wrong type, that is “Brand”, “Style” and “Country” which should be a Factor. Stars which should be a Numeric.
# Factor Column
col_factor <- c("Brand", "Style", "Country")
main_ramen[, col_factor] <- lapply(main_ramen[, col_factor], as.factor)
# Numeric Column
main_ramen$Stars <- as.numeric(main_ramen$Stars)## Warning: NAs introduced by coercionstr(main_ramen)## tibble [3,950 × 6] (S3: tbl_df/tbl/data.frame)
## $ Review_ID: num [1:3950] 3950 3949 3948 3947 3946 ...
## $ Brand : Factor w/ 584 levels "1 To 3 Noodles",..: 336 250 575 336 336 336 255 471 322 336 ...
## $ Variety : chr [1:3950] "Mocchi Cchi Hello Kitty Yakisoba" "Fish Head Casserole" "Artisanal Ramen Broth - Miso / Jongga Ramen Sari" "Cup Noodles Roasted Duck w/Sweet Onion Soup" ...
## $ Style : Factor w/ 8 levels "Bar","Bowl","Box",..: 5 6 6 5 2 6 6 5 6 2 ...
## $ Country : Factor w/ 53 levels "Australia","Bangladesh",..: 23 46 43 13 23 51 46 23 23 23 ...
## $ Stars : num [1:3950] 3.75 5 3.5 3.25 0 3.5 5 3.5 1 5 ...from structure check show that type of several columns already appropiate
colSums(is.na(main_ramen))## Review_ID Brand Variety Style Country Stars
## 0 0 0 0 0 12from checking above show that Stars columns contain 12 missing value,
and will handle using na.omit() to dealing with missing
value
main_ramen <- na.omit(main_ramen)
colSums(is.na(main_ramen))## Review_ID Brand Variety Style Country Stars
## 0 0 0 0 0 0Voila, missing value is gone
This step contain some of data manipulation and insight from ramen data in the world using data visualization.
sometimes we need to know Top 10 ramen brand based on
Variety, this happens because sometimes we are curious how
many varieties of ramen from each brand which can we taste.
top_brand <- main_ramen %>%
count(Brand) %>%
arrange(desc(n))
top_brand_plot <- ggplot(top_brand[1:10, ]) +
aes(x = n,
y = reorder(Brand, n),
fill = Brand,
text = glue("Frequency: {n}")) +
geom_col() +
labs(title = "Top 10 Ramen Brand From Variety",
x = NULL,
y = NULL) +
theme_minimal() +
theme(legend.position = "none")
ggplotly(top_brand_plot, tooltip = "text") %>%
config(displayModeBar = T)Insight > Brand Nissin be on top ranks with the highest number of Variety with a total 502 Variety around the world > Our Brand Indomie be on 9th ranks with a total 59 Variety, it is not bad because our brand can compete with other brand in the world
Did you know? which country that be a Top Ramen Producer in the world? let’s find out
top_country <- main_ramen %>%
group_by(Country) %>%
count(Country) %>%
arrange(desc(n))
top_country_plot <- ggplot(top_country[1:10, ]) +
aes(x = n,
y = reorder(Country, n),
fill = Country,
text = glue("Frequency: {n}")) +
geom_col() +
labs(title = "Top 10 Country of Ramen Producer From Variety",
x = NULL,
y = NULL) +
theme_minimal() +
theme(legend.position = "none")
ggplotly(top_country_plot, tooltip = "text") %>%
config(displayModeBar = T)Insight > Country Japan be on top ranks with the highest number of Ramen Produsen with a total 741 Variety around the world > And our Country Indonesia be on 9th rank with a total 167 Variety.
country_distribution <- main_ramen %>%
count(Country) %>%
arrange(desc(n))
country_distribution %>%
hchart(
"treemap", hcaes(x= Country, value = n, color = n)
) %>%
hc_title(text = "Country Distribution",
margin = 20,
align = "left",
style = list(useHTML = TRUE)) %>%
hc_colorAxis(stops = color_stops(colors = viridis::inferno(10)))After finding out some of the countries with the most variety of brands, and the countries with the most numbers, let’s explore more about Indonesia.
First, let’s find out what brands are there in Indonesia?
indonesia <- main_ramen[main_ramen$Country=="Indonesia", ]
idr_brand <- indonesia %>%
group_by(Brand) %>%
count(Brand) %>%
arrange(desc(n))
wordcloud2(data=idr_brand,
size=3.0,
color='random-dark',
minRotation = 0,
maxRotation = 0,
rotateRatio = 1)Is there your favorite brand? Curious about the ratings for each brand?
brand_stars <- aggregate(Stars ~ Brand, data = indonesia, FUN = mean)
brand_stars <- brand_stars[order(brand_stars$Stars, decreasing = T), ]
brand_stars_plot <- ggplot(brand_stars) +
aes(x = Stars,
y = reorder(Brand, Stars),
fill = Brand,
text = glue("Stars: {Stars}")) +
geom_col() +
labs(title = "Average Stars for Each Brand",
x = NULL,
y = NULL) +
theme_minimal() +
theme(legend.position = "none")
ggplotly(brand_stars_plot, tooltip = "text") %>%
config(displayModeBar = T)From the exploration carried out, Japan as the country that invented instant noodles still ranks first with the most instant noodle makers and also the most variations, while Indonesia ranks 9. And the Lemonilo brand is the brand with the best average rating among other brands.
Disclaimer: This analysis is based on a dataset from Ramen Rater which is an assessment by preference and this publication was analyzed on January 21, 2022 which may no longer be relevant to the latest data at this time.