Project: Visualizing the History of Nobel Prize Winners

The Nobel Prize has been among the most prestigious international awards since 1901. Each year, awards are bestowed in chemistry, literature, physics, physiology or medicine, economics, and peace. In addition to the honor, prestige, and substantial prize money, the recipient also gets a gold medal with an image of Alfred Nobel (1833 - 1896), who established the prize.

The Nobel Foundation has made a dataset available of all prize winners from the outset of the awards from 1901 to 2023. The dataset used in this project is from the Nobel Prize API and is available in the nobel.csv file in the data folder.

In this project, you'll get a chance to explore and answer several questions related to this prizewinning data. And we encourage you then to explore further questions that you're interested in!# Python Code

# Loading in required libraries
library(tidyverse)
library(readr)
library(ggplot2)

# Start coding here!
nbl <- read_csv("data/nobel.csv")
head(nbl)

# Question 1.1 (R-codes)

top_gender_1 <- nbl %>%
group_by(sex) %>%
summarise(total = n()) %>%
arrange(desc(total))

top_gender_1

top_gender <- top_gender_1$sex[1]
top_gender

# Question 1.2 (R-codes)

top_country_1 <- nbl %>%
group_by(birth_country) %>%
summarise(total = n()) %>%
arrange(desc(total))

head(top_country_1,5)

top_country <- top_country_1$birth_country[1]
top_country

# Question 2 (R-codes)

max_decade_usa_1 <- nbl %>%
filter(birth_country == 'United States of America') %>%
mutate(decade = (year %/% 10) * 10) %>%
group_by(decade) %>%
summarise(total = n()) %>%
arrange(desc(total)) 

head(max_decade_usa_1,5)

max_decade_usa <- max_decade_usa_1$decade[1]
max_decade_usa

# Question 2 (R-codes) Alternative

max_decade_usa_2 <- nbl %>% 
  mutate(decade = (year %/% 10) * 10) %>% 
  group_by(decade, birth_country) %>% 
  summarise(total = n(), .groups = "drop_last") %>%  # Ensure grouping is retained for decade
  mutate(per = total * 100 / sum(total)) %>%         # Calculate percentage within the group
  ungroup() %>%                                      # Drop all grouping
  select(decade, birth_country, total, per) %>% 
  arrange(desc(per))

head(max_decade_usa_2)

# Question 3 (R-codes)

max_female_list_1 <- nbl %>%
filter(sex == 'Female') %>%
mutate(decade = (year %/% 10)*10) %>%
group_by(decade, category) %>%
summarise(total = n(), , .groups = "drop_last") %>%
mutate(per = total*100/sum(total)) %>%
arrange(desc(total))

head(max_female_list_1, 5)

max_female_list <- list(2010, 'Peace')
max_female_list

# Question 4 (R-codes)

first_woman_name_1 <- nbl %>%
filter(sex == 'Female') %>%
arrange(year) %>%
select(year, full_name, category)

head(first_woman_name_1,1)

first_woman_name <- first_woman_name_1$full_name[1]
first_woman_name

first_woman_category <- first_woman_name_1$category[1]
first_woman_category

# Question 5

nobel <- nbl %>%
group_by(full_name, organization_name) %>%
summarise(total = n(), .groups = 'drop') %>%
arrange(desc(total))

head(nobel, 5)

repeats <- nobel$full_name[1]
repeats

Data frameas

df

variable

SELECT *
FROM nbl
LIMIT 5;

Data frameas

df1

variable

-- Question 2 (SQL)

SELECT 
  FLOOR(year / 10) * 10 AS decade, 
  birth_country,
  COUNT(*) AS total,
  COUNT(*)*100/SUM(COUNT(*)) OVER(PARTITION BY FLOOR(year / 10) * 10) AS per
FROM nbl
GROUP BY FLOOR(year/ 10) * 10, birth_country
ORDER BY per DESC
LIMIT 5;