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!
# Loading in required libraries
import pandas as pd
import seaborn as sns
import numpy as np
# load dataset
nobel = pd.read_csv("data/nobel.csv")
#find most common gener and birth country
top_gender = nobel["sex"].value_counts().index[0]
top_country = nobel["birth_country"].value_counts().index[0]
print("\n The gender with the most Nobel Laureates is :", top_gender)
print(" The most common birth country of Nobel laureates is : ", top_country)
#identify decade with highest proportion of US born winners
nobel["usa_born_winner"] = nobel["birth_country"] == "United States of America"
nobel["decade"] = (np.floor(nobel["year"]/10)*10).astype(int)
prop_usa_winners = nobel.groupby("decade",as_index=False)["usa_born_winner"].mean()
print("", highest_prop_usa_winners, "is the decade with the highest proportion of USA Nobel Prize winners!")
#identify decade with highest proportion of USA winners
max_decade_usa = prop_usa_winners[prop_usa_winners["usa_born_winner"]==prop_usa_winners["usa_born_winner"].max()]["decade"].values[0]
#Create a relational line plot
prop_usa_plot = sns.relplot(x = "decade", y = "usa_born_winner", data = prop_usa_winners, kind = "line")
#Find decade/category of highest proportion of female laureates
nobel["female_winner"] = nobel["sex"] == "Female"
prop_f_winners = nobel.groupby(["decade", "category"],as_index=False)["female_winner"].mean()
max_female_dec_cat = prop_f_winners[prop_f_winners["female_winner"]==prop_f_winners["female_winner"].max()][["decade", "category"]]
max_female_dict = {max_female_dec_cat["decade"].values[0]: max_female_dec_cat["category"].values[0]}
print(" The decade and category with the highest proportion of Female Nobel laureates and category is : ", max_female_dec_cat.values[0])
# plot the proportion of female laureates for each decade by category
max_female_plot = sns.relplot(x = "decade", y = "female_winner", hue = 'category', data = prop_f_winners, kind = "line")
#find first woman to win a Nobel Prize
nobel_women = nobel[nobel['female_winner']]
min_year = nobel_women[nobel_women['decade'] == nobel_women['decade'].min()]
first_woman_name = min_year['full_name'].values[0]
first_woman_category = min_year['category'].values[0]
print("\n The first woman to win the Nobel Prize was ", first_woman_name,",", "in the category of" ,first_woman_category,".")
#find laureates with 2 or more prizes
counts = nobel['full_name'].value_counts()
repeats = counts[counts >= 2].index
repeat_list = list(repeats)
print("\n The repeat winners are :", repeat_list)