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 the dataset and find the most common gender and birth country
df_nobel = pd.read_csv("data/nobel.csv")
df_nobel.head()
# Let's see if there is any missing values
df_nobel.columns[df_nobel.isnull().any()]#The number of missing values by columns
df_nobel.isnull().sum()# Dtypes for our columns
df_nobel.dtypes# Most common value in a column top_gender and top_country
top_gender = df_nobel['sex'].value_counts().index[0]
top_country = df_nobel['birth_country'].value_counts().index[0]
print(" D\n The gender with the most Nobel laureates is :", top_gender)
print(" The most common birth country of Nobel laureates is :", top_country)
# Create the US-born winners column
df_nobel['usa_born_winner'] = df_nobel['birth_country'] == 'United States of America'
df_nobel['decade'] = (np.floor(df_nobel['year'] / 10) * 10).astype(int)
prop_usa_winners = df_nobel.groupby('decade', as_index=False)['usa_born_winner'].mean()
# Identify the decade with the highest proportion of US-born winners
max_decade_usa = prop_usa_winners[prop_usa_winners['usa_born_winner'] == prop_usa_winners['usa_born_winner'].max()]['decade'].values[0]
# Optional: Plotting USA born winners
ax1 = sns.relplot(x='decade', y='usa_born_winner', data=prop_usa_winners, kind="line")
# Calculating the proportion of female laureates per decade
df_nobel['female_winner'] = df_nobel['sex'] == 'Female'
prop_female_winners = df_nobel.groupby(['decade', 'category'], as_index=False)['female_winner'].mean()
# Find the decade and category with the highest proportion of female laureates
max_female_decade_category = prop_female_winners[prop_female_winners['female_winner'] == prop_female_winners['female_winner'].max()][['decade', 'category']]
# Create a dictionary with the decade and category pair
max_female_dict = {max_female_decade_category['decade'].values[0]: max_female_decade_category['category'].values[0]}
# Optional: Plotting female winners with % winners on the y-axis
ax2 = sns.relplot(x='decade', y='female_winner', hue='category', data=prop_female_winners, kind="line")
# Finding the first woman to win a Nobel Prize
nobel_women = df_nobel[df_nobel['female_winner']]
min_row = nobel_women[nobel_women['year'] == nobel_women['year'].min()]
first_woman_name = min_row['full_name'].values[0]
first_woman_category = min_row['category'].values[0]
print(f"\n The first woman to win a Nobel Prize was {first_woman_name}, in the category of {first_woman_category}.")
# Selecting the laureates that have received 2 or more prizes
counts = df_nobel['full_name'].value_counts()
repeats = counts[counts >= 2].index
repeat_list = list(repeats)
print("\n The repeat winners are :", repeat_list)