# Loading in required libraries import pandas as pd import seaborn as sns import numpy as np # Reading in the Nobel Prize data nobel = pd.read_csv("datasets/nobel.csv") # Taking a look at the first several winners nobel.head(6)

# Display the number of (possibly shared) Nobel Prizes handed # out between 1901 and 2016 num_prizes = len(nobel) display(num_prizes) # Display the number of prizes won by male and female recipients. sex_counts = nobel['sex'].value_counts() display(sex_counts) # Display the number of prizes won by the top 10 nationalities. top_countries = nobel['birth_country'].value_counts().head(10) top_countries

# Calculating the proportion of USA born winners per decade nobel['usa_born_winner'] = nobel['birth_country'] == 'United States of America' nobel['decade'] = np.floor(nobel['year']/10).astype(int) * 10 prop_usa_winners = nobel.groupby('decade', as_index=False)['usa_born_winner'].mean() # Display the proportions of USA born winners per decade prop_usa_winners[['decade', 'usa_born_winner']]

# Setting the plotting theme sns.set() # and setting the size of all plots. import matplotlib.pyplot as plt plt.rcParams['figure.figsize'] = [11, 7] # Plotting USA born winners ax = sns.lineplot(data=prop_usa_winners, x='decade', y='usa_born_winner') # Adding %-formatting to the y-axis from matplotlib.ticker import PercentFormatter ax.yaxis.set_major_formatter(PercentFormatter(1.0))

# Calculating the proportion of female laureates per decade nobel['female_winner'] = nobel['sex'] == 'Female' prop_female_winners = nobel.groupby(['decade', 'category'], as_index=False)['female_winner'].mean() # Plotting USA born winners with % winners on the y-axis ax = sns.lineplot(data=prop_female_winners, x='decade', y='female_winner', hue='category') ax.yaxis.set_major_formatter(PercentFormatter(1.0))

# Picking out the first woman to win a Nobel Prize nobel_female = nobel[nobel['sex'] == 'Female'] nobel_female.nsmallest(1, columns='year')

nobel.groupby('full_name').filter(lambda group: len(group) >= 2)

# Converting birth_date from String to datetime nobel['birth_date'] = pd.to_datetime(nobel['birth_date'], errors='coerce') # Calculating the age of Nobel Prize winners nobel['age'] = nobel['year'] - nobel['birth_date'].dt.year # Plotting the age of Nobel Prize winners sns.lmplot(data=nobel, x='year', y='age', lowess=True, aspect=2, line_kws={'color': 'black'})

# Same plot as above, but separate plots for each type of Nobel Prize sns.lmplot(x='year', y='age', data=nobel, row='category', aspect=2)

# The oldest winner of a Nobel Prize as of 2016 display(nobel.nlargest(1, 'age')) # The youngest winner of a Nobel Prize as of 2016 nobel.nsmallest(1, 'age')

# The name of the youngest winner of the Nobel Prize as of 2016 youngest_winner = nobel.nsmallest(1, 'age')['full_name'].values[0].split()[0] youngest_winner