A Visual History of Nobel Prize Winners

# Loading in required libraries # ... YOUR CODE FOR TASK 1 ... 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 # ... YOUR CODE FOR TASK 1 ... nobel.head(6)

yearint64

categoryobject

1901

Chemistry

1901

Literature

1901

Medicine

1901

Peace

1901

Peace

1901

Physics

# Display the number of (possibly shared) Nobel Prizes handed # out between 1901 and 2016 # ... YOUR CODE FOR TASK 2 ... num_prizes = len(nobel) display(num_prizes) # Display the number of prizes won by male and female recipients. # ... YOUR CODE FOR TASK 2 ... sex_counts = nobel['sex'].value_counts() display(sex_counts) # Display the number of prizes won by the top 10 nationalities. # ... YOUR CODE FOR TASK 2 ... 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 # ... YOUR CODE FOR TASK 3 ... prop_usa_winners[['decade', 'usa_born_winner']]

decadeint64

1900 - 2010

usa_born_winnerfloat64

0.017543859649122806 - 0.42276422764227645

1900

0.017543859649122806

1910

0.075

1920

0.07407407407407407

1930

0.25

1940

0.3023255813953488

1950

0.2916666666666667

1960

0.26582278481012656

1970

0.3173076923076923

1980

0.31958762886597936

1990

0.40384615384615385

# 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 # ... YOUR CODE FOR TASK 4 ... 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 # ... YOUR CODE FOR TASK 5 ... 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 # ... YOUR CODE FOR TASK 5 ... nobel_female = nobel[nobel['sex'] == 'Female'] nobel_female.nsmallest(1, columns='year')

yearint64

categoryobject

1903

Physics

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

yearint64

1903 - 1981

categoryobject

Peace46.2%

Chemistry30.8%

Physics23.1%

1903

Physics

1911

Chemistry

1917

Peace

215

1944

Peace

278

1954

Chemistry

283

1954

Peace

298

1956

Physics

306

1958

Chemistry

340

1962

Peace

348

1963

Peace

# 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 # ... YOUR CODE FOR TASK 9 ... sns.lmplot(x='year', y='age', data=nobel, row='category', aspect=2)

# The oldest winner of a Nobel Prize as of 2016 # ... YOUR CODE FOR TASK 10 ... display(nobel.nlargest(1, 'age')) # The youngest winner of a Nobel Prize as of 2016 # ... YOUR CODE FOR TASK 10 ... nobel.nsmallest(1, 'age')

yearint64

categoryobject

885

2014

Peace

# 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