Project: Visualizing the History of Nobel Prize Winners

# Loading in required libraries
import pandas as pd
import seaborn as sns
import numpy as np
import matplotlib.pyplot as plt
# Start coding here!

df = pd.read_csv('data/nobel.csv')
df.head()

top_gender = df['sex'].value_counts().idxmax()
top_country = df['birth_country'].value_counts().idxmax()
print(top_gender, top_country)

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

# Create a new column 'decade' by flooring the 'year' divided by 10 and multiplying by 10 to get the decade
df['decade'] = np.floor(df['year'] / 10) * 10

# Convert the 'decade' column to integer type
df['decade'] = df['decade'].astype(int)

# Group the dataframe by the 'decade' column
grouped = df.groupby('decade')

# Define a function to calculate the ratio of USA-born laureates in a given group
def usa_born_ratio_per_decade(group_df):
    return (group_df['birth_country'] == 'United States of America').mean()

# Apply the function to each group and reset the index to get a dataframe with 'decade' and 'usa_born_ratio' columns
usa_born_ratios = grouped.apply(usa_born_ratio_per_decade).reset_index(name='usa_born_ratio')

# Find the decade with the highest USA-born ratio
max_decade_usa = usa_born_ratios.loc[usa_born_ratios['usa_born_ratio'].idxmax(), 'decade']

# Display the decade with the highest USA-born ratio
print('The decade with the highest USA-born ratio', max_decade_usa)

# Create a point plot of the USA-born ratio per decade
sns.pointplot(x='decade', y='usa_born_ratio', data=usa_born_ratios)

# Set the title of the plot
plt.title('USA-born Nobel Laureates Ratio per Decade')

# Set the x-axis label
plt.xlabel('Decade')

# Set the y-axis label
plt.ylabel('USA-born Ratio')

# Display the plot
plt.show()

# Group the dataframe by the 'decade' and 'category' column
grouped2 = df.groupby(['decade', 'category'])

# Define a function to calculate the ratio of female laureates in a given group
def female_ratio_per_decade(group_df):
    return (group_df['sex'] == 'Female').mean()

# Apply the function to each group and reset the index to get a dataframe with 'decade' and 'female_ratio' columns
female_ratios = grouped2.apply(female_ratio_per_decade).reset_index(name='female_ratio')

# Find the decade and category with the highest female ratio
max_female_row = female_ratios.loc[female_ratios['female_ratio'].idxmax()]
# max_female_dict = {'decade': max_female_row['decade'], 'category': max_female_row['category']}

# Create a point plot of the female ratio per decade
sns.lineplot(x='decade', y='female_ratio', data=female_ratios, markers=True, hue='category', style='category')

# Set the title of the plot
plt.title('Female Nobel Laureates Ratio per Decade')

# Set the x-axis label
plt.xlabel('Decade')

# Set the y-axis label
plt.ylabel('Female Ratio')

# Display the plot
plt.show()

# Calculating the proportion of female laureates per decade
df['female_winner'] = df['sex'] == 'Female'
prop_female_winners = df.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 = {
    'decade': max_female_decade_category['decade'].values[0],
    'category': max_female_decade_category['category'].values[0]
}

max_female_dict

first_woman_to_win_np = df[df['sex'] == 'Female'].sort_values(by='year', ascending=True)['full_name'].iloc[0]
print('The first woman to win a noble prize is', first_woman_to_win_np)

# repeats = df[df['full_name'].duplicated(keep=False)]['full_name'].sort_values(ascending=False).mode()

df2 = df[df['full_name'].duplicated(keep=False)]['full_name'].sort_values(ascending=False)

def amount_of_wins_per_laureat(count_df):
    return count_df.count()

repeats = df2.groupby(df2).apply(amount_of_wins_per_laureat).reset_index(name='count')

repeats

# Loading in required libraries
import pandas as pd
import seaborn as sns
import numpy as np

# Read in the Nobel Prize data
nobel = pd.read_csv('data/nobel.csv')

# Store and display the most commonly awarded gender and birth country in requested variables
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)

# Calculate 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) * 10).astype(int)
prop_usa_winners = 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
nobel['female_winner'] = nobel['sex'] == 'Female'
prop_female_winners = 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 = nobel[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 = nobel['full_name'].value_counts()
repeats = counts[counts >= 2].index
repeat_list = list(repeats)

print("\n The repeat winners are :", repeat_list)