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')

# Display the first few rows to understand the structure
print(df.head())

# Check column names and data types
print(df.info())

# Check for missing values
print(df.isnull().sum())

# Most common gender
top_gender = df['sex'].value_counts().index[0]
print("Most common gender:", top_gender)

# Most common birth country
top_country = df['birth_country'].value_counts().index[0]
print("Most common birth country:", top_country)

#Which decade had the highest ratio of US-born Nobel Prize winners to total winners in all categories?
# Create a column to flag US-born winners
df['us_born_winner'] = df['birth_country'] == 'United States of America'
# Create a decade column
df['decade'] = (np.floor(df['year'] / 10) * 10).astype(int)
# Group by decade and calculate the mean ratio of US-born winners
us_born_ratio = df.groupby('decade', as_index=False)['us_born_winner'].mean()
us_born_ratio.rename(columns={'us_born_winner': 'us_born_ratio'}, inplace=True)
# Find the decade with the highest ratio of US-born winners
max_decade_usa = us_born_ratio.loc[us_born_ratio['us_born_ratio'].idxmax(), 'decade']

print("Decade with the highest ratio of US-born winners:", max_decade_usa)

# Create a relational line plot to visualize the trend
sns.relplot(
    x='decade', 
    y='us_born_ratio', 
    data=us_born_ratio, 
    kind='line', 
    marker='o'
)

# Add labels and title
plt.title('Ratio of US-born Nobel Prize Winners by Decade')
plt.xlabel('Decade')
plt.ylabel('US-born Winner Ratio')
plt.show()

# Filter for female laureates
female_df = df[df['sex'] == 'Female']

# Add a column to indicate female winners
df['female_winner'] = df['sex'] == 'Female'

# Group by decade and category, then calculate the mean proportion of female winners
female_proportion = (
    df.groupby(['decade', 'category'], as_index=False)['female_winner'].mean().rename(columns={'female_winner': 'female_proportion'})
)

# Find the row with the highest proportion of female winners
max_female_row = female_proportion.loc[female_proportion['female_proportion'].idxmax()]

# Create a dictionary with the decade and category
max_female_dict = {max_female_row['decade']: max_female_row['category']}

print("Decade and category with the highest proportion of female laureates:", max_female_dict)

# Create a relational line plot with multiple categories
sns.relplot(
    x='decade', 
    y='female_proportion', 
    hue='category', 
    data=female_proportion, 
    kind='line', 
    marker='o'
)

# Add labels and title
plt.title('Proportion of Female Nobel Laureates by Decade and Category')
plt.xlabel('Decade')
plt.ylabel('Proportion of Female Laureates')
plt.show()

#Find first woman to win a Nobel Prize

# Filter the DataFrame for female winners
female_winners = df[df['sex'] == 'Female']

# Find the row with the earliest year
first_female_winner = female_winners[female_winners['year'] == female_winners['year'].min()]

# Extract relevant information
first_female_year = first_female_winner['year'].values[0]
first_woman_category = first_female_winner['category'].values[0]
first_woman_name = first_female_winner['full_name'].values[0]

print(f"The first woman to win a Nobel Prize was {first_woman_name} in {first_female_year}, in the category of {first_woman_category}.")

#Determine repeat winners

# Count the number of wins for each laureate
winner_counts = df['full_name'].value_counts()

# Filter for repeat winners (counts >= 2)
repeat_winners = winner_counts[winner_counts >= 2].index

# Save the names as a list
repeat_list = list(repeat_winners)

print("Repeat winners:", repeat_list)