Nobel prize winners and their years until death.

get_nobel_prize_years_until_death.py

#/usr/bin/python3

# gets demographics for nobel prize winners
# calculates yearly average of how many years between prize and death

import pandas as pd
import numpy as np

# api endpoint for all nobel winnters: https://nobelprize.readme.io/
url = 'http://api.nobelprize.org/v1/laureate.csv'

# import csv from web API
df = pd.read_csv(url)

# convert strings to datetime 
df['died'] = pd.to_datetime(df.died, format='%Y-%m-%d', errors='coerce')
df['year_date'] = pd.to_datetime(df.year, format='%Y', errors='coerce')

# calculate difference between death and prize years
df['years_until_death'] = (df['died'] - df['year_date'])/np.timedelta64(1,'Y')

# get mean years until death for each prize year
df = df.groupby('year')['years_until_death'].mean().round()

# write to csv
df.to_csv('nobel_prize_years_until_death.csv', header=True)

nobel_prize_years_until_death.csv