ATP age of Grand Slam winners

atp_age_grandslams.py

# Create dataframe with age of winners filtering Grand Slam finals
tennis_df_win=tennis_df[tennis_df['tourney_level'].isin(['G'])&(tennis_df['round']=='F')].dropna(subset=['winner_age'])
dfw = tennis_df_win[['tourney_year','tourney_name','winner_name','winner_age']]
dfw.columns = ['tourney_year','tourney_name','player','age']

dfs_final = dfw.groupby(['tourney_year','tourney_name']).agg({'age':'mean'}).reset_index()
dfs_final_2 = dfs_final.groupby(['tourney_year']).agg({'age':'mean'}).reset_index()

fig = plt.figure(figsize=(15,5))
ax = fig.add_subplot(111)
ax.set_prop_cycle(plt.cycler('color', plt.cm.jet(np.linspace(0, 1, 5))))

plt.title('Age of Grand Slams Champions 1968-2018')
plt.ylabel('Age')
plt.xlabel('Year')
plt.plot(dfs_final_2['tourney_year'], dfs_final_2['age'])
plt.scatter(dfs_final[dfs_final['tourney_name']=='Australian Open']['tourney_year'], dfs_final[dfs_final['tourney_name']=='Australian Open']['age'], alpha=0.3)
plt.scatter(dfs_final[dfs_final['tourney_name']=='Roland Garros']['tourney_year'], dfs_final[dfs_final['tourney_name']=='Roland Garros']['age'], alpha=0.3)
plt.scatter(dfs_final[dfs_final['tourney_name']=='Wimbledon']['tourney_year'], dfs_final[dfs_final['tourney_name']=='Wimbledon']['age'], alpha=0.3)
plt.scatter(dfs_final[dfs_final['tourney_name']=='US Open']['tourney_year'], dfs_final[dfs_final['tourney_name']=='US Open']['age'], alpha=0.3)
plt.legend(['All Grand Slams Avg.','Australian Open', 'Roland Garros', 'Wimbledon', 'US Open'], loc='upper center',prop={'size': 9})