atp_unique_gs_winners.py

# Unique number of players that won GS and Masters per period 
s = tennis_df[(tennis_df['round']=='F')&(tennis_df['tourney_level'].isin(['G']))&(tennis_df['tourney_year'].between('1975','1985'))].agg({'winner_name':'nunique'})
t = tennis_df[(tennis_df['round']=='F')&(tennis_df['tourney_level'].isin(['G']))&(tennis_df['tourney_year'].between('1986','1996'))].agg({'winner_name':'nunique'})
u = tennis_df[(tennis_df['round']=='F')&(tennis_df['tourney_level'].isin(['G']))&(tennis_df['tourney_year'].between('1997','2007'))].agg({'winner_name':'nunique'})
v = tennis_df[(tennis_df['round']=='F')&(tennis_df['tourney_level'].isin(['G']))&(tennis_df['tourney_year'].between('2008','2018'))].agg({'winner_name':'nunique'})

s['1975-1985'] = s['winner_name']
s=s.drop('winner_name')
t['1986-1996'] = t['winner_name']
t=t.drop('winner_name')
u['1997-2007'] = u['winner_name']
u=u.drop('winner_name')
v['2008-2018'] = v['winner_name']
v=v.drop('winner_name')

dfl = [s,t,u,v]
dfs = pd.concat(dfl)

x=pd.DataFrame(dfs, columns=['Unique_Count']).reset_index()
x.columns=['Year range','Unique winners']

ax=x.plot('Year range', 'Unique winners', kind='bar', title='Unique # of Players that Won GS Finals', legend=False)
ax.set_ylim(0,20)

for i, v in enumerate(x['Unique winners']):
    ax.text(i-0.1, v+0.6, str(v))