nescobar

# Function to plot effectiveness of a player
def plot_effectiveness(player):
    
    pw = tennis_df[(tennis_df['winner_name'] == player)].groupby(['tourney_year','surface'], as_index=False).agg(['count'])
    pww = pw['tourney_id'].reset_index()
    pl = tennis_df[(tennis_df['loser_name'] == player)].groupby(['tourney_year','surface'], as_index=False).agg(['count'])
    pll = pl['tourney_id'].reset_index()
    pww.columns = ['tourney_year','surface','wins']
    pll.columns = ['tourney_year','surface','loses']
    

nescobar

# 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)

nescobar

# Extract retirements
ret_df = tennis_df[tennis_df['score'].str.contains("RET")==True][['tourney_year','tourney_level','surface','tourney_id','winner_name']]
ref_df_f = ret_df.groupby(['tourney_year','surface'], as_index=False).agg('count')

fig = plt.figure(figsize=(15,5))

ax = fig.add_subplot(111)
plt.style.use('seaborn-colorblind')
plt.title('Retirements - Evolution of Retirements by Surface')
plt.ylabel('Number of Retirements')

nescobar

ret_df_f.columns = ['tourney_year','surface','rets']

notret_df = tennis_df[tennis_df['score'].str.contains("RET")==False][['tourney_year','surface','tourney_id']]
notret_df_f = notret_df.groupby(['tourney_year','surface'], as_index=False).agg('count')[['tourney_year','surface','tourney_id']]
notret_df_f.columns = ['tourney_year','surface','norets']

dfs = (ret_df_f, notret_df_f)
dfs_concat = pd.concat(dfs)

dfs_c = dfs_concat.fillna(0).groupby(['tourney_year','surface']).agg({'rets':'sum','norets':'sum'}).reset_index()

nescobar

h2h_wl = tennis_df_all.groupby(['winner_name','loser_name']).agg({'tourney_id':'count','tourney_year':'max'}).reset_index()
h2h_wl.columns = ['player_a','player_b','total','year']
h2h_lw = tennis_df_all.groupby(['loser_name','winner_name']).agg({'tourney_id':'count','tourney_year':'max'}).reset_index()
h2h_lw.columns = ['player_a','player_b','total','year']

h2h_f = h2h_wl.merge(h2h_lw, on=['player_a', 'player_b'])
h2h_f['total'] = h2h_f['total_x'] + h2h_f['total_y']
h2h_f['player_a'] = np.where(h2h_f['player_a'] < h2h_f['player_b'], h2h_f['player_a'], h2h_f['player_b'])
h2h_f['player_b'] = np.where(h2h_f['player_a'] > h2h_f['player_b'], h2h_f['player_a'], h2h_f['player_b'])
h2h_f['year'] = np.where(h2h_f['year_x'] > h2h_f['year_y'], h2h_f['year_x'], h2h_f['year_y'])