Batsman Statistics

batsman.py

# Group details on batsmen
batgroup = balldf.groupby(['batsman'])

# Create a batting dataframe with a summary statistics for each batsman
batdf = pd.DataFrame(batgroup['ball'].count()).rename(columns={'ball':'balls_faced'})
batdf['innings'] = batgroup['id'].nunique()
batdf['runs'] = batgroup['batsman_runs'].sum()
batdf['4s'] = balldf[balldf['batsman_runs'] == 4].groupby('batsman')['batsman_runs'].count()
batdf['4s'].fillna(0,inplace=True)
batdf['6s'] = balldf[balldf['batsman_runs'] == 6].groupby('batsman')['batsman_runs'].count()
batdf['6s'].fillna(0,inplace=True)

# Batting average = total rus scored/no. of times batsman is been dismissed
# Approximated here to matches instead of no. of dismissals
batdf['bat_average'] = round(batdf['runs']/batdf['innings'],2)

# Strike Rate = (Runs Scored / Balls faced) * 100
batdf['bat_strike'] = round(batdf['runs']/batdf['balls_faced']*100,2)