shot_dist_profile_by_team.py

# ========================================
# Now let's do the same for each team
# ========================================
shots_df["teamId"] = shots_df["teamId"].astype(int)
gdf_list = list()
for tm_id in shots_df.teamId.unique():
    tm_df = shots_df[shots_df.teamId == tm_id]
    tm_gdf = tm_df.groupby("shot_zone").agg({"shot_made": "sum", "period": "count"})
    tm_gdf = tm_gdf.reset_index().rename({"period": "shot_atts"}, axis=1)
    tm_name = teams.find_team_name_by_id(tm_id)["abbreviation"]
    tm_gdf = tm_gdf.assign(team=tm_name)
    tm_gdf = tm_gdf.assign(shot_freq=tm_gdf.shot_atts / tm_gdf.shot_atts.sum())
    tm_gdf = tm_gdf.assign(shot_acc=tm_gdf.shot_made / tm_gdf.shot_atts)
    tm_gdf = tm_gdf.assign(rel_freq=tm_gdf.shot_freq - gdf.shot_freq)
    tm_gdf = tm_gdf.assign(rel_acc=tm_gdf.shot_acc - gdf.shot_acc)
    tm_gdf = tm_gdf.assign(rel_ev=tm_gdf.rel_acc * 2)
    tm_gdf.loc[tm_gdf["shot_zone"].str.contains("3pt"), "rel_ev"] = tm_gdf[tm_gdf["shot_zone"].str.contains("3pt")]["rel_acc"] * 3
    gdf_list.append(tm_gdf)
gdf_tot = pd.concat(gdf_list)