player_consistency.py

# Add column for cold/neutral/hot start - based on (n_streak-margin) / n_streak makes or misses)
shots_df = shots_df.assign(start="Unknown")
for pl in players:
    logger.info(f"Processing data for {pl}")
    dates = shots_df[shots_df.player == pl].date.unique()
    for date in dates:
        day_filter = ((shots_df.player == pl) & (shots_df.date == date))
        day_df = shots_df[day_filter].sort_values("tot_time")
        if len(day_df) > n_streak:
            if day_df[:n_streak]["shot_made"].sum() >= n_streak - margin:
                shots_df.loc[day_filter, "start"] = "Hot"
            elif day_df[:n_streak]["shot_made"].sum() <= margin:
                shots_df.loc[day_filter, "start"] = "Cold"
            else:
                shots_df.loc[day_filter, "start"] = "Neutral"

# take a look at players' shot distances AFTER the hot / cold start
tmp_df = shots_df[shots_df.start.isin(["Hot", "Cold"])]
hot_grp_df = tmp_df[tmp_df.player.isin(players)].groupby(["player", "start"])