Sleeper League Roster Ages

dyno.py

import pandas as pd
from sleeper_wrapper import League, Players, User
import ipdb
import json
import os.path
from tabulate import tabulate

DYNO_LEAGUE = 976543638605881344
league = League(DYNO_LEAGUE)
rosters = league.get_rosters()
players_file = "players_cache.json"
if not os.path.exists(players_file):
    with open(players_file, "w") as ofp:
        buf = Players()
        ofp.write(json.dumps(buf))

players = None
with open(players_file, "r") as ifp:
    players = json.load(ifp)

rows = []
for roster in rosters:
    user = User(roster["owner_id"]).get_user()

    roster_players = [players[x] for x in roster["players"] if x in players]
    for x in roster_players:
        x["owner"] = user["display_name"]
    rows += roster_players

df = pd.DataFrame(rows)
# Filter out DST
df = df[df["age"].notna()]
df["name"] = df["first_name"] + " " + df["last_name"]
owner_df = (
    df[["owner", "age"]]
    .groupby("owner")
    .agg(
        Average=("age", "mean"),
        Median=("age", "median"),
        Maximum=("age", "max"),
        Minimum=("age", "min"),
    )
)
owner_df.sort_values("Average", inplace=True)
print("Roster Age Stats")
print(
    tabulate(owner_df, headers="keys", tablefmt="psql", showindex=True, floatfmt=".2f")
)

print(
    "League-wide age stats: avg: {0:.2f} median: {0:.2f} min: {0:.2f} max: {0:.2f}".format(
        df["age"].mean(), df["age"].median(), df["age"].max(), df["age"].min()
    )
)
num_print = 10
df.sort_values("age", inplace=True)
df_young = df[["name", "owner", "age", "position"]].head(num_print)
print(f"Top {num_print} Youngest Players")
print(tabulate(df_young, headers="keys", tablefmt="psql", showindex=False))

df.sort_values("age", inplace=True, ascending=False)
df_old = df[["name", "owner", "age", "position"]].head(num_print)
print(f"Top {num_print} Oldest Players")
print(tabulate(df_old, headers="keys", tablefmt="psql", showindex=False))

num_over_30 = len(df[df["age"] >= 30])
num_under_25 = len(df[df["age"] < 25])
num_25_29 = len(df[(df["age"] >= 25) & (df["age"] < 30)])
total = len(df)
print(
    "Players over 30: {} ({:.1f}%) Players 25-29: {} ({:.1f}%) Under 25: {} ({:.1f}%)".format(
        num_over_30,
        (num_over_30 / total) * 100,
        num_25_29,
        (num_25_29 / total) * 100,
        num_under_25,
        (num_under_25 / total) * 100,
    )
)