Build a tennis prediction or betting model

import os, time, requests

BASE = "https://api.citoapi.com/api/v1/tennis"
HEADERS = {"x-api-key": os.environ["CITO_API_KEY"]}

def pages(path, **params):
    page = 1
    while True:
        r = requests.get(f"{BASE}{path}", headers=HEADERS,
                         params={**params, "page_size": 100, "page": page})
        if r.status_code == 429:          # per-minute limit: wait and retry the same page
            time.sleep(6); continue
        body = r.json()
        yield from body["items"]
        if not body["has_next"]:
            return
        page += 1

def row(m):
    w, l = (m.get("stats") or {}).get("winner") or {}, (m.get("stats") or {}).get("loser") or {}
    return {
        "match_id": m["canonical_id"], "date": m["match_date"], "surface": m["surface"],
        "level": m["level"], "round": m["round"], "best_of": m["best_of"],
        "winner_id": m["winner_id"], "loser_id": m["loser_id"],
        "winner_rank": m["winner"]["rank"], "loser_rank": m["loser"]["rank"],
        "w_ace": w.get("aces"), "l_ace": l.get("aces"),
        "w_1st_in": w.get("first_serve_pct"), "l_1st_in": l.get("first_serve_pct"),
        "w_1st_won": w.get("first_serve_won_pct"), "l_1st_won": l.get("first_serve_won_pct"),
        "w_2nd_won": w.get("second_serve_won_pct"), "l_2nd_won": l.get("second_serve_won_pct"),
        "outcome": m["outcome"],          # COMPLETED, RETIREMENT, WALKOVER, DEFAULT, ABANDONED
    }

train = [row(m) for m in pages("/matches", edition_year=2025, tour="ATP", level="A", include="stats")]

from datetime import date, timedelta

yesterday = (date.today() - timedelta(days=1)).isoformat()
new_rows = [row(m) for m in pages("/matches/completed", date=yesterday, include="stats")]

# Serve statistics can land up to about 6 hours after a match ends.
# Re-read rows whose stats_available is false on the next run:
pending = [r["match_id"] for r in new_rows if r["w_ace"] is None]
for i in range(0, len(pending), 50):
    batch = requests.get(f"{BASE}/matches/stats", headers=HEADERS,
                         params={"ids": ",".join(pending[i:i + 50])}).json()
    # batch["items"] holds the same object as /matches/{id}/stats, batch["not_found"] any unknown ids

const BASE = "https://api.citoapi.com/api/v1/tennis";
const headers = { "x-api-key": process.env.CITO_API_KEY };
const get = (path) => fetch(BASE + path, { headers }).then((r) => r.json());

const [p1, p2] = ["atp_206173", "atp_207989"];
const [stats1, stats2, h2h, form1, form2] = await Promise.all([
  get(`/players/${p1}/stats?surface=Hard&year_from=2025`),
  get(`/players/${p2}/stats?surface=Hard&year_from=2025`),
  get(`/h2h?players=${p1},${p2}&surface=Hard`),
  get(`/players/${p1}/form?limit=10`),
  get(`/players/${p2}/form?limit=10`),
]);

const features = {
  hard_win_pct_p1: stats1.career_summary.win_percentage,
  hard_win_pct_p2: stats2.career_summary.win_percentage,
  first_serve_won_p1: stats1.serving_stats.first_serve_points_won_pct,
  first_serve_won_p2: stats2.serving_stats.first_serve_points_won_pct,
  return_games_won_p1: stats1.return_stats.return_games_won_pct,
  return_games_won_p2: stats2.return_stats.return_games_won_pct,
  h2h_p1_wins: h2h.summary.player1_wins,
  h2h_p2_wins: h2h.summary.player2_wins,
  deciding_sets_p1: h2h.deciding_sets.player1_deciding_set_wins,
  form_p1: form1.win_pct,
  form_p2: form2.win_pct,
  rank_p1: h2h.player1.current_rank,
  rank_p2: h2h.player2.current_rank,
};