import csv
import datetime
import urllib.request
import json
import matplotlib.pyplot as plt
import numpy as np

AWARD_DAY = 10
AWARD_MONTH = 12
CSV_FILENAME = "physics_nobel_laureates_ages_1901_2025.csv"

def parse_date(s):
    parts = [int(p) for p in s.split('-')]
    if len(parts) == 3:
        return datetime.date(parts[0], max(1, parts[1]), max(1, parts[2]))
    elif len(parts) == 2:
        return datetime.date(parts[0], max(1, parts[1]), 1)
    else:
        return datetime.date(parts[0], 1, 1)

def age_on(dob, year):
    award_date = datetime.date(year, AWARD_MONTH, AWARD_DAY)
    years = award_date.year - dob.year - (
        (award_date.month, award_date.day) < (dob.month, dob.day))
    return years

LURL = "https://[Log in to view URL]"
with urllib.request.urlopen(LURL) as url:
    data = json.loads(url.read().decode())

rows = []
for person in data.get("laureates", []):
    if person.get("knownName") is None:
        continue
    name = person["knownName"]["en"]
    birth = person.get("birth", {})
    birthdate = birth.get("date")
    if not birthdate:
        continue
    dob = parse_date(birthdate)
    for prize in person.get("nobelPrizes", []):
        if prize.get("category", {}).get("en") != "Physics":
            continue
        year = int(prize["awardYear"])
        age = age_on(dob, year)
        rows.append({
            "year": year,
            "laureate": name,
            "birthdate": birthdate,
            "age_on_award_date": age
        })

extra_2025 = [
    ("John Clarke", "1942-02-10"),
    ("Michel H. Devoret", "1953-01-01"),
    ("John M. Martinis", "1958-01-01"),
]
for name, birthdate in extra_2025:
    dob = parse_date(birthdate)
    rows.append({
        "year": 2025,
        "laureate": name,
        "birthdate": birthdate,
        "age_on_award_date": age_on(dob, 2025),
    })

seen = set()
deduped = []
for r in rows:
    key = (r["year"], r["laureate"])
    if key in seen:
        continue
    seen.add(key)
    deduped.append(r)
deduped.sort(key=lambda r: (r["year"], r["laureate"]))

# --- Write to CSV ---
with open(CSV_FILENAME, "w", newline="", encoding="utf-8") as f:
    writer = csv.DictWriter(f, fieldnames=["year", "laureate", "birthdate", "age_on_award_date"])
    writer.writeheader()
    writer.writerows(deduped)

print(f"Wrote {len(deduped)} rows to {CSV_FILENAME}")

years = [r["year"] for r in deduped]
ages = [r["age_on_award_date"] for r in deduped]

plt.figure(figsize=(10, 8))
plt.scatter(years, ages, color='orange', label="Laureates")

slope, intercept = np.polyfit(years, ages, 1)
plt.plot(years, slope * np.array(years) + intercept, color='red',
         label=f"Trend: y = {slope:.2f}x + {intercept:.1f}")

plt.title("Age of Nobel Physics Laureates (1901–2025)")
plt.xlabel("Year")
plt.ylabel("Age at Award")
plt.legend()
plt.grid(True)
plt.show()