# SETUP — edit only STUDENT_ID. Integers and quoted IDs both work.
STUDENT_ID = "YOUR_ID"
import hashlib
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from IPython.display import display

STUDENT_ID = str(STUDENT_ID).strip()
if not (STUDENT_ID.isascii() and STUDENT_ID.isdigit() and 6 <= len(STUDENT_ID) <= 12):
    raise ValueError("Replace YOUR_ID with your own 6–12 digit student ID, then run again.")
seed = int.from_bytes(hashlib.sha256(('FDS-Lab2-v1:' + STUDENT_ID).encode()).digest()[:8], 'big')
rng = np.random.default_rng(seed)
case_code = hashlib.sha256(('FDS-Lab2-v1:' + STUDENT_ID).encode()).hexdigest()[:10]
plt.rcParams.update({'figure.figsize': (8, 4), 'axes.spines.top': False, 'axes.spines.right': False})
pd.options.display.float_format = '{:.3f}'.format
N = 240
programme = rng.choice(['A', 'B'], N, p=[.55, .45])
entry = np.clip(rng.normal(rng.uniform(62,68), rng.uniform(8,11), N), 0, 100)
minutes = rng.lognormal(rng.uniform(4.1,4.4), .85, N)
# Two different teaching groups: their score patterns intentionally differ.
assessment = np.clip(rng.normal(np.where(programme == 'A', 43, 78), 4.5), 0, 100)
satisfaction = rng.choice([1.,2.,3.,4.,5.], N, p=[.08,.12,.2,.35,.25])
satisfaction[rng.choice(N, size=int(rng.integers(35,61)), replace=False)] = np.nan
students = pd.DataFrame({'record_id':np.arange(1,N+1), 'programme':programme,
    'entry_score':entry, 'weekly_minutes':minutes,
    'assessment_score':assessment, 'satisfaction':satisfaction})
small = np.sort(rng.choice(np.arange(35,86), 8, replace=False)).astype(float)
focus_index = int(np.argmax(entry))
coarse_bins = int(rng.choice([2,3,4]))
fine_bins = int(rng.choice([35,40,45]))
scenario = str(rng.choice(['typical use', 'total workload']))
print('Case:',case_code, '| ID:',STUDENT_ID, '| Final decision:',scenario)
print('Keep this case code in your submission. Setup complete.')