make_synthetic.py

# make_synthetic.py
import csv, random
streams = ["science","arts","commerce","vocational"]
rows = []
for i in range(800):
    stream = random.choices(streams, weights=[4,3,3,2])[0]
    answers = []
    for q in range(10):
        if stream=="science":
            answers.append(random.choices([1,2,3,4], weights=[5,2,1,1])[0])
        elif stream=="arts":
            answers.append(random.choices([1,2,3,4], weights=[1,1,5,2])[0])
        elif stream=="commerce":
            answers.append(random.choices([1,2,3,4], weights=[1,2,1,5])[0])
        else:
            answers.append(random.randint(1,4))
    rows.append(answers + [stream])

with open("dataset.csv","w",newline="") as f:
    w = csv.writer(f)
    w.writerow([f"Q{i+1}" for i in range(10)]+["Stream"])
    w.writerows(rows)
print("Wrote dataset.csv")