generate_dataset.py

# generate_dataset.py
# Run: python generate_dataset.py
import json, random, csv

with open('career_data.json','r',encoding='utf-8') as f:
    data = json.load(f)

# collect all interest keys across both levels
interest_keys = []
for lvl in data:
    for k in data[lvl].keys():
        if k not in interest_keys:
            interest_keys.append(k)

# collect all careers
all_careers = []
for lvl in data:
    for k, v in data[lvl].items():
        for c in v.get('careers', []):
            if c not in all_careers:
                all_careers.append(c)

# helper to pick target career based on selected interests
def pick_target(selected_interests):
    # prefer careers that appear in selected_interests' career lists
    candidates = []
    for key in selected_interests:
        # find careers for this key (search both levels)
        for lvl in data:
            if key in data[lvl]:
                candidates += data[lvl][key].get('careers', [])
    if not candidates:
        return random.choice(all_careers)
    # weighted pick: some randomness
    return random.choice(candidates)

rows = []
N = 2000  # generate 2000 synthetic rows (adjustable)
for _ in range(N):
    # random academic level
    level = random.choice(['10th','12th'])
    perc = round(random.uniform(30, 98),2)  # realistic perc
    # randomly select between 1 and 5 interests (from that level preferably)
    available_keys = list(data[level].keys())
    num_sel = random.randint(1, min(5,len(available_keys)))
    selected = random.sample(available_keys, num_sel)
    # compute quiz scores per interest (0-50)
    quiz_scores = [random.randint(0,50) for _ in selected]
    quiz_avg = round(sum(quiz_scores)/len(quiz_scores),2)
    top_interest = selected[quiz_scores.index(max(quiz_scores))]
    target = pick_target(selected)

    # create row dict
    row = {
        'percentage': perc,
        'academic_level': level,
        'num_selected_interests': num_sel,
        'quiz_average': quiz_avg,
        'top_interest': top_interest,
        'target_career': target
    }
    rows.append(row)

# write CSV
fieldnames = ['percentage','academic_level','num_selected_interests','quiz_average','top_interest','target_career']
with open('career_data.csv','w',newline='',encoding='utf-8') as f:
    writer = csv.DictWriter(f,fieldnames=fieldnames)
    writer.writeheader()
    for r in rows:
        writer.writerow(r)

print('Generated career_data.csv with', len(rows), 'rows')