Project: Build fraud dataset

I need a synthetic dataset for credit card transactions, with details on whether each transaction is potentially fraudulent. The dataset should include diverse records with fields such as Transaction ID, Amount, Merchant Type, Location (city and country), Transaction Time, Device Type, Customer Country, Customer State, Transaction Label (Fraud or Not Fraud), and a Comment. 

For each row:
- Generate a unique **Transaction ID**.
- Choose an **Amount** value, varying from low (e.g., below $100) to high (e.g., above $1,000).
- **Merchant Types** should include categories like Groceries, Electronics, Restaurants, Jewelry, and Online Retail.
- **Location** should be specific, including city and country (e.g., “New York, USA” or “Tokyo, Japan”).
- **Transaction Time** should include both date and time.
- For **Device Type**, pick from options like Mobile, Desktop, and Tablet.
- Include **Customer Country** and **Customer State**.
- Label each transaction as **Fraud** or **Not Fraud** based on the pattern of spending, geography, and amount:
  - Mark a transaction as "Fraud" if it’s a high amount in a location far from the customer's usual country/state.
  - Mark as "Not Fraud" for typical transactions (e.g., within usual geography, lower amounts).
- Include a **Comment** explaining the reason for the label (e.g., “unusually high amount outside customer’s region” or “typical transaction in customer’s area”).

Generate 5 example records in the following JSON format:

{
   "transaction_id": "...",
   "amount": ...,
   "merchant_type": "...",
   "location": "...",
   "transaction_time": "...",
   "Device Type": "...",
   "customer_country": "...",
   "customer_state": "...",
   "transaction_label": "not_fraud  |  fraud",
   "comment": "..."
}

[
    {
        "transaction_id": "TXN00123456",
        "amount": 85.50,
        "merchant_type": "Groceries",
        "location": "Chicago, USA",
        "transaction_time": "2024-10-28 14:32:15",
        "Device Type": "Mobile",
        "customer_country": "USA",
        "customer_state": "IL",
        "transaction_label": "not_fraud",
        "comment": "Typical grocery purchase within customer's state"
    },
    {
        "transaction_id": "TXN00123457",
        "amount": 1200.75,
        "merchant_type": "Jewelry",
        "location": "Paris, France",
        "transaction_time": "2024-10-28 09:15:42",
        "Device Type": "Desktop",
        "customer_country": "USA",
        "customer_state": "CA",
        "transaction_label": "fraud",
        "comment": "High amount spent internationally, unusual for customer location"
    }
]

import json

# This file has the synthetic data in JSON [ ] format
j_file = "./synthetic-credit-card-fraud/credit-card-fraud-chatgpt.json"

with open(j_file) as f:
    dat = json.load(f)

# JSON array is converted to json line format
def  write_jsonl_file(dat_subset, file_name):
    jsonl = ""
    for rec in dat_subset:
        jsonl = jsonl + json.dumps(rec) + "\n"

    with open(file_name, "w") as f:
        f.write(jsonl)

    print(file_name, "# of lines : ", len(dat_subset))

# Train - split
output_file_prefix = "./synthetic-credit-card-fraud/credit-card-fraud-chatgpt-"
file_name = output_file_prefix+"train.jsonl"
write_jsonl_file(dat[0:56], file_name)

# Validation - split
file_name = output_file_prefix+"validate.jsonl"
write_jsonl_file(dat[56:70], file_name)

# Test - split
file_name = output_file_prefix+"test.jsonl"
write_jsonl_file(dat[70:], file_name)

# Get the counts for fraud & not_fraud examples
training_file_name = "./synthetic-credit-card-fraud/credit-card-fraud-chatgpt-train.jsonl"

# Count fraud vs not fraud examples in the training file
def get_training_dataset_distribution(data_file_name):
    fraud_count = 0
    not_fraud_count = 0
    with open(data_file_name) as f:
        for line in f:
            if json.loads(line)["transaction_label"] == "fraud":
                fraud_count = fraud_count + 1
            else:
                not_fraud_count = not_fraud_count + 1
    
    # Calculate % of examples labeled as Fraud
    fraud_pct = int(fraud_count*100/(fraud_count + not_fraud_count))
    
    print("Fraud labels : ", fraud_pct, "%  ")
    print("Not_Fraud labels : ", (100-fraud_pct), "%  ")

    return fraud_count, not_fraud_count

# Check the balance
fraud_count, not_fraud_count = get_training_dataset_distribution(training_file_name)

# Check number of additional examples to be generated
if (fraud_count - not_fraud_count) > 0:
    print("Augmentation suggested. add examples for 'Not Fraud':", (fraud_count - not_fraud_count))
elif (fraud_count - not_fraud_count) < 0:
    print("Augmentation suggested. add examples for 'Fraud':", (not_fraud_count - fraud_count))
else:
    print("Dataset is balanced")

# JSON file with additional examples
j_file_additional = './synthetic-credit-card-fraud/credit-card-fraud-chatgpt-train-additional.json'

# Open the file and read the JSON array data
with open(j_file_additional) as f:
    additional_dat = json.load(f)

# Print count of additional examples for validation
print( "# of additional examples : ", len(additional_dat))

# Convert JSON array to JSON Line
jsonl = ""
for rec in additional_dat:
    jsonl = jsonl + json.dumps(rec) + "\n"

# Open the credit-card-fraud-chatgpt-train.json and append the augmentation examples to it
training_file_name = "./synthetic-credit-card-fraud/credit-card-fraud-chatgpt-train.jsonl"

with open(training_file_name) as training_file:
    original_training_dat = training_file.read()

output_train_file = './synthetic-credit-card-fraud/credit-card-fraud-chatgpt-train-augmented.jsonl'
with open(output_train_file, "w") as f:
    f.write(original_training_dat)
    f.write(jsonl)

# Check if the dataset is now balanced
get_training_dataset_distribution(output_train_file)