Detecting Credit Card fraudulent transactions using Machine Learning It is important that credit card companies are able to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase.
Dataset used is from Kaggle - https://www.kaggle.com/mlg-ulb/creditcardfraud The dataset contains transactions made by credit cards in September 2013 by European cardholders. This dataset presents transactions that occurred in two days, where we have 492 frauds out of 284,807 transactions. The dataset is highly unbalanced, the positive class (frauds) account for 0.172% of all transactions. Features V1, V2, … V28 are the principal components obtained with PCA, the only features which have not been transformed with PCA are 'Time' and 'Amount'. Feature 'Time' contains the seconds elapsed between each transaction and the first transaction in the dataset. The feature 'Amount' is the transaction Amount, this feature can be used for example-dependant cost-sensitive learning. Feature 'Class' is the response variable and it takes value 1 in case of fraud and 0 otherwise.
- Make sure python3 and git is installed. Install Python : From official website
- Clone this repository to your local machine.
- Run the following command for installing all the required dependencies all at once-
py -m pip install -r requirements.txt
- Download the dataset file creditcard.csv from Kaggle link provided above.
- Run fraud_detection.ipynb in a jupyter notebook
jupyter notebook fraud_detection.ipynb
From official website
py --version
python --version
py -m venv blog_app
.\Scripts\activate
.\Scripts\deactivate
pip -V
If you are running the virtual env, it'll show the path to the environment's location.
py -m pip install package_name
py -m pip install django
django --version
py -m django --version
python manage.py startapp your_app_name
Then make an entry for the app in the INSTALLED_APPS section in settings.py Include URL's of your new app using include() in url.py (main app)
There are 4 policy levels to choose from. From most secure to most insecure:
-
Restricted: No Powershell scripts can be run. This is the default setting.
-
AllSigned: Scripts can be run, but all must have a digital signature. Even if you wrote the script yourself on the local computer.
-
RemoteSigned: Locally-written scripts can be run. But scripts from outside (email, IM, Internet) must be signed by a trusted publisher.
-
Unrestricted: Any script will run. Regardless of who created them or whether they are signed.
To view the current systemwide Execution Policy setting :
Get-ExecutionPolicy
To set execution policy :
Set-ExecutionPolicy remotesigned
$null > file_name.cpp
git config --global user.email "user_mail"
git config --global user.name "user_name"
python manage.py runserver
python manage.py makemigrations
python manage.py migrate
{% csrf_token %}
git checkout <branch-name>
git branch -a
py -m pip freeze
py -m pip list
Change to master branch
git checkout master
git merge <branch-name>
git log --graph --oneline --decorate --all
git remote -v
git push --all <remote-origin>
git remote add new-remote-origin-name https://github.com/user_name/repo.git
python manage.py migrate
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.