Machine Learning Socketify.py API using DescionTree Classifier to predict if a account is Fake or Not
- Socketify.py
- Scikit-Learn
- Sql lite
- instaloader api
- Docker
- Nginx Proxy Manager
- Self Hosted using Docker,Docker-Compose and Nginx Proxy manager on Home Server(Arch linux)
- Uses Socketify.py along with Scikit learn & Pandas To predict wheter a account is fake or not
- First It Uses a Jupyter Notebook to put all generated json data into a SQL lite database
- Uses Attributes like Followers,Following ,like etc. and DescionTree Classifier to determine the result
- Model is serialized into a Pickle file
- The api take a get request with username ,parses data using Instagrapi and predicts using serialized model
user_media_count- Total number of posts, an account has.user_follower_count- Total number of followers, an account has.user_following_count- Total number of followings, an account has.user_has_profil_pic- Whether an account has a profil picture, or not.user_is_private- Whether an account is a private profile, or not.user_biography_length- Number of characters present in account biography.username_length- Number of characters present in account username.username_digit_count- Number of digits present in account username.is_fake- True, if account is a spam/fake account, False otherwise