Skip to content

Collection of Initial, First Efforts Kaggle Projects

Notifications You must be signed in to change notification settings

leyldy/kaggle_projects

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

kaggle_projects

Collection of initial Kaggle projects. Note files are not as well organized.

Project 1: Housing Prices

Predicting housing prices based on series of attributes. Beginner project, using linear regression mainly and focusing on encoding variables, creating dummy columns for categorical data, etc.

Jupyter Notebook

Project 2: Facebook Checkin Prediction

Predict what kind of checkin users made in each different location in a large area. Coordinates for each observation was given along with user data and attributes. Since the dataset was larger than normal (700MB), processed data by dividing the data into n x n grids, by utilizing coordinate data. Processed and predicted data on each grid by using KNN within each grid for classification.

Python Code

Project 3: Allstate Claims

Predict cost of claims (severity of claims) based on claim attributes. Utilized more advanced machine learning algorithms such as XGBoost, RandomForest, as well as more data transformations, correlation checks, feature engineering, etc.

Jupyter Notebook

About

Collection of Initial, First Efforts Kaggle Projects

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published