A complete front-to-end ML Project which predicts selection and salary in Placements by Sanidhya Singh
The aim of the project was simple, to analyze the dataset properly and try to make models which predict Selection Status and Salary as accurately as possible. The models used ulimately in the project were Support Vector Classifer and Elastic Net (Regularised Linear Regression) after performing a lot of Analysis and Tests. The notebook contains a complete view of the approach and provides an explanative walk-through towards all the processes done and the thought-process behind them. Make sure to read the Markdown Annotations to understand the steps to solve the problem in hand and why they were done!
- Datasets/Placement_Data_Full_Class.csv - Dataset used in csv file format.
- project.ipynb - The entire project in the form of an Integrated Python Notebook(ipynb)
Note: In this project, various libraries of python have been used, most importantly sklearn which is the backbone of the project. Other libraries used are numpy, pandas, warnings, matplotlib, seaborn, xgboost. Make sure you have them installed if you want to run the code yourself in the notebook or otherwise.
Dataset Source and its Description, on Kaggle.
Kaggle Submission, of the project.