Predict FIFA Players Value | Machine Learning

Project Steps (End-to-End):

• Gather data from Kaggle.
• Perform data cleaning and preprocessing.
• Perform exploratory data analysis.
• Perform feature engineering.
• Build an ensemble technique model.
• Build client-facing API with Flask.
• Deployed solution to Heroku.

Project Details:

Python: 3.7

Packages: numpy, pandas, seaborn, matplotlib, missingno, plotly, sklearn, boruta_py, lightgbm, xgboost, pickle

Model: XGBoost Regressor

RMSE Score:: 0.0056

EDA Charts:











Code Snippets:

Data Cleaning:



EDA:



Feature Engineering:



Modelling:



For full source code and project details please visit the GitHub repository.