- Project motivations
- Installations
- File Descriptions
- Results
- Link to the blog post
FIFA 19 is one of the most popular football games. In this project we analyzed Fifa 19 players dataset and try to predict a player potential. The analysis uses CRISP-DM method for our analysis process. The process is as follows:
- Business Understanding
- Data Understanding
- Data Preparation
- Modeling
- Evaluation
- Deployment
The following are the questions we are interested in answering:
Q1: What's the ratio of total wages/ total potential for clubs.
Q2: Which are the high spending clubs? Which clubs are the most economical ?
Q3: What's the age distribution like? Is it related to player's overall rating? if yes, how is it related?
Q4: How is a player's skils set influence his potential? Can we predict a player's potential based on his skills' set?
- Python
- Libraries: sklearn, pandas, numpy, matplotlib, seaborn
- Jupyter notebook
- data.csv: Contains the FIFA 19 dataset
- Data Analysis of blog post: jupyter notebook which contains the analysis of FIFA 19 dataset
-
Money plays a crucial role in a club’s performance. Big clubs have been and will continue to spend huge amount of money in order to compete to win trophies.
-
A lot of players ended the career after 26 years of age. But there are a few players who continue to play football even at the age of 40.
-
Ball control, reaction, and age are the main determinants of a player’s potential. People playing this game should focus on these factors to purchase players for their clubs.
The following is the link to the blog post of the analysis: Predicting a players potential on FIFA 19