- Completed
This analysis is based on a fictional data, but with real background and situation.
Flyball is a relay team competition for dogs where participants jump obstacles to retrieve a ball from a special box. The competitions are run in teams of four dogs, as a relay. If you want to know more information about the Flyball sprt, visit this Wikipedia page).
The data imitates that the fictional Flyball team's (Wild Runners Flyball Team – or WRFT) coach hired me to analyze their last year's dataset from different races. The overall goal is to find insights that will help to improve their performace.
The analysis was originally made for the in-house competition of the Data36.com data science club, where I ranked at first place with this EDA.
A one-sentence summary of the overall goal:
Processing the WRFT flyball team's competition data from the past year to build up a comprehensive picture, which will also help them to achieve even higher levels of performance in the future.
The initial dataset contains the results of the Czech national and the international competition related to the WRFT team, furthermore the base data of the racing dogs. A detailed description of the dataset variables is available here.
The final analysis consists of 3 main parts:
- Data preprocessing and cleaning
- Basic EDA
- Advanced EDA (with collecting data from external sources)
- Team composition optimization
I will summarize the main tasks and challenges of each section below.
A detailed description for the following will be published soon.
- Data Cleaning
- Data Exploration
- Investigate Statistical Metrics
- Data Visualization
- Feature Importance analysis with Machine learning
- Optimization with Machine learning
- API usage
- Presentation of found insights
- Python
- Excel