Body performance analysis

multi class classification

Body performance analysis dataset - Kaggle. This is data that confirmed the grade of performance with age and some exercise performance data.

Workflow

1. Data analysis

   • look at data
   • set proper data types / get dummies
   • fill missing data
   • create train / test split

2. Feature selection & regularization

   • remove unnecessary / collinear features
   • scale data
   • search outliers
   • create baseline models

3. Best model selection

   • create pipelines
   • run optuna
   • choose best model

4. Testing & Interpretation

   • test model in order to baseline model
   • calculate model scores

5. Use & Serve

Additional files

• Pipelines - created to be optimized in optuna
• Serving - contains class to serve model via http

Data

data shape : (13393, 12)

• age : 20 ~64
• gender : F,M
• height_cm : (If you want to convert to feet, divide by 30.48)
• weight_kg
• body fat_%
• diastolic : diastolic blood pressure (min)
• systolic : systolic blood pressure (min)
• gripForce
• sit and bend forward_cm
• sit-ups counts
• broad jump_cm
• class : A,B,C,D (A: best) / stratified

Source

Korea Sports Promotion Foundation Some post-processing and filtering has done from the raw data.