By: William-CCS96
This notebook is the result of the practice carried out in the course "Curso de Matemáticas para Data Science: Estadística Descriptiva", where the Dataset "ObesityDataSet_raw_and_data_synthetic" was used evaluates obesity rates in individuals from Colombia, Peru and Mexico.
The purpose of the project is to put into practice the concepts of descriptive statistics focused on data science, through the following workflow:
- Development
- Data types and description
- Null Data Review
- Statistical analysis
- Measures of central tendency
- Measures of dispersion
- Measures of dispersion
- Standard deviation:
- Range and quartiles
- Outlier detection
- Linear scaling of numerical variables
- Linear scaling min-max
- Z-score scaling
- Nonlinear scaling of numerical variables
- Scaling of categorical variables
- One-hot scaling
- One-hot with Scikit learn
- One-hot with pandas "dummies" method