data-science

Exploratory data analysis is performed by profiling data, analyzing distributions, identifying correlations, and detecting outliers. This skill provides a structured methodology using pandas to quickly profile your dataframe and visualize its underlying statistical properties.

Feature engineering for machine learning involves transforming numeric and categorical data and extracting features from time-series. This skill offers structured methods to process your variables, ensuring optimal inputs for your predictive models.

Evaluating machine learning models with scikit-learn requires train/test splits, cross-validation, and performance assessment. This skill guides you through model selection, hyperparameter tuning, and best practices for robust quality assurance.

Statistical hypothesis testing and effect size calculation are fully supported for robust data interpretation. Using the statsmodels library, this skill facilitates rigorous statistical analysis to validate your data findings and hypothesis results.

Building customer churn prediction models is supported by analyzing transaction data to identify key purchasing behavior drivers. You can develop predictive models, evaluate performance, and visualize results to directly inform retention strategies.

Python libraries needed for statistical analysis and model development include pandas, scikit-learn, and statsmodels. These dependencies support data manipulation, statistical testing, modeling, and visualization throughout the structured workflow.