Python: Scikit-learn
Scikit-learn is the core machine learning library for Python. It allows you to run a wide range of classification, clustering, regression, and prediction algorithms all using the same framework. It includes tools for splitting your data into test and training sets, parameter estimation using grid search and cross validation, evaluating your models, and making predictions. It works with NumPy and SciPy. If you want to use Python for predictive modeling, Scikit-learn is the place to start.
Things you’ll learn in this workshop:
Scikit-learn workflow
Creating test and training data sets
Fitting both supervised and unsupervised models
Maximizing model performance with parameter grid search and cross validation
Evaluating model fit
Predicting outcomes for new data
Prerequisites:
Basic Python and how to use Jupyter Notebooks.
Familiarity with the process of building predictive models for classification, clustering, regression, or other applications (separate from Python); this workshop covers how to use Python for machine learning, not the theories behind machine learning