Evaluate Machine Learning Models with Yellowbrick

They will utilize visualizations to guide machine learning workflow in this course. Based on passive sensor data such as temperature, humidity, light, and CO2 levels, they will attempt to forecast whether rooms in flats are inhabited or vacant. For binary classification, they will create a logistic regression model. This is a follow-up to the Room Occupancy Detection course. They will cover the following topics in machine learning workflow, with an emphasis on visual steering of analysis: model evaluation with ROC/AUC plots, confusion matrices, cross-validation scores, and defining discrimination thresholds for logistic regression models.

This course uses Rhyme, Coursera's hands-on project platform. Rhyme allows you to work on projects in your browser in a hands-on manner. You'll have immediate access to pre-configured cloud PCs with all of the applications and data you'll need for the job. Everything is fully set up in your browser, so you can concentrate solely on learning. You'll get immediate access to a cloud desktop with Python, Jupyter, Yellowbrick, and scikit-learn pre-installed for this project.

Notes:

• You will have 5 attempts to access the cloud desktop. You will, however, be allowed to watch the instructional films as many times as you like.
• Learners in the North American region will benefit the most from this course. They were working on bringing the same experience to other parts of the world.

THE SKILLS YOU WILL DEVELOP

• Data science
• Machine-learning
• Python Programming
• Data Visualization (DataViz)
• Scikit-Learn

• ROC/AUC Plots
• Classification Report and Confusion Matrix
• Cross Validation Scores
• Evaluating Class Balance
• Discrimination Threshold for Logistic Regression

Rating: 4.8/5

Enroll here: coursera.org/projects/machine-learning-model-yellowbrick