Hands-on Predicitive Analytics with Python
At Course Completion
This course is approximately 50% hands-on, combining expert lecture, real-world demonstrations and group discussions with machine-based practical labs and exercises. Our engaging instructors and mentors are highly experienced practitioners who bring years of current "on-the-job" experience into every classroom. Working in a hands-on learning environment, guided by our expert team, attendees will learn to:
· Understand the main concepts and principles of predictive analytics
· Use the Python data analytics ecosystem to implement end-to-end predictive analytics projects
· Explore advanced predictive modeling algorithms w with an emphasis on theory with intuitive explanations
· Learn to deploy a predictive model's results as an interactive application
· Learn about the stages involved in producing complete predictive analytics solutions
· Understand how to define a problem, propose a solution, and prepare a dataset
· Use visualizations to explore relationships and gain insights into the dataset
· Learn to build regression and classification models using scikit-learn
· Use Keras to build powerful neural network models that produce accurate predictions
· Learn to serve a model's predictions as a web application
Audience Profile
This course is geared for Python experienced attendees who wish to learn and use basic machine learning algorithms and concepts.
Prerequisites
Students should have skills at least equivalent to the following course(s) or should have attended as a pre-requisite:
· TTPS4873 Introduction to Python for Data Science
Outline
1. The Predictive Analytics Process
· Technical requirements
· What is predictive analytics?
· Reviewing important concepts of predictive analytics
· The predictive analytics process
· A quick tour of Python's data science stack
2. Problem Understanding and Data Preparation
· Technical requirements
· Understanding the business problem and proposing a solution
· Practical project – diamond prices
· Practical project – credit card default
3. Dataset Understanding – Exploratory Data Analysis
· Technical requirements
· What is EDA?
· Univariate EDA
· Bivariate EDA
· Introduction to graphical multivariate EDA
4. Predicting Numerical Values with Machine Learning
· Technical requirements
· Introduction to ML
· Practical considerations before modeling
· MLR
· Lasso regression
· KNN
· Training versus testing error
5. Predicting Categories with Machine Learning
· Technical requirements
· Classification tasks
· Credit card default dataset
· Logistic regression
· Classification trees
· Random forests
· Training versus testing error
· Multiclass classification
· Naive Bayes classifiers
6. Introducing Neural Nets for Predictive Analytics
· Technical requirements
· Introducing neural network models
· Introducing TensorFlow and Keras
· Regressing with neural networks
· Classification with neural networks
· The dark art of training neural networks
7. Model Evaluation
· Technical requirements
· Evaluation of regression models
· Evaluation for classification models
· The k-fold cross-validation
8. Model Tuning and Improving Performance
· Technical requirements
· Hyperparameter tuning
· Improving performance
9. Implementing a Model with Dash
· Technical requirements
· Model communication and/or deployment phase
· Introducing Dash
· Implementing a predictive model as a web application
Sorry! It looks like we haven’t updated our dates for the class you selected yet. There’s a quick way to find out. Contact us at 502.265.3057 or email info@training4it.com
Request a Date