Machine Learning with Python
Gain hands-on proficiency with Python & SciKit-Learn to build, evaluate, and deploy supervised and unsupervised Machine-Learning models on real datasets.
Get Course Info
Audience: Data Analysts, Software Engineers, Data Scientists
Duration: 3 days
Format: Lectures and hands-on labs (50% lecture, 50% lab)
Overview
Machine Learning (ML) is changing the world. To use ML effectively, one needs to understand the algorithms and how to utilise them. This course provides an introduction to the most popular Machine-Learning algorithms using the SciKit-Learn package in Python. It approaches ML from a practical perspective; in-depth maths/statistics is beyond the scope of this class. Students tackle real-world use-cases drawn from finance, healthcare, customer service, text-analytics, travel, and more. A cloud-based lab environment is provided – no local installs required.
Objective
Gain hands-on proficiency with Python & SciKit-Learn to build, evaluate, and deploy supervised and unsupervised Machine-Learning models on real datasets.
What You Will Learn
- Python and SciKit-Learn fundamentals
- ML concepts: supervised / unsupervised / reinforcement
- Feature Engineering & Exploratory Data Analysis (EDA)
- Regression algorithms: Linear & Logistic
- Classification algorithms: Naïve Bayes, SVM, Decision Trees, Random Forests
- Clustering (K-Means) & Dimensionality Reduction (PCA)
- Recommendation systems with Collaborative Filtering
- Model evaluation: Confusion Matrix, ROC/AUC, over- / under-fitting
- Hands-on labs with Jupyter notebooks
Course Details
Audience: Data Analysts, Software Engineers, Data Scientists
Duration: 3 days
Format: Lectures and hands-on labs (50% lecture, 50% lab)
- Good programming background (Python helpful but not required); no prior ML knowledge assumed.
Setup: Cloud-based lab provided • Modern laptop with unrestricted Internet • Chrome browser
Detailed Outline
- Introduction to Python programming environment
- Working with Jupyter notebooks
- NumPy & Pandas primer
- Labs: notebook workflow, NumPy, Pandas
- ML landscape & AI vocabulary
- Deep-Learning use-cases vs. traditional ML
- Types of ML: Supervised, Unsupervised, Reinforcement
- scikit-learn utilities overview
- Lab: scikit-learn APIs
- Preparing data for ML
- Statistics primer, data clean-up
- Extracting & enhancing features
- Visualising data
- Labs: data clean-up, exploration, visualisation
- Training vs. Testing splits
- Gradient Descent
- Over-/Under-fitting, Cross-validation, Bootstrapping
- Confusion Matrix, ROC curve, AUC
- Linear & Multiple Linear Regression (house-price use-case)
- Logistic Regression (credit-card & college-admission labs)
- SVM (customer-churn lab)
- Decision Trees & Random Forests (loan-default & election-contribution labs)
- Naïve Bayes (spam-filtering lab)
- K-Means (Uber-demand & shopping-trip labs)
- Principal Component Analysis (wine-quality & census-income labs)
- Collaborative Filtering (movie & song-rating labs)
- Group capstone: analyse real-world datasets & present findings
Ready to Get Started?
Contact us to learn more about this course and schedule your training.