Data science and machine learning is achieved through complex algorithms and techniques. It generates various insights that can be used for several business purposes. Python, being a programming language known to have simple syntax and to integrate well in environments of production systems of organizations, is powerful tool in performing data science and machine learning. This course provides immediately applicable skills in using Python to implement data science and machine learning algorithms. Focus is on application of the most actionable analytical techniques in addressing the most common business problems.
What You Will Learn
Upon completion of this course, the learners are expected to:
- implement data science and machine learning algorithms using Python libraries; and
- perform the six powerful analytical techniques using Python and identify which among such techniques would be applicable for a specific business purpose.
You will need a computer or laptop with Python installed. Computer or laptop requirements are:
- 8GB RAM and Core i5, or get a production type, download and install Anaconda package tool.
Note to SPARTA scholars: Upon enrollment, you will have 6 months to finish a SPARTA course. Failure to complete the course in 6 months and/or inactivity for 3 months will result in course access revocation.
Subject Matter Expert
Week 1: Introduction to Data Science and Machine Learning using Python
3 Videos | 3 Activities
- Welcome to the course!
- Why Machine Learning?
- Why Python?
- Try it out: Word Cloud
- Let's recall: Anagram
- Quiz: Machine Learning and Python
Week 2: Supervised Machine Learning
8 Videos | 3 Activities
- Generalization, Overfitting, and Underfitting
- K-Nearest Neighbors
- Linear Models-Part 2 (2 Videos)
- Decision Trees
- Ensemble of Decision Trees
- Kernel Support Vector Machine
- The Decision Function and Predicting Probabilities
- Try it out: Labelled Diagram
- Let's recall: Find the Match
- Peer-Graded Assignment: Supervised Machine Learning
Week 3: Unsupervised Learning
4 Videos | 2 Activities
- Types of Unsupervised Learning
- Preprocessing and Scaling
- Dimensionality Reduction, Feature Extraction, and Manifold Learning
- Let's recall: Cloze Activity
- Peer-Graded Assignment: Unsupervised Learning
Week 4: Representing Data and Engineering Features
4 Videos | 2 Activities
- Categorical Variables
- Binning, Discretization, Linear Models, and Trees
- Interaction and Polynomials
- Univariate Non Linear Transformations, Automatic Feature Selection, and Utilizing Expert Knowledge
- Let's recall: Pop Quiz!
- Peer-Graded Assignment: Data Engineering Features
Week 5: Model Evaluation and Improvement
5 Videos | 4 Activities
- Cross Validation
- Grid Search
- Evaluation Metrics and Scoring (2 Videos)
- Key Takeaways
- Try it out: Decoding Model Evaluation
- Ponder and Prove: Padlet Activity
- Let’s recall: Word Grid
- Capstone Project: Python for Data Science and Machine Learning