UpCode Academy Mobile Logo

Main Links

Signup Login

Data Science I (Python)

Data Science I (Python) featured image

About this Course:

The course is a highly practical introduction to data-science using Python as a language of choice for its wide variety of libraries and tools designed for the subject.

Students will learn to use widely-used libraries: pandas for data preparation and reporting, numpy for efficient array computations and scikit-learn for unsupervised learning (clustering and data compression) and supervised learning (linear regression, logistic regression, decision trees, and support vector classifiers). Students will also be introduced to the process of designing their own machine learning method through recommendation systems. The provided course materials also will serve as a useful reference (of practical examples) that supports post-course revision and practice. Students who gain competence in the materials (a function of effort) will be ready to enhance their work with elements of data science.


Students are required to have basic knowledge of programming before signing up for this course.

If you want to pick up basic programming skills, please register for our Python Development course instead.

What You Get

Students will learn how to perform the various parts of the "data science process":
- Preparing data: Cleaning, transforming, etc.
- Selecting a machine learning model (algorithm & settings)
- Training a model
- Evaluating a model
- Making predictions

Course Plan

Lesson 1: Pandas and Managing Data

- Exploration of Data
- DataFrames and Series
- Visualization
- Data Aggregation for Reporting
- Data Preparation: Cleaning, Transforming, Data Fusion

Lesson 2: Hello Machine Learning

- Introduction to Unsupervised Learning (clustering and data compression)
- Introduction to Supervised Learning (linear regression, and briefly, logistic regression, decision trees, & support vector classifiers)
- numpy Arrays

Lesson 3: Delving Deeper into Supervised Learning

- Linear Regression: Talking about the Learning in Machine Learning
- Feature Generation
- Underfitting and Overfitting: Qualitatively and Quantitatively
- Model Selection in Linear Regression
- Another Regressor: The Decision Tree Regressor
- Mixing Methods: Clustering and Predictors

Lesson 4: Introduction to Recommendation Systems

- Classification Performance: Confusion Matrix
- Classification Performance: The ROC Curve
- Classification Performance: Linking Classifier Performance to Business Outcomes
- Making Sense of Logistic Regression
- Visualizing Decision Trees
- Extracting Information from Decision Trees
- Visualizing Classification Boundaries
- Naive Bayes for Classification

Lesson 5: Developing a Practical Recommendation System

- Item-Item Similarity-based Collaborative Filtering
- Exploring a Ratings Data Set and Similarity as a Basis for Recommendations
- Beginning to work on our Item-Item Similarity-based Collaborative Filtering Method

Lesson 6: Outstanding Material, Clarifications and Assessment

- Broadcasting in numpy
- Iterating on the Item-Item Similarity-based Collaborative Filtering Method
- Writing a performant Item/User-Based Collaborative Filtering method
- The Surprise package and other methods for collaborative filtering



September 11th, 2018 September 15th, 2018 September 19th, 2018
Lesson 1 11/09/18
07:30pm - 10:00pm
01:00pm - 03:30pm
07:30pm - 10:00pm
Lesson 2 18/09/18
07:30pm - 10:00pm
01:00pm - 03:30pm
07:30pm - 10:00pm
Lesson 3 25/09/18
07:30pm - 10:00pm
01:00pm - 03:30pm
07:30pm - 10:00pm
Lesson 4 02/10/18
07:30pm - 10:00pm
01:00pm - 03:30pm
07:30pm - 10:00pm
Lesson 5 09/10/18
07:30pm - 10:00pm
01:00pm - 03:30pm
07:30pm - 10:00pm
Lesson 6 16/10/18
07:30pm - 10:00pm
01:00pm - 03:30pm
07:30pm - 10:00pm

Similar Courses