Pragmatic Data Curriculum

     Essential Tools      Practical Machine Learning      Advanced Machine Learning      AI with TensorFlow      Data Visualization

Practical Machine Learning

Every company wishes it had a crystal ball to see into its future. With machine learning, you can get a glimpse at what is coming using the data you already have. Predict potential failures before they happen. Anticipate increases in demand before you run out of product. Understand what your customers will do next before they've even made a decision.

Data Science II: Practical Machine Learning 
is a 3-day hands-on course that teaches you the basics of machine learning by building predictive models using real-world data. Utilize Python and Scikit-Learn tools to build regression models, classification models and dimensionality-reduction and clustering models that can be utilized in your business. This course gives you greater understanding of linear regression, logistics regression, model evaluation metrics, overfitting, cross-validation, and more to improve revenue, reduce costs, create new opportunities and foundational skills for this in-demand field.

Download a copy of the syllabus to convince your manager the importance of this course

Business Benefits

Data science allows businesses to improve operations at every step, and after this module, you will be able to build useful machine learning models that deliver data-driven insights. Through these insights, your company will be able to make better decisions that can improve revenue, reduce costs, create new opportunities, identify new ideas, improve the customer experience and more. See into the future of your business and your market with Data Science II: Practical Machine Learning.

 Who Should Attend

Data analysts, economists, researchers, software or data engineers who want to expand your understanding of machine learning with hands-on experience

 Key Skills Covered

Python’s Scikit-Learn library, building predictive models, solving regression and classification problems, performing dimensionality reduction and clustering

 Prerequisites

To achieve the greatest benefit from this course, attendees must take Data Science I: Essential Tools, or possess the following skills prior to attending:

  • Knowledge and understanding of basic Python
  • Basics of mathematical functions (linear functions, polynomials, logarithms, etc.)
  • Basic linear algebra
  • Basic statistics
  • Basic calculus

Not sure if this is the right course for you? Take our self-assessment and see where you should begin your data science journey with Pragmatic Institute.

Take Assessment

Earn a coveted data science certification upon successful completion of class project
What You'll Learn

Over the course of 3 days, you'll get hands-on experience with practical machine learning techniques that you can use the very next day.

Fundamentals of
machine learning
  • Gain familiarity with machine learning, supervised learning, unsupervised learning, regression and classification problems
  • Train a machine learning model
  • Use Scikit-Learn’s fit and predict methods to build a linear regression model
  • Evaluate trained models using mean squared error and coefficient of determination
  • Create new features that encode nonlinearities and use linear regression on an enhanced data matrix
  • Build a prediction model using real-world data, and understand how this model can be used to achieve business goals

Learn how to do classification
and prevent overfitting
  • Use Scikit-Learn’s GridSearchCV to find optimal values to tune hyperparameters
  • Evaluate model performance using appropriate classification metrics
  • Identify issues with unbalanced classes and improve model performance
  • Include categorical features by using a one-hot encoder
  • Build a Scikit-Learn pipeline to predict customer churn
  • Understand key concepts including in-sample and out-of-sample errors, variance-bias tradeoff and logistic regression

Build a clustering algorithm
with real-world data
  • Perform principal component analysis using Scikit-Learn and build a custom transformer to use in a pipeline to transform data
  • Use PCA-transformed data to build a K-Means clustering algorithm
  • Gain familiarity with metrics for clustering, such as silhouette coefficient
  • Obtain segments and extract information about each segment using techniques learned throughout the course

Ready to take on the future of data?

Pricing

Public Training
$3,185 USD
For the 3-Day Course

Early-bird discounts available


BUY TRAINING
Private Training


Prefer private training delivered specifically for your company?

Contact our account team for pricing and availability.

LEARN MORE

Netflix pragmatic live

How does someone become a modern-day data scientist for one of the biggest digital companies in the world?

Check out this podcast featuring Becky Tucker, Ph.D., senior data scientist at Netflix. See how she got her start and wound up at the world’s largest streaming service. Listen now

Read more about what other students have done with their data science education on our sister company site:

Learn more about our entire data science curriculum