Certificate in Data Science

Organizations today are overwhelmed with data; Data that, if treated properly, can render a tremendous competitive advantage in terms of reducing waste and increasing revenues. Data science is the science of generating valuable insights and predictions from data. Python is the most popular programming language for doing data science. This 5-day live certification course gives participants a solid foundation for doing data science in Python, so that they can earn an advantage and return to their organizations and apply data science to generate insights from business data.

Course Methodology

Participants will be led through a series of lectures and hands-on exercises. Following each set, they will work through and practice writing Python code to perform data science tasks. Participants will come away from this course with data science coding experience, unique printouts, and practical demonstrations and exercises that they can take to their organizations and apply for customized analyses. As part of this course, participants will complete an end-to-end data science project.

Course Objectives

By the end of the course, participants will be able to:

• Clean, reshape, reformat, and describe data
• Generate data visualizations for desktop viewing and for interactive web-based display
• Spot and remove outliers
• Generate predictions using machine learning methods
• “Scrape” the internet to generate data sources
• Visualize and analyze spatial and network data

Target Audience

This course is designed for working professionals who want to use business data to make improved decisions through predictive analytics. This includes, but is not limited to, technical professionals such as database administrators, system administrators, business analysts, business intelligence specialists, GIS specialists, and web developers.

Recommended pre-knowledge includes experience analyzing data in Excel, as well as a basic understanding of correlation, probability, and statistics. Participants should have prior experience working with data that is stored in traditional relational database systems. Some experience with an object-oriented programming language would be useful but is not required.

Target Competencies

• Data cleaning
• Data visualization
• Data analysis
• Predictive modeling
• Python programming
• Certificate in Data Science

Course Outline

• Basics in data munging
• Working with filters and data selections
• Resolving problems caused by missing values
• De-duplicating datasets
• Making data concatenations and
• transformations
• Aggregating your data by group
• Basics in data visualization
• Generating line, bar, and pie charts
• Generating plot elements
• Formatting a plot
• Labeling and annotating a plot
• Plotting time series
• Generating statistical plots
• Basics in math and statistics
• Doing basic arithmetic
• Using statistical methods to summarize your
• data
• Generating summaries for categorical
• variables
• Quantifying correlation between variables
• Transforming distributions
• Reducing dataset dimensionality
• Getting to know machine learning
• Factor analysis in Python
• Reducing dimensionality with PCA
• Discovering and removing outliers
• Applying extreme value analysis
• Applying multivariate analysis
• Applying the linear projection method
• Identifying and analyzing segments within data
• Clustering with K-means
• Clustering with hierarchical methods
• Classifying with instance-based methods
• Basics in network analysis
• Generating and editing graph objects
• Plotting graph objects
• Applying directed network analysis in social
• media simulations
• Generating quantitative descriptions of graphs
• Basics in algorithmic learning
• Regressing linearly
• Regressing with logits
• Classifying with Naïve Bayes
• Making interactive, collaborative data Vvsualizations
• Generating basic charts with Plotly
• Generating statistical charts with Plotly
• Generating maps with Plotly
• Scraping the web with Beautiful Soup
• Getting to know objects
• Parsing data
• Scraping the web