Python for Data Science Certificate

Data science is one of today’s most in-demand functions — and Python is an essential skill in any data scientist’s
toolbox. In this program, you will master the ability to analyze and visualize data in meaningful ways using Python
to help solve complex business problems. Working with tools such as Jupyter Notebooks, NumPy, and Pandas, you
will have the opportunity to analyze real-world datasets to identify patterns and relationships in data. You will gain
experience using both built-in and custom-built data types to create expressive and computationally robust data
science projects. Finally, you will build predictive machine learning models using Python and scikit-learn.

To be successful in this program, it is recommended that students have some experience in analytics and
programming, specifically with creating visualizations in spreadsheets.

The amount of time you spend on these courses will depend on your prior experience. Since these courses are
designed for someone with limited exposure to programming, you can expect them to start off with the foundations
and then quickly move into more advanced and complex topics.

Inside the Program Who Should Enroll

• Certificate consists of 7 three-week courses • Data analysts and business analysts
• Courses include multiple choice quizzes, instructor- • Database managers
moderated discussions, and a final project to practice • Technical and systems analysts
what you’ve learned in real-world context
• Programmers interested in data science
• Opportunities for collaboration and networking with
• Marketers
fellow students both during and after your courses
• Business managers
• Course materials available 24/7 during the two-week
course and a third week to review the content
• Plan to spend 3-5 hours per week on each course What You’ll Earn
• Python for Data Science Certificate from Cornell
Center for Advanced Computing
What You’ll Learn
• 105 Professional Development Hours (7 CEUs)
• Visualize data with Python
• Write custom functions and data classes in Python
that can be stored for reuse Total Investment
• Use key elements of Python control flow • $3,600 with monthly payment options available
and iteration
• 5 months to complete all the courses
• Use Jupyter Notebooks to integrate data analysis,
visualization, and documentation
• Manipulate data arrays and tables using NumPy
and Pandas
• Filter, integrate, and prepare data for analysis To learn more, visit:
• Perform statistical data analysis and visualization eCornell.com/PythonDataScience
• Explore datasets with machine learning

CHAT
info@ecornell.com • (866) 326-7635 or (607) 330-3200 outside the USA • eCornell.com
NOW
Python for Data Science Certificate Courses
Constructing Expressions in Python (CAC101)
Expressions are a core attribute of any Python program.
In this course, you will construct expressions and reuse
them to manipulate and compute variables in a variety
of applications. This reusability enables a “create once,
use everywhere” development paradigm which will
streamline development of your current and future
Python programs. You will develop the knowledge
and skills to assign and access variables, combine
variables and data in expressions, and leverage
Python as a powerful calculator. You’ll also use the
enhanced capabilities of the IPython environment to
do interactive work with Python and to explore your
data through new analyses. The knowledge and skills
you gain will help you construct Python expressions to
streamline the development of your current and future
Python data science projects.
Writing Custom Python Functions, Classes, and
Workflows (CAC102)
This course introduces you to the different scenarios
in which you will utilize built-in Python functions,
classes, and data types as opposed to creating your
own or using a combination of built-in and custom-
built capabilities. You will gain experience working
with both built-in and custom-built functions, classes,
and data types. Through practice and application of
these basic building blocks/tools, you will gain an in-
depth understanding of how these aspects of Python
interoperate to create useful programs.
Developing Data Science Applications (CAC103)
Python is much more than a programming language.
In this course, you will leverage the comprehensive
Python ecosystem of libraries, frameworks, and
tools to develop complex data science applications.
Throughout this course, you will practice using the
different Python tools appropriate to your dataset. You
will leverage library resources for data acquisition and
analysis as well as machine learning. Dataframes will
be introduced as a means of manipulating structured
data tables for advanced analysis. Additionally, you will
practice basic routines for data visualization utilizing
Jupyter Notebooks.
CHAT
info@ecornell.com • (866) 326-7635 or (607) 330-3200 outside the USA • eCornell.com
NOW
Creating Data Arrays and Tables in Python (CAC104)
Decision-makers generally do not use raw data to
make decisions; they prefer data be summarized
in easily understood formats that facilitate
efficient decision-making. This course introduces
data manipulation and visualization, both critical
components of any data science project. This course
introduces two commonly used data manipulation
tools in the Python ecosystem: NumPy and Pandas.
In addition, the Python ecosystem also includes a
variety of data plotting packages such as Matplotlib,
Seaborn, and Bokeh — each of which specialize in
particular aspects of data visualization. This course will
give you experience integrating NumPy, Pandas, and
the plotting packages to create rich, interactive data
visualizations that help drive efficient decision-making.
Organizing Data with Python (CAC105)
Most data science projects that use Python will require
you to access and integrate different types of data
from a variety of external sources. This course will give
you experience identifying and integrating data from
spreadsheets, text files, websites, and databases. To
prepare for downstream analyses, you first need to
integrate any external data sources into your Python
program. You will utilize existing packages and
develop your own code to read data from a variety of
sources. You will also practice using Python to prepare
disorganized, unstructured, or unwieldy datasets for
analysis by other stakeholders.
Analyzing and Visualizing Data with Python (CAC106)
In order to be useful within a professional environment,
data must be structured in a way that can be
understood and applied to real-world scenarios. This
course introduces using Python to perform statistical
data analysis and create visualizations that uncover
patterns in your data. Using the tools and workflows
you developed in earlier courses, you will carry out
analyses on real-world datasets to become familiar
with recognizing and utilizing patterns. Finally, you
will form and test hypotheses about your data which
will become the foundation upon which data-driven
decision-making is built.
Python for Data Science Certificate Courses
Building Predictive Machine Learning Models (CAC107)
In this course, you will explore some of the machine
learning tools you can use to magnify the analytical
power of Python data science programs. You will
use the scikit-learn package — a Python package
developed for machine learning applications — to
develop predictive machine learning models. You
will then practice using these models to discover
new relationships and patterns in your data. These
capabilities allow you to unlock additional value in your
data that will aid in making predictions and, in some
cases, creating new data.

CHAT
info@ecornell.com • (866) 326-7635 or (607) 330-3200 outside the USA • eCornell.com
NOW