Congratulations on completing
the course successfully. Now that you've developed
a robust foundation in data warehousing, there's a whole world of
possibilities out there to keep building your knowledge and put those skills to work. But before we dive into that, let's revisit some
of the key concepts and takeaways from the course. A data warehouse
is a system that aggregates data from
one or more sources into a single
consistent data store to help you with the
analysis of data. Some popular data
warehouse vendors you explored in this
course are IBM, Teradata, Google,
Oracle, Microsoft, Snowflake, Amazon, and others. When you select a data
warehouse system, you should consider the
total cost of ownership, including infrastructure,
storage, data mitigation, administration, and
data maintenance costs in your calculations. A data mart is an
isolated part of the larger enterprise
data warehouse that is specifically built to serve as a particular business function,
purpose, or community. Whereas a data lake is a
pool of raw data where each data element is given a unique identifier and is tagged with meta tags
for further use. If you generate large amounts
of data on an ongoing basis but don't want to
be restricted to specific or
predefined use cases, you can opt for a data lake. In designing a general
data warehousing platform, you'll typically
include data sources, ETL pipelines, staging
and sandbox areas, an enterprise data
warehouse repository, and optional data marts. You can also modify
this architecture to match your specific
analytics needs. A data cube represents the dimensions of a star
or snowflake schema as coordinates with a fact from the schema populating
its cells and values. You can apply various
operations to data cubes, such as drilling down into
hierarchical dimensions, slicing, dicing, and rolling up. Moreover, materialized views are a local read-only copy or snapshot of the results of
a query that can be used to replicate data or precompute
expensive queries. In business, data can
be classified into two main categories:
facts and dimensions. Facts typically represent numerical measures of
business processes. Dimensions, on the other hand, categorize facts by
providing context, such as who sold the product, when, and from which
store it was sold. A star schema is a data
modeling technique in which nodes represent fact
tables and dimension tables, while the edges represent the relationships
between those tables. Whereas snowflake schema, another data modeling technique, is a generalization
of star schema and can be seen as
normalized star schema. You can use facts and
dimension tables, along with foreign
and primary keys, as the fundamental
building blocks while designing star schema
and snowflake schema. When you're populating an
enterprise data warehouse, start by creating the
fact and dimension tables and establishing
their relationships. Then load clean data
into these tables. The practice and final projects in this course provide you with examples to showcase your skills to your
prospective employers. Now that you've
reviewed the core concepts from this course, you can apply and refine
your skills by working with other data sets to further enhance your data
warehousing skills. If you're eager to
know more about data management and analysis, you might want to
check out the programs affiliated with this course, such as IBM Data Warehouse Engineer
Professional Certificate; IBM Data Engineering
Professional Certificate; IBM Business Intelligence, BI, Analyst Professional
Certificate; and BI Foundations with SQL, ETL, and Data
Warehousing Program. Depending on your schedule and the number of courses
in the programs, they can typically be
completed within 3-6 months. You'll find the links
to these programs in the Congratulations
and Next Steps reading at the end
of this course. Congratulations on
completing this course and good luck in your
data warehousing journey!