Data Analysis

Chapter 1: Intro. To data and data analysis:

Roles:
1. Data Worker
 The most universal role dealing with data.
 Consumes and work with data regularly.
 Perform data manipulation.
2. Data Analysis
 Analysis and present data in deeper level.
 Module and automate the flow of data.
3. Data Engineer
 Build and design data sets.
4. Data Architect
 Design data system.
5. Data Scientist
 Possess all skills of data workers, analysts, engineers
and architects.
Data Literate
 Ability to read, speak, listen, and understand data.
Data Fluent
 Ability to create something beyond just being able to read,
understand and use it.
Data Governance
 The framework that incorporates strategies to create secure
and quality data, enable accountability and provide
transparency to data in the organization.
Quality Data
 Data that can be trusted to produce accurate insights.
 Hallmarks of quality data:
 Completeness
 Consistency
  Validity
 Accuracy
Chapter 2: Intro. To Business Intelligence
Data and Business Intelligence (BI)
 Give you the ability and information to make intelligent
decisions.
Business Analysis:
 Analyzing data and creating more of it.
Data Analysis:
 Analyzing and capturing data to compare over time.
Business Intelligence:
 Understanding where we stand on any given day.
Business Analytics:
 Seeing trends and predicting future outcomes.
Data Points
Chapter 3: Identifying Data
1. Data Driven decision: using all available information to help
driving decisions for an organization.
2. Analysis Paralysis: overthink a problem that stops you from
moving forward.
 Overcoming analysis paralysis:
 Build approach
 Think through standard questions
 Practice active listening and use critical thinking
3. Types of Company Data. These systems are disconnected.
 People Management
 Marketing and Sales
 Purchasing
 Warehouse
 Shipment
  Accounting
The challenge question is which system is the most accurate
information.
4. Data Structure
 Value >>> 30 November 1998
 Type >>> Date
 Field Name >> date of birth
 Record >> value + type + field name
People use records and spreadsheets all the time, you should
know that spreadsheet is just a table.
When the fields are combined in a database, they stored in
tables.
5. Types of system used to collect and store data:
 Spreadsheets
 Databases
 Data Warehouses
6. Data Lakes: help organization to capture data to store before
it’s refined for reporting.
Chapter 4: Preparing Data
1. Data Profiling: clean, order, count values and basic
transformations requirements
2. Data Rules or Business Rules: control and define the flow of
data
3. Preparing the data.
4. Dealing with data via Excel
 Ensure that the data set is recognized by Excel, no
column separates the data or row…
 Power Query
 Duplicate
 Delimiter
 Replace values
 Remove entire column
 Load or Transform data then load
Chapter 5: Transforming Data
1. Add column, custom or conditional column
Add pivot table to show how much a value is repeated
Show value as of grand total
2. Structured Query Language (SQL) is a computer language
that works with data and the relationships between them.
 Select >> fields from table
 From >> table name
 Where >> filter data
 Order by >> sort data
Chapter 6: Modeling Data
1. Relational Data: when data or tables are related to each
other through the system.
2. RDBMS: Relational Databases Management System.
3. Master Data Management.
4. Structured Data: data that fits accurately in tables or
spreadsheets.
5. Unstructured Data: needs brain to overview and analyze.
6. Semi-Structured Data: a mix between the two.
Chapter 7: Visualizing Data
1. Be the person you are designing for
2. Be consistent
3. Do not complicated, keep it simple
4. Title, tables and add tooltips appropriately
5. Paginated reports enable you to connect data in power BI,
Paginated reports can provide valuable reporting when your
data expands over many pages and can easily be published
or printed.
6. The best way to express your ideas is to create a mockup of
the dashboard.
7. If it is multiple pages with navigation, build a wireframe
which helps communicate the navigation of information
before you build it.
 8. Presenting data challenges, talk to the leadership, ask,
research and check always
9. Filters and how to add or delete in Power BI, Modifying
dashboard tooltips.
Slicers are another way of filtering. They narrow the portion
of the dataset that is shown in the other report
visualizations. Slicers are a useful way to filter information
and focus on a specific portion of the dataset.
Chapter 8: Job Mapping in Data Analytics Field
1. Data Workers:
 Export Data out of the system
 Build a weekly or monthly reposts and presentations
 Work with functions
 Growth Opportunities:
 Power Query
 Pivot Tables
 Microsoft PowerPoint
 Microsoft Word
2. Data Analysts
 Deeper understanding of data systems
 More knowledge about database design
 Basic SQL query skills
 Understand data governance path
 Clean and transform data to meet the requirements of the
project.
 Create functions of varying types
 Work with statistics and aggregate functions
 Growth Opportunities:
 Go a little bit deep in statistics not full statistics
 Understanding joins, soft skills like data storytelling,
critical thinking and active listening

3. Data Engineers
 Translate large amount of data into data sets
Know how to refine data sets into smaller sets
Have more access to data
Understand more about security and privacy
Can transition to Data Architect who covers more
systems, more servers, and more security strategies
 Growth Opportunities:
 Structured and unstructured data and how to convert it
to sensible data sets
 Relational database system design methodologies
 Database Design
 Soft skills, effective presentation, active listening and
critical thinking
 Define tables into usable tables for other process using
ELT or ETL (extract, transform, load or extract, load,
transform).

4. Data Scientists
 Develop tools and instruments that provide valuable
insights
 Interpret large data sets, likely build machine learning
models
 Present outcomes and make suggestions
 Provide support and strategy to the overall data
governance path
 Growth Opportunities:
 Programmatic thinking
 Code like Python
 Heavier code, math, and stats