UNDERSTANDING DIFFERENT STRUCTURES OF DATA
& CHOOSING THE APPROPRIATE CHART AND
ANALYTICS ACCORDINGLY
‘Data Analytics & BI Career Path’ By-
Md. Shabbir Hossain Bhuiyea (Rossi)
& Interactive Cares Lecture 01
Types of Data
So far we might only be familiar with data in the following format:
This is just an example of our most familiar FLAT TABLE (Structured Data)
Types of Data
Data can be classified into three main categories based on its structure:
Structured, Semi-structured and Unstructured.
Structured Data: Data that is organized in a well-defined manner, such as in a table or database.
Examples of structured data include:
-Customer data in a CRM system, with fields for name, address, email, and phone number.
-Stock data in a financial database, with fields for date, closing price, and volume traded.
Semi-structured Data: Data that has some structure, but also contains unstructured elements.
Examples of semi-structured data include:
- Social media posts, which have a author, timestamp, and text, but the text may contain hashtags, mentions, andemojis.
- NoSQL Database Data, JSON (JavaScript Object Notation) or XML (Extensible Markup Language) data, which has a nested
structure, but the values may contain unstructured text or binary data.
Type of Data
Shape of Semi-structured
Data
Unstructured Data: Data that does not have a well-defined structure and may not fit neatly
into a table or database. Examples of unstructured data include:
- Images, such as photographs and medical images.
- Videos, such as movies and TV shows.
Semi-structured and unstructured data require additional processing and analysis
techniques compared to structured data, as they do not have a well-defined structure
and may contain complex relationships between elements.
1. Numerical Variable: Data that can be expressed as a number, such as Height, Weight, Age,
and Income. There are two types of numerical variable: Continuous (e.g., Height, which
can take on any value) and Discrete (e.g., Number of Children in a household, which can
only take on certain values).
2. Categorical Variable: Data that can be divided into categories, such as Gender, Hair Color,
and Education Level. There are two types of categorical variable: Nominal (e.g., Hair Color,
which has no order) and Ordinal (e.g., education level, which has an order, such as
"Primary School," "High School," and "College").
3. Binary/Dummy Variable: Data that can only take on two values, such as "yes/no" or
Type of 4.
"present/absent."
Time Series Data: Data that is collected over time, such as Stock Prices, Weather data, and
Variable Sales data.
& Data 5. Text Data: Data that is in the form of text, such as customer reviews, emails, and social
media posts.
6. Image Data: Data that is in the form of images, such as photographs, medical images, and
satellite images.
7. Audio Data: Data that is in the form of sound, such as speech, music, and environmental
sounds.
8. Video Data: Data that is in the form of video, such as movies, TV shows, and surveillance
footage.
There are many types of plot available, but we will only discuss about the ones
frequently used in Data Analysis, Data Science & Machine Learning:
❖ For Univariate Analysis
- Numerical Variable:
- Histogram, Density Plot/Chart
Charts - Box and Whisker Plot
Require to - Qualitative Data:
- Bar/Column Chart
Explore - Pie Chart, Doughnut Chart
your Data ❖ For Bivariate Analysis
- Numerical Data:
- Scatter Plot
- Correlogram/Correlation Plot
- Line Chart
- Categorical Data
- Stacked/Clustered Bar/Column Chart
Histogram,
Box &
Whisker
Plot,
Density Plot
Column Chart, Stacked Column Chart,
Clustered/Group Column Plot
Pie Chart & Doughnut Chart
Scatter Plot, Correlogram & Line Chart
