Foundations of Data Science

Module 1
Lecture 3
Types of Data
 Objective
 Explore various ways in which data is formed.
 Structured vs Unstructured Data
 Quantitative vs Qualitative Data
 Four Levels of Data
Need for knowing type of data (Flavour of
Data)
The type of data primarily answers two major
questions:
Knowing whether data is structured or not,
qualitative or quantitative tells us about the
real world phenomenon being measured
It indicates the methods used to analyze and
extract results.
 Need for knowing classification of data

• Consider an example where we are looking at

election results for a county.
• In the dataset of people, there is a "race"
column that is denoted via an identifying
number to save space.
• For example perhaps White is denoted by 1
while Brown is 2, Black is 3, etc.
• If analysis is made on lines that Brown > Black
since 2 > 1, it would be a terrible misjudgement.
Parallels of the example to datascience
• When given a dataset, it is tempting to:
Jump right into exploring, applying statistical
models, and researching the applications of
machine learning to get results faster.
 However, if you don't understand the type of
data that you are working with, then you might
waste a lot of time applying models that are
known to be ineffective with that specific type
of data.
 First Distinction
(Structured vs Unstructured)
 Structured (Organized) Data: Data sorted into a
row/column structure.
• Every row represents represents a single
observation and column represent the
characteristics of that observation.
• Unstructured (Unorganized) Data: Type of data
that is in the free form and does not follow any
standard format/hierarchy.
• Eg: Text or raw audio signals that must be parsed
further to become organized.
 Identify if the data is Structured or
Unstructured
 Facebook Posts
o Unstructured Data
 Scientific observations recorded carefully by
scientists
o Structured Data
 Genetic sequence of chemical nucleotides
• Unstructured Data (we cannot form descriptors
of the sequence using a row/column format
without taking a further look)
 Pros of Structured Data
 Structured data is generally thought of as being
much easier to work with and analyze.
 Most statistical and machine learning models
were built with structured data in mind and
cannot work on the loose interpretation of
unstructured data.
 The natural row and column structure is easy to
digest for human and machine eyes.
Why even talk about Unstructured Data?

 Because it is VERY common!

 Most estimates place unstructured data as 80-
90% of the world's data.
 This data exists in many forms and for the most
part, goes unnoticed by humans as a potential
source of data.
 Tweets, e-mails, literature, and server logs are
generally unstructured forms of data.
 Takeaway from Discussion
• While a data scientist likely prefers structured
data, they must be able to deal with the world's
massive amounts of unstructured data.
• Massive Potential: If 90% of the world's data is
unstructured, that implies that about 90% of the
world's information is trapped in a difficult format.
• Approach: We utilize common pre-analysis
techniques, called preprocessing, in order to apply
structure to at least a part of the data for further
analysis.
 Example of Data Pre-processing
for Text Data
• Text data is generally unstructured and hence
there is need to transform data into structured
form.
• Few characteristics that describe the data to
assist transformation are:
Word/phrase count
The existence of certain special characters
The relative length of text
Picking out topics
 Example: A Tweet
• This Wednesday morn, are you early to rise? Then look East.
The Crescent Moon joins Venus & Saturn. Afloat in the dawn
skies.

• Pre-processing is necessary for this tweet because a vast

majority of learning algorithms require numerical data.
• Pre-processing allows us to explore features that have been
created from the existing features.
• For example, we can extract features such as word count and
special characters from the mentioned tweet.
 Example:This Wednesday morn, are you early to rise? Then look East. The
Crescent Moon joins Venus & Saturn. Afloat in the dawn skies.

1. Word/phrase counts:-
• We may break down a tweet into its word/phrase count.
• The word ‘this’ appears in the tweet once, as does every
other word.
• We can represent this tweet in a structured format,
converting the unstructured set of words into a row/column
format:
 Example:This Wednesday morn, are you early to rise? Then look East. The
Crescent Moon joins Venus & Saturn. Afloat in the dawn skies.

• 2. Presence of certain special characters

• We observe the presence of special characters, such as the
question mark and exclamation mark.
• The appearance of these characters gives certain
• ideas about the data that are otherwise difficult to know.
• For example, the fact that this tweet contains a question
mark might strongly imply that this tweet contains a
• question for the reader.
 Example:This Wednesday morn, are you early to rise? Then look East. The
Crescent Moon joins Venus & Saturn. Afloat in the dawn skies.

• 3. Relative length of text

• This tweet is 121 characters long.
• The average tweet, as discovered by analysts, is about 30
characters in length.
• So, we calculate a new characteristic, called relative length,
(which is the length of the tweet divided by the average length),
i.e. 121/30 telling us the length of this tweet as compared to
average tweet.
• This tweet is actually 4.03 times longer than the average tweet.
 Example:This Wednesday morn, are you early to rise? Then look East. The
Crescent Moon joins Venus & Saturn. Afloat in the dawn skies.

• 4. Picking out topics

• We can pick out some topics of the tweet to add as columns. This
tweet is about astronomy, so we can add that information as a
column.
• Thus, we can convert a piece of text into structured/organized
data, ready for use in our models and exploratory analysis.
• Topic is the only extracted feature we looked at that is not
automatically derivable from the tweet.
(Field of Topic Models help in achieving the outcome)
 Next characterization of Data
• When you ask a data scientist, "what type of
data is this?“
• Most common answer received is that Data is
Qualitative/Quantitative.
• It can be described as the most common way
of describing the specific characteristics of a
dataset.
 2. Qualitative/Quantitative
1. Quantitative data: Data that can be described
using numbers, and basic mathematical
procedures, including addition, subtraction etc.

2. Qualitative data: This data cannot be described

using numbers and basic Mathematics, and
described using "natural" categories and
language.
 Example of Qualitative/Quantitative
Coffee Shop Data
Observations of coffee shops in a major city was made.
Following characteristics were recorded.
1. Name of coffee shop
2. Revenue (in thousands of dollars)
3. Zip code
4. Average monthly customers
5. Country of coffee origin
Let us try to classify each characteristic as Qualitative OR
Quantitative
 Example of Qualitative/Quantitative
Coffee Shop Data
1. Name of coffee shop
• Qualitative
• The name of a coffee shop is not expressed as a
number and we cannot perform math on the
name of the shop.
 Example of Qualitative/Quantitative
Coffee Shop Data
2. Revenue
• Revenue – Quantitative
• How much money a cafe brings in can definitely
be described using a number.
• Also, we can do basic operations such as adding
up the revenue for 12 months to get a year's
worth of revenue.
 Example of Qualitative/Quantitative
Coffee Shop Data
3. Zipcode
• This one is tricky!!!
• Zip code – Qualitative
• A zip code is always represented using numbers, but what
makes it qualitative is that it does not fit the second part of the
definition of quantitative—we cannot perform basic
mathematical operations on a zip code.
• If we add together two zip codes, it is a nonsensical
measurement.
• We don't necessarily get a new zip code and we definitely
don't get "double the zip code".
 Example of Qualitative/Quantitative
Coffee Shop Data
4. Average monthly customers
• Average monthly customers – Quantitative
• Again, describing this factor using numbers and
addition makes sense.
• Add up all of your monthly customers and you
get your yearly customers.
 Example of Qualitative/Quantitative
Coffee Shop Data
• 5. Country of coffee origin
• Country of coffee origin – Qualitative
• We will assume this is a very small café with
coffee from a single origin.
• This country is described using a name
(Ethiopian, Colombian), and not numbers.
 Thumb rule for classification as
Qualitative/Quantitative
• Q1. Can you describe it using numbers?
• No? It is qualitative.
• Yes? Move on to next question.
• Q2. Does it still makes sense after you add
them together?
• No? They are qualitative.
• Yes? You very likely have quantitative data.
Types of Questions for Quantitative Data

• What is the average value?

• Does this quantity increase or decrease over
time (if time is a factor)?
• Is there a threshold that if this number grew
above or be too low would signal trouble for
the company?
Types of Questions for Qualitative Data
• Can we ask questions like
• What is the average value?
• Does this quantity increase or decrease over time
(if time is a factor)?
• NO!!
Questions that can be asked for Qualitative:
• Which value occurs the most and the least?
• How many unique values are there?
• What are these unique values?
 Example 2: World alcohol consumption
data
• The World Health Organization released a
dataset describing the average drinking habits
of people in countries across the world.
• The first step in analysis is to explore for the
nature and type of data.
• Coding tool used for discussion is Python
utilizing Pandas library
 Example 2: World alcohol consumption
data
Code:
• import pandas as pd
• # read in the CSV file from a URL
• drinks =
pd.read_csv('https://raw.githubusercontent.com/si
nanuozdemir/principles_of_data_science/
master/data/chapter_2/drinks.csv')
• # examine the data's first five rows
• drinks.head() # print the first 5 rows
 Example 2: World alcohol consumption
data
• These three lines have done the following:
• Imported pandas, which will be referred to as pd
in the future
• Read in a CSV (comma separated value) file as a
variable called drinks
• Called a method, head, that reveals the first five
rows of the dataset
Example 2: World alcohol consumption
data
 Example 2: World alcohol consumption
data
• Classification of attributes as Quantitative OR
Qualitative
• country: Qualitative
• beer_servings: Quantitative
• spirit_servings: Quantitative
• wine_servings: Quantitative
• total_litres_of_pure_alcohol: Quantitative
• continent: Qualitative
 Example 2: World alcohol consumption
data
• To know more details about the column continent
(Also confirm Qualitative/Quantitative), I give the
following command:
• drinks['continent'].describe()
• >> count 193
• >> unique 5
• >> top AF
• >> freq 53
 Example 2: World alcohol consumption
data
• To know more details about the beer_servings
column (Also confirm Qualitative/Quantitative), I
give the following command:
• drinks[' beer_servings'].describe()
• >> mean 106.160622
• >> min 0.000000
• >> max 376.000000
Quantitative data can be broken down, one step
further, into discrete and continuous quantities.
• Discrete data: This describes data that is
counted. It can only take on certain values.
• Examples of discrete quantitative data include
a dice roll, because it can only take on six
values, and the number of customers in a café,
because you can't have a real range of people.
Quantitative data can be broken down, one step
further, into discrete and continuous quantities.
• Continuous data: This describes data that is
measured. It exists on an infinite range of values.
• A good example of continuous data would be a
person's weight because it can be 150 pounds or
197.66 pounds (note the decimals).
• The height of a person or building is a continuous
number because an infinite scale of decimals is
possible.
• Other examples of continuous data would be time
and temperature.
 Summary
• Data as a whole can either be structured or
unstructured, meaning that the data can
either take on an organized row/column
structure with distinct features that describe
each row of the dataset, or exist in a free-form
state that usually must be preprocessed into a
form that is easily digestible.
 Summary
• If data is structured, we can look at each column
(feature) of the dataset as being either quantitative
or qualitative.
• Basically, can the column be described using
mathematics and numbers or not?
• The next part of this chapter will break down data
into four very specific and detailed levels.
• At each order, we will apply more complicated rules
of mathematics, and in turn, we can gain a more
intuitive and quantifiable understanding of the data.