Data Exploration
• Used to obtain basic
understanding of data to
determine its suitability for
training AI algorithm
Data
Structured Unstructured
• Symmetrical documents • Does not have a predefined,fixed
model
• XML files, simple tables, • Piece of text,photographs,maps,
spreadsheets & Database tables satellite images,audio or video
clips
• Easy to explore and refine as
training data • Demands high level of expertise
in exploring
Missing Values
• Remove the records
• Find the missing value and fill the gaps
• Look for the value in another similar record
• Estimate or calculate for the missing value
• Predict a value for missing value by careful analysis of
existing value
Feature Engineering
Technique of extracting useful information
from the existing data-sets
Data Visualisation
•Data visualisation occurs when we begin
to identify the patterns, trends and
logical relationships among data values
while exploring and analysing the data
Graphical representation of data
• Charts and graphs (Bar, Column, pie,area, line etc)
• Process flow (flowchart, illustration diagram etc)
• Patterns (Histogram,timeline etc)
• Distribution(Bubble chart, Density chart etc)
• Maps and Location (Dot map etc)
• Comparisons(Bar chart,line graph etc)
• Relationships(venn diagram,Scattered column etc)
• Hierarchy (Tree diagram, Tree map etc)
Visualising data for various requirements
COMPARING THE ESTABLISHING DISTRIBUTIONS AND
VALUES RELATIONSHIPS COMPOSITIONS
Comparing the values
• For smaller data set
• Bar chart, Column chart, Line chart, Area chart etc.
Establishing relationship
• Finding positive or negative effects of one variable on another
• Various value corelate each other
• Line chart,Scatter plot and bubble chart
Analysing distribution and Composition
• Amount of parts in a whole
• Example – Percentage performance / contribution of sales
• Pie chart, scatter chart, Mekko chart
Purchase(Items)
Dealer 1 Dealer 2 Dealer 3 Dealer 4 Dealer 5
Data Visualisations Tools
• Google Facets
• Tableau
• Candela