S2: E1: C1: Types of Graphs

Scatter Plot

This type of graph is used to determine the relationship between two features. It is also called as scatter chart or scatter graph. As the name indicates, points are scattered over the graph for the two variables.
Algorithms:
It is effectively used for data analysis in Linear Regression models.

How does it look?

Scatter plot

Line Graph

This graph is considered to be one of the basic starting point for data visualization. This is mostly used in time series data visualizations. It effectively shows progress over a period of time.
Algorithms:
It is also helpful to determine the efficiency of the Linear Regression model.

How does it look?

Line Graph

Histogram

This graph is commonly used to display corporate data. It is easy to understand and widely used in Machine Learning.
It is used to show the underlying frequency distribution of the continuous data which allows the inspection of the data for its distribution (e.g., normal distribution, Binomial distribution, Bernoulli Distribution), outliers, skewness, etc.
Algorithms:
It is also helpful while doing Exploratory Data Analysis.

How does it look?

Histogram

Pie Charts

In this graph a circle is divided into sectors or slices that each represent a proportion of the whole.
The arc length of each slice (and consequently its central angle and area), is proportional to the proportion it represents.
The graph/chart is useful for displaying data that is classified into nominal or ordinal categories.
Algorithms:
It is also helpful while doing Exploratory Data Analysis. Also used to represent data after use of classification algorithm like Logistic Regression and Clustering algorithm like K Means.

How does it look?

Courtsey: Wikipedia

HEAT MAPS

SYMBOL MAPS

TREE MAPS

Horizontal Bars

Stacked Bars

Side by Side Bars

Circle Views

Side by side Circle Views

Dual combination

Box and Whisker plots

Gantt Charts

Bullet Graphs

Packed Bubbles

Be the first to comment

Leave a Reply

Your email address will not be published.


*