Is Machine Learning, the only way for Data Visualization?
Introduction to Cognos Analytics
Data Visualization
Data visualization is the graphic representation of data. It involves producing images that communicate relationships among the represented data to viewers of the images.
Humans are visual creatures.
Methods of Data Visualisation (Few famous)
- Python libraries like Matplotlib, Seaborn, Plotly, etc.
- Excel
- Tableau, etc.
Should we really visualize the data?
YES!!! Visualization is critical to storytelling with data, Visualisation can prompt people to ask different questions and have different ideas, Visualisation are the easiest way to help people quickly and effectively understand what is going, Our brain can easily process a chart as opposed to looking at a hundred rows in a spreadsheet.
A picture is worth a thousand words.
Techniques of Data Visualization
There are many elements for visualizing the data. It can be charts, maps, graphs, and so on. Let us dive into a few of those.
Line Chart
A line chart can compare different but related data sets. Perfect for showing trends in data at equal time intervals, data that are arranged in columns or rows, or where your data contains multiple data series. Show how data values change in relation to a continuous variable(eg.time).
The Horizontal axis signifies time or a similar category. The Vertical axis signifies numerical values. This displays continuous data over a given time period.
Pie Chart
A pie chart is a type of circular graph, used to show the relative contribution of different categories (which we see as slices), to make an overall total (which we see as a pie).
A pie chart can show the breakdown of an entity into various sub-parts. Each subpart represents a static value or category. The sum of all subparts will be 100%. Data points on a pie chart, that is, the slices, are represented as percentages of the complete pie.
Use this when you only have one data series. Make sure your data contains no more than maybe a dozen categories or else it is going to look clumsy.
Bar Charts
A bar chart is a type of graph used to compare values across categories using horizontal bars. The bar chart is the most commonly used type of chart. This is great for comparing related data sets or parts.
Eg. The population numbers of 10 different countries and how they compare to one another.
Stacked Bar Charts
In the stacked bar charts each bar is divided into sub bars stacked end to end, each one corresponding to a level of the second categorical variable.
Eg. The population of each country split into 4 age-ranges.
Column Charts
Column charts can be used effectively to show change over time. This can also compare values side by side. The categories are arranged on the horizontal axis, and the values are arranged on the vertical axis.
The column chart looks similar to a bar chart. A column chart may be better suited for showing negative and positive values.
Eg. Showing page views Vs user session time on a website as it changes on a month to month basis.
Treemaps
Treemaps are useful for displaying complex hierarchies using nested rectangles. This compares values across different hierarchy levels, shows proportions as rectangles. A good way to display lots of data in one graphic. Color, size, and closeness of shapes represent hierarchical data categories.
Eg. Statewide employment rates, the size of the rectangle represents the population, color represents the employment rate.
Funnel Charts
The funnel charts display a pipeline or different stages of a continuous process. This helps you visualize a linear process that has sequential connected stages.
Eg. showing the conversion rate at each stage of the sales process from lead generation to the final sale.
Scatter Charts
The circular colors in scatter charts represent the categories of data, the size of the circle is indicative of the volume of data. This is great for revealing trends, clusters, patterns, and the correlation between data points.
Scatter charts are commonly used to compare statistical, scientific, and engineering values.
Eg. Each product line by the number of units sold and the revenue it brings.
Bubble charts
Bubble charts are a variant of scatter charts. These are very useful for comparing a handful of categories to one another.
Eg. understanding the areas of significant expenditure in an organization's sales budget.
Sparklines
A sparkline provides the greatest impact when it is placed close to the data it represents. They do not include an axis, display trends simply and effectively.
Sparklines are mini charts placed inside single cells to represent a selected range of data. They are typically used to show data trends, such as seasonal increase-decrease, economic cycles, and share, rate, or price fluctuations, and many more. They can also be used to highlight max-min values.
Eg. stock market price fluctuations from the opening to the closing of a training day.
Histograms
Histograms show the distribution of data grouped into ‘bins’. They look similar to bar charts but are very different. Bar charts compare data, while histograms display data distribution.
Filled Map chart
A filled map chart is a type of chart used to compare values and show categories across geographical regions. This chart is suitable for data that contains geographical regions like countries, states, or postal codes.
Pivot Charts
Pivot charts show data series, categories, and chart axes just like standard charts do. However, the source data is hosted in a pivot table.
Pivot charts are useful for making sense of complex data in a pivot table.
Area Charts
Area chart show information as a series of data points connected by straight lines. They have a filled area below the connected data points. Area charts can show both positive and negative values.
Dashboards
Data analysis dashboards provide key information in one place. Dashboards can provide user interaction capabilities Eg. filters, slicers, timelines, and map charts. Dashboard users get consolidated and visualized insight into their most important business data and Key Performance Indicator(KPI).
Dashboard users get a controllable self-service Business Intelligence(BI) interface. They are typically created in a data analysis application by using multiple pivot tables and charts. Pivot tables and charts could be created from a single data source or from multiple data sources.
Benefits of using Dashboards!
- Offer insights into your data.
- Can alert you to trends and patterns.
- Provides an interactive experience using filters.
- They are dynamically updated as data changes.
- Provides a centralized consolidated view of business data.
- A dashboard can be a very useful tool in areas of the business such as financial, forecasting, and reporting, project management, executive reporting, human resources, customer service, helpdesk issue tracking, healthcare monitoring, call center analytics, social media marketing, and many more.
Things to keep in mind before creating a dashboard
- Collect and organize data!!
- Verify whether your data is clean, error-free, and has no blank rows or columns.
- Format your data as a table.
- Create pivot tables.
- Create several visualizations to populate your dashboard with(chart, map…)
If you provide too much information such as charts, amps, etc. there is a higher possibility that your key message can get lost.
Narrow down the amount of visualization. Make visualizations more focused to highlight just one or two important points.
Why use Dashboards, when you have many other options?
Dashboards are great for executives or business owners on the go looking at dashboards from a mobile device. Dashboard in a spreadsheet should tell a person what they need to focus on immediately.
Don't put information that is ‘Nice to know’ in a dashboard, it should be on a ‘Need to know basis’.
When you create your dashboard or report you can highlight things that are important to your audience. People fear of numbers dissipates if we can show them what numbers actually mean and make it real to them, through dashboards.
Cognos Analytics
Cognos Analytics is an AI-fueled business intelligence platform that supports the entire analytics cycle, from discovery to operationalization.
Why choose Cognos Analytics?
Cognos Analytics can really help you create a better visualization and dashboards. There are templates that allow you to quickly drag and drop your visualizations into the slots to help you create something that's visually compelling. There is a visualization recommender.
Cognos also started to infuse Artificial Intelligence into the offering, where the system can generate an entire dashboard for you.
You can have a conversation with your personal assistant and ask it questions and once you’ve focussed on the area you’re interested in, simply say ‘generate dashboard’.
Advanced analytic capabilities through the key driver analysis or the AI-infused forecasting. Ability to share your visualizations and your dashboards in just a few clicks through various social media.
What does it provide?
- Sales Solution
- Marketing Solution
- Operations
Save time with automated data preparation. Protect your data.
Let AI help you uncover the patterns hidden in your data!
