Welcome to the AI and Statistics series!
Let’s dive into how AI can transform tabular data into various types of charts.
Today, we will be using a 2D Data Table structure to generate a Pareto Chart.
This chart helps identify key factors contributing to the majority of outcomes and is often employed in economics and quality control.
In our analysis, we aim to reveal the most critical Keyword Phrases affecting Estimated Weekly Impressions from our data source, Cattree Competitor Keywords_Relevance Scores.xlsx.
Don’t worry about using the AI Agent-driven Bayeslab, all you need is natural language to get the data analysis result.
All content will be explained in the most comprehensible natural language descriptions to help you get started with data analysis from scratch.
We’ll start with a data table featuring fields such as Keyword Phrase and Estimated Weekly Impressions, among others.
A Pareto chart is used to highlight the most significant factors in a dataset, where 80% of the effects usually come from 20% of the causes.
We’ll delve into how these prompts influence the final charts and uncover techniques for effective data visualization.
In just 2 minutes, you’ll learn to identify key performance indicators using Pareto charts.
Let’s start it right now.
Using different prompt inputs, we’ll demonstrate how AI generates two dual-axis chart results.
Our steps will include:
▪︎Step1 . Pareto chart without Parameter Line
▪︎ Step2 . Pareto chart with Parameter Line
Step 1 — Pareto chart without Parameter Line
Filter the data to compare “ReverseASIN” equal to B0794T79KM and “Estimated Weekly Impressions” not equal to zero, creating a dual Y-axis Pareto chart.
The Promt is:
Read Cattree Competitor Keywords_Relevance Scores.xlsx , filter to compare “ReverseASIN” = B0794T79KM and “Estimated Weekly Impressions” not equal to zero, and create a dual Y-axis Pareto chart:
1. Left Y1 axis: Use “Estimated_Weekly_Impressions” to create a bar chart, adjusting the units to fill the entire vertical axis height.
2 Right Y2 axis: Use the cumulative percentage of “Estimated_Weekly_Impressions”; only a line needs to be drawn, with a line width of 2pt.
3. X-axis: Use “%Keyword Phrase”, formatted from 0% to 100%, with no negative values. Arrange in descending order based on the total value of “Estimated Weekly Impressions”.
4. % Keyword Phrase calculation: Index() / Size(), representing the proportion of all previous “Keyword Phrases”.Once the above prompt is written, click ‘Run’ to see a Pareto chart showing Estimated Weekly Impressions and their cumulative percentage.
Step 2 — Pareto chart with Parameter Line
Similar to step 1, with added parameter lines indicating key points.
The Prompt is:
……
5. Create Parameter Line 1: “Click Total Percentage” = 80%
6. Create Parameter Line 2: Based on the intersection of Parameter Line 1 and the cumulative percentage curve, draw a vertical parameter line down to the X-axis.
7. Finally, mark the specific coordinate values at the intersection of the two parameter lines.
Beautify the chart:
1. Optimize the Y1 axis to distribute the bar chart over the entire vertical axis height, with light blue fill color for the bars.
2. Optimize the X-axis to ensure the values span the entire view.
3. Adjust the Y-axis range to reduce the maximum value, making the bar chart more focused.
4. Adjust the X-axis range, expanding it to ease dense label arrangement.
5. Use a blue dashed line for Reference Line 1.
7. Use a green dashed line for Reference Line 2.
Once the above prompt is written, click ‘Run’ to generate a Pareto chart with parameter lines highlighting the 80% threshold and its intersection with the cumulative curve.
Thank you for reading this installment of the AI and Statistics series!
We showed how to leverage a 2D Data Table to create a Pareto Chart, identifying the factors that have the greatest impact on outcomes.
Stay tuned for our upcoming demonstrations to explore more fascinating data visualization.
Using AI Agent and Bayeslab, anyone can organize, analyze, plot data charts, and make business data predictions like a professional data analyst based on previous data.
About Bayeslab
Bayeslab: Website
The AI First Data Workbench
X: @BayeslabAI
Documents:
https://bayeslab.gitbook.io/docs
Blogs:
Bayeslab, an AI-first data workbench designed for everyone — whether you’re a solo entrepreneur, a business analyst, or just someone looking to work smarter with data. Bayeslab is here to empower you to analyze, visualize, and harness the power of your data without needing a full-fledged data team.
Try our product for free: https://bayeslab.ai