🎁 New Features

It's been a colorful month ... we've added the ability to change the color of any categorical variable and extended the spectrum of colors automatically generated for your values. We've also added a new enrichment letting you fill missing values in your data!

01. Extended Variable Colors

We've increased the scale of our default color palette to include 30 colors!

On top of this - clicking to show more categorical values will add appropriate color to nodes in your Graph that would previously have been grey.

Color is a powerful analytical tool and lets you quickly identify the features of your data points inside visualisations. Up until now, we've used grey to color any categorical value beyond the 10 most frequently occurring.

We believe that more color means more clarity. Clicking to see more categorical values will extend the colors presented in your Graph.

How can I start using it?

• Open a project with a categorical variable that contains many values.

• Apply color mapping to this variable in your project's Graph.

• Click to show moreshow more values.

• Notice how your color palette extends inside the Graph and variable sidebar chart.

02. Changing Colors For Any Categorical Value

You can now change the color of any categorical value!

Although every value in your categorical variable will be automatically assigned a color - you can change these by editing the variable and selecting a new one using the color picker.

How can I start using it?

• Open up a project and find a categorical variable.

• Click the edit button at the top of your variable card.

• Now, click the color picker icon.

• Choose a new color and save your changes!

03. New Enrichment: Fill Missing Values

We've built an enrichment to fill missing values in your data. Missing values can be annoying, misleading and disruptive to your analysis. Replacing them with specific values can help to clean up and prepare your dataset for analysis.

Choose Fill Missing Values from the data enrichment tab inside of the project setup wizard to start replacing missing values. Then, select a variable with missing values and tell Graphext how you would like to fill these values. You can choose from options like using a constant value, using the most or least frequently occurring value and using the column's minimum or maximum value. Look for the replaced variable in your transformed dataset.

If you'd prefer, you can always use a different enrichment to predict missing values!

How can I start using it?

• Start building a project using a dataset with missing values.

• Choose Fill Missing Values from the data enrichment tab inside your project setup wizard.

• Tell Graphext which column contains your missing values.

• Choose how you want to replace your missing values.

• That's it. Look for the replaced replaced variable in your transformed dataset.

04: Dataset Info: Sources & Descriptions

We've added space to describe your dataset and reference it's original source inside Graphext.

Context is always important but when dealing with data - it is essential. Referencing your data leaves behind a trail that other team members or researchers can trace to validate or continue your analysis.

To start describing and referencing a dataset, find it from inside of your team's Graphext workspace. Then open the dataset info menu using the 3 dots on the far right of your dataset card. Enter the source URL and write a description then click on the dataset to see this information listed above your data.

How Can I Start Using It?

• Find a dataset inside your Graphext workspace and select the three dots from the far right of the dataset card.

• Choose Dataset Info from the menu list.

• Enter a source URL and write a short description.

• Save your changes.

🐞 Bug Fixes & Improvements

• Added the ability to change the name of a team.

• Fixed an issue with info cards not appearing after clicking on a node in the Graph.

• Fixed a bug causing the creation of a new project to fail after moving some data to the trash.

• Added a menu button to instantly open a variable in the Correlations panel.

• Added a legend to list variables. A white circle indicates that white-white-coloured nodes refer to data belonging to more than one list category.

📖 Stories worth Sharing

01. Segmenting 1000 Supermarket Customers Using Sales Data

Our team clustered 1000 supermarket sales in order to segment customers according to their buying habits.

Graphext | Graphtex | Graphnext: Grouping Similar Spellings Using Chars2Vec and Agglomerative Clustering

'España' and 'Españha' are just spelling variations. We built a way of grouping words spelt differently but referring to the same concept and made it available alongside any type of analysis you perform with Graphext.

Getting Started Videos

We've created a collection of Getting Started videos to help guide you in using Graphext's interface panels and core features.

🎁 Correlations

Our new Correlations panel lets you study the relationships between variables. Find it inside of any new Graphext project you create and start discovering the associations in your data.

What is Correlation?

Correlation is a statistical concept referring to the relationship between two variables. We can use correlation to understand whether observing a change in variable A will also mean observing a change in variable B.

Positive correlations refer to a relationship between two variables in which both variables move in the same direction. Negative correlations refer to a relationship between two variables in which an increase in one variable is associated with a decrease in the other.

“Correlation doesn't imply causation, but it does waggle its eyebrows suggestively and gesture furtively while mouthing 'look over there.” - Randall MunroeRandall Munroe

The Correlations Panel

Inside your project's Correlations panel you'll find a series of charts as you would inside the Compare panel. Choose a variable to study using the search bar and Graphext will generate charts showing the correlation between this variable and other variables in your data.

Use correlation charts to understand how the values of one variable are associated with the values of another. You can export charts from the Correlations panel or save them as insights.

Reading Correlation Charts

Charts in your Correlations panel reveal the number of data points where values from two variables meet. Your y-axis represents values from the variable in your search bar and the x-axis represents values from the correlated variable - labelled in the top right of each card.

The blue circles in your correlation charts represent the number of data points at each value intersection. Bigger and brighter circles represent a higher number of data points at an intersection whereas lower and duller circles represent fewer data points at an intersection.

A strong positive correlation would be signified by a trend of big & bright circles moving diagonally upwards from left to right 📈

A strong negative correlation would be signified by a trend of big & bright circles moving diagonally upwards from right to left 📉

The Docs

Correlation is a powerful tool but its key concepts aren't always self-explanatory. Here are a couple of articles to help you use and understand Correlations.

How To | Correlations

Start here. This article walks you around the new Correlations panel - pointing out the different features and showing you how to use them.

Technical Docs | Understanding Correlation

Read about the concepts key to understanding correlation. In this article, we explain how correlation works, the different types of correlation alongside pointing out the common pitfalls associated with misinterpreting correlation.

How can I start using it?

• Build a Graphext project.

• Once your project is ready, navigate to the Correlations panel.

• Chose a variable using the search bar.

• Study the charts to inspect the correlation between this variable and other variables in your data.

• Change the collection of variable charts presented using the dropdown menu at the top left of your Correlations panel.

🎁 Models

We're excited to say that we've added a new panel to your projects! Find Models after you've built a prediction model with Graphext.

About Models

Models is designed to help you understand more about the creation and performance of predictions models you build. You'll find three tabs - General - Training - Result - each containing distinct information about your model.

This information helps you unpick how your model was built, its strengths and weaknesses as well as how it performed in specific areas.

“It takes characteristics of the individual as input, and provides a predictive score as output. The higher the score, the more likely it is that the individual will exhibit the predicted behavior.” Eric Siegel

Why We Built Models

Examining the mechanics behind a model is a crucial aspect of ensuring that it's application is appropriate. We've included references to the technology used to develop the model, descriptions of its primary use cases as well as notes from our team on its performance.

Evaluating a prediction model helps us to understand how good the model is. Using accuracy scores and other performance metrics, we get a sense of whether the model is able to make correct or inaccurate predictions. Not only this, but through evaluation of a model, we can understand how to improve it by changing its factors or parameters.

The Docs

Prediction can be pretty complex at the best of times. We've written a few articles to help you get your head around the concepts key to Models.

How To | Models

Start here. This article walks you around the new Models panel - pointing out the different features and showing you how to use them.

Technical Docs | Training Models

Learn why and how to build models. Here, we explicate the process of building a prediction model in Graphext - considering the reasons for doing so alongside some of the key concepts involved.

Technical Docs | Evaluating Models

Use as a dictionary to your Models panel. As well as explaining the usefulness of evaluating models, this article offers explanations for all of the technical terms used inside your project's Models panel.

How can I start using it?

• Build a project using Models → Train & Predict as your analysis type.

• Once your project is ready, navigate to the Models panel.

• Check the mechanics of your model using the General tab.

• Inspect how it was created using the Training tab.

• Inspect its performance using the Result tab.

🎁 New Features

Throughout May, we've been pouring our efforts into fixing bugs and making improvements in Graphext's UX. We've redesigned the project setup wizard, cleaning up the types of analysis you can conduct as well as improving key flows.

We've also added the ability to source and describe datasets as well as adding a new enrichment that groups similar spellings.

01. Cluster Variables Flow

We've made substantial improvements to our old Network of Columns analysis type. This flow lets you study the links between variables in your dataset.

Choose Models → Cluster Variables to build a project that maps the relationships between variables in your data.

This can be a useful way to understand which factors to feed into a model or to simply grasp which variables are strongly linked to one another.

When setting up a Cluster Variables project, choosing a target variable means that your project will focus on mapping other variables relationships to that target variable.

How Can I Start Using It?

• Choose a dataset with at least two variables.

• Select Models → Cluster Variables as your analysis type.

• Pick which variables you want to cluster in your project.

• Refine your configuration using the questions in the setup wizard.

• Execute your project and study the relationships between your variables.

02. New Enrichment: Group Similar Spellings

Aimed at improving the way you conduct Text Analysis in Graphext, our latest data enrichment groups words with similar spellings. Simply put - the idea is to stop Graphext and Graphex from being considered as two separate entities.

Whether it be typos, misplaced punctuation or a missing letter or two, unintended variation in data is a common - and annoying - occurrence in text analysis. Motivated to overcome this common shortcoming, our team of data scientists and engineers built this algorithm to merge words with similar spellings and made it instantly deployable in Graphext using any type of analysis.

Chose Group similar spellings from the list of enrichment options in your data enrichment tab to start grouping similar text or categorical values. Then, set a threshold to configure the strength of the merges taking place.

How Can I Start Using It?

• Start building a project using a dataset with a text column.

• Choose an analysis type and open the data enrichment tab.

• Select Group similar spellings from the list of enrichment options.

• Set a threshold to control the strength of your word joinings.

• Continue building your project.

• Open your project and check out the new merged merged variable.

🐞 Bug Fixes & Improvements

• Improved the design of the project setup wizard. Without removing any of our capabilities, we've tidied up the way that flows are presented. We've removed Employees and Survey analysis types and renamed Google Analytics to Marketing Attribution. You can build the same project using the Models analysis type. We've done this to make it simpler to find the right kind of analysis for your project.

• Fixed a bug preventing users from segmenting data using a direct selection of nodes in the Graph.

• Fixed a bug stopping users on some Mac OS from extracting CSV files downloaded from Graphext.

• Fixed an issue causing some minor Graph UI features to overlap on Safari browsers.

• Disabled a users ability to create insights inside of projects embedded on external websites.

• Fixed a bug stopping users from changing the color of a segmentation whilst - at the same time - renaming the segmentation.

📖 Stories worth Sharing

Good Risk vs Bad Risk: Deconstructing the Feature of 1000 German Loans

Attempting to discover the most influential features of a loan application when considering risk, our team built a model using the features of a loan application to predict whether an applicant would have a good or bad risk rating.

Predicting Stroke Probability

In this guide, Maria and Paul walk you through the process of building a prediction model that analyzes a dataset of 5110 healthcare patients. The model we help you to build will use factors detailing the lifestyle and existing health conditions of a person in order to predict the likelihood of that person suffering a stroke.

🎁 New Features

We've been improving the flow of key Graphext features to make them more instinctive to work with. You can now save insights to your recipe so that you don't lose them when you recreate a project. It's also easier to save and edit new segmentations. We're also getting ready to introduce you to some substantial - and colorful - new features next month!

01. Saving Insights to a Recipe

Insights are key. They help store your discoveries and build data-driven narratives. You don't want to lose them if you recreate a project using a different flow. We've added the ability to save insights to your recipe. Choose key aspects of your analysis, toggle the save switch and move your analysis forward without losing your findings.

Insights that you save will appear in the Insights panel of your recreated project. You can change the configuration of your recreated project as much as you like - this won't affect the insights that you save.

How can I start using it?

• Start by saving some insights in a project you have built.

• Then, click the green recipe icon at the bottom of the insights that you want to save.

• Toggle the switch to save the insight.

• Recreate the project using the settings menu located on the top left of your screen.

• Edit your projects configuration until you are happy with the changes. Execute it.

• Head over to the new project's insights panel to inspect your saved insights.

02. Editing Segmentation Properties

Creating manual or automatic segmentations is a powerful way to discover sub-communities in your data. We've made it easier to customizing the properties of segmentations by improving the logic with which you edit a segmentation. We've also added a button to help you cancel the changes that you make and made it simpler to undo steps like renaming or coloring segments.

Segmentations act like a new variable in your dataset, dividing your values along lines that let you see your data from different perspectives. Segmentations are communities in your data and it is important to control how they appear.

Changes we've made to the flow of editing a segmentation are designed to give you greater freedom in renaming, coloring or removing segmentations. Make use of the undo and cancel buttons to control your changes precisely and quickly.

How can I start using it?

• Create a segmentation in one of your Graphext projects.

• Click on the Edit Segmentation icon from inside the segmentations sidebar card.

• Use the icons to rename, color and remove segments.

• Undo and cancel any changes you make using the icons next to the Save button.

🐞 Bug Fixes & Improvements

• Fixed a bug preventing sub-cluster region labels from appearing after sub-clustering segments.

• Fixed an issue with the product basket analysis flow.

• Fixed an issue with the network of columns flow.

• Fixed a bug in the keywords flow when using datasets containing URL variables.

• Improved the display of categorical values in your sidebar variable charts. Now, - no matter the number of values - categorical variables are always presented in bar charts, not lists.

• Describe the fix in a sentence; what it does, where to find it and why we've added it.

• Describe the fix in a sentence; what it does, where to find it and why we've added it.

📖 Stories worth Sharing

01. Good Risk vs Bad Risk: Dissecting the Features of 1000 German Loans

Paul has been digging into a dataset of 1000 loan applications from 1970 to uncover the mystery of good vs bad risk lending. Pulling apart the financial and social factors of a loan application, this post looks at the characteristics most likely to help people improve their risk profiles.

02. Analyzing Reviews

Businesses fighting to understand feedback from hundreds or thousands of customer reviews can analyze what people are saying using NLP techniques but it takes time and resources to do so. This guide is intended to walk you through the process of analyzing customer reviews with Graphext. We will analyze a dataset of 42,656 reviews about 3 Disneyland branches using the Text → Topics flow.