Use the Correlations panel to discover the relationships between variables in your data. After you build any kind of Graphext project, you'll be able to generate correlation charts that reveal how the values belonging to one variable are associated with the values belonging to another.
Inside Models, you'll find the - General - Training - Result - tabs. These contain information helping you to grasp how your model was built and how accurate it was.
You can use the code editor to build projects using datasets that you have stored in your Graphext workspace. Using the code editor is like assembling code to execute your project and gives you more control over the configuration of your network and the transformations made to your dataset.
You can integrate databases and remotely hosted datasets with Graphext by creating integrations within your workspace. This creates a link between your source and your Graphext 'Datasets' panel, meaning you can regularly pull fresh data from databases and instantly start analyzing it.
Tractor is a tool to scrape data from popular platforms. Use it to build datasets from information on Google, Twitter and Facebook Ads.
Embedding a project means that visitors to your site can interact and explore a project for themselves without leaving your page.
Recipes that you build as part of a Graphext project can be saved and reused elsewhere. They will be exported as plain text files.
When you create a project you build a recipe to transform your data. This is a crucial part of your analysis and determines the output of your project.
Your username and password let you log in to Graphext. Changing them isn't a glamourous task but is an important one.
When you remove a team it no longer exists in your Graphext workspace. You, along with all other team members, will lose access to all of the projects and datasets inside of it.
Projects are the home to your analysis and will often be explored by many people. You can change the information describing a project as well as sharing it with others or deleting it.
You can share projects with other users of Graphext. This gives people outside of your current team the ability to view or edit a project that you've been working on.
When you publish a project it will be given a public URL that can be accessed by anyone. This URL gives people the ability to explore your analysis without being able to save any changes they make to the project.
To share your insights, you can present them inside of a projects Insights panel, export a pdf report including all of your project's insights or download them individually as image files.
Capturing an aspect of your analysis as an insight means that you can add supplementary elements that elaborate on your findings.
Insights are a way of saving bitesize chunks of analysis that highlight significant patterns in your data. They capture a snapshot of a Graph or chart and appear as report cards inside your project's Insights panel.
You can export and share charts from your project at any point throughout your analysis. These charts will download as image files to your computer.
When building a recipe you can aggregate data to combine points that share features into collections.
As part of building a recipe to analyse your data, you can enrich your data with information and functions built into Graphext. Enriching your data increases the information available which Graphext can use to build your recipe.
You might not always want to work with a full dataset. Sampling allows you to select a specific sample of your data to work with.
Based on the value of your variables, Graphext will automatically set the data types for each column in your data. You can change variable types from the 'Datasets' panel of your Graphext workspace.
Providing clear and descriptive information to accompany your datasets makes it easier for yourself and others to manage data in Graphext.
When you build a project, Graphext will often make changes to your data. After you've created a project you can export the data so that you have local access to the fields added in the process of transforming your original data.
The foundation of any data science project is the data you are working with. You can upload a range of dataset formats to Graphext.
Plot lets you visualize variable relationships using simple charts. There are different types of charts to plot different data types including time-series, heatmaps and bar charts.
Compare charts let you quickly explore the similarities and differences between values and variables in your data. After you choose aspects of your data to compare, Graphext will generate a series of charts comparing the values from those aspects.
The Graph is the foundation for exploring data in Graphext. It contains a visual representation of your data points often grouped together into clusters.
Start filtering your data by interacting with the sidebar charts that represent your variables.