Data Map Controls

The Atlas Data Map provides controls for exploring and analyzing your data.

Selections

The way you focus on subsets of data for analysis in Atlas is by creating selections. These are groups of points from your dataset that you can select using several different tools:

Vector Search

Search datasets based on similar vector embeddings.

Vector search has three modes:

Query Search (Default): Find data points that best answer a question you have about your data (e.g. "What's happening with the stock market?")

Document Search: Find data points that are most similar to a text sample you provide. (e.g. "Stock market performance")

Embedding Search: Find data points that are close to a user-inputted embedding (e.g. [0.42, 0.87, 0.013, ...]). This is the only mode supported for Embedding datasets. The search will fail or provide incorrect results if your embedding does not have the same dimensionality as your dataset's embeddings or comes from a different embedding model/space.

Exact Search

Search datasets based on exact keyword or regular expression matches.

Search any column in your dataset to highlight exact-matching points on your Atlas Map.

For complex searches, use the helper tools below to match complete words or exact case. Regular expressions enable advanced pattern matching.

Search options

Only match complete words

Match case exactly

Regular expression search

Filter

Apply filters to your data to filter over metadata, giving you new views and greater insight into your dataset. Slicing by timestamp allows you to see change in topics over time. Filter over any of your numerical metadata values like sentiment value, temperature, price, score, and much more.

Lasso

Drag a lasso around a region of space to select all points contained in your region

The Lasso tool allows you to select points on the map by circling them with your mouse. Lassoing can be a part of your data pipeline as you find, select, tag, and clean your data.

Cherry Pick

Click individual points to add them to a selection.

With the cherrypick tool activated, each point you individually click on will be added to your selection.

Adding Tags to a Selection

Here we demonstrate how to add tags to a selection. We select two regions using the lasso tool, one in the top right and one in the left regions of our map. We can combine these lasso selections with a union operation by clicking 'any' in the top section of the selection tools. (Choose 'all' if you want the strict intersection of the lassos.)

To save and label these points, click the 'tag' icon. This will open a pop-up that shows the different tags already applied to your selection, and a bar chart of counts for each tag. To add a new tag or apply an existing tag to a selection, type your desired tag name into the textbox at the top of the pop-up and press Enter on your keyboard or click 'Add'.

You can use this pattern to annotate complex subsets of your data by combining different Atlas selection tools. For example, we perform a full-text search for "New York" and intersect it with a lasso over the newspaper region to create a "new york newspapers" tag.

Atlas gives you the ability to fine-tune your tagged selections. Browsing through selected points in "new york newspapers", we can apply a new or existing tag to specific points by clicking the '+' icon, and remove a tag by clicking on 'x' for a label that we do not want a point to have.

Example: Identifying an outlier cluster from a news dataset

In the news dataset example below, we can use Lasso to select an outlier cluster.

On inspection, we see an area of the map containing points related to betting and casinos. Let's say we don’t want to include these points in our news analysis.

To tag these points using the Lasso tool:

1. Select the lasso function under “Selection Tools.”
2. Draw an outline on the map which captures the points of interest.
3. On the data sidebar, click +tag all and add the name of the tag you want to apply to all lassoed points.
4. Your points are now tagged!

note

See the API reference or the data tagging walkthrough to learn how to use Python to use your tags for cleaning data.

Atlas News Map zoomed into betting and gambling area

Video: Example of lasso tool used to tag Atlas map

View Settings

Color

You can customize the color scheme and point sizes on your map in View Settings.

You may color by existing columns in your data. Depending on your metadata, you might be able to color a news map, for example, by language, news outlet name, country of origin, or number of views. Coloring works for both categorical or numerical data types.

To color datapoints by topic clusters, you can color by Nomic Topic: 1/2/3. Depth level 1 is most general and depth level 3 is the most specific. This can give you a clearer view of the divisions and overlap between different topics in your data.

The legend on your graph will describe the current labels corresponding to colors of points on the map. If the colorable field is one of the Nomic Topic depth levels, then the labels in the legend and on the map will be the topic labels themselves.

Adjust your point size to any size that works for you — the right point size can better highlight the structures in the map, help you more quickly identify outliers, or more easily identify color patterns.

Edit Topic Labels

An editor of a dataset can update topic labels from within the Atlas Map.

In the View Settings panel, click the "Edit Topics" toggle to enter edit mode. In edit mode, click on a topic label to open a modal where the topic label can be altered. Within that modal the most prominent keywords related to that topic can also be viewed.

Once an edited topic label is saved, it is immediately reflected in the map, and propagated to the server. Other users of the map will see the updated topic upon refreshing the map.

XY Positions

tip

Try combining XY positioning modes with selection filters for more precise data exploration. For example, make a selection in one mode then switch to another to see those points in a different context.

Atlas provides multiple ways to position points on your map:

Points are positioned using our Nomic Project projection algorithm by default.

To use custom X-Y coordinates, include paired columns in your dataset following this naming pattern:

• Position_X and Position_Y
• Position-X and Position-Y
• Position.X and Position.Y
• Position X and Position Y

These will appear as "Position XY" in the Position Mode dropdown. Multiple X-Y pairs are supported.

Geospatial Coordinates

For geospatial data, include:

• lat/latitude and lon/longitude columns

note

Currently, only one pair of latitude/longitude columns is supported per dataset.