Data Insights is a data visualization feature of the MindsDB editor.

It lets you explore the queried data by initially displaying and analyzing a subset of the first ten rows. You can choose to analyze a full dataset by clicking the Full Data Analysis button. The analysis presents the distribution of your data aggregated by column.

The data used here comes from one of our tutorials. For details, click here.

Before you see the Data Insights pane, you must run a SELECT query on your dataset. Let’s have a look at the available features.


Distribution of Data per Column

When opening the Data Insights pane, you see the distribution of data of each output dataset column. Initially, the visualization and analysis of the first ten rows is shown, as below.

There is one histogram per column that depicts the column name, data types of the distribution, and the distribution itself.

Potential Bias Flag

To see the Potential Bias flag, enter a full-screen mode of the Data Insights pane.

Here, the location column exhibits potential bias, as there are more great column values than good or poor column values. Such cases are typically flagged. However, it does not necessarily mean that there is a problem with the dataset.

The Potential Bias flag is used when data does not distribute normally or uniformly, likely over-representing or under-representing some values. This may be normal, hence, bias is only potential.

Missing Values Flag

To see the Missing Values flag, enter a full-screen mode of the Data Insights pane.

This flag indicates the proportion of missing values in a column. Columns with a high percentage of missing values are not useful for modeling purposes. Hence, it is recommended to pay attention to the Missing Values flag and try to mitigate it whenever possible, as it indicates the degrading quality of your data.

Hovering Over the Histogram

When hovering over the histogram, you get the information on a particular column value and how many of such values are present in a column. The format is (column_value, count).

It is helpful to determine the exact data value counts from the histograms.

Full Data Analysis

Let’s do a full data analysis step by step.

First, we need to query data for analysis in the MindsDB editor. Please note that you need to query your dataset without using a LIMIT keyword to be able to perform a complete data analysis.

FROM example_db.demo_data.home_rentals;

On execution, we get:

|number_of_rooms|number_of_bathrooms|sqft|location|days_on_market|neighborhood  |rental_price|
|2              |1                  |917 |great   |13            |berkeley_hills|3901        |
|0              |1                  |194 |great   |10            |berkeley_hills|2042        |
|1              |1                  |543 |poor    |18            |westbrae      |1871        |
|2              |1                  |503 |good    |10            |downtown      |3026        |
|3              |2                  |1066|good    |13            |thowsand_oaks |4774        |

Now, open the Data Insights pane by clicking the Data Insights button to the right of the output table. Initially, it shows the analysis of the first ten rows of the output table.

To perform a complete analysis of your data, you can either go to a full-screen mode or stay in a pane mode and click on the Full Data Analysis button. Below is the complete data analysis.

Also, whenever your dataset changes, you can click on the Refresh Data Analysis button to update the data visualization and analysis.

What’s Next?

Want to do more exploratory data analysis in MindsDB? We’re collecting feedback to develop even more data visualization features. Let us know what you’d like to see as part of Data Insights.