Skip to main content
Version: v0.15.0

View a dataset's summary

An imported dataset contains a dataset summary that you can view anytime. A dataset summary contains an array of summary metrics, for example, count, mean, STD, min, max, missing, etc.


To access a dataset summary, consider the following instructions:

  1. In the H2O Model Validation navigation menu, click Datasets.
  2. In the datasets table, click the name of the dataset you want to view its dataset summary.

A dataset summary table will appear, highlighting several summary metrics about the dataset (for example, frequency). To learn more, see Dataset summary table.

Dataset summary table

Column nameDescription
FeatureFeature name (one of the column names in the dataset)
Data typeData type (for example, Int)
CountNumber (count) of value features present in the feature column
MissingNumber of missing feature values
Missing ratioPercentage of missing feature values (N) (N/ Number of rows)
MeanThe typical feature value
Standard deviationThe standard deviation (a measure of divergence or distribution) of the feature values
MinThe minimum feature value
MaxThe maximum feature value
Number of uniqueUnique feature values
FrequencyThe feature frequency value
Datetime formatThe detected date string format (for example, yy-mm-dd, hh-mm-ss (hourly granularity) or dd-mm-yy)
Datetime unitThe highest unit of time, based on incremental date changes (for example, seconds, minutes, hours, days, or weeks)

H2O Model Validation will mark feature columns with N/A (not applicable) if the column feature value is non-numeric.