Hands-On Machine Learning on Google Cloud Platform

Mismatched values

A mismatched value is any value that seems to be of a different data type than the type specified for the column. In the database we are analyzing at this point, there are several values that seem to deviate from the type attributed to the column. For example, in the right column is a cell that contains a dot; it is clear that this is an error in the phase of populating the database. It is equally clear that such a value can cause many problems during the analysis phase, which is why it must be appropriately dealt with.

As seen for missing values, mismatched values are also represented in the data quality bar at the top of each column. In the data quality bar, mismatched values are identified in red, as shown in the following ...