# FAQ: K-Means Clustering - Evaluation

This community-built FAQ covers the “Evaluation” exercise from the lesson “K-Means Clustering”.

Paths and Courses
This exercise can be found in the following Codecademy content:

## Join the Discussion. Help a fellow learner on their journey.

Agree with a comment or answer? Like () to up-vote the contribution!

Found a bug? Report it!

Have a question about your account or billing? Reach out to our customer support team!

None of the above? Find out where to ask other questions here!

A quick question that might be a bit tangential:

After dataframe construction, the letter “b” with an apostrophe is appended to each of the iris names that I assigned. (This occurs within my own code, as well as after running the solution code.)

Could someone explain what this character represents and why the dataframe construction results in its appendage?

Thanks.!

Screen Shot 2020-05-12 at 5.08.27 PM|622x500

4 Likes

It seems to be a prefix about literals. The “b” indicates that the literal should become a bytes literal.

It should be noted that 0, 1, 2 in `target` and 0, 1, 2 in `labels` do not necessarily have the same meaning.

``````labels    setosa    versicolor    virginica
0             50             0            0
1              0             2           36
2              0            48           14
``````

In this example, 0 in `labels` means `setosa`, the same as 0 in `target`. But 1 in `labels` seems to mean `virginica` (2 in `target`) and 2 in `labels` seems to mean `versicolor` (1 in target).

The “96% accuracy” about Iris-versicolor is, strictly speaking, the “96% recall”. The 48 true positives is divided by the sum of the 48 true positives and 2 false negatives.

So, it says “Iris-virginica didn’t do so well”, but it is on recall. If we compare another evaluation called precision, the conclusion will be different. The precision about Iris-versicolor is 77%, the 48 true positives divided by the sum of the 48 true positives and 14 false positives. This is not good than the 95% precision about Iris-virginica, the 36 true positives divided by the sum of the 36 true positives and 2 false positives.

1 Like