The errata list is a list of errors and their corrections that were found after the product was released. If the error was corrected in a later version or reprint the date of the correction will be displayed in the column titled "Date Corrected".
The following errata were submitted by our customers and approved as valid errors by the author or editor.
Color key: Serious technical mistake Minor technical mistake Language or formatting error Typo Question Note Update
| Version |
Location |
Description |
Submitted By |
Date submitted |
Date corrected |
| Printed |
Page page 75 website oreil.ly/J6NMG
Second or third paragraph |
Website printed that does not have the Data Structure file for the lab. Please Help. Thank you.
Note from the Author or Editor:
I have updated the github repo with the correct information. |
Anonymous |
Sep 07, 2025 |
Sep 16, 2025 |
| PDF |
Page Chapter 4, Binary Classification
Tables 4-8, 4-10 |
The credit scores presented in the validation training set in Table 4-7 do not seem to equate to real credit scores like they do in Table 4-6, and the sigmoid function in Figure 4-7 seems to have values which do not correspond to the material presented in the section prior (lower credit scores don't appear to have defaulted but higher credit scores appear to have defaulted).
Additionally, the Evaluation Metrics for Binary Classification section has a confusion matrix output in table 4-10 which appears to have the false positive and false negative values swapped. Comparing the contents of the confusion matrix to other confusion matrices online (like IBM's website) shows the false negatives and false positives are swapped.
I am trying to determine if these are real errors or if I am misunderstanding the contents of the book. Thank you!
Note from the Author or Editor:
For the first question, everything is OK. However, there should probably be a note like the following:
“Note: The credit score values shown in Table 4-7 are normalized for demonstration purposes and do not reflect actual credit score ranges.”
As for the next part of the feedback, Table 4-10 needs to be revised as follows:
Predicted Positive Predicted Negative
Actual Positive True Positive False Negative
Actual Negative False Positive True Negative
|
Cameron Co Covey |
Sep 10, 2025 |
Nov 07, 2025 |
| Printed |
Page 55
after "Evaluate Metrics for Binary Classification" |
Predicted Positive Predicted Negative
Actual Positive True Positive (TP) False Positive (FP) ❌
Actual Negative False Negative (FN) ❌ True Negative (TN)
“It also made 45 incorrect predictions where it classified negatives as positive.”
❌ Incorrect — logical mismatch.
Here’s why:
The value 45 sits in the Actual Positive / Predicted Negative cell.
→ That means actual positives were predicted as negative.
→ That’s False Negatives, not negatives classified as positive.
If the book says “classified negatives as positive,” it’s referring to False Positives, which are Actual Negative / Predicted Positive, i.e., the number 20 in the table.
So that line in your book should have said:
“It also made 20 incorrect predictions where it classified negatives as positives.”
The book mixed up the wording — they reversed the error types in their description.
4. “Similarly, there are 20 instances of false negatives and 19 true negatives.”
❌ Also incorrect (swapped).
From the table:
The 20 is under Actual Negative / Predicted Positive → False Positives
The 45 is under Actual Positive / Predicted Negative → False Negatives
The 19 is indeed True Negatives (bottom-right)
So the correct statement would be:
“Similarly, there are 45 instances of false negatives and 20 instances of false positives, and 19 true negatives.” At this point, I want my money back.
|
Wonkyu Lee |
Oct 23, 2025 |
Nov 07, 2025 |