Fix typos in Practical Issues

book/prac.tex

@@ -118,9 +118,9 @@ \section{Irrelevant and Redundant Features}
 the addition of noisy or irrelevant features.  Intuitively, an
 irrelevant feature is one that is completely uncorrelated with the
 prediction task.  A feature $f$ whose expectation does not depend on
-the label $\Ep[f \| Y] = \Ep[f]$ might be irrelevant.  For instance,
-the presence of the word ``the'' might be largely irrelevant for
-predicting whether a course review is positive or negative.  
+the label $Y$, that is $\Ep[f \| Y] = \Ep[f]$ might be irrelevant.
+For instance, the presence of the word ``the'' might be largely irrelevant for
+predicting whether a course review is positive or negative.
 
 A secondary issue is how well these algorithms deal with
 \concept{redundant features}.  Two features are redundant if they are
@@ -158,7 +158,7 @@ \section{Irrelevant and Redundant Features}
 one feature, the second feature now looks mostly useless.  The only
 possible issue with irrelevant features is that even though they're
 irrelevant, they \emph{happen to} correlate with the class label on
-the training data, but chance.
+the training data, by chance.
 
 As a thought experiment, suppose that we have $N$ training examples,
 and exactly half are positive examples and half are negative
@@ -628,7 +628,7 @@ \section{Evaluating Model Performance}
 curve, you can compute the \concept{area under the curve} (or
 \concept{AUC}) metric, which also provides a meaningful single number
 for a system's performance.  Unlike f-measures, which tend to be low
-because the require agreement, AUC scores tend to be very high, even
+because they require agreement, AUC scores tend to be very high, even
 for not great systems.  This is because random chance will give you an
 AUC of $0.5$ and the best possible AUC is $1.0$.