\item \points{40} {\bf Linear Classifiers (logistic regression and GDA)}

In this problem, we cover two probabilistic linear classifiers we have
covered in class so far. First, a discriminative linear classifier: logistic
regression. Second, a generative linear classifier: Gaussian discriminant
analysis (GDA). Both the algorithms find a linear decision boundary that
separates the data into two classes, but make different assumptions. Our goal
in this problem is to get a deeper understanding of the similarities and
differences (and, strengths and weaknesses) of these two algorithms.

For this problem, we will consider two datasets, along with starter codes provided in the following
files:
\begin{center}
\begin{itemize} %[label=\roman*.]
	\item \url{src/linearclass/ds1_{train,valid}.csv}
	\item \url{src/linearclass/ds2_{train,valid}.csv}
        \item \url{src/linearclass/logreg.py}
        \item \url{src/linearclass/gda.py}
\end{itemize}
\end{center}
Each file contains $\nexp$ examples, one example $(x^{(i)}, y^{(i)})$ per row.
In particular, the $i$-th row contains columns $x^{(i)}_1\in\Re$,
$x^{(i)}_2\in\Re$, and $y^{(i)}\in\{0, 1\}$. In the subproblems that follow, we
will investigate using logistic regression and Gaussian discriminant analysis
(GDA) to perform binary classification on these two datasets.

\begin{enumerate}
	\input{linearclass/01-logreg}
        \ifnum\solutions=1 {
            \input{linearclass/01-logreg-sol}
        } \fi

	\input{linearclass/02-solve-logreg}
        \ifnum\solutions=1 {
            \input{linearclass/02-solve-logreg-sol}
        } \fi


	\input{linearclass/03-gda}
        \ifnum\solutions=1 {
            \input{linearclass/03-gda-sol}
        }\fi

	\input{linearclass/04-gda-ll}
        \ifnum\solutions=1 {
            \input{linearclass/04-gda-ll-sol}
        } \fi

	\input{linearclass/05-solve-gda}
        \ifnum\solutions=1 {
            \input{linearclass/05-solve-gda-sol}
        } \fi

	\input{linearclass/06-plot-ds1}
        \ifnum\solutions=1 {
            \input{linearclass/06-plot-ds1-sol}
        } \fi

	\input{linearclass/07-plot-ds2}
        \ifnum\solutions=1{
            \input{linearclass/07-plot-ds2-sol}
        }\fi

	\input{linearclass/08-transform}
        \ifnum\solutions=1{
            \input{linearclass/08-transform-sol}
        }\fi

\end{enumerate}