Update example environment style <noupdate>

src/year1/machine-learning-and-data-mining/sections/_classification.tex

@@ -30,7 +30,7 @@
         \end{example}
 
     \item[Data exploration] \marginnote{Data exploration}
-        \begin{figure}[ht]
+        \begin{figure}[H]
             \begin{subfigure}{.5\textwidth}
                 \centering
                 \includegraphics[width=\linewidth]{img/_iris_boxplot_general.pdf}
@@ -137,7 +137,7 @@ As $N$ is at the denominator, this means that for large values of $N$, the uncer
         Note that cross-validation is done on the training set, so a final test set can still be used to
         evaluate the resulting model.
 
-        \begin{figure}[h]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.6\textwidth]{img/cross_validation.png}
             \caption{Cross-validation example}
@@ -287,7 +287,7 @@ a macro (unweighted) average or a class-weighted average.
         When the area between the two curves is large and the curve is above the random classifier, 
         the model can be considered a good classifier.
 
-        \begin{figure}[h]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.5\textwidth]{img/lift_chart.png}
             \caption{Example of lift chart}
@@ -301,7 +301,7 @@ a macro (unweighted) average or a class-weighted average.
         A straight line is used to represent a random classifier.
         A threshold can be considered good if it is high on the y-axis and low on the x-axis.
         
-        \begin{figure}[h]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.35\textwidth]{img/roc_curve.png}
             \caption{Example of ROC curves}
@@ -408,7 +408,7 @@ Possible solutions are:
             \item Classes distribution.
         \end{itemize}
 
-        \begin{figure}[h]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.5\textwidth]{img/_iris_decision_tree_example.pdf}
             \caption{Example of decision tree}
@@ -458,7 +458,7 @@ Possible solutions are:
                 Skipped.
         \end{descriptionlist}
 
-        \begin{figure}[h]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.35\textwidth]{img/impurity_comparison.png}
             \caption{Comparison of impurity measures}
@@ -633,7 +633,7 @@ This has complexity $O(h)$, with $h$ the height of the tree.
     \item[Perceptron] \marginnote{Perceptron}
         A single artificial neuron that takes $n$ inputs $x_1, \dots, x_n$ and a bias $b$,
         and computes a linear combination of them with weights $w_1, \dots, w_n, w_b$.
-        \begin{figure}[h]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.25\textwidth]{img/_perceptron.pdf}
             \caption{Example of perceptron}
@@ -686,7 +686,7 @@ In practice, a maximum number of iterations is set.
         In general, a subset of points (support vectors) \marginnote{Support vectors} 
         in the training set is sufficient to define the hulls.
 
-        \begin{figure}[h]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.4\textwidth]{img/svm.png}
             \caption{Maximum margin hyperplane of linearly separable data}
@@ -724,7 +724,7 @@ For non-linearly separable data, the boundary can be found using a non-linear ma
 to map the data into a new space (feature space) where a linear separation is possible.
 Then, the data and the boundary is mapped back into the original space.
 
-\begin{figure}[h]
+\begin{figure}[H]
     \begin{subfigure}{0.49\textwidth}
         \centering
         \includegraphics[width=\linewidth]{img/svm_kernel_example1.png}
@@ -840,7 +840,7 @@ Train a set of base classifiers and make predictions by majority vote.
 If all the classifiers have the same but independent error rate, 
 the overall error of the ensemble model is lower (derived from a binomial distribution).
 
-\begin{figure}[h]
+\begin{figure}[H]
     \centering
     \includegraphics[width=0.6\textwidth]{img/ensemble_error.png}
     \caption{Relationship between the error of base classifiers and ensemble models}

src/year1/machine-learning-and-data-mining/sections/_clustering.tex

@@ -13,7 +13,7 @@
         0 indicates no difference while the upper bound varies.
 \end{description}
 
-\begin{table}[ht]
+\begin{table}[H]
     \centering
     \renewcommand{\arraystretch}{2}
     \begin{tabular}{c | c | c}
@@ -64,7 +64,7 @@ Given two $D$-dimensional data entries $p$ and $q$, possible distance metrics ar
         The Mahalanobis distance of $p$ and $q$ increases when the segment connecting them 
         points towards a direction of greater variation of the data.
 
-        \begin{figure}[h]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.35\textwidth]{img/mahalanobis.png}
             \caption{The Mahalanobis distance between $(A, B)$ is greater than $(A, C)$, while the Euclidean distance is the same.}

src/year1/machine-learning-and-data-mining/sections/_crisp.tex

@@ -3,7 +3,7 @@
 \begin{description}
     \item[\Acl{crisp}] \marginnote{\acs{crisp}}
         Standardized process for data mining.
-        \begin{figure}[ht]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.45\textwidth]{img/crisp.png}
             \caption{\ac{crisp} workflow}

src/year1/machine-learning-and-data-mining/sections/_data_lake.tex

@@ -25,7 +25,7 @@
                 Less expensive.
         \end{descriptionlist}
 
-        \begin{figure}[ht]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.5\textwidth]{img/_storage.pdf}
             \caption{Data storage technologies}
@@ -155,7 +155,7 @@
     \item[Speed layer] 
         Receives the data and prepares real-time views. The views are also stored in the serving layer.
 \end{description}
-\begin{figure}[ht]
+\begin{figure}[H]
     \centering
     \includegraphics[width=0.5\textwidth]{img/lambda_lake.png}
     \caption{Lambda lake architecture}
@@ -165,7 +165,7 @@
 \marginnote{Kappa lake}
 The data are stored in a long-term store.
 Computations only happen in the speed layer (avoids lambda lake redundancy between batch layer and speed layer).
-\begin{figure}[ht]
+\begin{figure}[H]
     \centering
     \includegraphics[width=0.5\textwidth]{img/kappa_lake.png}
     \caption{Kappa lake architecture}
@@ -181,7 +181,7 @@ Framework that adds features on top of an existing data lake.
     \item Unified batch and streaming
     \item Schema enforcement
 \end{itemize}
-\begin{figure}[ht]
+\begin{figure}[H]
     \centering
     \includegraphics[width=0.7\textwidth]{img/delta_lake.png}
     \caption{Delta lake architecture}

src/year1/machine-learning-and-data-mining/sections/_data_warehouse.tex

@@ -34,7 +34,7 @@
         Navigation path created by the operations that a user applied.
 \end{description}
 
-\begin{figure}[ht]
+\begin{figure}[H]
     \centering
     \includegraphics[width=0.35\textwidth]{img/_olap_cube.pdf}
     \caption{\ac{olap} data cube}
@@ -280,13 +280,13 @@ The architecture of a data warehouse should meet the following requirements:
         \end{descriptionlist}
 \end{description}
 
-\begin{figure}[ht]
+\begin{figure}[H]
     \centering
     \includegraphics[width=0.8\textwidth]{img/dfm.png}
     \caption{Example of \ac{dfm}}
 \end{figure}
 
-\begin{figure}[ht]
+\begin{figure}[H]
     \centering
     \includegraphics[width=0.5\textwidth]{img/dfm_events.png}
     \caption{Example of primary and secondary events}
@@ -318,7 +318,7 @@ Aggregation operators can be classified as:
 \begin{description}
     \item[Additivity] \marginnote{Additive measure}
     A measure is additive along a dimension if an aggregation operator can be applied. 
-    \begin{table}[ht]
+    \begin{table}[H]
         \centering
         \begin{tabular}{l | c | c}
                                         & \textbf{Temporal hierarchies}                             & \textbf{Non-temporal hierarchies} \\
@@ -340,7 +340,7 @@ There are two main strategies:
 \begin{descriptionlist}
     \item[Star schema] \marginnote{Star schema}
         A fact table that contains all the measures is linked to dimensional tables.
-        \begin{figure}[ht]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=\textwidth]{img/logical_star_schema.png}
             \caption{Example of star schema}

src/year1/machine-learning-and-data-mining/sections/_intro.tex

@@ -87,7 +87,7 @@ Different levels of insight can be extracted by:
 
     \item[Data mining] \marginnote{Data mining}
         Discovery process for unstructured decisions.
-        \begin{figure}[ht]
+        \begin{figure}[H]
             \centering
             \includegraphics[width=0.8\textwidth]{img/data_mining_process.png}
             \caption{Data mining process}