Merge pull request #223 from chhoumann/table-caption-fix

baseline/experiment_analysis/experiment_analysis.ipynb

@@ -2380,8 +2380,8 @@
     "    with open(path, \"w\") as file:\n",
     "        file.write(\"\\\\begin{table}[!htb]\\n\")\n",
     "        file.write(\"\\\\centering\\n\")\n",
+    "        file.write(\"\\\\caption{Overview of model types for \\\\ce{\" + oxide_name + \"} oxide}.\\n\")\n",
     "        file.write(latex_table)\n",
-    "        file.write(\"\\\\caption{Overview of model types for \\\\ce{\" + oxide_name + \"} oxide}\\n\")\n",
     "        file.write(\"\\\\label{tab:\" + oxide + \"_overview}\\n\")\n",
     "        file.write(\"\\\\end{table}\\n\")\n"
    ]

report_thesis/src/sections/appendix/index.tex

@@ -53,6 +53,7 @@ \subsection{Cross-Validation Fold Plots for Major Oxides}\label{subsec:cv_plots}
 \subsection{Initial Experiment: Model Hyperparameters}\label{subsec:initial_experiment_hyperparameters}
 \begin{table}[!htb]
 \centering
+\caption{Explictly set hyperparameters for the \gls{pls}, \gls{svr}, ridge, \gls{lasso}, \gls{enet}, \gls{rf}, and \gls{etr} models. When not explicitly set, the default hyperparameters provided by the libraries listed in Section~\ref{sec:experimental_setup} are used.}
 \begin{tabular}{@{}llp{0.5\textwidth}@{}}
 \toprule
 \textbf{Model} & \textbf{Hyperparameter} & \textbf{Value} \\
@@ -102,14 +103,14 @@ \subsection{Initial Experiment: Model Hyperparameters}\label{subsec:initial_expe
 & \texttt{random\_state} & 42 \\
 \midrule
 \end{tabular}
-\caption{Explictly set hyperparameters for the \gls{pls}, \gls{svr}, ridge, \gls{lasso}, \gls{enet}, \gls{rf}, and \gls{etr} models. When not explicitly set, the default hyperparameters provided by the libraries listed in Section~\ref{sec:experimental_setup} are used.}
 \label{tab:combined_hyperparameters}
 \end{table}
 
 \FloatBarrier
 
 \begin{table}[!htb]
 \centering
+\caption{Explictly set hyperparameters for the \gls{gbr} and \gls{xgboost} models. When not explicitly set, the default hyperparameters provided by the libraries listed in Section~\ref{sec:experimental_setup} are used. The \gls{ngboost} model does not have any explicitly set hyperparameters.}
 \begin{tabular}{@{}llp{0.5\textwidth}@{}}
 \toprule
 \textbf{Model} & \textbf{Hyperparameter} & \textbf{Value} \\
@@ -149,7 +150,6 @@ \subsection{Initial Experiment: Model Hyperparameters}\label{subsec:initial_expe
 & \texttt{eval\_metric} & rmse \\
 \bottomrule
 \end{tabular}
-\caption{Explictly set hyperparameters for the \gls{gbr} and \gls{xgboost} models. When not explicitly set, the default hyperparameters provided by the libraries listed in Section~\ref{sec:experimental_setup} are used. The \gls{ngboost} model does not have any explicitly set hyperparameters.}
 \label{tab:combined_hyperparameters}
 \end{table}
 
@@ -173,14 +173,15 @@ \subsection{Initial Experiment: Model Hyperparameters}\label{subsec:initial_expe
     \multicolumn{3}{l}{\textbf{Learning Rate:} 0.001} \\
     \bottomrule
   \end{tabular}
-  \caption{Summary of the Neural Network Architecture}
+  \caption{Summary of the \gls{ann} architecture.}
   \label{tab:nn_architecture}
 \end{table}
 
 \FloatBarrier
 
 \begin{table}[!htb]
   \centering
+  \caption{Summary of the \gls{cnn} architecture.}
   \begin{tabular}{lll}
     \toprule
     \textbf{Layer} & \textbf{Output Shape} & \textbf{Hyperparameter} \\ \midrule
@@ -211,7 +212,6 @@ \subsection{Initial Experiment: Model Hyperparameters}\label{subsec:initial_expe
     \multicolumn{3}{l}{\textbf{Learning Rate:} 0.001} \\
     \bottomrule
   \end{tabular}
-  \caption{Summary of the Convolutional Neural Network Architecture}
   \label{tab:cnn_architecture}
 \end{table}
 

report_thesis/src/sections/appendix/tables/Al2O3_overview.tex

@@ -1,5 +1,6 @@
 \begin{table}[!htb]
 \centering
+\caption{Overview of model types for \ce{Al2O3} oxide.}
 \begin{tabular}{llllllll}
 \toprule
 \ce{Al2O3} & Model Type & Transformer Type & PCA Type & Scaler Type & \gls{rmsecv} & Std. dev. CV & \gls{rmsep} \\
@@ -16,6 +17,5 @@
  & \texttt{random\_forest} & \texttt{power\_transformer} & \texttt{none} & \texttt{max\_abs\_scaler} & 2.302 & 2.295 & 2.111 \\
 \bottomrule
 \end{tabular}
-\caption{Overview of model types for \ce{Al2O3} oxide}
 \label{tab:Al2O3_overview}
 \end{table}

report_thesis/src/sections/appendix/tables/CaO_overview.tex

@@ -1,5 +1,6 @@
 \begin{table}[!htb]
 \centering
+\caption{Overview of model types for \ce{CaO} oxide.}
 \begin{tabular}{llllllll}
 \toprule
 \ce{CaO} & Model Type & Transformer Type & PCA Type & Scaler Type & \gls{rmsecv} & Std. dev. CV & \gls{rmsep} \\
@@ -16,6 +17,5 @@
  & \texttt{lasso} & \texttt{power\_transformer} & \texttt{none} & \texttt{min\_max\_scaler} & 1.529 & 1.514 & 1.684 \\
 \bottomrule
 \end{tabular}
-\caption{Overview of model types for \ce{CaO} oxide}
 \label{tab:CaO_overview}
 \end{table}

report_thesis/src/sections/appendix/tables/FeOT_overview.tex

@@ -1,5 +1,6 @@
 \begin{table}[!htb]
 \centering
+\caption{Overview of model types for \ce{FeO_T} oxide.}
 \begin{tabular}{llllllll}
 \toprule
 \ce{FeO_T} & Model Type & Transformer Type & PCA Type & Scaler Type & \gls{rmsecv} & Std. dev. CV & \gls{rmsep} \\
@@ -16,6 +17,5 @@
  & \texttt{random\_forest} & \texttt{quantile\_transformer} & \texttt{none} & \texttt{norm3\_scaler} & 3.079 & 3.044 & 2.018 \\
 \bottomrule
 \end{tabular}
-\caption{Overview of model types for \ce{FeO_T} oxide}
 \label{tab:FeOT_overview}
 \end{table}

report_thesis/src/sections/appendix/tables/K2O_overview.tex

@@ -1,5 +1,6 @@
 \begin{table}[!htb]
 \centering
+\caption{Overview of model types for \ce{K2O} oxide.}
 \begin{tabular}{llllllll}
 \toprule
 \ce{K2O} & Model Type & Transformer Type & PCA Type & Scaler Type & \gls{rmsecv} & Std. dev. CV & \gls{rmsep} \\
@@ -16,6 +17,5 @@
  & \texttt{extra\_trees} & \texttt{power\_transformer} & \texttt{none} & \texttt{robust\_scaler} & 0.714 & 0.709 & 0.464 \\
 \bottomrule
 \end{tabular}
-\caption{Overview of model types for \ce{K2O} oxide}
 \label{tab:K2O_overview}
 \end{table}

report_thesis/src/sections/appendix/tables/MgO_overview.tex

@@ -1,5 +1,6 @@
 \begin{table}[!htb]
 \centering
+\caption{Overview of model types for \ce{MgO} oxide.}
 \begin{tabular}{llllllll}
 \toprule
 \ce{MgO} & Model Type & Transformer Type & PCA Type & Scaler Type & \gls{rmsecv} & Std. dev. CV & \gls{rmsep} \\
@@ -16,6 +17,5 @@
  & \texttt{random\_forest} & \texttt{quantile\_transformer} & \texttt{none} & \texttt{norm3\_scaler} & 1.640 & 1.630 & 0.973 \\
 \bottomrule
 \end{tabular}
-\caption{Overview of model types for \ce{MgO} oxide}
 \label{tab:MgO_overview}
 \end{table}

report_thesis/src/sections/appendix/tables/Na2O_overview.tex

@@ -1,5 +1,6 @@
 \begin{table}[!htb]
 \centering
+\caption{Overview of model types for \ce{Na2O} oxide.}
 \begin{tabular}{llllllll}
 \toprule
 \ce{Na2O} & Model Type & Transformer Type & PCA Type & Scaler Type & \gls{rmsecv} & Std. dev. CV & \gls{rmsep} \\
@@ -16,6 +17,5 @@
  & \texttt{ridge} & \texttt{quantile\_transformer} & \texttt{none} & \texttt{norm3\_scaler} & 1.011 & 1.001 & 0.467 \\
 \bottomrule
 \end{tabular}
-\caption{Overview of model types for \ce{Na2O} oxide}
 \label{tab:Na2O_overview}
 \end{table}

report_thesis/src/sections/appendix/tables/SiO2_overview.tex

@@ -1,5 +1,6 @@
 \begin{table}[!htb]
 \centering
+\caption{Overview of model types for \ce{SiO2} oxide.}
 \begin{tabular}{llllllll}
 \toprule
 \ce{SiO2} & Model Type & Transformer Type & PCA Type & Scaler Type & \gls{rmsecv} & Std. dev. CV & \gls{rmsep} \\
@@ -16,6 +17,5 @@
  & \texttt{random\_forest} & \texttt{none} & \texttt{none} & \texttt{norm3\_scaler} & 5.204 & 5.192 & 3.788 \\
 \bottomrule
 \end{tabular}
-\caption{Overview of model types for \ce{SiO2} oxide}
 \label{tab:SiO2_overview}
 \end{table}

report_thesis/src/sections/appendix/tables/TiO2_overview.tex

@@ -1,5 +1,6 @@
 \begin{table}[!htb]
 \centering
+\caption{Overview of model types for \ce{TiO2} oxide.}
 \begin{tabular}{llllllll}
 \toprule
 \ce{TiO2} & Model Type & Transformer Type & PCA Type & Scaler Type & \gls{rmsecv} & Std. dev. CV & \gls{rmsep} \\
@@ -16,6 +17,5 @@
  & \texttt{pls} & \texttt{power\_transformer} & \texttt{kernel\_pca} & \texttt{robust\_scaler} & 0.441 & 0.441 & 0.411 \\
 \bottomrule
 \end{tabular}
-\caption{Overview of model types for \ce{TiO2} oxide}
 \label{tab:TiO2_overview}
 \end{table}

report_thesis/src/sections/background/data_overview.tex

@@ -5,6 +5,7 @@ \subsection{Data Overview}\label{sec:data-overview}
 
 \begin{table*}
 \centering
+\caption{Example of CCS data for a single location (from \citet{p9_paper}).}
 \begin{tabular}{llllllll}
 \toprule
      wave &         shot1 &         shot2 &  $\cdots$ &        shot49 &       shot50  & median        & mean          \\
@@ -16,7 +17,6 @@ \subsection{Data Overview}\label{sec:data-overview}
 905.57349 & 1.9864713e+10 & 1.2956832e+10 & $\cdots$  & 1.9785415e+10 & 7.1994239e+09 & 1.1311150e+10 & 1.2201224e+10 \\
 \bottomrule
 \end{tabular}
-\caption{Example of CCS data for a single location (from \citet{p9_paper})}
 \label{tab:ccs_data_example}
 \end{table*}
 

report_thesis/src/sections/baseline_replica.tex

@@ -62,6 +62,7 @@ \section{Baseline \& Replica}\label{sec:baseline_replica}
 
 \begin{table*}
 	\centering
+	\caption{\gls{rmse}s of the original and our replicas of the \gls{pls1-sm}, \gls{ica}, and \gls{moc} models.}
 	\begin{tabular*}{\textwidth}{@{\extracolsep{\fill}}lllllll}
 		\toprule
 		Element    & \gls{pls1-sm} (original) & PLS1-SM (replica) & \gls{ica} (original) & ICA (replica) & \gls{moc} (original) & \gls{moc} (replica) \\
@@ -76,7 +77,6 @@ \section{Baseline \& Replica}\label{sec:baseline_replica}
 		\ce{K2O}   & 0.72                     & 0.72              & 0.98                 & 1.38          & 0.82                 & 1.91                \\
 		\bottomrule
 	\end{tabular*}
-	\caption{\gls{rmse}s of the original and our replicas of the \gls{pls1-sm}, \gls{ica}, and \gls{moc} models.}
 	\label{tab:replica_results_rmses}
 \end{table*}
 

report_thesis/src/sections/experiments/data_preparation.tex

@@ -27,6 +27,7 @@ \subsection{Data Preparation}\label{sec:data-preparation}
 
 \begin{table*}
 \centering
+\caption{Excerpt from the composition dataset (from \citet{p9_paper}).}
 \begin{tabular}{lllllllllllll}
 \toprule
      Target & Spectrum Name & Sample Name & \ce{SiO2} & \ce{TiO2} & \ce{Al2O3} & \ce{FeO_T} & \ce{MnO} & \ce{MgO} & \ce{CaO} & \ce{Na2O} & \ce{K2O} & \ce{MOC total} \\
@@ -38,7 +39,6 @@ \subsection{Data Preparation}\label{sec:data-preparation}
     TB2 & --- & --- & 60.4 & 0.93 & 20.5 & 11.6536 & 0.047 & 1.86 & 0.2 & 1.29 & 3.86 & 100.7406 \\
 \bottomrule
 \end{tabular}
-\caption{Excerpt from the composition dataset (from \citet{p9_paper})}
 \label{tab:composition_data_example}
 \end{table*}
 
@@ -48,6 +48,7 @@ \subsection{Data Preparation}\label{sec:data-preparation}
 
 \begin{table*}
 \centering
+\caption{Excerpt from the final dataset (values have been rounded to two decimal places for brevity).}
 \footnotesize
 \begin{tabular}{llllllllllllllllllllll}
 \toprule
@@ -66,6 +67,5 @@ \subsection{Data Preparation}\label{sec:data-preparation}
 	$\vdots$ & $\cdots$ & $\vdots$ & $\vdots$ & $\cdots$ & $\vdots$ & $\vdots$ & $\vdots$ & $\vdots$ & $\vdots$ & $\vdots$ & $\vdots$ & $\vdots$ & $\vdots$ & $\vdots$ & $\vdots$ \\
 \midrule
 \end{tabular}
-\caption{Excerpt from the final dataset (values have been rounded to two decimal places for brevity).}
 \label{tab:final_dataset_example}
 \end{table*}

report_thesis/src/sections/experiments/inital_experiments/best_model_occurrences_table.tex

@@ -8,5 +8,6 @@
 \gls{pls} & 4 \\
 \gls{gbr} & 3 \\
 \gls{ngboost} & 2 \\
+\hline
 \end{tabular}
 \label{tab:best_model_occurrences}

report_thesis/src/sections/experiments/inital_experiments/best_results_table.tex

@@ -9,5 +9,6 @@
 $\ce{CaO}$ & 1.626 (\gls{svr}) & 1.467 (\gls{xgboost}) & 1.594 (\gls{svr}) & 1.457 (\gls{xgboost}) \\
 $\ce{Na2O}$ & 0.387 (\gls{xgboost}) & 0.908 (\gls{pls}) & 0.387 (\gls{xgboost}) & 0.906 (\gls{pls}) \\
 $\ce{K2O}$ & 0.524 (\gls{rf}) & 0.609 (\gls{gbr}) & 0.476 (\gls{rf}) & 0.610 (\gls{gbr}) \\
+\hline
 \end{tabular}%
 \label{tab:best_results}

report_thesis/src/sections/experiments/inital_experiments/init_results_table.tex

@@ -1,5 +1,6 @@
 \begin{table*}[]
 \centering
+\caption{Initial results for the different models and metrics.}
 \resizebox{1\textwidth}{!}{%
 \begin{tabular}{l|cccc|cccc|cccc}
 Model & \multicolumn{4}{c}{Ridge} & \multicolumn{4}{c}{\gls{lasso}} & \multicolumn{4}{c}{\gls{enet}} \\
@@ -60,6 +61,5 @@
 \hline
 \end{tabular}%
 }
-\caption{Initial results for the different models and metrics.}
 \label{tab:init_results}
 \end{table*}

report_thesis/src/sections/experiments/inital_experiments/initial_results.tex

@@ -46,6 +46,7 @@ \subsection{Initial Results}
 \end{figure*}
 
 \begin{table}
+\caption{Relative performance of each model compared to the best performing model, measured by normalized RMSECV and multiplied by 100 for percentage. A higher percentage indicates worse performance. The 'Diff. vs Prev.' column shows the difference in performance compared to the next best model, measured in percentage points.}
 \begin{tabular}{lrr}
 \toprule
 Model & Relative Performance (\%) & Diff. vs Prev. \\
@@ -64,7 +65,6 @@ \subsection{Initial Results}
 CNN & 143.18 & 15.36 \\
 \bottomrule
 \end{tabular}
-\caption{Relative performance of each model compared to the best performing model, measured by normalized RMSECV and multiplied by 100 for percentage. A higher percentage indicates worse performance. The 'Diff. vs Prev.' column shows the difference in performance compared to the next best model, measured in percentage points.}
 \label{tab:relative_performance}
 \end{table}
 
@@ -74,15 +74,15 @@ \subsection{Initial Results}
 \centering
 \begin{minipage}{.7\textwidth}
   \centering
-  \input{sections/experiments/inital_experiments/best_results_table.tex}
   \caption{Lowest metric and corresponding model for each oxide.}
+  \input{sections/experiments/inital_experiments/best_results_table.tex}
   \label{tab:best_results}
 \end{minipage}%
 \hspace{0.03\textwidth}
 \begin{minipage}{.25\textwidth}
   \centering
-  \input{sections/experiments/inital_experiments/best_model_occurrences_table.tex}
   \caption{Occurrences of the best model for each oxide.}
+  \input{sections/experiments/inital_experiments/best_model_occurrences_table.tex}
   \label{tab:best_model_occurrences}
 \end{minipage}
 \end{table*}

report_thesis/src/sections/experiments/optimization_experiment/optuna_ranges.tex

@@ -1,5 +1,6 @@
 \begin{table*}
 \centering
+\caption{Optuna preprocessing configuration ranges.}
 \begin{tabular}{@{}l>{\ttfamily}lp{0.5\textwidth}@{}}
 \toprule
 \textbf{Model}                       & \textbf{Parameter}                & \textbf{Range}                           \\ \midrule
@@ -22,13 +23,13 @@
 MaxAbsScaler                         & -                                 & -                                        \\ \midrule
 Norm3Scaler                          & -                                 & -                                        \\ \midrule
 \end{tabular}
-\caption{Optuna preprocessing configuration ranges.}
 \label{tab:optuna_preprocessing_configurations}
 \end{table*}
 
 
 \begin{table*}
 \centering
+\caption{Optuna model configuration ranges.}
 \begin{tabular}{@{}l>{\ttfamily}lp{0.5\textwidth}@{}}
 \toprule
 \textbf{Model}                 & \textbf{Parameter}          & \textbf{Range}                           \\ \midrule
@@ -76,6 +77,5 @@
                                & min\_samples\_leaf          & 1 - 10                                    \\ \cmidrule{2-3}
                                & max\_features               & \{sqrt, log2\}                            \\ \bottomrule
 \end{tabular}
-\caption{Optuna model configuration ranges.}
 \label{tab:optuna_model_configurations}
 \end{table*}

report_thesis/src/sections/experiments/stacking_ensemble.tex

@@ -79,6 +79,7 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results}
 
 \begin{table}
 \centering
+\caption{Stacking ensemble results using the \gls{enet} model as the meta-learner with default hyperparameters.}
 \begin{tabular}{lcccc}
 \toprule
 Oxide          & \gls{rmsep} & STDDEV & \gls{rmsecv}         & Std. Dev. CV          \\
@@ -94,11 +95,11 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results}
 \bottomrule
 \end{tabular}
 \label{tab:stacking_ensemble_results_enet}
-\caption{Stacking ensemble results using the \gls{enet} model as the meta-learner with default hyperparameters.}
 \end{table}
 
 \begin{table}
 \centering
+\caption{Stacking ensemble results using the \gls{enet} model as the meta-learner with $\alpha = 0.1$.}
 \begin{tabular}{lcccc}
 \toprule
 Oxide          & \gls{rmsep} & STDDEV & \gls{rmsecv}         & Std. Dev. CV          \\
@@ -114,11 +115,11 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results}
 \bottomrule
 \end{tabular}
 \label{tab:stacking_ensemble_results_enet_01}
-\caption{Stacking ensemble results using the \gls{enet} model as the meta-learner with $\alpha = 0.1$.}
 \end{table}
 
 \begin{table}
 \centering
+\caption{Stacking ensemble results using the \gls{svr} model as the meta-learner with default hyperparameters.}
 \begin{tabular}{lcccc}
 \toprule
 Oxide          & \gls{rmsep} & STDDEV & \gls{rmsecv}         & Std. Dev. CV          \\
@@ -134,7 +135,6 @@ \subsubsection{Results}\label{subsec:stacking_ensemble_results}
 \bottomrule
 \end{tabular}
 \label{tab:stacking_ensemble_results_svr}
-\caption{Stacking ensemble results using the \gls{svr} model as the meta-learner with default hyperparameters.}
 \end{table}
 
 \begin{figure*}

report_thesis/src/sections/introduction.tex

@@ -55,6 +55,7 @@ \section{Introduction}\label{sec:introduction}
 
 \begin{table}
 \centering
+\caption{Table of terminology.}
 \begin{tabularx}{\columnwidth}{lX} % l for left, X for the cell that should be wrapped
 \toprule
 Term & Definition \\
@@ -65,6 +66,5 @@ \section{Introduction}\label{sec:introduction}
 Extreme Concentration Values & The concentration values of oxides in the targets that are significantly higher or lower than the majority of the data. \\
 \bottomrule
 \end{tabularx}
-\caption{Table of Terms}
 \label{tab:terms}
 \end{table}