Commit d06f9a6b authored by Ask Hjorth Larsen's avatar Ask Hjorth Larsen

various minor fixes (spelling)

parent 99df3c77
......@@ -101,7 +101,7 @@
"</div>",
"-->",
"<div>",
"\"Run\" to check the algorithm; \"Background\" for a breve explanation; \"Instructions\" to know how things works. \"Settings\" to change the algorithm inputs and outputs.",
"\"Run\" to run the algorithm; \"Background\" for a brief explanation; \"Instructions\" to see how things work. \"Settings\" to change inputs and outputs.",
"</div>",
"<div style=\"padding-top: 2ex;\">",
"",
......@@ -234,9 +234,9 @@
"",
" <p> We here use the simple Kernel Ridge Regression algorithm [MW-KRR]. The algorithm relies on numerical descriptors that express the similarity of two molecules as a distance. The predicted value is calculated by weighting known reference values from the training set according to their similarity to the test molecule.</p>",
"",
" <p> Choose different sizes of training set and different descriptors. The sorted Coulomb matrix (determined by the geometric structure) or the HOMO–LUMO gap (energy difference between highest occupied molecular orbital and lowest unoccupied molecular orbital which correlates with the actual excitation energy). Different types of descriptor can be weighted differently when determining the distance; these weights (called sigma) will affect how well the quantities are taken into account and affect the quality of predictions. </p>",
" <p> Choose different sizes of training set and different descriptors. The sorted Coulomb matrix (determined by the geometric structure) or the HOMO–LUMO gap (energy difference between highest occupied molecular orbital and lowest unoccupied molecular orbital which correlates with the actual excitation energy). Different types of descriptor can be weighted differently when determining the distance; these weights (called σ) will affect how well the quantities are taken into account and affect the quality of predictions. </p>",
"",
" <p> Some exact definitions: The distance between two molecules is the L1 norm of the difference between their descriptors. The descriptor of a molecule is the vector containing all values of the sorted Coulomb matrix of the molecule divided by the structural normalization factor, and the HOMO–LUMO gap of the molecule divided by the electronic normalization factor. The kernel is the matrix of all values [exp(-|d(i) - d(j)|)] for each pair of descriptors d(i) and d(j). </p>",
" <p> Some exact definitions: The distance between two molecules is the L1 norm of the difference between their descriptors. The descriptor of a molecule is the vector containing all values of the sorted Coulomb matrix of the molecule divided by the structural normalization factor, and the HOMO–LUMO gap of the molecule divided by the electronic normalization factor. The kernel is the matrix of all values [exp(–|d(i) – d(j)|)] for each pair of descriptors d(i) and d(j). </p>",
"",
" <!-- <img style=\"width:67%;height:67%\" src=\"2016-08-02_ZB_RS3-2.png\">-->",
" <br/>",
......@@ -268,11 +268,9 @@
" <h4 class=\"modal-title\" id=\"instructions-modal-label\">Instructions</h4>",
" </div>",
" <div class=\"modal-body instructions\">",
"<b><p>Instructions list </p></b>",
"<b><p>Instructions </p></b>",
"",
"<p>This Beaker is preset with a small group of parameters are used by default, if you want to change something, the button <b>Settings</b>, allow you to do that.</p>",
"",
"<p>The section “Settings” has tree subsections:</p>",
"<p>The section “Settings” has three subsections:</p>",
"<ul>",
" ",
" <b><li> ML algorithm settings:</li></b>",
......@@ -293,10 +291,6 @@
" <li>Electronic Descriptor: The HOMO-LUMO gap is the energy difference between highest occupied state and lowest unoccupied state in the ground-state calculation. This is a reasonable approximation of the excitation energy, and hence a good descriptor for predicting excitation energies. However it is only a single number and therefore cannot distinguish well between two different molecules that have (close to) the same HOMO-LUMO gap without the help of another descriptor.</li>",
" <li>Electronic normalization (σ): Distances between electronic descriptors are divided by this number. Distances are typically between 1 to 10 eV; hence a reasonable normalization is on the order of 1 to 10.</li> ",
" </ul>",
" <b><li>Feature to predict:</li></b>",
" <ul>",
" <li>Property to predict: Here yo can chose from two properties “Excitations energy” or the “Oscillations Strength”</li>",
" </ul>",
"</ul>",
"<p>After you feel comfortable with the parameters press the <b>RUN</b> button button and wait for the results.</p>",
" <!-- <p>References:</p>",
......@@ -598,8 +592,6 @@
"input": {
"body": [
"",
"try",
"{",
" def ref_pred_plot = new Plot( xLabel: \"References values (R)\", yLabel: \"Predicted values (P)\");",
" ",
" def out_put_label = \"\";",
......@@ -643,7 +635,7 @@
" x: [min_values.min(), max_values.max()], ",
" base: [min_values.min() - mae, max_values.max() - mae], ",
" color: new Color(255, 0, 0, 50), ",
" displayName: \"MAE: \" + mae.rount(3) )",
" displayName: \"MAE: \" + mae.round(3) )",
" ref_pred_plot << new Area(y: [min_values.min() + (mae +devi), max_values.max() + (mae+devi)], ",
" x: [min_values.min(), max_values.max()], ",
" base: [min_values.min() - (mae+devi), max_values.max() - (mae+devi)], ",
......@@ -656,10 +648,6 @@
" \", predicted_value = \" + ys.round(3) + ",
" \", molecule = \" + ",
" outfile_data[h][2]});",
"}",
"catch(Exception)",
"{",
"}",
"/*cplot.add(ref_pred_plot,3);",
"",
"if (ref_range > 1)",
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment