## Visualising Molecular Graphs : now showing first and last five mol…

…ecules from all three datasets

geometric_gnn_101.ipynb

@@ -562,9 +562,9 @@
       "source": [
         "## Visualising Molecular Graphs\n",
         "\n",
-        "To get a better understanding of how the QM9 molecular graphs look like, let's visualise a few samples from the training set along with their corresponding target (their dipole moment).\n",
+        "To get a better understanding of how the QM9 molecular graphs look like, let's visualise a few samples from the three sets along with their corresponding target (their normalized electric dipole moment).\n",
         "\n",
-        "In the following plot we visualise **sparse graphs** where edges represent physical connections (i.e. bonds). In this practical, however, we will use **fully-connected graphs** and encode the graph structure in the attributes of each. Later in this practical, we will study the advantages and downsides of both approaches.\n",
+        "In the following plots we visualise **sparse graphs** where edges represent physical connections (i.e. bonds). In this practical, however, we will use **fully-connected graphs** and encode the graph structure in the attributes of each. Later in this practical, we will study the advantages and downsides of both approaches.\n",
         "\n",
         "**❗️Note:** we have implemented some code for you to convert the PyG graph into a Molecule object that can be used by RDKit, a python package for chemistry and visualing molecules. It is not important for you to understand RDKit beyond visualisation purposes."
       ]
@@ -577,11 +577,52 @@
       },
       "outputs": [],
       "source": [
-        "num_viz = 50\n",
-        "mols = [to_rdkit(train_dataset[i]) for i in range(num_viz)]\n",
-        "values = [str(round(float(train_dataset[i].y), 3)) for i in range(num_viz)]\n",
+        "num_viz = 10\n",
+        "draw_range_train = list(range(0, 5)) + list(range(len(train_dataset)-5, len(train_dataset)))\n",
+        "draw_range_val = list(range(0, 5)) + list(range(len(val_dataset)-5, len(val_dataset)))\n",
+        "draw_range_test = list(range(0, 5)) + list(range(len(test_dataset)-5, len(test_dataset)))\n",
         "\n",
-        "Chem.Draw.MolsToGridImage(mols, legends=[f\"y = {value}\" for value in values], molsPerRow=5)"
+        "print(\"First and last five molecules in the TRAINING dataset\")\n",
+        "print(\"  with normalized electric dipole moment (original, non-normalized, value in parenthesis)\")\n",
+        "mols = [to_rdkit(train_dataset[i]) for i in draw_range_train]\n",
+        "values_norm = [str(round(float(train_dataset[i].y), 3)) for i in range(num_viz)]\n",
+        "values_denorm = [str(round(float(train_dataset[i].y * std + mean), 3)) for i in draw_range_train]\n",
+        "legs = [str(round(float(train_dataset[i].y), 3)) + \" (\" +\n",
+        "        str(round(float(train_dataset[i].y * std + mean), 3)) + \")\" for i in range(num_viz)]\n",
+        "Chem.Draw.MolsToGridImage(mols, legends=legs, molsPerRow=5)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"First and last five molecules in the VALIDATION dataset\")\n",
+        "print(\"  with normalized electric dipole moment (original, non-normalized, value in parenthesis)\")\n",
+        "mols = [to_rdkit(val_dataset[i]) for i in draw_range_val]\n",
+        "values_norm = [str(round(float(val_dataset[i].y), 3)) for i in range(num_viz)]\n",
+        "values_denorm = [str(round(float(val_dataset[i].y * std + mean), 3)) for i in draw_range_val]\n",
+        "values = [str(round(float(val_dataset[i].y), 3)) for i in range(num_viz)]\n",
+        "legs = [str(round(float(val_dataset[i].y), 3)) + \" (\" +\n",
+        "        str(round(float(val_dataset[i].y * std + mean), 3)) + \")\" for i in range(num_viz)]\n",
+        "Chem.Draw.MolsToGridImage(mols, legends=legs, molsPerRow=5)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "print(\"First and last five molecules in the TESTING dataset\")\n",
+        "print(\"  with normalized electric dipole moment (original, non-normalized, value in parenthesis)\")\n",
+        "mols = [to_rdkit(test_dataset[i]) for i in draw_range_test]\n",
+        "values_norm = [str(round(float(test_dataset[i].y), 3)) for i in range(num_viz)]\n",
+        "values_denorm = [str(round(float(test_dataset[i].y * std + mean), 3)) for i in draw_range_test]\n",
+        "legs = [str(round(float(test_dataset[i].y), 3)) + \" (\" +\n",
+        "        str(round(float(test_dataset[i].y * std + mean), 3)) + \")\" for i in range(num_viz)]\n",
+        "Chem.Draw.MolsToGridImage(mols, legends=legs, molsPerRow=5)"
       ]
     },
     {