Updated advanced notebook.

Now using Bipartite method of leidenalg. Now also mention that the
leiden algorithm is also available from igraph directly.

02-advanced.ipynb

@@ -221,9 +221,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "clusters[30]"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -246,9 +244,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "clusters.membership[:10]"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -371,9 +367,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "optimiser.optimise_partition(clusters, n_iterations=10)"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
@@ -431,6 +425,25 @@
     "clusters.compare_to(clustering, method='nmi')"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Finally, the Leiden algorithm is also directly implemented in `igraph` itself nowadays. It is somewhat less elaborate than the `leidenalg` package, but it is also substantially faster. If you are analysing very large networks, it might be better to use the `igraph` Leiden algorithm. Using it is straightforward."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "clusters = G_vosviewer.community_leiden(objective_function='CPM',weights='weight_normalized', \n",
+    "                                        resolution_parameter=1.0, n_iterations=10)\n",
+    "\n",
+    "clusters.compare_to(clustering, method='nmi')"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -588,7 +601,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We now employ a small trick in order to do clustering in a bipartite network. We will not explain the full details, but it involves creating two empty networks. Please see the [documentation](https://leidenalg.readthedocs.io/en/latest/multiplex.html#bipartite) for a brief explanation of this approach."
+    "We now employ a small trick in the `leidenalg` package in order to do clustering in a bipartite network. We will not explain the full details here, please see the [documentation](https://leidenalg.readthedocs.io/en/latest/multiplex.html#bipartite) for a brief explanation of this approach. Please note that this approach is *not* possible using the internal `igraph` Leiden algorithm."
    ]
   },
   {
@@ -597,37 +610,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "H_docs = G_doc_term.subgraph_edges([], delete_vertices=False);\n",
-    "H_docs.vs['node_sizes'] = [1 if v['type'] == 'doc' else 0 for v in H_docs.vs];\n",
-    "\n",
-    "H_terms = G_doc_term.subgraph_edges([], delete_vertices=False);\n",
-    "H_terms.vs['node_sizes'] = [1 if v['type'] == 'term' else 0 for v in H_terms.vs];"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In order to make this trick work, we now also have to create three separate partitions as follows. The `res_param` contains the resolution parameter that we previously used, and again plays a similar role. A value of around `1` seems to give reasonable results in this case."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "res_param = 1\n",
-    "partition = leidenalg.CPMVertexPartition(G_doc_term, weights='weight', \n",
-    "                                       resolution_parameter=res_param)\n",
-    "\n",
-    "partition_docs = leidenalg.CPMVertexPartition(H_docs, weights='weight', \n",
-    "                                       node_sizes=H_docs.vs['node_sizes'], \n",
-    "                                       resolution_parameter=res_param)\n",
-    "\n",
-    "partition_terms = leidenalg.CPMVertexPartition(H_terms, weights='weight', \n",
-    "                                        node_sizes=H_terms.vs['node_sizes'], \n",
-    "                                        resolution_parameter=res_param)"
+    "partition, partition_docs, partition_terms = leidenalg.CPMVertexPartition.Bipartite(\n",
+    "    G_doc_term, types='type', weights='weight', resolution_parameter_01=1)"
    ]
   },
   {
@@ -944,7 +928,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.2"
+   "version": "3.8.2"
   }
  },
  "nbformat": 4,