From 911b630137d8ae87a138d01ffa92fdf30371ece1 Mon Sep 17 00:00:00 2001
From: victor barbier <victor.barbier@recherche.gouv.fr>
Date: Mon, 30 Oct 2023 17:21:22 +0100
Subject: [PATCH] feat(notebook): filter edges for structures graph

---
 notebooks/communityDetectionStructures.ipynb | 41 +++++++++++---------
 1 file changed, 22 insertions(+), 19 deletions(-)

diff --git a/notebooks/communityDetectionStructures.ipynb b/notebooks/communityDetectionStructures.ipynb
index eb0597cf..5eaf8ba4 100644
--- a/notebooks/communityDetectionStructures.ipynb
+++ b/notebooks/communityDetectionStructures.ipynb
@@ -184,14 +184,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 148,
+   "execution_count": 182,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Number of nodes (structures) found : 978\n"
+      "Number of nodes (structures) found : 1641\n"
      ]
     }
    ],
@@ -203,9 +203,9 @@
     "        work_id = work.get(\"id\")\n",
     "        for affiliation in work.get(\"affiliations\") or {}:\n",
     "            affiliation_id = affiliation.get(\"id\")\n",
-    "            country = affiliation.get(\"address\")[0].get(\"country\") if (\"address\" in affiliation) else None\n",
+    "            # country = affiliation.get(\"address\")[0].get(\"country\") if (\"address\" in affiliation) else None\n",
     "            gps = affiliation.get(\"address\")[0].get(\"gps\") if (\"address\" in affiliation) else None\n",
-    "            if affiliation_id and gps and country == \"France\":\n",
+    "            if affiliation_id and gps:\n",
     "                if affiliation_id in nodes_dict:\n",
     "                    nodes_dict[affiliation_id][\"publications\"].append(work_id)\n",
     "                else:\n",
@@ -221,7 +221,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 143,
+   "execution_count": 183,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -237,7 +237,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 144,
+   "execution_count": 197,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -249,54 +249,56 @@
     "    G.add_node(node.get(\"id\"), label=node.get(\"name\"), weight=len(node.get(\"publications\")))\n",
     "\n",
     "# Add edges\n",
+    "min_weight_edge = 10\n",
     "for edge in edges:\n",
-    "    G.add_edge(edge.get(\"source\"), edge.get(\"target\"), weight=edge.get(\"weight\"))"
+    "    if edge.get(\"weight\") > min_weight_edge:\n",
+    "        G.add_edge(edge.get(\"source\"), edge.get(\"target\"), weight=edge.get(\"weight\"))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 145,
+   "execution_count": 198,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Graph filtered : 96 \n",
-      "Minimum number of works required: 24\n"
+      "Graph filtered : 100 \n",
+      "Minimum number of works required: 25\n"
      ]
     }
    ],
    "source": [
     "# Filter graph\n",
     "max_order = 100\n",
-    "min_weight = 1\n",
+    "min_weight_node = 1\n",
     "\n",
     "while G.order() > max_order:\n",
-    "    min_weight += 1\n",
-    "    G = G.subgraph([node for node, attrdict in G.nodes.items() if attrdict.get(\"weight\") >= min_weight]) \n",
+    "    min_weight_node += 1\n",
+    "    G = G.subgraph([node for node, attrdict in G.nodes.items() if attrdict.get(\"weight\") >= min_weight_node]) \n",
     "    # print(f\"Minimum number of works auto computed : {min_weight} (order={G.order()})\")\n",
     "\n",
-    "print(f\"Graph filtered : {len(G.nodes) or 0} \\nMinimum number of works required: {min_weight}\")"
+    "print(f\"Graph filtered : {len(G.nodes) or 0} \\nMinimum number of works required: {min_weight_node}\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 181,
+   "execution_count": 199,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d333909ccf6541cdb87b0c7cd4e53c74",
+       "model_id": "0d6ef99c0f354e77af5469a8d6f8cfbd",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "Sigma(nx.Graph with 96 nodes and 2,019 edges)"
+       "Sigma(nx.Graph with 100 nodes and 540 edges)"
       ]
      },
-     "execution_count": 181,
+     "execution_count": 199,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -309,7 +311,8 @@
     "      node_border_color_from=\"node\",\n",
     "      # layout=nodes_dict,\n",
     "      default_edge_type=\"curve\",\n",
-    "      hide_edges_on_move=True)"
+    "      hide_edges_on_move=True,\n",
+    "      start_layout=1)"
    ]
   },
   {