From d9e14ca389cf566fcbcb5825d2e98630cf4cfa2b Mon Sep 17 00:00:00 2001
From: Adam Janovsky
Date: Fri, 14 Apr 2023 13:55:18 +0200
Subject: fix references notebook

---
 notebooks/cc/references.ipynb | 106 ++++++++----------------------------------
 1 file changed, 20 insertions(+), 86 deletions(-)

diff --git a/notebooks/cc/references.ipynb b/notebooks/cc/references.ipynb
index ae191431..c6d2ddb0 100644
--- a/notebooks/cc/references.ipynb
+++ b/notebooks/cc/references.ipynb
@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -73,21 +73,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
     }
    },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Downloading CC Dataset: 100%|██████████████████████████████████████████████████████████████████████████████████████████████| 135M/135M [00:26<00:00, 5.34MB/s]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# Initialize\n",
     "dset = CCDataset.from_web_latest()"
@@ -95,7 +87,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -126,25 +118,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
     },
     "scrolled": true
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\\newcommand{\\numCcAllDirectReferencing}{1500}\n",
-      "\\newcommand{\\numCcAllNotDirectReferencing}{3641}\n",
-      "\\newcommand{\\numCcWithIdDirectReferencing}{1500}\n",
-      "\\newcommand{\\numCcWithIdNotDirectReferencing}{3565}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df[\"has_outgoing_direct_references\"] = df.directly_referencing.notnull()\n",
     "df[\"has_incoming_direct_references\"] = df.directly_referenced_by.notnull()\n",
@@ -169,26 +150,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\\newcommand{\\numCCActiveDirectReferencing}{545}\n",
-      "\\newcommand{\\numCCActiveDirectReferencingArchived}{169}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "print(f\"\\\\newcommand{{\\\\numCCActiveDirectReferencing}}{{{df_id_rich.loc[df_id_rich.status == 'active'].has_outgoing_direct_references.sum()}}}\")\n",
     "\n",
     "archived_cert_id_list = set(df_id_rich[df_id_rich.status == \"archived\"].cert_id)\n",
     "def contains_archived_cert_reference(referencing):\n",
-    "    if referencing is np.nan:\n",
+    "    if pd.isnull(referencing):\n",
     "        return False\n",
-    "    \n",
     "    return bool(archived_cert_id_list.intersection(referencing))\n",
     "print(f\"\\\\newcommand{{\\\\numCCActiveDirectReferencingArchived}}{{{df_id_rich[df_id_rich.status == 'active'].directly_referencing.apply(contains_archived_cert_reference).sum()}}}\")"
    ]
@@ -202,7 +173,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -229,31 +200,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
     }
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\\newcommand{\\numCCDirectRefsSameCategory}{2133}\n",
-      "\\newcommand{\\numCCDirectRefsOtherCategory}{192}\n",
-      "\\newcommand{\\numCCDirectRefs}{2325}\n",
-      "\\newcommand{\\numCCDirectRefsFromSmartcards}{1896}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "cert_id_to_category_mapping = dict(zip(df.cert_id, df.category))\n",
     "cert_id_to_category_mapping[np.NaN] = \"No references\"\n",
     "\n",
     "exploded = df_id_rich.loc[:, [\"category\", \"directly_referencing\"]].explode(\"directly_referencing\")\n",
-    "\n",
-    "exploded[\"ref_category\"] = exploded.directly_referencing.map(cert_id_to_category_mapping)\n",
+    "exploded[\"ref_category\"] = exploded.directly_referencing.map(lambda x: cert_id_to_category_mapping[x] if pd.notnull(x) else np.nan)\n",
     "exploded = exploded.loc[exploded.ref_category.notnull()]\n",
     "\n",
     "exploded_with_refs = exploded.loc[exploded.ref_category != \"No references\"]\n",
@@ -286,7 +245,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -320,21 +279,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
     }
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of certificates that reference some archived certificate: 933\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "def references_archived_cert(references):\n",
     "    if pd.isnull(references):\n",
@@ -373,7 +324,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -406,18 +357,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\\newcommand{\\numCCUSReferencing}{4}\n",
-      "\\newcommand{\\numCCUS}{959}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "print(f\"\\\\newcommand{{\\\\numCCUSReferencing}}{{{len(df_id_rich.loc[(df_id_rich.scheme == 'US') & (df_id_rich.directly_referencing.notnull())])}}}\")\n",
     "print(f\"\\\\newcommand{{\\\\numCCUS}}{{{len(df_id_rich.loc[(df_id_rich.scheme == 'US')])}}}\")"
@@ -434,7 +376,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -1194,7 +1136,6 @@
     "    for i, label in enumerate(labels):\n",
     "        label_widths = {}\n",
     "        label_widths[side] = df[df[side] == label][side + \"Weight\"].sum()\n",
-    "        print(\"a\")\n",
     "        if i == 0:\n",
     "            label_widths[\"bottom\"] = 0\n",
     "            label_widths[\"top\"] = label_widths[side]\n",
@@ -1208,13 +1149,6 @@
     "        LOGGER.debug(\"%s position of '%s' : %s\", side, label, label_widths)\n",
     "    return widths, topEdge\n"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
-- 
cgit v1.3.1