new plots for chain-of-trust extended paper

1 files changed, 162 insertions, 4 deletions

diff --git a/notebooks/cc/chain_of_trust_plots.ipynb b/notebooks/cc/chain_of_trust_plots.ipynb
index 2d58af8b..2e5dd035 100644
--- a/notebooks/cc/chain_of_trust_plots.ipynb
+++ b/notebooks/cc/chain_of_trust_plots.ipynb
@@ -17,8 +17,10 @@
     "from matplotlib import lines\n",
     "from sklearn import metrics\n",
     "\n",
+    "from sec_certs.dataset import CCDataset\n",
+    "\n",
     "# LaTeX plotting\n",
-    "matplotlib.use(\"pgf\")\n",
+    "# matplotlib.use(\"pgf\")\n",
     "sns.set_palette(\"Set2\")\n",
     "sns.set_context(\"paper\")\n",
     "\n",
@@ -42,14 +44,15 @@
     "plt.rcParams[\"ytick.major.width\"] = 0.5\n",
     "plt.rcParams[\"ytick.major.pad\"] = 0.1\n",
     "\n",
-    "plt.rcParams[\"legend.title_fontsize\"] = 12\n",
-    "plt.rcParams[\"legend.fontsize\"] = 12\n",
+    "plt.rcParams[\"legend.title_fontsize\"] = 10\n",
+    "plt.rcParams[\"legend.fontsize\"] = 10\n",
     "plt.rcParams[\"legend.handletextpad\"] = 0.3\n",
     "plt.rcParams[\"lines.markersize\"] = 0.5\n",
     "plt.rcParams[\"savefig.pad_inches\"] = 0.01\n",
     "\n",
     "INPUT_DIR = Path(\"./paper_artifacts/chain_of_trust/data/plots/\")\n",
     "OUTPUT_DIR = Path(\"./results/figures/\")\n",
+    "DATASET_PATH = Path(\"./dataset/cc_november_23/dataset.json\")\n",
     "INPUT_DIR.mkdir(exist_ok=True, parents=True)"
    ]
   },
@@ -57,6 +60,161 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Ecosystem insights plots"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "figure_width = 3.5\n",
+    "figure_height = 2.5\n",
+    "\n",
+    "dset = CCDataset.from_json(DATASET_PATH)\n",
+    "df = dset.to_pandas()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Validity boxplot\n",
+    "df_validity = pd.read_csv(INPUT_DIR / \"df_validity.csv\")\n",
+    "fig = plt.figure(figsize=(figure_width, figure_height))\n",
+    "box = sns.boxplot(data=df_validity, x=\"year_from\", y=\"validity_period\", linewidth=0.75, flierprops={\"marker\": \"x\"})\n",
+    "box.set(xlabel=\"\", ylabel=\"\")\n",
+    "plt.xticks([5 * i for i in range(6)], [1997, 2002, 2007, 2012, 2017, 2022])\n",
+    "fig.savefig(OUTPUT_DIR / \"boxplot_validity.pdf\", bbox_inches=\"tight\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Average EAL level\n",
+    "\n",
+    "avg_levels = pd.read_csv(INPUT_DIR / \"avg_eal.csv\").loc[lambda _df: _df.year_from < 2023]\n",
+    "eal_to_num_mapping = {eal: index for index, eal in enumerate(df[\"eal\"].cat.categories)}\n",
+    "avg_levels[\"smartcard_category\"] = avg_levels.category.map(\n",
+    "    lambda x: x if x == \"ICs, Smartcards\" else \"Other categories\"\n",
+    ")\n",
+    "line = sns.lineplot(\n",
+    "    data=avg_levels,\n",
+    "    x=\"year_from\",\n",
+    "    y=\"eal_number\",\n",
+    "    hue=\"smartcard_category\",\n",
+    "    errorbar=None,\n",
+    "    style=\"smartcard_category\",\n",
+    "    markers=True,\n",
+    "    linewidth=2,\n",
+    ")\n",
+    "line.set(xlabel=None, ylabel=None, title=None, xlim=(1999.6, 2023.4))\n",
+    "ymin = 1\n",
+    "ymax = 9\n",
+    "ylabels = [\n",
+    "    x if \"+\" in x else x + r\"\\phantom{+}\" for x in list(eal_to_num_mapping.keys())[ymin : ymax + 1]\n",
+    "]  # this also aligns the labels by adding phantom spaces\n",
+    "plt.yticks(range(ymin, ymax + 1), ylabels)\n",
+    "plt.xticks([1997, 2002, 2007, 2012, 2017, 2022])\n",
+    "line.legend(title=None, labels=avg_levels.smartcard_category.unique())\n",
+    "plt.legend(frameon=False)\n",
+    "\n",
+    "fig = matplotlib.pyplot.gcf()\n",
+    "fig.set_size_inches(figure_width, figure_height)\n",
+    "fig.tight_layout(pad=0.1)\n",
+    "fig.savefig(OUTPUT_DIR / \"temporal_trends_categories.pdf\")\n",
+    "plt.show()\n",
+    "plt.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Interesting schemes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "interesting_schemes = pd.read_csv(INPUT_DIR / \"interesting_schemes.csv\")\n",
+    "\n",
+    "line = sns.lineplot(\n",
+    "    data=interesting_schemes,\n",
+    "    x=\"year_from\",\n",
+    "    y=\"size\",\n",
+    "    hue=\"scheme\",\n",
+    "    style=\"scheme\",\n",
+    "    markers=True,\n",
+    "    dashes=True,\n",
+    "    linewidth=2,\n",
+    ")\n",
+    "line.set(xlabel=None, ylabel=None, title=None, xlim=(1999.6, 2022.4), ylim=(0, 60))\n",
+    "line.set_xticks([1997, 2002, 2007, 2012, 2017, 2022])\n",
+    "line.legend(title=None)\n",
+    "fig = matplotlib.pyplot.gcf()\n",
+    "fig.set_size_inches(figure_width, figure_height)\n",
+    "fig.tight_layout(pad=0.1)\n",
+    "fig.savefig(OUTPUT_DIR / \"temporal_trends_schemes.pdf\")\n",
+    "plt.show()\n",
+    "plt.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Popular categories"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "n_certs = pd.read_csv(INPUT_DIR / \"popular_categories.csv\").astype({\"year_from\": \"category\"})\n",
+    "dct = {\n",
+    "    \"ICs, Smart Cards and Smart Card-Related Devices and Systems\": \"ICs and Smart Cards\",\n",
+    "    \"Network and Network-Related Devices and Systems\": \"Network-Related Devices\",\n",
+    "    \"Other Devices and Systems\": \"Other Devices\",\n",
+    "    \"One of 11 other categories\": \"11 Other Categories\",\n",
+    "}\n",
+    "n_certs.popular_categories = n_certs.popular_categories.map(lambda x: dct.get(x, x))\n",
+    "cats = n_certs.popular_categories.unique()\n",
+    "years = n_certs.year_from.cat.categories[:-1]\n",
+    "data = [n_certs.loc[n_certs.popular_categories == c, \"size\"].tolist()[:-1] for c in cats]\n",
+    "\n",
+    "plt.stackplot(\n",
+    "    years,\n",
+    "    data,\n",
+    "    labels=cats,\n",
+    ")\n",
+    "plt.legend(frameon=False, loc=\"upper left\", bbox_to_anchor=(0, 1))\n",
+    "plt.xticks([1997, 2002, 2007, 2012, 2017, 2022])\n",
+    "plt.xlim(1997, 2022)\n",
+    "\n",
+    "fig = matplotlib.pyplot.gcf()\n",
+    "fig.set_size_inches(figure_width, figure_height)\n",
+    "fig.tight_layout(pad=0.1)\n",
+    "fig.savefig(OUTPUT_DIR / \"temporal_trends_stackplot.pdf\")\n",
+    "plt.show()\n",
+    "plt.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
     "## Average number of transitive references over time"
    ]
   },
@@ -312,7 +470,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "3.10.14"
   }
  },
  "nbformat": 4,