diff options
| author | adamjanovsky | 2024-02-20 10:00:12 +0100 |
|---|---|---|
| committer | adamjanovsky | 2024-02-20 10:00:12 +0100 |
| commit | 80d60885e4e424f15860e30405addc165e30f009 (patch) | |
| tree | a4e7681394bdfcd7c06937501c51b53f0a7b852c | |
| parent | 6f8a09d7696f3309455246f6e2b9623ecdd34d27 (diff) | |
| download | sec-certs-80d60885e4e424f15860e30405addc165e30f009.tar.gz sec-certs-80d60885e4e424f15860e30405addc165e30f009.tar.zst sec-certs-80d60885e4e424f15860e30405addc165e30f009.zip | |
final adjustments of references notebook
| -rw-r--r-- | notebooks/cc/references.ipynb | 29 |
1 files changed, 2 insertions, 27 deletions
diff --git a/notebooks/cc/references.ipynb b/notebooks/cc/references.ipynb index ec06099d..cb57f537 100644 --- a/notebooks/cc/references.ipynb +++ b/notebooks/cc/references.ipynb @@ -36,7 +36,6 @@ "from pathlib import Path\n", "from typing import Literal\n", "\n", - "import matplotlib\n", "import matplotlib.pyplot as plt\n", "import networkx as nx\n", "import networkx.algorithms.community as nx_comm\n", @@ -49,7 +48,6 @@ "from scipy import stats\n", "from tqdm import tqdm\n", "\n", - "from sec_certs.dataset import CCDatasetMaintenanceUpdates\n", "from sec_certs.dataset.cc import CCDataset\n", "from sec_certs.utils.parallel_processing import process_parallel\n", "\n", @@ -90,9 +88,7 @@ "\n", "plt.style.use(\"default\")\n", "sns.set_palette(\"deep\")\n", - "sns.set_context(\"paper\") # Set to \"paper\" for use in paper :)\n", - "\n", - "# plt.rcParams['figure.figsize'] = (10, 6)\n", + "sns.set_context(\"notebook\")\n", "\n", "REPO_ROOT = Path().resolve()\n", "RESULTS_DIR = Path(\"./results/references\")\n", @@ -172,14 +168,6 @@ " \"indirectly_referenced_by\": \"in_trans_refs\",\n", " }\n", " )\n", - " # Old date computation\n", - " # .assign(\n", - " # longer_than_5_years=lambda df_: df_.not_valid_after - df_.not_valid_before\n", - " # > pd.Timedelta(days=(5 * 365) + 2),\n", - " # not_valid_after=lambda df_: df_.not_valid_after.where(\n", - " # ~df_.longer_than_5_years, df_.not_valid_before + pd.Timedelta(days=(5 * 365) + 2)\n", - " # ),\n", - " # )\n", " .assign(\n", " longer_than_5_years=lambda df_: df_.not_valid_after - df_.not_valid_before\n", " > pd.Timedelta(days=(5 * 365) + 2),\n", @@ -187,7 +175,7 @@ " ~df_.longer_than_5_years, df_.not_valid_before.apply(choose_archival_date)\n", " ),\n", " )\n", - " .drop_duplicates(subset=[\"cert_id\"], keep=\"first\") # TODO: Investigate high number of duplicates and resolve\n", + " .drop_duplicates(subset=[\"cert_id\"], keep=\"first\")\n", " )\n", "\n", "\n", @@ -1244,9 +1232,6 @@ " lambda x: cert_id_to_category_mapping[x] if pd.notnull(x) else np.nan\n", " )\n", " exploded = exploded.loc[exploded.ref_category.notnull()]\n", - "\n", - " exploded_with_refs = exploded.loc[exploded.ref_category != \"No references\"]\n", - "\n", " all_categories = set(exploded.category.unique()) | set(exploded.ref_category.unique())\n", " colors = list(sns.color_palette(\"hls\", len(all_categories), as_cmap=False).as_hex())\n", " color_dict = dict(zip(all_categories, colors))\n", @@ -1599,7 +1584,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ @@ -1612,15 +1596,6 @@ "metadata": {}, "outputs": [], "source": [ - "REPO_ROOT" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ "def print_category_commands(category: Literal[\"smartcard\", \"related\", \"others\"]) -> None:\n", " if category == \"smartcard\":\n", " categories = {SMARTCARD_CATEGORY}\n", |