diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000000000000000000000000000000000000..8425c58da9c0f9da88753738c33ad4cd9b91ff75
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1 @@
+*.ipynb filter=strip-notebook-output
diff --git a/results/ls_compare/Untitled.ipynb b/results/ls_compare/Untitled.ipynb
index 5738876c61899dcae5c485ddb80cff06c7a78d22..f951806f98cab8efd6d2c9160eea772e75319f41 100644
--- a/results/ls_compare/Untitled.ipynb
+++ b/results/ls_compare/Untitled.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 117,
+ "execution_count": null,
"id": "78d64649-e669-45d3-8849-a3f278769df4",
"metadata": {},
"outputs": [],
@@ -15,30 +15,10 @@
},
{
"cell_type": "code",
- "execution_count": 140,
+ "execution_count": null,
"id": "635b9a9c-32ac-42a3-b787-50ef7d233160",
"metadata": {},
- "outputs": [
- {
- "ename": "TypeError",
- "evalue": "'>' not supported between instances of 'str' and 'int'",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn [140], line 21\u001b[0m\n\u001b[1;32m 19\u001b[0m results_df \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mconcat(treat_json(f) \u001b[38;5;28;01mfor\u001b[39;00m f \u001b[38;5;129;01min\u001b[39;00m glob\u001b[38;5;241m.\u001b[39mglob(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m*.json\u001b[39m\u001b[38;5;124m\"\u001b[39m))\n\u001b[1;32m 20\u001b[0m results_df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m# demands total\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdemandsFilename\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mapply(get_total_nb_demands)\n\u001b[0;32m---> 21\u001b[0m display(results_df\u001b[38;5;241m.\u001b[39mquery(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m# demands total\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m > 0\u001b[39m\u001b[38;5;124m\"\u001b[39m))\n\u001b[1;32m 22\u001b[0m results_df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124macceptance\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m results_df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdemands\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m/\u001b[39m results_df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m# demands total\u001b[39m\u001b[38;5;124m'\u001b[39m]\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/util/_decorators.py:317\u001b[0m, in \u001b[0;36mdeprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 311\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m>\u001b[39m num_allow_args:\n\u001b[1;32m 312\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[1;32m 313\u001b[0m msg\u001b[38;5;241m.\u001b[39mformat(arguments\u001b[38;5;241m=\u001b[39marguments),\n\u001b[1;32m 314\u001b[0m \u001b[38;5;167;01mFutureWarning\u001b[39;00m,\n\u001b[1;32m 315\u001b[0m stacklevel\u001b[38;5;241m=\u001b[39mfind_stack_level(inspect\u001b[38;5;241m.\u001b[39mcurrentframe()),\n\u001b[1;32m 316\u001b[0m )\n\u001b[0;32m--> 317\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/frame.py:4464\u001b[0m, in \u001b[0;36mDataFrame.query\u001b[0;34m(self, expr, inplace, **kwargs)\u001b[0m\n\u001b[1;32m 4462\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlevel\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlevel\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;241m0\u001b[39m) \u001b[38;5;241m+\u001b[39m \u001b[38;5;241m2\u001b[39m\n\u001b[1;32m 4463\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtarget\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 4464\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43meval\u001b[49m\u001b[43m(\u001b[49m\u001b[43mexpr\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 4466\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 4467\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mloc[res]\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/util/_decorators.py:317\u001b[0m, in \u001b[0;36mdeprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 311\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m>\u001b[39m num_allow_args:\n\u001b[1;32m 312\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[1;32m 313\u001b[0m msg\u001b[38;5;241m.\u001b[39mformat(arguments\u001b[38;5;241m=\u001b[39marguments),\n\u001b[1;32m 314\u001b[0m \u001b[38;5;167;01mFutureWarning\u001b[39;00m,\n\u001b[1;32m 315\u001b[0m stacklevel\u001b[38;5;241m=\u001b[39mfind_stack_level(inspect\u001b[38;5;241m.\u001b[39mcurrentframe()),\n\u001b[1;32m 316\u001b[0m )\n\u001b[0;32m--> 317\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/frame.py:4602\u001b[0m, in \u001b[0;36mDataFrame.eval\u001b[0;34m(self, expr, inplace, **kwargs)\u001b[0m\n\u001b[1;32m 4599\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtarget\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\n\u001b[1;32m 4600\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mresolvers\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mtuple\u001b[39m(kwargs\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mresolvers\u001b[39m\u001b[38;5;124m\"\u001b[39m, ())) \u001b[38;5;241m+\u001b[39m resolvers\n\u001b[0;32m-> 4602\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_eval\u001b[49m\u001b[43m(\u001b[49m\u001b[43mexpr\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minplace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minplace\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/computation/eval.py:359\u001b[0m, in \u001b[0;36meval\u001b[0;34m(expr, parser, engine, truediv, local_dict, global_dict, resolvers, level, target, inplace)\u001b[0m\n\u001b[1;32m 357\u001b[0m eng \u001b[38;5;241m=\u001b[39m ENGINES[engine]\n\u001b[1;32m 358\u001b[0m eng_inst \u001b[38;5;241m=\u001b[39m eng(parsed_expr)\n\u001b[0;32m--> 359\u001b[0m ret \u001b[38;5;241m=\u001b[39m \u001b[43meng_inst\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mevaluate\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 361\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m parsed_expr\u001b[38;5;241m.\u001b[39massigner \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 362\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m multi_line:\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/computation/engines.py:135\u001b[0m, in \u001b[0;36mPythonEngine.evaluate\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 134\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mevaluate\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[0;32m--> 135\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexpr\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/computation/expr.py:820\u001b[0m, in \u001b[0;36mExpr.__call__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 819\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[0;32m--> 820\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mterms\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43menv\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/computation/ops.py:407\u001b[0m, in \u001b[0;36mBinOp.__call__\u001b[0;34m(self, env)\u001b[0m\n\u001b[1;32m 404\u001b[0m left \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlhs(env)\n\u001b[1;32m 405\u001b[0m right \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrhs(env)\n\u001b[0;32m--> 407\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mleft\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mright\u001b[49m\u001b[43m)\u001b[49m\n",
- "\u001b[0;31mTypeError\u001b[0m: '>' not supported between instances of 'str' and 'int'"
- ]
- }
- ],
+ "outputs": [],
"source": [
"def treat_results(f):\n",
" with open(f) as fd:\n",
@@ -66,28 +46,10 @@
},
{
"cell_type": "code",
- "execution_count": 114,
+ "execution_count": null,
"id": "73db44f3-f160-4c91-b0a7-45dcfde65696",
"metadata": {},
- "outputs": [
- {
- "ename": "KeyError",
- "evalue": "'topologyFilename'",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn [114], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m results_df\u001b[38;5;241m.\u001b[39mpivot_table(columns\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124malgorithm\u001b[39m\u001b[38;5;124m'\u001b[39m, index\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtopologyFilename\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/frame.py:8721\u001b[0m, in \u001b[0;36mDataFrame.pivot_table\u001b[0;34m(self, values, index, columns, aggfunc, fill_value, margins, dropna, margins_name, observed, sort)\u001b[0m\n\u001b[1;32m 8704\u001b[0m \u001b[38;5;129m@Substitution\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 8705\u001b[0m \u001b[38;5;129m@Appender\u001b[39m(_shared_docs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpivot_table\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[1;32m 8706\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpivot_table\u001b[39m(\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 8717\u001b[0m sort\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 8718\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m DataFrame:\n\u001b[1;32m 8719\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpandas\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mreshape\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpivot\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m pivot_table\n\u001b[0;32m-> 8721\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mpivot_table\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 8722\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8723\u001b[0m \u001b[43m \u001b[49m\u001b[43mvalues\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8724\u001b[0m \u001b[43m \u001b[49m\u001b[43mindex\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mindex\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8725\u001b[0m \u001b[43m \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcolumns\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8726\u001b[0m \u001b[43m \u001b[49m\u001b[43maggfunc\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maggfunc\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8727\u001b[0m \u001b[43m \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfill_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8728\u001b[0m \u001b[43m \u001b[49m\u001b[43mmargins\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmargins\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8729\u001b[0m \u001b[43m \u001b[49m\u001b[43mdropna\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdropna\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8730\u001b[0m \u001b[43m \u001b[49m\u001b[43mmargins_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmargins_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8731\u001b[0m \u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mobserved\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8732\u001b[0m \u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8733\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/reshape/pivot.py:96\u001b[0m, in \u001b[0;36mpivot_table\u001b[0;34m(data, values, index, columns, aggfunc, fill_value, margins, dropna, margins_name, observed, sort)\u001b[0m\n\u001b[1;32m 93\u001b[0m table \u001b[38;5;241m=\u001b[39m concat(pieces, keys\u001b[38;5;241m=\u001b[39mkeys, axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m 94\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m table\u001b[38;5;241m.\u001b[39m__finalize__(data, method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpivot_table\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 96\u001b[0m table \u001b[38;5;241m=\u001b[39m \u001b[43m__internal_pivot_table\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 97\u001b[0m \u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 98\u001b[0m \u001b[43m \u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 99\u001b[0m \u001b[43m \u001b[49m\u001b[43mindex\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 100\u001b[0m \u001b[43m \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 101\u001b[0m \u001b[43m \u001b[49m\u001b[43maggfunc\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 102\u001b[0m \u001b[43m \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 103\u001b[0m \u001b[43m \u001b[49m\u001b[43mmargins\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 104\u001b[0m \u001b[43m \u001b[49m\u001b[43mdropna\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 105\u001b[0m \u001b[43m \u001b[49m\u001b[43mmargins_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 106\u001b[0m \u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 107\u001b[0m \u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 108\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 109\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m table\u001b[38;5;241m.\u001b[39m__finalize__(data, method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpivot_table\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/reshape/pivot.py:165\u001b[0m, in \u001b[0;36m__internal_pivot_table\u001b[0;34m(data, values, index, columns, aggfunc, fill_value, margins, dropna, margins_name, observed, sort)\u001b[0m\n\u001b[1;32m 162\u001b[0m \u001b[38;5;28;01mpass\u001b[39;00m\n\u001b[1;32m 163\u001b[0m values \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(values)\n\u001b[0;32m--> 165\u001b[0m grouped \u001b[38;5;241m=\u001b[39m \u001b[43mdata\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgroupby\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkeys\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mobserved\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 166\u001b[0m agged \u001b[38;5;241m=\u001b[39m grouped\u001b[38;5;241m.\u001b[39magg(aggfunc)\n\u001b[1;32m 167\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m dropna \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(agged, ABCDataFrame) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(agged\u001b[38;5;241m.\u001b[39mcolumns):\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/frame.py:8392\u001b[0m, in \u001b[0;36mDataFrame.groupby\u001b[0;34m(self, by, axis, level, as_index, sort, group_keys, squeeze, observed, dropna)\u001b[0m\n\u001b[1;32m 8389\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYou have to supply one of \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mby\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m and \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlevel\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 8390\u001b[0m axis \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_axis_number(axis)\n\u001b[0;32m-> 8392\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mDataFrameGroupBy\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 8393\u001b[0m \u001b[43m \u001b[49m\u001b[43mobj\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8394\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mby\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8395\u001b[0m \u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8396\u001b[0m \u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlevel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8397\u001b[0m \u001b[43m \u001b[49m\u001b[43mas_index\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mas_index\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8398\u001b[0m \u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8399\u001b[0m \u001b[43m \u001b[49m\u001b[43mgroup_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgroup_keys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8400\u001b[0m \u001b[43m \u001b[49m\u001b[43msqueeze\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msqueeze\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8401\u001b[0m \u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mobserved\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8402\u001b[0m \u001b[43m \u001b[49m\u001b[43mdropna\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdropna\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8403\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/groupby/groupby.py:959\u001b[0m, in \u001b[0;36mGroupBy.__init__\u001b[0;34m(self, obj, keys, axis, level, grouper, exclusions, selection, as_index, sort, group_keys, squeeze, observed, mutated, dropna)\u001b[0m\n\u001b[1;32m 956\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m grouper \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 957\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpandas\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgroupby\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgrouper\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m get_grouper\n\u001b[0;32m--> 959\u001b[0m grouper, exclusions, obj \u001b[38;5;241m=\u001b[39m \u001b[43mget_grouper\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 960\u001b[0m \u001b[43m \u001b[49m\u001b[43mobj\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 961\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 962\u001b[0m \u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 963\u001b[0m \u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlevel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 964\u001b[0m \u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 965\u001b[0m \u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mobserved\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 966\u001b[0m \u001b[43m \u001b[49m\u001b[43mmutated\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmutated\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 967\u001b[0m \u001b[43m \u001b[49m\u001b[43mdropna\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdropna\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 968\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 970\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mobj \u001b[38;5;241m=\u001b[39m obj\n\u001b[1;32m 971\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxis \u001b[38;5;241m=\u001b[39m obj\u001b[38;5;241m.\u001b[39m_get_axis_number(axis)\n",
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/groupby/grouper.py:889\u001b[0m, in \u001b[0;36mget_grouper\u001b[0;34m(obj, key, axis, level, sort, observed, mutated, validate, dropna)\u001b[0m\n\u001b[1;32m 887\u001b[0m in_axis, level, gpr \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m, gpr, \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 888\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 889\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(gpr)\n\u001b[1;32m 890\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(gpr, Grouper) \u001b[38;5;129;01mand\u001b[39;00m gpr\u001b[38;5;241m.\u001b[39mkey \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 891\u001b[0m \u001b[38;5;66;03m# Add key to exclusions\u001b[39;00m\n\u001b[1;32m 892\u001b[0m exclusions\u001b[38;5;241m.\u001b[39madd(gpr\u001b[38;5;241m.\u001b[39mkey)\n",
- "\u001b[0;31mKeyError\u001b[0m: 'topologyFilename'"
- ]
- }
- ],
+ "outputs": [],
"source": [
"results_df.pivot_table(columns='algorithm', index='topologyFilename')#.boxplot()"
]
diff --git a/src/InstanceConversion.ipynb b/src/InstanceConversion.ipynb
index 649c1703c9b45a3f7586120f9e2247e7ea1960d1..299adcc8a2ab7bced93d960b5094884fefdb9ce4 100644
--- a/src/InstanceConversion.ipynb
+++ b/src/InstanceConversion.ipynb
@@ -2,21 +2,12 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": null,
"id": "ff977009-904d-4f2d-a617-43a9c6d6e6d5",
"metadata": {
"tags": []
},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The autoreload extension is already loaded. To reload it, use:\n",
- " %reload_ext autoreload\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2\n",
@@ -29,56 +20,10 @@
},
{
"cell_type": "code",
- "execution_count": 23,
+ "execution_count": null,
"id": "3ca5aef1-3cf9-46a1-a621-78a3a5219b97",
- "metadata": {
- "scrolled": true
- },
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "/Users/nhuin/data/isp-data/src/utils.py:113: ParserWarning: Length of header or names does not match length of data. This leads to a loss of data with index_col=False.\n",
- " demands_df = pd.read_csv(filename, delimiter=',', index_col=False, header=None, names=['src', 'dst', 'delay', 'loss'])\n"
- ]
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "DiGraph with 24 nodes and 102 edges\n",
- "0 [0, 16, 19, 2, 13] [51, 8, 0, 28] (1680570.0, 1149861.9) (28821.0, 42018.0)\n",
- "1 [5, 4, 2, 19, 16, 22] [37, 35, 1, 9, 98] (1857470.0, 1385730.9) (30178.0, 37929.0)\n",
- "2 [8, 22, 19, 16] [17, 13, 9] (1297280.0, 1164602.9) (20019.0, 34942.0)\n",
- "3 [9, 14, 10] [44, 47] (869767.0, 825542.0) (39434.0, 22167.0)\n",
- "4 [9, 20, 17, 14, 2, 13] [15, 55, 61, 31, 28] (2343950.0, 2211273.0) (68193.0, 40819.0)\n",
- "5 [9, 20, 17, 10, 14, 19, 16] [15, 55, 52, 46, 7, 9] (2594560.0, 2314466.9) (72573.0, 47744.0)\n",
- "6 [9, 14, 19, 21] [44, 7, 10] (2550340.0, 2550338.0) (66790.0, 44742.0)\n",
- "7 [9, 14, 19, 16, 22] [44, 7, 9, 98] (2063860.0, 2063854.9) (72786.0, 51908.0)\n",
- "8 [9, 14, 19, 16, 22, 23] [44, 7, 9, 98, 20] (2181790.0, 2181789.9) (72447.0, 58854.0)\n",
- "9 [10, 14, 9] [46, 45] (869767.0, 825542.0) (39434.0, 22167.0)\n",
- "10 [10, 14, 19, 2, 13] [46, 7, 0, 28] (2255500.0, 2063855.0) (42760.0, 41246.0)\n",
- "11 [10, 14, 19, 21] [46, 7, 10] (2461890.0, 2461888.0) (51461.0, 34363.0)\n",
- "12 [10, 14, 19, 16, 22, 23] [46, 7, 9, 98, 20] (2093340.0, 2093339.9) (47014.0, 48475.0)\n",
- "13 [12, 11, 19, 16, 22] [91, 5, 9, 98] (1651080.0, 1459440.9) (38537.0, 46288.0)\n",
- "14 [13, 22, 19, 14, 9] [19, 13, 6, 45] (2343950.0, 2343949.0) (68193.0, 52260.0)\n",
- "15 [13, 22, 19, 14, 10] [19, 13, 6, 47] (2255500.0, 2255499.0) (42760.0, 41881.0)\n",
- "16 [16, 19, 22, 8] [8, 12, 16] (1297280.0, 1164602.9) (20019.0, 34942.0)\n",
- "17 [16, 19, 2, 14, 9] [8, 0, 30, 45] (2594560.0, 1547890.9) (72573.0, 51065.0)\n",
- "18 [16, 19, 2, 14, 9, 20, 17, 10] [8, 0, 30, 45, 15, 55, 52] (2506110.0, 2417658.9) (47140.0, 65243.0)\n",
- "19 [16, 19, 2, 14, 1, 18] [8, 0, 30, 27, 56] (2624040.0, 2373432.9) (49142.0, 62456.0)\n",
- "20 [18, 14, 19, 16, 22, 23] [59, 7, 9, 98, 20] (2299720.0, 2211273.9) (49016.0, 64052.0)\n",
- "21 [21, 19, 14, 9] [11, 6, 45] (2550340.0, 2550338.0) (66790.0, 44742.0)\n",
- "22 [21, 19, 14, 10] [11, 6, 47] (2461890.0, 2461888.0) (51461.0, 34363.0)\n",
- "23 [22, 19, 2, 4, 5] [13, 0, 34, 36] (1857470.0, 1385730.0) (30178.0, 30179.0)\n",
- "No path for 24\n",
- "25 [22, 19, 2, 4, 12] [13, 0, 34, 92] (1651080.0, 1606858.0) (38537.0, 35237.0)\n",
- "26 [23, 22, 19, 14, 9] [21, 13, 6, 45] (2181790.0, 2181789.0) (72447.0, 51104.0)\n",
- "27 [23, 22, 19, 14, 10] [21, 13, 6, 47] (2093340.0, 2093339.0) (47014.0, 40725.0)\n"
- ]
- }
- ],
+ "metadata": {},
+ "outputs": [],
"source": [
"instance = 'ta1_2'\n",
"demands = utils.load_csv_demands_without_path(f'../csv/{instance}.txtdemand.csv')\n",
@@ -102,43 +47,12 @@
},
{
"cell_type": "code",
- "execution_count": 24,
+ "execution_count": null,
"id": "cd88e315-39e1-4dcb-bbac-3372a634b8a9",
"metadata": {
- "scrolled": true,
"tags": []
},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "toy\n",
- "Loaded 26 links\n",
- "After droping duplicates: 26 links\n"
- ]
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "/Users/nhuin/data/isp-data/src/utils.py:113: ParserWarning: Length of header or names does not match length of data. This leads to a loss of data with index_col=False.\n",
- " demands_df = pd.read_csv(filename, delimiter=',', index_col=False, header=None, names=['src', 'dst', 'delay', 'loss'])\n"
- ]
- },
- {
- "ename": "NameError",
- "evalue": "name 'edgelist' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn[24], line 8\u001b[0m\n\u001b[1;32m 6\u001b[0m topo_df \u001b[38;5;241m=\u001b[39m utils\u001b[38;5;241m.\u001b[39mload_csv_topo(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m../csv/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00minstance\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.txtLink.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 7\u001b[0m demands_df \u001b[38;5;241m=\u001b[39m utils\u001b[38;5;241m.\u001b[39mload_csv_demands_without_path(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m../csv/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00minstance\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.txtdemand.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m----> 8\u001b[0m \u001b[43mutils\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconvert_instance_json\u001b[49m\u001b[43m(\u001b[49m\u001b[43minstance\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtopo_df\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdemands_df\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 9\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m*\u001b[39m \u001b[38;5;241m38\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m OK \u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m*\u001b[39m \u001b[38;5;241m38\u001b[39m)\n\u001b[1;32m 10\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mAssertionError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
- "File \u001b[0;32m~/data/isp-data/src/utils.py:152\u001b[0m, in \u001b[0;36mconvert_instance_json\u001b[0;34m(name, topo_df, demands_df, prefix)\u001b[0m\n\u001b[1;32m 149\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLoaded \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(raw_topo_df)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m links\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 150\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAfter droping duplicates: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(topo_df)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m links\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 152\u001b[0m topo \u001b[38;5;241m=\u001b[39m nx\u001b[38;5;241m.\u001b[39mDiGraph([(e[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124msrc\u001b[39m\u001b[38;5;124m'\u001b[39m], e[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdst\u001b[39m\u001b[38;5;124m'\u001b[39m], {\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdelay\u001b[39m\u001b[38;5;124m'\u001b[39m: e[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdelay\u001b[39m\u001b[38;5;124m'\u001b[39m], \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mloss\u001b[39m\u001b[38;5;124m'\u001b[39m: e[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mloss\u001b[39m\u001b[38;5;124m'\u001b[39m]}) \u001b[38;5;28;01mfor\u001b[39;00m e \u001b[38;5;129;01min\u001b[39;00m \u001b[43medgelist\u001b[49m[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124medges\u001b[39m\u001b[38;5;124m'\u001b[39m]])\n\u001b[1;32m 153\u001b[0m instance \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtopology\u001b[39m\u001b[38;5;124m'\u001b[39m: \n\u001b[1;32m 154\u001b[0m {\u001b[38;5;124m'\u001b[39m\u001b[38;5;124medges\u001b[39m\u001b[38;5;124m'\u001b[39m: [{\u001b[38;5;124m'\u001b[39m\u001b[38;5;124me\u001b[39m\u001b[38;5;124m'\u001b[39m: index, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msrc\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;28mint\u001b[39m(src), \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdst\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;28mint\u001b[39m(dst), \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdelay\u001b[39m\u001b[38;5;124m'\u001b[39m: delay, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mloss\u001b[39m\u001b[38;5;124m'\u001b[39m: loss} \u001b[38;5;28;01mfor\u001b[39;00m index, (src, dst, delay, loss) \u001b[38;5;129;01min\u001b[39;00m topo_df\u001b[38;5;241m.\u001b[39miterrows()]},\n\u001b[1;32m 155\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdemands\u001b[39m\u001b[38;5;124m'\u001b[39m: \n\u001b[1;32m 156\u001b[0m {\u001b[38;5;124m'\u001b[39m\u001b[38;5;124medges\u001b[39m\u001b[38;5;124m'\u001b[39m: [{\u001b[38;5;124m'\u001b[39m\u001b[38;5;124msrc\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;28mint\u001b[39m(src), \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdst\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;28mint\u001b[39m(dst), \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdelay\u001b[39m\u001b[38;5;124m'\u001b[39m: delay, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mloss\u001b[39m\u001b[38;5;124m'\u001b[39m: loss, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mweight\u001b[39m\u001b[38;5;124m'\u001b[39m: weight} \u001b[38;5;28;01mfor\u001b[39;00m index, (src, dst, delay, loss, weight) \u001b[38;5;129;01min\u001b[39;00m demands_df[[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124msrc\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdst\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdelay\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mloss\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mweight\u001b[39m\u001b[38;5;124m'\u001b[39m]]\u001b[38;5;241m.\u001b[39miterrows()]}\n\u001b[1;32m 157\u001b[0m }\n\u001b[1;32m 158\u001b[0m json\u001b[38;5;241m.\u001b[39mdump(instance, \u001b[38;5;28mopen\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mprefix\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/wdn/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.json\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mw\u001b[39m\u001b[38;5;124m'\u001b[39m))\n",
- "\u001b[0;31mNameError\u001b[0m: name 'edgelist' is not defined"
- ]
- }
- ],
+ "outputs": [],
"source": [
"import glob\n",
"for f in glob.glob('../csv/*.txtDemand.csv'):\n",
diff --git a/src/InstanceInformations.ipynb b/src/InstanceInformations.ipynb
index 14174af8816c23215a0c2a75bd85468f559ac645..5d9bf50060d949e0a13582a6bbbe79f4e874cb1c 100644
--- a/src/InstanceInformations.ipynb
+++ b/src/InstanceInformations.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 14,
+ "execution_count": null,
"id": "bdb1ae69-720c-40c7-a195-35b8172012b0",
"metadata": {},
"outputs": [],
@@ -13,331 +13,10 @@
},
{
"cell_type": "code",
- "execution_count": 32,
+ "execution_count": null,
"id": "0e9716c7-8b90-462c-ae83-ce06003ce001",
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Topo: DiGraph with 27 nodes and 102 edges\n",
- "Demands: DiGraph with 25 nodes and 156 edges\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n",
- "path delay: True\n",
- "path loss: True\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"topo = nx.read_graphml(f'{name}.gml')\n",
"raw_topo = pd.read_csv(f'{name}.txtLink.csv', delimiter=',', header=None, index_col=False, names=['src', 'dst', 'delay', 'loss']).query('delay.notna()')\n",
diff --git a/src/ResultExtraction.ipynb b/src/ResultExtraction.ipynb
index 784bc3c1da243528c672a4ecd7357efb1baf6234..aae2c41c7cc00812a73df3f7bdbd8ef5f5428ab7 100644
--- a/src/ResultExtraction.ipynb
+++ b/src/ResultExtraction.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": null,
"id": "c166a37c-cbc3-4e47-b0cc-e589ccf7f155",
"metadata": {},
"outputs": [],
@@ -32,160 +32,10 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": null,
"id": "b5dcb691-5a6b-4c2a-a731-3f47b5d827a6",
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>toy</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>zib54_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>norway_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>pioro40_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>cost266_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>france_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>janos-us-ca_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>giul39_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>india35_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>france_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>pioro40_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>nobel-eu_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>ta2_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>germany50_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>janos-us-ca_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>pioro40_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>nobel-eu_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>cost266_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>ta2_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>sun_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>cost266_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>giul39_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>india35_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>india35_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>france_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>janos-us-ca_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>zib54_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>norway_9</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>sun_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>zib54_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>ta2_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>giul39_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>germany50_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>nobel-eu_4</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>germany50_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>sun_2</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>norway_4</th>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- "Empty DataFrame\n",
- "Columns: []\n",
- "Index: [toy, zib54_9, norway_2, pioro40_2, cost266_4, france_2, janos-us-ca_9, giul39_9, india35_2, france_4, pioro40_9, nobel-eu_2, ta2_2, germany50_9, janos-us-ca_4, pioro40_4, nobel-eu_9, cost266_2, ta2_9, sun_9, cost266_9, giul39_4, india35_9, india35_4, france_9, janos-us-ca_2, zib54_4, norway_9, sun_4, zib54_2, ta2_4, giul39_2, germany50_4, nobel-eu_4, germany50_2, sun_2, norway_4]"
- ]
- },
- "execution_count": 2,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
+ "outputs": [],
"source": [
"instances_available = [re.search(r\"../results/(.*)_greedy_200.json\", filename).groups()[0] for filename in glob.glob(\"../results/*_greedy_200.json\")]\n",
"pd.DataFrame(index=instances_available)"
@@ -193,278 +43,10 @@
},
{
"cell_type": "code",
- "execution_count": 16,
+ "execution_count": null,
"id": "9a7f5f99-12ab-4e22-9119-6390380a0624",
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>instance</th>\n",
- " <th>algorithm</th>\n",
- " <th>nb_virtual_topologies</th>\n",
- " <th>nb_real_topologies</th>\n",
- " <th>nb_total_topologies</th>\n",
- " <th>execution_time</th>\n",
- " <th>vigp_time</th>\n",
- " <th>nb_demands_virtual</th>\n",
- " <th>nb_demands_real</th>\n",
- " <th>average_demands_real</th>\n",
- " <th>average_demands_virtual</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>0</th>\n",
- " <td>toy</td>\n",
- " <td>vIGP</td>\n",
- " <td>1</td>\n",
- " <td>6</td>\n",
- " <td>7</td>\n",
- " <td>0.278842</td>\n",
- " <td>0.012976</td>\n",
- " <td>[24]</td>\n",
- " <td>[2, 1, 2, 1, 1, 1]</td>\n",
- " <td>1.333333</td>\n",
- " <td>24.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>zib54_9</td>\n",
- " <td>vIGP</td>\n",
- " <td>9</td>\n",
- " <td>8</td>\n",
- " <td>17</td>\n",
- " <td>155.567672</td>\n",
- " <td>11.742800</td>\n",
- " <td>[37, 15, 85, 186, 32, 30, 4, 4, 10]</td>\n",
- " <td>[25, 3, 1, 14, 2, 1, 1, 2]</td>\n",
- " <td>6.125000</td>\n",
- " <td>44.777778</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>2</th>\n",
- " <td>norway_2</td>\n",
- " <td>vIGP</td>\n",
- " <td>3</td>\n",
- " <td>5</td>\n",
- " <td>8</td>\n",
- " <td>21.324783</td>\n",
- " <td>0.137158</td>\n",
- " <td>[16, 4, 12]</td>\n",
- " <td>[5, 4, 9, 9, 1]</td>\n",
- " <td>5.600000</td>\n",
- " <td>10.666667</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>3</th>\n",
- " <td>pioro40_2</td>\n",
- " <td>vIGP</td>\n",
- " <td>9</td>\n",
- " <td>12</td>\n",
- " <td>21</td>\n",
- " <td>136.992976</td>\n",
- " <td>1.847440</td>\n",
- " <td>[80, 32, 56, 14, 10, 8, 8, 4, 2]</td>\n",
- " <td>[13, 1, 17, 3, 4, 10, 9, 1, 1, 1, 1, 1]</td>\n",
- " <td>5.166667</td>\n",
- " <td>23.777778</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>4</th>\n",
- " <td>cost266_4</td>\n",
- " <td>vIGP</td>\n",
- " <td>1</td>\n",
- " <td>2</td>\n",
- " <td>3</td>\n",
- " <td>15.211914</td>\n",
- " <td>0.374182</td>\n",
- " <td>[30]</td>\n",
- " <td>[1, 1]</td>\n",
- " <td>1.000000</td>\n",
- " <td>30.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>...</th>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>32</th>\n",
- " <td>germany50_4</td>\n",
- " <td>Greedy</td>\n",
- " <td>0</td>\n",
- " <td>9</td>\n",
- " <td>9</td>\n",
- " <td>189.632973</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
- " <td>[163, 33, 15, 5, 1, 45, 8, 2, 2]</td>\n",
- " <td>30.444444</td>\n",
- " <td>0.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>33</th>\n",
- " <td>nobel-eu_4</td>\n",
- " <td>Greedy</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>1</td>\n",
- " <td>1.896481</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
- " <td>[12]</td>\n",
- " <td>12.000000</td>\n",
- " <td>0.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>34</th>\n",
- " <td>germany50_2</td>\n",
- " <td>Greedy</td>\n",
- " <td>0</td>\n",
- " <td>9</td>\n",
- " <td>9</td>\n",
- " <td>186.969407</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
- " <td>[163, 33, 15, 5, 1, 45, 8, 2, 2]</td>\n",
- " <td>30.444444</td>\n",
- " <td>0.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>35</th>\n",
- " <td>sun_2</td>\n",
- " <td>Greedy</td>\n",
- " <td>0</td>\n",
- " <td>7</td>\n",
- " <td>7</td>\n",
- " <td>30.745669</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
- " <td>[101, 14, 25, 13, 1, 1, 1]</td>\n",
- " <td>22.285714</td>\n",
- " <td>0.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>36</th>\n",
- " <td>norway_4</td>\n",
- " <td>Greedy</td>\n",
- " <td>0</td>\n",
- " <td>5</td>\n",
- " <td>5</td>\n",
- " <td>22.097282</td>\n",
- " <td>NaN</td>\n",
- " <td>NaN</td>\n",
- " <td>[23, 6, 18, 12, 1]</td>\n",
- " <td>12.000000</td>\n",
- " <td>0.000000</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "<p>74 rows × 11 columns</p>\n",
- "</div>"
- ],
- "text/plain": [
- " instance algorithm nb_virtual_topologies nb_real_topologies \\\n",
- "0 toy vIGP 1 6 \n",
- "1 zib54_9 vIGP 9 8 \n",
- "2 norway_2 vIGP 3 5 \n",
- "3 pioro40_2 vIGP 9 12 \n",
- "4 cost266_4 vIGP 1 2 \n",
- ".. ... ... ... ... \n",
- "32 germany50_4 Greedy 0 9 \n",
- "33 nobel-eu_4 Greedy 0 1 \n",
- "34 germany50_2 Greedy 0 9 \n",
- "35 sun_2 Greedy 0 7 \n",
- "36 norway_4 Greedy 0 5 \n",
- "\n",
- " nb_total_topologies execution_time vigp_time \\\n",
- "0 7 0.278842 0.012976 \n",
- "1 17 155.567672 11.742800 \n",
- "2 8 21.324783 0.137158 \n",
- "3 21 136.992976 1.847440 \n",
- "4 3 15.211914 0.374182 \n",
- ".. ... ... ... \n",
- "32 9 189.632973 NaN \n",
- "33 1 1.896481 NaN \n",
- "34 9 186.969407 NaN \n",
- "35 7 30.745669 NaN \n",
- "36 5 22.097282 NaN \n",
- "\n",
- " nb_demands_virtual \\\n",
- "0 [24] \n",
- "1 [37, 15, 85, 186, 32, 30, 4, 4, 10] \n",
- "2 [16, 4, 12] \n",
- "3 [80, 32, 56, 14, 10, 8, 8, 4, 2] \n",
- "4 [30] \n",
- ".. ... \n",
- "32 NaN \n",
- "33 NaN \n",
- "34 NaN \n",
- "35 NaN \n",
- "36 NaN \n",
- "\n",
- " nb_demands_real average_demands_real \\\n",
- "0 [2, 1, 2, 1, 1, 1] 1.333333 \n",
- "1 [25, 3, 1, 14, 2, 1, 1, 2] 6.125000 \n",
- "2 [5, 4, 9, 9, 1] 5.600000 \n",
- "3 [13, 1, 17, 3, 4, 10, 9, 1, 1, 1, 1, 1] 5.166667 \n",
- "4 [1, 1] 1.000000 \n",
- ".. ... ... \n",
- "32 [163, 33, 15, 5, 1, 45, 8, 2, 2] 30.444444 \n",
- "33 [12] 12.000000 \n",
- "34 [163, 33, 15, 5, 1, 45, 8, 2, 2] 30.444444 \n",
- "35 [101, 14, 25, 13, 1, 1, 1] 22.285714 \n",
- "36 [23, 6, 18, 12, 1] 12.000000 \n",
- "\n",
- " average_demands_virtual \n",
- "0 24.000000 \n",
- "1 44.777778 \n",
- "2 10.666667 \n",
- "3 23.777778 \n",
- "4 30.000000 \n",
- ".. ... \n",
- "32 0.000000 \n",
- "33 0.000000 \n",
- "34 0.000000 \n",
- "35 0.000000 \n",
- "36 0.000000 \n",
- "\n",
- "[74 rows x 11 columns]"
- ]
- },
- "execution_count": 16,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
+ "outputs": [],
"source": [
"greedy_df = pd.DataFrame([utils.get_greedy_stats(instance) for instance in instances_available])\n",
"vigp_df = pd.DataFrame([utils.get_vigp_stats(instance) for instance in instances_available])\n",
@@ -476,784 +58,10 @@
},
{
"cell_type": "code",
- "execution_count": 17,
+ "execution_count": null,
"id": "40eb6586-3718-4471-b801-e3a6f1d477ef",
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead tr th {\n",
- " text-align: left;\n",
- " }\n",
- "\n",
- " .dataframe thead tr:last-of-type th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr>\n",
- " <th></th>\n",
- " <th colspan=\"2\" halign=\"left\">average_demands_real</th>\n",
- " <th colspan=\"2\" halign=\"left\">average_demands_virtual</th>\n",
- " <th colspan=\"2\" halign=\"left\">execution_time</th>\n",
- " <th colspan=\"2\" halign=\"left\">nb_real_topologies</th>\n",
- " <th colspan=\"2\" halign=\"left\">nb_total_topologies</th>\n",
- " <th colspan=\"2\" halign=\"left\">nb_virtual_topologies</th>\n",
- " <th>vigp_time</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>algorithm</th>\n",
- " <th>Greedy</th>\n",
- " <th>vIGP</th>\n",
- " <th>Greedy</th>\n",
- " <th>vIGP</th>\n",
- " <th>Greedy</th>\n",
- " <th>vIGP</th>\n",
- " <th>Greedy</th>\n",
- " <th>vIGP</th>\n",
- " <th>Greedy</th>\n",
- " <th>vIGP</th>\n",
- " <th>Greedy</th>\n",
- " <th>vIGP</th>\n",
- " <th>vIGP</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>instance</th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>cost266_2</th>\n",
- " <td>4.571429</td>\n",
- " <td>1.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>30.000000</td>\n",
- " <td>48.105944</td>\n",
- " <td>15.903579</td>\n",
- " <td>7</td>\n",
- " <td>2</td>\n",
- " <td>7</td>\n",
- " <td>3</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.373587</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>cost266_4</th>\n",
- " <td>4.571429</td>\n",
- " <td>1.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>30.000000</td>\n",
- " <td>46.860643</td>\n",
- " <td>15.211914</td>\n",
- " <td>7</td>\n",
- " <td>2</td>\n",
- " <td>7</td>\n",
- " <td>3</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.374182</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>cost266_9</th>\n",
- " <td>4.571429</td>\n",
- " <td>1.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>30.000000</td>\n",
- " <td>49.364375</td>\n",
- " <td>15.086771</td>\n",
- " <td>7</td>\n",
- " <td>2</td>\n",
- " <td>7</td>\n",
- " <td>3</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.373706</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>france_2</th>\n",
- " <td>3.333333</td>\n",
- " <td>1.500000</td>\n",
- " <td>0.0</td>\n",
- " <td>7.000000</td>\n",
- " <td>10.123589</td>\n",
- " <td>7.582157</td>\n",
- " <td>3</td>\n",
- " <td>2</td>\n",
- " <td>3</td>\n",
- " <td>3</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.014791</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>france_4</th>\n",
- " <td>3.333333</td>\n",
- " <td>1.500000</td>\n",
- " <td>0.0</td>\n",
- " <td>7.000000</td>\n",
- " <td>6.665486</td>\n",
- " <td>4.461218</td>\n",
- " <td>3</td>\n",
- " <td>2</td>\n",
- " <td>3</td>\n",
- " <td>3</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.014696</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>france_9</th>\n",
- " <td>3.333333</td>\n",
- " <td>1.500000</td>\n",
- " <td>0.0</td>\n",
- " <td>7.000000</td>\n",
- " <td>10.266920</td>\n",
- " <td>7.532834</td>\n",
- " <td>3</td>\n",
- " <td>2</td>\n",
- " <td>3</td>\n",
- " <td>3</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.014685</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>germany50_2</th>\n",
- " <td>30.444444</td>\n",
- " <td>5.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>40.666667</td>\n",
- " <td>186.969407</td>\n",
- " <td>115.312697</td>\n",
- " <td>9</td>\n",
- " <td>6</td>\n",
- " <td>9</td>\n",
- " <td>12</td>\n",
- " <td>0</td>\n",
- " <td>6</td>\n",
- " <td>3.101980</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>germany50_4</th>\n",
- " <td>30.444444</td>\n",
- " <td>5.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>40.666667</td>\n",
- " <td>189.632973</td>\n",
- " <td>118.689689</td>\n",
- " <td>9</td>\n",
- " <td>6</td>\n",
- " <td>9</td>\n",
- " <td>12</td>\n",
- " <td>0</td>\n",
- " <td>6</td>\n",
- " <td>3.112930</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>germany50_9</th>\n",
- " <td>30.444444</td>\n",
- " <td>5.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>40.666667</td>\n",
- " <td>196.930574</td>\n",
- " <td>116.372007</td>\n",
- " <td>9</td>\n",
- " <td>6</td>\n",
- " <td>9</td>\n",
- " <td>12</td>\n",
- " <td>0</td>\n",
- " <td>6</td>\n",
- " <td>3.099310</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>giul39_2</th>\n",
- " <td>21.076923</td>\n",
- " <td>12.750000</td>\n",
- " <td>0.0</td>\n",
- " <td>34.400000</td>\n",
- " <td>166.512498</td>\n",
- " <td>100.729838</td>\n",
- " <td>13</td>\n",
- " <td>8</td>\n",
- " <td>13</td>\n",
- " <td>13</td>\n",
- " <td>0</td>\n",
- " <td>5</td>\n",
- " <td>1.629080</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>giul39_4</th>\n",
- " <td>21.076923</td>\n",
- " <td>12.750000</td>\n",
- " <td>0.0</td>\n",
- " <td>34.400000</td>\n",
- " <td>170.805808</td>\n",
- " <td>100.198280</td>\n",
- " <td>13</td>\n",
- " <td>8</td>\n",
- " <td>13</td>\n",
- " <td>13</td>\n",
- " <td>0</td>\n",
- " <td>5</td>\n",
- " <td>1.639610</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>giul39_9</th>\n",
- " <td>21.076923</td>\n",
- " <td>12.750000</td>\n",
- " <td>0.0</td>\n",
- " <td>34.400000</td>\n",
- " <td>169.645091</td>\n",
- " <td>102.558270</td>\n",
- " <td>13</td>\n",
- " <td>8</td>\n",
- " <td>13</td>\n",
- " <td>13</td>\n",
- " <td>0</td>\n",
- " <td>5</td>\n",
- " <td>1.640000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>india35_2</th>\n",
- " <td>5.714286</td>\n",
- " <td>1.333333</td>\n",
- " <td>0.0</td>\n",
- " <td>12.000000</td>\n",
- " <td>62.482397</td>\n",
- " <td>28.938689</td>\n",
- " <td>7</td>\n",
- " <td>3</td>\n",
- " <td>7</td>\n",
- " <td>6</td>\n",
- " <td>0</td>\n",
- " <td>3</td>\n",
- " <td>0.175666</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>india35_4</th>\n",
- " <td>5.714286</td>\n",
- " <td>1.333333</td>\n",
- " <td>0.0</td>\n",
- " <td>12.000000</td>\n",
- " <td>63.119016</td>\n",
- " <td>29.122703</td>\n",
- " <td>7</td>\n",
- " <td>3</td>\n",
- " <td>7</td>\n",
- " <td>6</td>\n",
- " <td>0</td>\n",
- " <td>3</td>\n",
- " <td>0.175600</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>india35_9</th>\n",
- " <td>5.714286</td>\n",
- " <td>1.333333</td>\n",
- " <td>0.0</td>\n",
- " <td>12.000000</td>\n",
- " <td>72.256013</td>\n",
- " <td>31.588107</td>\n",
- " <td>7</td>\n",
- " <td>3</td>\n",
- " <td>7</td>\n",
- " <td>6</td>\n",
- " <td>0</td>\n",
- " <td>3</td>\n",
- " <td>0.175304</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>janos-us-ca_2</th>\n",
- " <td>5.000000</td>\n",
- " <td>4.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>8.000000</td>\n",
- " <td>36.441556</td>\n",
- " <td>27.472770</td>\n",
- " <td>4</td>\n",
- " <td>3</td>\n",
- " <td>4</td>\n",
- " <td>4</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.106930</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>janos-us-ca_4</th>\n",
- " <td>5.000000</td>\n",
- " <td>4.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>8.000000</td>\n",
- " <td>39.290821</td>\n",
- " <td>25.447117</td>\n",
- " <td>4</td>\n",
- " <td>3</td>\n",
- " <td>4</td>\n",
- " <td>4</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.106714</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>janos-us-ca_9</th>\n",
- " <td>5.000000</td>\n",
- " <td>4.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>8.000000</td>\n",
- " <td>37.693707</td>\n",
- " <td>26.608627</td>\n",
- " <td>4</td>\n",
- " <td>3</td>\n",
- " <td>4</td>\n",
- " <td>4</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.106804</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>nobel-eu_2</th>\n",
- " <td>12.000000</td>\n",
- " <td>0.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>12.000000</td>\n",
- " <td>1.683972</td>\n",
- " <td>0.053230</td>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.053229</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>nobel-eu_4</th>\n",
- " <td>12.000000</td>\n",
- " <td>0.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>12.000000</td>\n",
- " <td>1.896481</td>\n",
- " <td>0.053029</td>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.053028</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>nobel-eu_9</th>\n",
- " <td>12.000000</td>\n",
- " <td>0.000000</td>\n",
- " <td>0.0</td>\n",
- " <td>12.000000</td>\n",
- " <td>1.909050</td>\n",
- " <td>0.053061</td>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>1</td>\n",
- " <td>0</td>\n",
- " <td>1</td>\n",
- " <td>0.053060</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>norway_2</th>\n",
- " <td>12.000000</td>\n",
- " <td>5.600000</td>\n",
- " <td>0.0</td>\n",
- " <td>10.666667</td>\n",
- " <td>23.824929</td>\n",
- " <td>21.324783</td>\n",
- " <td>5</td>\n",
- " <td>5</td>\n",
- " <td>5</td>\n",
- " <td>8</td>\n",
- " <td>0</td>\n",
- " <td>3</td>\n",
- " <td>0.137158</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>norway_4</th>\n",
- " <td>12.000000</td>\n",
- " <td>5.600000</td>\n",
- " <td>0.0</td>\n",
- " <td>10.666667</td>\n",
- " <td>22.097282</td>\n",
- " <td>14.883294</td>\n",
- " <td>5</td>\n",
- " <td>5</td>\n",
- " <td>5</td>\n",
- " <td>8</td>\n",
- " <td>0</td>\n",
- " <td>3</td>\n",
- " <td>0.136240</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>norway_9</th>\n",
- " <td>12.000000</td>\n",
- " <td>5.600000</td>\n",
- " <td>0.0</td>\n",
- " <td>10.666667</td>\n",
- " <td>23.109758</td>\n",
- " <td>18.918477</td>\n",
- " <td>5</td>\n",
- " <td>5</td>\n",
- " <td>5</td>\n",
- " <td>8</td>\n",
- " <td>0</td>\n",
- " <td>3</td>\n",
- " <td>0.136492</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>pioro40_2</th>\n",
- " <td>21.230769</td>\n",
- " <td>5.166667</td>\n",
- " <td>0.0</td>\n",
- " <td>23.777778</td>\n",
- " <td>170.362274</td>\n",
- " <td>136.992976</td>\n",
- " <td>13</td>\n",
- " <td>12</td>\n",
- " <td>13</td>\n",
- " <td>21</td>\n",
- " <td>0</td>\n",
- " <td>9</td>\n",
- " <td>1.847440</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>pioro40_4</th>\n",
- " <td>21.230769</td>\n",
- " <td>5.166667</td>\n",
- " <td>0.0</td>\n",
- " <td>23.777778</td>\n",
- " <td>173.517142</td>\n",
- " <td>139.289051</td>\n",
- " <td>13</td>\n",
- " <td>12</td>\n",
- " <td>13</td>\n",
- " <td>21</td>\n",
- " <td>0</td>\n",
- " <td>9</td>\n",
- " <td>1.847570</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>pioro40_9</th>\n",
- " <td>21.230769</td>\n",
- " <td>5.166667</td>\n",
- " <td>0.0</td>\n",
- " <td>23.777778</td>\n",
- " <td>173.644933</td>\n",
- " <td>138.333486</td>\n",
- " <td>13</td>\n",
- " <td>12</td>\n",
- " <td>13</td>\n",
- " <td>21</td>\n",
- " <td>0</td>\n",
- " <td>9</td>\n",
- " <td>1.870450</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>sun_2</th>\n",
- " <td>22.285714</td>\n",
- " <td>8.800000</td>\n",
- " <td>0.0</td>\n",
- " <td>37.333333</td>\n",
- " <td>30.745669</td>\n",
- " <td>22.938442</td>\n",
- " <td>7</td>\n",
- " <td>5</td>\n",
- " <td>7</td>\n",
- " <td>8</td>\n",
- " <td>0</td>\n",
- " <td>3</td>\n",
- " <td>0.757831</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>sun_4</th>\n",
- " <td>22.285714</td>\n",
- " <td>8.800000</td>\n",
- " <td>0.0</td>\n",
- " <td>37.333333</td>\n",
- " <td>22.429657</td>\n",
- " <td>16.496639</td>\n",
- " <td>7</td>\n",
- " <td>5</td>\n",
- " <td>7</td>\n",
- " <td>8</td>\n",
- " <td>0</td>\n",
- " <td>3</td>\n",
- " <td>0.757164</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>sun_9</th>\n",
- " <td>22.285714</td>\n",
- " <td>8.800000</td>\n",
- " <td>0.0</td>\n",
- " <td>37.333333</td>\n",
- " <td>22.810439</td>\n",
- " <td>18.158503</td>\n",
- " <td>7</td>\n",
- " <td>5</td>\n",
- " <td>7</td>\n",
- " <td>8</td>\n",
- " <td>0</td>\n",
- " <td>3</td>\n",
- " <td>0.757359</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>ta2_2</th>\n",
- " <td>49.500000</td>\n",
- " <td>6.363636</td>\n",
- " <td>0.0</td>\n",
- " <td>131.428571</td>\n",
- " <td>740.569172</td>\n",
- " <td>403.744536</td>\n",
- " <td>20</td>\n",
- " <td>11</td>\n",
- " <td>20</td>\n",
- " <td>18</td>\n",
- " <td>0</td>\n",
- " <td>7</td>\n",
- " <td>29.818400</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>ta2_4</th>\n",
- " <td>49.500000</td>\n",
- " <td>6.363636</td>\n",
- " <td>0.0</td>\n",
- " <td>131.428571</td>\n",
- " <td>723.787310</td>\n",
- " <td>406.952759</td>\n",
- " <td>20</td>\n",
- " <td>11</td>\n",
- " <td>20</td>\n",
- " <td>18</td>\n",
- " <td>0</td>\n",
- " <td>7</td>\n",
- " <td>29.643000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>ta2_9</th>\n",
- " <td>49.500000</td>\n",
- " <td>6.363636</td>\n",
- " <td>0.0</td>\n",
- " <td>131.428571</td>\n",
- " <td>739.115006</td>\n",
- " <td>411.110420</td>\n",
- " <td>20</td>\n",
- " <td>11</td>\n",
- " <td>20</td>\n",
- " <td>18</td>\n",
- " <td>0</td>\n",
- " <td>7</td>\n",
- " <td>29.500600</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>zib54_2</th>\n",
- " <td>37.666667</td>\n",
- " <td>6.125000</td>\n",
- " <td>0.0</td>\n",
- " <td>44.777778</td>\n",
- " <td>227.583080</td>\n",
- " <td>155.150290</td>\n",
- " <td>12</td>\n",
- " <td>8</td>\n",
- " <td>12</td>\n",
- " <td>17</td>\n",
- " <td>0</td>\n",
- " <td>9</td>\n",
- " <td>11.766700</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>zib54_4</th>\n",
- " <td>37.666667</td>\n",
- " <td>6.125000</td>\n",
- " <td>0.0</td>\n",
- " <td>44.777778</td>\n",
- " <td>227.560660</td>\n",
- " <td>157.364048</td>\n",
- " <td>12</td>\n",
- " <td>8</td>\n",
- " <td>12</td>\n",
- " <td>17</td>\n",
- " <td>0</td>\n",
- " <td>9</td>\n",
- " <td>11.737000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>zib54_9</th>\n",
- " <td>37.666667</td>\n",
- " <td>6.125000</td>\n",
- " <td>0.0</td>\n",
- " <td>44.777778</td>\n",
- " <td>227.062362</td>\n",
- " <td>155.567672</td>\n",
- " <td>12</td>\n",
- " <td>8</td>\n",
- " <td>12</td>\n",
- " <td>17</td>\n",
- " <td>0</td>\n",
- " <td>9</td>\n",
- " <td>11.742800</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " average_demands_real average_demands_virtual \\\n",
- "algorithm Greedy vIGP Greedy \n",
- "instance \n",
- "cost266_2 4.571429 1.000000 0.0 \n",
- "cost266_4 4.571429 1.000000 0.0 \n",
- "cost266_9 4.571429 1.000000 0.0 \n",
- "france_2 3.333333 1.500000 0.0 \n",
- "france_4 3.333333 1.500000 0.0 \n",
- "france_9 3.333333 1.500000 0.0 \n",
- "germany50_2 30.444444 5.000000 0.0 \n",
- "germany50_4 30.444444 5.000000 0.0 \n",
- "germany50_9 30.444444 5.000000 0.0 \n",
- "giul39_2 21.076923 12.750000 0.0 \n",
- "giul39_4 21.076923 12.750000 0.0 \n",
- "giul39_9 21.076923 12.750000 0.0 \n",
- "india35_2 5.714286 1.333333 0.0 \n",
- "india35_4 5.714286 1.333333 0.0 \n",
- "india35_9 5.714286 1.333333 0.0 \n",
- "janos-us-ca_2 5.000000 4.000000 0.0 \n",
- "janos-us-ca_4 5.000000 4.000000 0.0 \n",
- "janos-us-ca_9 5.000000 4.000000 0.0 \n",
- "nobel-eu_2 12.000000 0.000000 0.0 \n",
- "nobel-eu_4 12.000000 0.000000 0.0 \n",
- "nobel-eu_9 12.000000 0.000000 0.0 \n",
- "norway_2 12.000000 5.600000 0.0 \n",
- "norway_4 12.000000 5.600000 0.0 \n",
- "norway_9 12.000000 5.600000 0.0 \n",
- "pioro40_2 21.230769 5.166667 0.0 \n",
- "pioro40_4 21.230769 5.166667 0.0 \n",
- "pioro40_9 21.230769 5.166667 0.0 \n",
- "sun_2 22.285714 8.800000 0.0 \n",
- "sun_4 22.285714 8.800000 0.0 \n",
- "sun_9 22.285714 8.800000 0.0 \n",
- "ta2_2 49.500000 6.363636 0.0 \n",
- "ta2_4 49.500000 6.363636 0.0 \n",
- "ta2_9 49.500000 6.363636 0.0 \n",
- "zib54_2 37.666667 6.125000 0.0 \n",
- "zib54_4 37.666667 6.125000 0.0 \n",
- "zib54_9 37.666667 6.125000 0.0 \n",
- "\n",
- " execution_time nb_real_topologies \\\n",
- "algorithm vIGP Greedy vIGP Greedy vIGP \n",
- "instance \n",
- "cost266_2 30.000000 48.105944 15.903579 7 2 \n",
- "cost266_4 30.000000 46.860643 15.211914 7 2 \n",
- "cost266_9 30.000000 49.364375 15.086771 7 2 \n",
- "france_2 7.000000 10.123589 7.582157 3 2 \n",
- "france_4 7.000000 6.665486 4.461218 3 2 \n",
- "france_9 7.000000 10.266920 7.532834 3 2 \n",
- "germany50_2 40.666667 186.969407 115.312697 9 6 \n",
- "germany50_4 40.666667 189.632973 118.689689 9 6 \n",
- "germany50_9 40.666667 196.930574 116.372007 9 6 \n",
- "giul39_2 34.400000 166.512498 100.729838 13 8 \n",
- "giul39_4 34.400000 170.805808 100.198280 13 8 \n",
- "giul39_9 34.400000 169.645091 102.558270 13 8 \n",
- "india35_2 12.000000 62.482397 28.938689 7 3 \n",
- "india35_4 12.000000 63.119016 29.122703 7 3 \n",
- "india35_9 12.000000 72.256013 31.588107 7 3 \n",
- "janos-us-ca_2 8.000000 36.441556 27.472770 4 3 \n",
- "janos-us-ca_4 8.000000 39.290821 25.447117 4 3 \n",
- "janos-us-ca_9 8.000000 37.693707 26.608627 4 3 \n",
- "nobel-eu_2 12.000000 1.683972 0.053230 1 0 \n",
- "nobel-eu_4 12.000000 1.896481 0.053029 1 0 \n",
- "nobel-eu_9 12.000000 1.909050 0.053061 1 0 \n",
- "norway_2 10.666667 23.824929 21.324783 5 5 \n",
- "norway_4 10.666667 22.097282 14.883294 5 5 \n",
- "norway_9 10.666667 23.109758 18.918477 5 5 \n",
- "pioro40_2 23.777778 170.362274 136.992976 13 12 \n",
- "pioro40_4 23.777778 173.517142 139.289051 13 12 \n",
- "pioro40_9 23.777778 173.644933 138.333486 13 12 \n",
- "sun_2 37.333333 30.745669 22.938442 7 5 \n",
- "sun_4 37.333333 22.429657 16.496639 7 5 \n",
- "sun_9 37.333333 22.810439 18.158503 7 5 \n",
- "ta2_2 131.428571 740.569172 403.744536 20 11 \n",
- "ta2_4 131.428571 723.787310 406.952759 20 11 \n",
- "ta2_9 131.428571 739.115006 411.110420 20 11 \n",
- "zib54_2 44.777778 227.583080 155.150290 12 8 \n",
- "zib54_4 44.777778 227.560660 157.364048 12 8 \n",
- "zib54_9 44.777778 227.062362 155.567672 12 8 \n",
- "\n",
- " nb_total_topologies nb_virtual_topologies vigp_time \n",
- "algorithm Greedy vIGP Greedy vIGP vIGP \n",
- "instance \n",
- "cost266_2 7 3 0 1 0.373587 \n",
- "cost266_4 7 3 0 1 0.374182 \n",
- "cost266_9 7 3 0 1 0.373706 \n",
- "france_2 3 3 0 1 0.014791 \n",
- "france_4 3 3 0 1 0.014696 \n",
- "france_9 3 3 0 1 0.014685 \n",
- "germany50_2 9 12 0 6 3.101980 \n",
- "germany50_4 9 12 0 6 3.112930 \n",
- "germany50_9 9 12 0 6 3.099310 \n",
- "giul39_2 13 13 0 5 1.629080 \n",
- "giul39_4 13 13 0 5 1.639610 \n",
- "giul39_9 13 13 0 5 1.640000 \n",
- "india35_2 7 6 0 3 0.175666 \n",
- "india35_4 7 6 0 3 0.175600 \n",
- "india35_9 7 6 0 3 0.175304 \n",
- "janos-us-ca_2 4 4 0 1 0.106930 \n",
- "janos-us-ca_4 4 4 0 1 0.106714 \n",
- "janos-us-ca_9 4 4 0 1 0.106804 \n",
- "nobel-eu_2 1 1 0 1 0.053229 \n",
- "nobel-eu_4 1 1 0 1 0.053028 \n",
- "nobel-eu_9 1 1 0 1 0.053060 \n",
- "norway_2 5 8 0 3 0.137158 \n",
- "norway_4 5 8 0 3 0.136240 \n",
- "norway_9 5 8 0 3 0.136492 \n",
- "pioro40_2 13 21 0 9 1.847440 \n",
- "pioro40_4 13 21 0 9 1.847570 \n",
- "pioro40_9 13 21 0 9 1.870450 \n",
- "sun_2 7 8 0 3 0.757831 \n",
- "sun_4 7 8 0 3 0.757164 \n",
- "sun_9 7 8 0 3 0.757359 \n",
- "ta2_2 20 18 0 7 29.818400 \n",
- "ta2_4 20 18 0 7 29.643000 \n",
- "ta2_9 20 18 0 7 29.500600 \n",
- "zib54_2 12 17 0 9 11.766700 \n",
- "zib54_4 12 17 0 9 11.737000 \n",
- "zib54_9 12 17 0 9 11.742800 "
- ]
- },
- "execution_count": 17,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
+ "outputs": [],
"source": [
"stats_table = df.pivot_table(columns='algorithm', values=['nb_virtual_topologies', 'nb_real_topologies', 'nb_total_topologies', 'execution_time', 'vigp_time', 'average_demands_real', 'average_demands_virtual'], index='instance').query('instance != \"toy\"')\n",
"stats_table"
@@ -1261,115 +69,10 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": null,
"id": "99c643fc-1459-4293-abc0-e01c002ecbef",
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>MTR</th>\n",
- " <th>vMTR (real)</th>\n",
- " <th>vMTR (virtual)</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>count</th>\n",
- " <td>36.000000</td>\n",
- " <td>36.000000</td>\n",
- " <td>36.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>mean</th>\n",
- " <td>8.500000</td>\n",
- " <td>5.416667</td>\n",
- " <td>4.083333</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>std</th>\n",
- " <td>5.113009</td>\n",
- " <td>3.620379</td>\n",
- " <td>2.970089</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>min</th>\n",
- " <td>1.000000</td>\n",
- " <td>0.000000</td>\n",
- " <td>1.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>25%</th>\n",
- " <td>5.500000</td>\n",
- " <td>2.750000</td>\n",
- " <td>1.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>50%</th>\n",
- " <td>7.000000</td>\n",
- " <td>5.000000</td>\n",
- " <td>3.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>75%</th>\n",
- " <td>12.250000</td>\n",
- " <td>8.000000</td>\n",
- " <td>6.250000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>max</th>\n",
- " <td>20.000000</td>\n",
- " <td>12.000000</td>\n",
- " <td>9.000000</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " MTR vMTR (real) vMTR (virtual)\n",
- "count 36.000000 36.000000 36.000000\n",
- "mean 8.500000 5.416667 4.083333\n",
- "std 5.113009 3.620379 2.970089\n",
- "min 1.000000 0.000000 1.000000\n",
- "25% 5.500000 2.750000 1.000000\n",
- "50% 7.000000 5.000000 3.000000\n",
- "75% 12.250000 8.000000 6.250000\n",
- "max 20.000000 12.000000 9.000000"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 505.625x312.5 with 1 Axes>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"import matplotlib\n",
@@ -1393,115 +96,10 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": null,
"id": "c93d1d90-42d4-4f6d-89f4-987ec8dbe58e",
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>MTR</th>\n",
- " <th>vMTR (real)</th>\n",
- " <th>vMTR (virtual)</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>count</th>\n",
- " <td>36.000000</td>\n",
- " <td>36.000000</td>\n",
- " <td>36.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>mean</th>\n",
- " <td>18.568630</td>\n",
- " <td>4.803220</td>\n",
- " <td>32.670899</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>std</th>\n",
- " <td>14.293838</td>\n",
- " <td>3.528397</td>\n",
- " <td>32.968742</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>min</th>\n",
- " <td>3.333333</td>\n",
- " <td>0.000000</td>\n",
- " <td>7.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>25%</th>\n",
- " <td>5.535714</td>\n",
- " <td>1.458333</td>\n",
- " <td>11.666667</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>50%</th>\n",
- " <td>16.538462</td>\n",
- " <td>5.083333</td>\n",
- " <td>26.888889</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>75%</th>\n",
- " <td>24.325397</td>\n",
- " <td>6.184659</td>\n",
- " <td>38.166667</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>max</th>\n",
- " <td>49.500000</td>\n",
- " <td>12.750000</td>\n",
- " <td>131.428571</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " MTR vMTR (real) vMTR (virtual)\n",
- "count 36.000000 36.000000 36.000000\n",
- "mean 18.568630 4.803220 32.670899\n",
- "std 14.293838 3.528397 32.968742\n",
- "min 3.333333 0.000000 7.000000\n",
- "25% 5.535714 1.458333 11.666667\n",
- "50% 16.538462 5.083333 26.888889\n",
- "75% 24.325397 6.184659 38.166667\n",
- "max 49.500000 12.750000 131.428571"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 505.625x312.5 with 1 Axes>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"import matplotlib\n",
@@ -1528,115 +126,10 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": null,
"id": "f296a054-d43f-4807-934b-ba7932908a49",
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr style=\"text-align: right;\">\n",
- " <th></th>\n",
- " <th>MTR</th>\n",
- " <th>vMTR (greedy)</th>\n",
- " <th>vMTR (lambda)</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>count</th>\n",
- " <td>36.000000</td>\n",
- " <td>36.000000</td>\n",
- " <td>36.000000</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>mean</th>\n",
- " <td>134.016254</td>\n",
- " <td>86.283388</td>\n",
- " <td>4.134753</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>std</th>\n",
- " <td>185.205136</td>\n",
- " <td>112.044950</td>\n",
- " <td>8.428490</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>min</th>\n",
- " <td>2.829474</td>\n",
- " <td>0.053029</td>\n",
- " <td>0.014685</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>25%</th>\n",
- " <td>21.042372</td>\n",
- " <td>15.730663</td>\n",
- " <td>0.128912</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>50%</th>\n",
- " <td>55.597346</td>\n",
- " <td>28.205729</td>\n",
- " <td>0.565673</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>75%</th>\n",
- " <td>168.271831</td>\n",
- " <td>123.265511</td>\n",
- " <td>2.177665</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>max</th>\n",
- " <td>695.004179</td>\n",
- " <td>411.110420</td>\n",
- " <td>29.818400</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " MTR vMTR (greedy) vMTR (lambda)\n",
- "count 36.000000 36.000000 36.000000\n",
- "mean 134.016254 86.283388 4.134753\n",
- "std 185.205136 112.044950 8.428490\n",
- "min 2.829474 0.053029 0.014685\n",
- "25% 21.042372 15.730663 0.128912\n",
- "50% 55.597346 28.205729 0.565673\n",
- "75% 168.271831 123.265511 2.177665\n",
- "max 695.004179 411.110420 29.818400"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 505.625x312.5 with 1 Axes>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"import matplotlib\n",
@@ -1662,7 +155,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": null,
"id": "3f6a4652-b872-4b32-b1d7-d57a54922dcf",
"metadata": {},
"outputs": [],
@@ -1674,264 +167,10 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": null,
"id": "3e91d290-a665-4437-b51f-20463b91e003",
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "<div>\n",
- "<style scoped>\n",
- " .dataframe tbody tr th:only-of-type {\n",
- " vertical-align: middle;\n",
- " }\n",
- "\n",
- " .dataframe tbody tr th {\n",
- " vertical-align: top;\n",
- " }\n",
- "\n",
- " .dataframe thead tr th {\n",
- " text-align: left;\n",
- " }\n",
- "\n",
- " .dataframe thead tr:last-of-type th {\n",
- " text-align: right;\n",
- " }\n",
- "</style>\n",
- "<table border=\"1\" class=\"dataframe\">\n",
- " <thead>\n",
- " <tr>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th colspan=\"2\" halign=\"left\">delay</th>\n",
- " <th colspan=\"2\" halign=\"left\">loss</th>\n",
- " <th colspan=\"2\" halign=\"left\">topo_id</th>\n",
- " <th>delay_ratio</th>\n",
- " <th>loss_ratio</th>\n",
- " <th>delay_ratio</th>\n",
- " <th>loss_ratio</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th></th>\n",
- " <th>algo</th>\n",
- " <th>Greedy</th>\n",
- " <th>vIGP</th>\n",
- " <th>Greedy</th>\n",
- " <th>vIGP</th>\n",
- " <th>Greedy</th>\n",
- " <th>vIGP</th>\n",
- " <th>Greedy</th>\n",
- " <th>Greedy</th>\n",
- " <th>vIGP</th>\n",
- " <th>vIGP</th>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>instance</th>\n",
- " <th>demand_id</th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " <th></th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th rowspan=\"5\" valign=\"top\">cost266_2</th>\n",
- " <th>0</th>\n",
- " <td>415710.0</td>\n",
- " <td>415710.0</td>\n",
- " <td>3362.0</td>\n",
- " <td>3362.0</td>\n",
- " <td>6</td>\n",
- " <td>v0</td>\n",
- " <td>0.989929</td>\n",
- " <td>0.970554</td>\n",
- " <td>0.989929</td>\n",
- " <td>0.970554</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>456300.0</td>\n",
- " <td>456300.0</td>\n",
- " <td>3800.0</td>\n",
- " <td>3800.0</td>\n",
- " <td>6</td>\n",
- " <td>v0</td>\n",
- " <td>0.990817</td>\n",
- " <td>0.97386</td>\n",
- " <td>0.990817</td>\n",
- " <td>0.97386</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>2</th>\n",
- " <td>394200.0</td>\n",
- " <td>394200.0</td>\n",
- " <td>3165.0</td>\n",
- " <td>3165.0</td>\n",
- " <td>6</td>\n",
- " <td>v0</td>\n",
- " <td>0.989386</td>\n",
- " <td>0.968779</td>\n",
- " <td>0.989386</td>\n",
- " <td>0.968779</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>3</th>\n",
- " <td>347940.0</td>\n",
- " <td>347940.0</td>\n",
- " <td>2802.0</td>\n",
- " <td>2802.0</td>\n",
- " <td>6</td>\n",
- " <td>v0</td>\n",
- " <td>0.987992</td>\n",
- " <td>0.968545</td>\n",
- " <td>0.987992</td>\n",
- " <td>0.968545</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>4</th>\n",
- " <td>445140.0</td>\n",
- " <td>432180.0</td>\n",
- " <td>3748.0</td>\n",
- " <td>3756.0</td>\n",
- " <td>6</td>\n",
- " <td>v0</td>\n",
- " <td>0.955382</td>\n",
- " <td>0.998136</td>\n",
- " <td>0.927566</td>\n",
- " <td>1.000266</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>...</th>\n",
- " <th>...</th>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " <td>...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th rowspan=\"5\" valign=\"top\">zib54_9</th>\n",
- " <th>447</th>\n",
- " <td>619156.8</td>\n",
- " <td>619156.8</td>\n",
- " <td>41980.0</td>\n",
- " <td>41980.0</td>\n",
- " <td>11</td>\n",
- " <td>v5</td>\n",
- " <td>0.251498</td>\n",
- " <td>0.961873</td>\n",
- " <td>0.251498</td>\n",
- " <td>0.961873</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>448</th>\n",
- " <td>2034370.9</td>\n",
- " <td>530705.9</td>\n",
- " <td>37926.0</td>\n",
- " <td>35272.0</td>\n",
- " <td>11</td>\n",
- " <td>v2</td>\n",
- " <td>0.857144</td>\n",
- " <td>0.786618</td>\n",
- " <td>0.223603</td>\n",
- " <td>0.731572</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>449</th>\n",
- " <td>1385731.0</td>\n",
- " <td>1385731.0</td>\n",
- " <td>17268.0</td>\n",
- " <td>17268.0</td>\n",
- " <td>11</td>\n",
- " <td>v3</td>\n",
- " <td>0.80342</td>\n",
- " <td>0.441355</td>\n",
- " <td>0.80342</td>\n",
- " <td>0.441355</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>450</th>\n",
- " <td>3051558.0</td>\n",
- " <td>3051558.0</td>\n",
- " <td>50270.0</td>\n",
- " <td>50270.0</td>\n",
- " <td>11</td>\n",
- " <td>v3</td>\n",
- " <td>0.848362</td>\n",
- " <td>0.680538</td>\n",
- " <td>0.848362</td>\n",
- " <td>0.680538</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>451</th>\n",
- " <td>3066300.0</td>\n",
- " <td>3257942.0</td>\n",
- " <td>55900.0</td>\n",
- " <td>61714.0</td>\n",
- " <td>11</td>\n",
- " <td>7</td>\n",
- " <td>0.848979</td>\n",
- " <td>0.882051</td>\n",
- " <td>0.90204</td>\n",
- " <td>0.973791</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "<p>7716 rows × 10 columns</p>\n",
- "</div>"
- ],
- "text/plain": [
- " delay loss topo_id \\\n",
- "algo Greedy vIGP Greedy vIGP Greedy vIGP \n",
- "instance demand_id \n",
- "cost266_2 0 415710.0 415710.0 3362.0 3362.0 6 v0 \n",
- " 1 456300.0 456300.0 3800.0 3800.0 6 v0 \n",
- " 2 394200.0 394200.0 3165.0 3165.0 6 v0 \n",
- " 3 347940.0 347940.0 2802.0 2802.0 6 v0 \n",
- " 4 445140.0 432180.0 3748.0 3756.0 6 v0 \n",
- "... ... ... ... ... ... ... \n",
- "zib54_9 447 619156.8 619156.8 41980.0 41980.0 11 v5 \n",
- " 448 2034370.9 530705.9 37926.0 35272.0 11 v2 \n",
- " 449 1385731.0 1385731.0 17268.0 17268.0 11 v3 \n",
- " 450 3051558.0 3051558.0 50270.0 50270.0 11 v3 \n",
- " 451 3066300.0 3257942.0 55900.0 61714.0 11 7 \n",
- "\n",
- " delay_ratio loss_ratio delay_ratio loss_ratio \n",
- "algo Greedy Greedy vIGP vIGP \n",
- "instance demand_id \n",
- "cost266_2 0 0.989929 0.970554 0.989929 0.970554 \n",
- " 1 0.990817 0.97386 0.990817 0.97386 \n",
- " 2 0.989386 0.968779 0.989386 0.968779 \n",
- " 3 0.987992 0.968545 0.987992 0.968545 \n",
- " 4 0.955382 0.998136 0.927566 1.000266 \n",
- "... ... ... ... ... \n",
- "zib54_9 447 0.251498 0.961873 0.251498 0.961873 \n",
- " 448 0.857144 0.786618 0.223603 0.731572 \n",
- " 449 0.80342 0.441355 0.80342 0.441355 \n",
- " 450 0.848362 0.680538 0.848362 0.680538 \n",
- " 451 0.848979 0.882051 0.90204 0.973791 \n",
- "\n",
- "[7716 rows x 10 columns]"
- ]
- },
- "execution_count": 9,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
+ "outputs": [],
"source": [
"path_table = all_results_df.pivot(index=['instance', 'demand_id'], values=['delay', 'loss', 'topo_id'], columns=['algo']).dropna()\n",
"qos_table = qos_df.pivot(index=['instance', 'demand_id'], values=['delay', 'loss'], columns=[]).dropna()\n",
@@ -1942,45 +181,10 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": null,
"id": "0aa46331-ac5c-4d1a-b975-1b3a67911b29",
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "algo\n",
- "Greedy 0.848647\n",
- "vIGP 0.751779\n",
- "dtype: float64"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "text/plain": [
- "algo\n",
- "Greedy 0.878225\n",
- "vIGP 0.858603\n",
- "dtype: float64"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 1011.25x312.5 with 2 Axes>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"import seaborn\n",
"nrows = 1\n",
@@ -2013,51 +217,10 @@
},
{
"cell_type": "code",
- "execution_count": 23,
+ "execution_count": null,
"id": "d745fb22-0f12-4e54-81b8-55f49d19886f",
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "<Axes: ylabel='max_label'>"
- ]
- },
- "execution_count": 23,
- "metadata": {},
- "output_type": "execute_result"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 1600x900 with 1 Axes>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 1600x900 with 1 Axes>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 1600x900 with 1 Axes>"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"import seaborn as sns\n",
"\n",
diff --git a/src/vIGPed.ipynb b/src/vIGPed.ipynb
index d58896416edd0b331ac53d12189ad825965c89e5..c8a72df3c66876d4cceae1cfc1f0a7f3475099cf 100644
--- a/src/vIGPed.ipynb
+++ b/src/vIGPed.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 48,
+ "execution_count": null,
"id": "cc81b76d-1f93-4faa-9705-4bdbee69eaad",
"metadata": {},
"outputs": [],
@@ -14,7 +14,7 @@
},
{
"cell_type": "code",
- "execution_count": 82,
+ "execution_count": null,
"id": "d07b4e2a-e690-47cb-9fae-eee0ee13d825",
"metadata": {},
"outputs": [],
@@ -33,7 +33,7 @@
},
{
"cell_type": "code",
- "execution_count": 83,
+ "execution_count": null,
"id": "ed658052-027f-4e3f-8632-ca10cd02aa81",
"metadata": {},
"outputs": [],
@@ -43,7 +43,7 @@
},
{
"cell_type": "code",
- "execution_count": 84,
+ "execution_count": null,
"id": "c3ee16db-6498-4bf5-a70f-8a2fff771f59",
"metadata": {},
"outputs": [],
@@ -54,7 +54,7 @@
},
{
"cell_type": "code",
- "execution_count": 85,
+ "execution_count": null,
"id": "c23483cd-3c2c-4db3-bd4f-40533b74e17f",
"metadata": {},
"outputs": [],