Added bunch of experiment notebooks

experiment.ipynb

@@ -0,0 +1,203 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-25T17:47:32.798261Z",
+     "start_time": "2024-04-25T17:47:19.035622Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from torch_geometric.loader import DataLoader, ImbalancedSampler\n",
+    "from torch_geometric.transforms import FaceToEdge, OneHotDegree\n",
+    "import torchvision.transforms as transforms\n",
+    "import torch.nn.functional as F\n",
+    "\n",
+    "from mantra.simplicial import SimplicialDataset\n",
+    "from mantra.transforms import (\n",
+    "    TriangulationToFaceTransform,\n",
+    "    OrientableToClassTransform,\n",
+    "    DegreeTransform,\n",
+    ")\n",
+    "from validation.validate_homology import validate_betti_numbers\n",
+    "\n",
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Percentage: 0.27, 0.73\n"
+     ]
+    }
+   ],
+   "source": [
+    "class NameToClass: \n",
+    "    def __init__(self):\n",
+    "        self.class_dict = {'Klein bottle': 0, '': 1, 'RP^2': 2, 'T^2': 3, 'S^2': 4}\n",
+    "    \n",
+    "    def __call__(self,data):\n",
+    "        data.y = F.one_hot(torch.tensor(self.class_dict[data.name]),num_classes=5)\n",
+    "        return data\n",
+    "\n",
+    "tr = transforms.Compose(\n",
+    "    [\n",
+    "        TriangulationToFaceTransform(),\n",
+    "        FaceToEdge(remove_faces=False),\n",
+    "        DegreeTransform(),\n",
+    "        OrientableToClassTransform(),\n",
+    "        NameToClass()\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "dataset = SimplicialDataset(root=\"./data\", transform=tr)\n",
+    "\n",
+    "print(\n",
+    "    f\"Percentage: {sum(dataset.orientable) / len(dataset):.2f}, {(len(dataset) - sum(dataset.orientable)) / len(dataset):.2f}\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\ernst\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python310\\site-packages\\torch_geometric\\data\\storage.py:450: UserWarning: Unable to accurately infer 'num_nodes' from the attribute set '{'betti_numbers', 'name', 'torsion_coefficients', 'orientable', 'n_vertices', 'genus', 'dimension', 'face'}'. Please explicitly set 'num_nodes' as an attribute of 'data' to suppress this warning\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "tensor([0, 0, 0, 0, 1])"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = dataset[0]\n",
+    "data.y"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "'NoneType' object has no attribute 'name'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[19], line 5\u001b[0m\n\u001b[0;32m      3\u001b[0m cnt \u001b[38;5;241m=\u001b[39m Counter()\n\u001b[0;32m      4\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m data \u001b[38;5;129;01min\u001b[39;00m dataset:\n\u001b[1;32m----> 5\u001b[0m     cnt[\u001b[43mdata\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mname\u001b[49m] \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m      7\u001b[0m cnt\n",
+      "\u001b[1;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'name'"
+     ]
+    }
+   ],
+   "source": [
+    "from collections import Counter\n",
+    "# Tally occurrences of words in a list\n",
+    "cnt = Counter()\n",
+    "for data in dataset:\n",
+    "    cnt[data.name] += 1\n",
+    "\n",
+    "cnt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of training graphs: 562\n",
+      "Number of test graphs: 150\n"
+     ]
+    }
+   ],
+   "source": [
+    "dataset = dataset.shuffle()\n",
+    "\n",
+    "train_dataset = dataset[:-150]\n",
+    "test_dataset = dataset[-150:]\n",
+    "\n",
+    "print(f\"Number of training graphs: {len(train_dataset)}\")\n",
+    "print(f\"Number of test graphs: {len(test_dataset)}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([0, 0, 0, 1, 1, 0, 0, 1, 0, 1])"
+      ]
+     },
+     "execution_count": 59,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_loader = DataLoader(train_dataset,batch_size=10)#,sampler=ImbalancedSampler(train_dataset))\n",
+    "test_loader = DataLoader(test_dataset,batch_size=10)\n",
+    "\n",
+    "\n",
+    "for batch in train_loader:\n",
+    "    break\n",
+    "\n",
+    "batch.y"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}