ABLkit/examples/hed/hed_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import torch.nn as nn\n",
    "import torch\n",
    "\n",
    "from abl.reasoning.reasoner import ReasonerBase\n",
    "from abl.reasoning.kb import prolog_KB\n",
    "\n",
    "from abl.utils.plog import logger\n",
    "from abl.learning.basic_nn import BasicNN\n",
    "from abl.learning.abl_model import ABLModel\n",
    "from abl.utils.utils import reform_idx\n",
    "\n",
    "from models.nn import SymbolNet\n",
    "from datasets.get_hed import get_hed, split_equation\n",
    "import framework_hed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize logger\n",
    "recorder = logger()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Logic Part"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize knowledge base and abducer\n",
    "class HED_prolog_KB(prolog_KB):\n",
    "    def __init__(self, pseudo_label_list, pl_file):\n",
    "        super().__init__(pseudo_label_list, pl_file)\n",
    "        \n",
    "    def consist_rule(self, exs, rules):\n",
    "        rules = str(rules).replace(\"\\'\",\"\")\n",
    "        return len(list(self.prolog.query(\"eval_inst_feature(%s, %s).\" % (exs, rules)))) != 0\n",
    "\n",
    "    def abduce_rules(self, pred_res):\n",
    "        prolog_result = list(self.prolog.query(\"consistent_inst_feature(%s, X).\" % pred_res))\n",
    "        if len(prolog_result) == 0:\n",
    "            return None\n",
    "        prolog_rules = prolog_result[0]['X']\n",
    "        rules = [rule.value for rule in prolog_rules]\n",
    "        return rules\n",
    "        \n",
    "    \n",
    "kb = HED_prolog_KB(pseudo_label_list=[1, 0, '+', '='], pl_file='./datasets/learn_add.pl')\n",
    "\n",
    "class HED_Abducer(ReasonerBase):\n",
    "    def __init__(self, kb, dist_func='hamming'):\n",
    "        super().__init__(kb, dist_func, zoopt=True)\n",
    "    \n",
    "    def _revise_by_idxs(self, pred_res, key, all_address_flag, idxs):\n",
    "        pred = []\n",
    "        k = []\n",
    "        address_flag = []\n",
    "        for idx in idxs:\n",
    "            pred.append(pred_res[idx])\n",
    "            k.append(key[idx])\n",
    "            address_flag += list(all_address_flag[idx])\n",
    "        address_idx = np.where(np.array(address_flag) != 0)[0]   \n",
    "        candidate = self.revise_by_idx(pred, k, address_idx)\n",
    "        return candidate\n",
    "    \n",
    "    def zoopt_revision_score(self, pred_res, pseudo_label, pred_res_prob, key, sol): \n",
    "        all_address_flag = reform_idx(sol.get_x(), pseudo_label)\n",
    "        lefted_idxs = [i for i in range(len(pred_res))]\n",
    "        candidate_size = []         \n",
    "        while lefted_idxs:\n",
    "            idxs = []\n",
    "            idxs.append(lefted_idxs.pop(0))\n",
    "            max_candidate_idxs = []\n",
    "            found = False\n",
    "            for idx in range(-1, len(pred_res)):\n",
    "                if (not idx in idxs) and (idx >= 0):\n",
    "                    idxs.append(idx)\n",
    "                candidate = self._revise_by_idxs(pseudo_label, key, all_address_flag, idxs)\n",
    "                if len(candidate) == 0:\n",
    "                    if len(idxs) > 1:\n",
    "                        idxs.pop()\n",
    "                else:\n",
    "                    if len(idxs) > len(max_candidate_idxs):\n",
    "                        found = True\n",
    "                        max_candidate_idxs = idxs.copy() \n",
    "            removed = [i for i in lefted_idxs if i in max_candidate_idxs]\n",
    "            if found:\n",
    "                candidate_size.append(len(removed) + 1)\n",
    "                lefted_idxs = [i for i in lefted_idxs if i not in max_candidate_idxs]\n",
    "        candidate_size.sort()\n",
    "        score = 0\n",
    "        import math\n",
    "        for i in range(0, len(candidate_size)):\n",
    "            score -= math.exp(-i) * candidate_size[i]\n",
    "        return score\n",
    "\n",
    "    def abduce_rules(self, pred_res):\n",
    "        return self.kb.abduce_rules(pred_res)\n",
    "        \n",
    "abducer = HED_Abducer(kb)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Machine Learning Part"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize necessary component for machine learning part\n",
    "cls = SymbolNet(\n",
    "    num_classes=len(kb.pseudo_label_list),\n",
    "    image_size=(28, 28, 1),\n",
    ")\n",
    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
    "criterion = nn.CrossEntropyLoss()\n",
    "optimizer = torch.optim.RMSprop(cls.parameters(), lr=0.001, weight_decay=1e-6)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Pretrain NN classifier\n",
    "framework_hed.hed_pretrain(kb, cls, recorder)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize BasicNN\n",
    "# The function of BasicNN is to wrap NN models into the form of an sklearn estimator\n",
    "base_model = BasicNN(\n",
    "    cls,\n",
    "    criterion,\n",
    "    optimizer,\n",
    "    device,\n",
    "    save_interval=1,\n",
    "    save_dir=recorder.save_dir,\n",
    "    batch_size=32,\n",
    "    num_epochs=1,\n",
    "    recorder=recorder,\n",
    ")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Use ABL model to join two parts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = ABLModel(base_model)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "total_train_data = get_hed(train=True)\n",
    "train_data, val_data = split_equation(total_train_data, 3, 1)\n",
    "test_data = get_hed(train=False)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Train and save"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "model, mapping = framework_hed.train_with_rule(model, abducer, train_data, val_data, select_num=10, min_len=5, max_len=8)\n",
    "framework_hed.hed_test(model, abducer, mapping, train_data, test_data, min_len=5, max_len=8)\n",
    "\n",
    "recorder.dump()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "ABL",
   "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": "3.8.16"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "fb6f4ceeabb9a733f366948eb80109f83aedf798cc984df1e68fb411adb27d58"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}