aitech-eks-pub/cw/11_NER_RNN.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Podejście softmax z embeddingami na przykładzie NER"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/media/kuba/ssdsam/anaconda3/lib/python3.8/site-packages/gensim/similarities/__init__.py:15: UserWarning: The gensim.similarities.levenshtein submodule is disabled, because the optional Levenshtein package <https://pypi.org/project/python-Levenshtein/> is unavailable. Install Levenhstein (e.g. `pip install python-Levenshtein`) to suppress this warning.\n",
      "  warnings.warn(msg)\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import gensim\n",
    "import torch\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "from datasets import load_dataset\n",
    "from torchtext.vocab import Vocab\n",
    "from collections import Counter\n",
    "\n",
    "from sklearn.datasets import fetch_20newsgroups\n",
    "# https://scikit-learn.org/0.19/datasets/twenty_newsgroups.html\n",
    "\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "from tqdm.notebook import tqdm\n",
    "\n",
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Reusing dataset conll2003 (/home/kuba/.cache/huggingface/datasets/conll2003/conll2003/1.0.0/40e7cb6bcc374f7c349c83acd1e9352a4f09474eb691f64f364ee62eb65d0ca6)\n"
     ]
    }
   ],
   "source": [
    "dataset = load_dataset(\"conll2003\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def build_vocab(dataset):\n",
    "    counter = Counter()\n",
    "    for document in dataset:\n",
    "        counter.update(document)\n",
    "    return Vocab(counter, specials=['<unk>', '<pad>', '<bos>', '<eos>'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "vocab = build_vocab(dataset['train']['tokens'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "23627"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(vocab.itos)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "15"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vocab['on']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def data_process(dt):\n",
    "    return [ torch.tensor([vocab['<bos>']] +[vocab[token]  for token in  document ] + [vocab['<eos>']], dtype = torch.long) for document in dt]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "def labels_process(dt):\n",
    "    return [ torch.tensor([0] + document + [0], dtype = torch.long) for document in dt]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_tokens_ids = data_process(dataset['train']['tokens'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_tokens_ids = data_process(dataset['test']['tokens'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "validation_tokens_ids =  data_process(dataset['validation']['tokens'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "train_labels = labels_process(dataset['train']['ner_tags'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "validation_labels = labels_process(dataset['validation']['ner_tags'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_labels = labels_process(dataset['test']['ner_tags'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([    2,   966, 22409,   238,   773,     9,  4588,   212,  7686,     4,\n",
       "            3])"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_tokens_ids[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'chunk_tags': [11, 21, 11, 12, 21, 22, 11, 12, 0],\n",
       " 'id': '0',\n",
       " 'ner_tags': [3, 0, 7, 0, 0, 0, 7, 0, 0],\n",
       " 'pos_tags': [22, 42, 16, 21, 35, 37, 16, 21, 7],\n",
       " 'tokens': ['EU',\n",
       "  'rejects',\n",
       "  'German',\n",
       "  'call',\n",
       "  'to',\n",
       "  'boycott',\n",
       "  'British',\n",
       "  'lamb',\n",
       "  '.']}"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset['train'][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([0, 3, 0, 7, 0, 0, 0, 7, 0, 0, 0])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_labels[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_scores(y_true, y_pred):\n",
    "    acc_score = 0\n",
    "    tp = 0\n",
    "    fp = 0\n",
    "    selected_items = 0\n",
    "    relevant_items = 0 \n",
    "\n",
    "    for p,t in zip(y_pred, y_true):\n",
    "        if p == t:\n",
    "            acc_score +=1\n",
    "\n",
    "        if p > 0 and p == t:\n",
    "            tp +=1\n",
    "\n",
    "        if p > 0:\n",
    "            selected_items += 1\n",
    "\n",
    "        if t > 0 :\n",
    "            relevant_items +=1\n",
    "\n",
    "            \n",
    "            \n",
    "    if selected_items == 0:\n",
    "        precision = 1.0\n",
    "    else:\n",
    "        precision = tp / selected_items\n",
    "        \n",
    "            \n",
    "    if relevant_items == 0:\n",
    "        recall = 1.0\n",
    "    else:\n",
    "        recall = tp / relevant_items\n",
    "    \n",
    "    \n",
    "    if precision + recall == 0.0 :\n",
    "        f1 = 0.0\n",
    "    else:\n",
    "        f1 = 2* precision * recall  / (precision + recall)\n",
    "\n",
    "    return precision, recall, f1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_tags = max([max(x) for x in dataset['train']['ner_tags'] ]) + 1 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "class LSTM(torch.nn.Module):\n",
    "\n",
    "    def __init__(self):\n",
    "        super(LSTM, self).__init__()\n",
    "        self.emb = torch.nn.Embedding(len(vocab.itos),100)\n",
    "        self.rec = torch.nn.LSTM(100, 256, 1, batch_first = True)\n",
    "        self.fc1 = torch.nn.Linear( 256 , 9)\n",
    "\n",
    "    def forward(self, x):\n",
    "        emb = torch.relu(self.emb(x))\n",
    "        \n",
    "        lstm_output, (h_n, c_n) = self.rec(emb)\n",
    "        \n",
    "        out_weights = self.fc1(lstm_output)\n",
    "\n",
    "        return out_weights"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "lstm = LSTM()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "criterion = torch.nn.CrossEntropyLoss()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "optimizer = torch.optim.Adam(lstm.parameters())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "def eval_model(dataset_tokens, dataset_labels, model):\n",
    "    Y_true = []\n",
    "    Y_pred = []\n",
    "    for i in tqdm(range(len(dataset_labels))):\n",
    "        batch_tokens = dataset_tokens[i].unsqueeze(0)\n",
    "        tags = list(dataset_labels[i].numpy())\n",
    "        Y_true += tags\n",
    "        \n",
    "        Y_batch_pred_weights = model(batch_tokens).squeeze(0)\n",
    "        Y_batch_pred = torch.argmax(Y_batch_pred_weights,1)\n",
    "        Y_pred += list(Y_batch_pred.numpy())\n",
    "        \n",
    "\n",
    "    return get_scores(Y_true, Y_pred)\n",
    "        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "NUM_EPOCHS = 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "75184b632ce54ae690b3444778f44651",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=14041.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "74a55a414fa948a3b251b89f780564d0",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=3250.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "(0.5068524970963996, 0.5072649075903755, 0.5070586184860281)\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "0c9c580076fb4ec48b7ea2f300878594",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=14041.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "0be8681c67f64aca95ce5d3c44f10538",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=3250.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "(0.653649243957614, 0.6381494827385795, 0.6458063757205035)\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2dec403004bb4ae298bc73553ea3f4bc",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=14041.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "eebed0407ba343e29cf8c2d607f631dc",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=3250.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "(0.7140486069946651, 0.7001046146693014, 0.7070078647728607)\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "70792f22eea343c8916bcfcf9215c298",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=14041.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5d400bf1b656433ba2091cf750ec2d78",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=3250.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "(0.756327964151629, 0.725909566430315, 0.7408066429418744)\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "604c4fa13c03435d81bf68be37977d74",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=14041.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2f78871f366f4fd1b7de6c4be5303906",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=3250.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "(0.7963248522230789, 0.7203301174009067, 0.7564235581324383)\n"
     ]
    }
   ],
   "source": [
    "for i in range(NUM_EPOCHS):\n",
    "    lstm.train()\n",
    "    #for i in tqdm(range(500)):\n",
    "    for i in tqdm(range(len(train_labels))):\n",
    "        batch_tokens = train_tokens_ids[i].unsqueeze(0)\n",
    "        tags = train_labels[i].unsqueeze(1)\n",
    "        \n",
    "        \n",
    "        predicted_tags = lstm(batch_tokens)\n",
    "\n",
    "        \n",
    "        optimizer.zero_grad()\n",
    "        loss  = criterion(predicted_tags.squeeze(0),tags.squeeze(1))\n",
    "        \n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "        \n",
    "    lstm.eval()\n",
    "    print(eval_model(validation_tokens_ids, validation_labels, lstm))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5159f7a61c3a439bab45573f15ea55b2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=3250.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(0.7963248522230789, 0.7203301174009067, 0.7564235581324383)"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "eval_model(validation_tokens_ids, validation_labels, lstm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4b604bbb796f4d4cb99528fad98cfdff",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=3453.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(0.7450810185185185, 0.6348619329388561, 0.685569755058573)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "eval_model(test_tokens_ids, test_labels, lstm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "14041"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(train_tokens_ids)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## pytania\n",
    "\n",
    "- co zrobić z trenowaniem na batchach > 1 ?\n",
    "- co zrobić, żeby sieć uwzględniała następne tokeny, a nie tylko poprzednie?\n",
    "- w jaki sposób wykorzystać taką sieć do zadania zwykłej klasyfikacji?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Zadanie na zajęcia ( 20 minut)\n",
    "\n",
    "zmodyfikować sieć tak, żeby była używała dwuwarstwowej, dwukierunkowej warstwy GRU oraz dropoutu. Dropout ma nałożony na embeddingi.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Zadanie domowe\n",
    "\n",
    "\n",
    "- sklonować repozytorium https://git.wmi.amu.edu.pl/kubapok/en-ner-conll-2003\n",
    "- stworzyć model seq labelling bazujący na sieci neuronowej opisanej w punkcie niżej (można bazować na tym jupyterze lub nie).\n",
    "- model sieci to GRU (o dowolnych parametrach) + CRF w pytorchu korzystając z modułu CRF z poprzednich zajęć- - stworzyć predykcje w plikach dev-0/out.tsv oraz test-A/out.tsv\n",
    "- wynik fscore sprawdzony za pomocą narzędzia geval (patrz poprzednie zadanie) powinien wynosić conajmniej 0.65\n",
    "- proszę umieścić predykcję oraz skrypty generujące (w postaci tekstowej a nie jupyter) w repo, a w MS TEAMS umieścić link do swojego repo\n",
    "termin 22.06, 60 punktów, za najlepszy wynik- 100 punktów\n",
    " "
   ]
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}