run.py

@@ -1,20 +1,4 @@
 #!/usr/bin/python3
 import sys
 for line in sys.stdin:
-    spitted_line = line.split('\t')
+    print('the:0.6 a:0.4')
-    left_context = spitted_line[6]
-    right_context = spitted_line[7]
-    left_context_words = left_context.split(' ')
-    right_context_words = right_context.split(' ')
-    # print(left_context_words)
-    # print()
-    # print(right_context_words)
-
-    if left_context_words[-1] == 'At' or left_context_words[-1] == 'at':
-        print('first:0.6 which:0.3 :01')
-    elif left_context_words[-1] == 'the':
-        print('it:0.5 a:0.4 :01')
-    elif left_context_words[-1] == 'a':
-        print('the:0.7 it:0.2 :01')
-    else:
-        print('the:0.6 a:0.3 :01')

run2.py

@@ -1,36 +0,0 @@
-import torch
-from transformers import AutoTokenizer, AutoModelForMaskedLM
-import sys
-
-tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
-model = AutoModelForMaskedLM.from_pretrained("bert-base-uncased")
-
-for line in sys.stdin:
-    splitted_line = line.split("\t")
-    left_context = splitted_line[6].split(" ")[-1]
-    right_context = splitted_line[7].split(" ")[0]
-
-    word = "[MASK]"
-
-    text = f"{left_context} {word} {right_context}"
-
-    input_ids = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt", max_length=512, truncation=True)
-
-    mask_token_index = torch.where(input_ids == tokenizer.mask_token_id)[1][0]
-
-    with torch.inference_mode():
-        outputs = model(input_ids)
-        predictions = outputs[0][0, mask_token_index].softmax(dim=0)
-
-    top_k = 500
-    top_k_tokens = torch.topk(predictions, top_k).indices.tolist()
-    result = ''
-    prob_sum = 0
-    for token in top_k_tokens:
-        word = tokenizer.convert_ids_to_tokens([token])[0]
-        prob = predictions[token].item()
-        prob_sum += prob 
-        result += f"{word}:{prob} "
-    diff = 1.0 - prob_sum
-    result += f":{diff}"
-    print(result)

run7.ipynb

@@ -1,273 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true,
-    "pycharm": {
-     "is_executing": true
-    }
-   },
-   "outputs": [],
-   "source": [
-    "import itertools\n",
-    "import lzma\n",
-    "\n",
-    "import regex as re\n",
-    "import torch\n",
-    "from torch import nn\n",
-    "from torch.utils.data import IterableDataset, DataLoader\n",
-    "from torchtext.vocab import build_vocab_from_iterator"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "from google.colab import drive"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "def clean_line(line: str):\n",
-    "    separated = line.split('\\t')\n",
-    "    prefix = separated[6].replace(r'\\n', ' ')\n",
-    "    suffix = separated[7].replace(r'\\n', ' ')\n",
-    "    return prefix + ' ' + suffix\n",
-    "\n",
-    "def get_words_from_line(line):\n",
-    "    line = clean_line(line)\n",
-    "    for m in re.finditer(r'[\\p{L}0-9\\*]+|\\p{P}+', line):\n",
-    "        yield m.group(0).lower()\n",
-    "\n",
-    "def get_word_lines_from_file(file_name):\n",
-    "    with lzma.open(file_name, mode='rt', encoding='utf-8') as fid:\n",
-    "        for line in fid:\n",
-    "            yield get_words_from_line(line)\n",
-    "\n",
-    "def look_ahead_iterator(gen):\n",
-    "    prev = None\n",
-    "    for item in gen:\n",
-    "        if prev is not None:\n",
-    "            yield (prev, item)\n",
-    "        prev = item\n",
-    "\n",
-    "def prediction(word: str) -> str:\n",
-    "    ixs = torch.tensor(vocab.forward([word])).to(device)\n",
-    "    out = model(ixs)\n",
-    "    top = torch.topk(out[0], 5)\n",
-    "    top_indices = top.indices.tolist()\n",
-    "    top_probs = top.values.tolist()\n",
-    "    top_words = vocab.lookup_tokens(top_indices)\n",
-    "    zipped = list(zip(top_words, top_probs))\n",
-    "    for index, element in enumerate(zipped):\n",
-    "        unk = None\n",
-    "        if '<unk>' in element:\n",
-    "            unk = zipped.pop(index)\n",
-    "            zipped.append(('', unk[1]))\n",
-    "            break\n",
-    "    if unk is None:\n",
-    "        zipped[-1] = ('', zipped[-1][1])\n",
-    "    return ' '.join([f'{x[0]}:{x[1]}' for x in zipped])\n",
-    "\n",
-    "def create_outputs(folder_name):\n",
-    "    print(f'Creating outputs in {folder_name}')\n",
-    "    with lzma.open(f'{folder_name}/in.tsv.xz', mode='rt', encoding='utf-8') as fid:\n",
-    "        with open(f'{folder_name}/out.tsv', 'w', encoding='utf-8', newline='\\n') as f:\n",
-    "            for line in fid:\n",
-    "                separated = line.split('\\t')\n",
-    "                prefix = separated[6].replace(r'\\n', ' ').split()[-1]\n",
-    "                output_line = prediction(prefix)\n",
-    "                f.write(output_line + '\\n')\n",
-    "\n",
-    "class Bigrams(IterableDataset):\n",
-    "    def __init__(self, text_file, vocabulary_size):\n",
-    "        self.vocab = build_vocab_from_iterator(\n",
-    "            get_word_lines_from_file(text_file),\n",
-    "            max_tokens=vocabulary_size,\n",
-    "            specials=['<unk>'])\n",
-    "        self.vocab.set_default_index(self.vocab['<unk>'])\n",
-    "        self.vocabulary_size = vocabulary_size\n",
-    "        self.text_file = text_file\n",
-    "\n",
-    "    def __iter__(self):\n",
-    "        return look_ahead_iterator(\n",
-    "            (self.vocab[t] for t in itertools.chain.from_iterable(get_word_lines_from_file(self.text_file))))\n",
-    "\n",
-    "class SimpleBigramNeuralLanguageModel(nn.Module):\n",
-    "    def __init__(self, vocabulary_size, embedding_size):\n",
-    "        super(SimpleBigramNeuralLanguageModel, self).__init__()\n",
-    "        self.model = nn.Sequential(\n",
-    "            nn.Embedding(vocabulary_size, embedding_size),\n",
-    "            nn.Linear(embedding_size, vocabulary_size),\n",
-    "            nn.Softmax()\n",
-    "        )\n",
-    "\n",
-    "    def forward(self, x):\n",
-    "        return self.model(x)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "vocab_size = 15000\n",
-    "embed_size = 150\n",
-    "batch_size = 3000\n",
-    "device = 'cuda'\n",
-    "path_to_train = 'train/in.tsv.xz'\n",
-    "path_to_model = 'model1.bin'"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "drive.mount('/content/drive')\n",
-    "%cd /content/drive/MyDrive/"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "vocab = build_vocab_from_iterator(\n",
-    "    get_word_lines_from_file(path_to_train),\n",
-    "    max_tokens=vocab_size,\n",
-    "    specials=['<unk>']\n",
-    ")\n",
-    "\n",
-    "vocab.set_default_index(vocab['<unk>'])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "train_dataset = Bigrams(path_to_train, vocab_size)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "model = SimpleBigramNeuralLanguageModel(vocab_size, embed_size).to(device)\n",
-    "data = DataLoader(train_dataset, batch_size=batch_size)\n",
-    "optimizer = torch.optim.Adam(model.parameters())\n",
-    "criterion = torch.nn.NLLLoss()\n",
-    "\n",
-    "model.train()\n",
-    "step = 0\n",
-    "for x, y in data:\n",
-    "    x = x.to(device)\n",
-    "    y = y.to(device)\n",
-    "    optimizer.zero_grad()\n",
-    "    ypredicted = model(x)\n",
-    "    loss = criterion(torch.log(ypredicted), y)\n",
-    "    if step % 100 == 0:\n",
-    "        print(step, loss)\n",
-    "    step += 1\n",
-    "    loss.backward()\n",
-    "    optimizer.step()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "torch.save(model.state_dict(), path_to_model)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "model = SimpleBigramNeuralLanguageModel(vocab_size, embed_size).to(device)\n",
-    "model.load_state_dict(torch.load(path_to_model))\n",
-    "model.eval()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "create_outputs('dev-0')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
-   "source": [
-    "create_outputs('test-A')"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 2
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 0
-}