{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"!pip install datasets --no-index --find-links=file:///kaggle/input/coleridge-packages/packages/datasets\n!pip install ../input/coleridge-packages/seqeval-1.2.2-py3-none-any.whl\n!pip install ../input/coleridge-packages/tokenizers-0.10.1-cp37-cp37m-manylinux1_x86_64.whl\n!pip install ../input/coleridge-packages/transformers-4.5.0.dev0-py3-none-any.whl","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"MAX_SAMPLE = None","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport re\nimport json\nimport time\nimport datetime\nimport random\nimport glob\nimport importlib\n\nimport numpy as np\nimport pandas as pd\n\nfrom tqdm import tqdm\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nrandom.seed(123)\nnp.random.seed(456)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_path = '../input/coleridgeinitiative-show-us-the-data/train.csv'\ntrain = pd.read_csv(train_path)\ntrain = train[:MAX_SAMPLE]\n\npaper_train_folder = '../input/coleridgeinitiative-show-us-the-data/train'\npapers = {}\nfor paper_id in train['Id'].unique():\n    with open(f'{paper_train_folder}/{paper_id}.json', 'r') as f:\n        paper = json.load(f)\n        papers[paper_id] = paper","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission_path = '../input/coleridgeinitiative-show-us-the-data/sample_submission.csv'\nsample_submission = pd.read_csv(sample_submission_path)\n\npaper_test_folder = '../input/coleridgeinitiative-show-us-the-data/test'\nfor paper_id in sample_submission['Id']:\n    with open(f'{paper_test_folder}/{paper_id}.json', 'r') as f:\n        paper = json.load(f)\n        papers[paper_id] = paper","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Literal matching","metadata":{}},{"cell_type":"code","source":"all_labels = set()\n\nfor label_1, label_2, label_3 in train[['dataset_title', 'dataset_label', 'cleaned_label']].itertuples(index=False):\n    all_labels.add(str(label_1).lower())\n    all_labels.add(str(label_2).lower())\n    all_labels.add(str(label_3).lower())\n    \nprint(f'No. different labels: {len(all_labels)}')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def clean_text(txt):\n    return re.sub('[^A-Za-z0-9]+', ' ', str(txt).lower()).strip()\n\ndef totally_clean_text(txt):\n    txt = clean_text(txt)\n    txt = re.sub(' +', ' ', txt)\n    return txt","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"literal_preds = []\n\nfor paper_id in sample_submission['Id']:\n    paper = papers[paper_id]\n    text_1 = '. '.join(section['text'] for section in paper).lower()\n    text_2 = totally_clean_text(text_1)\n    \n    labels = set()\n    for label in all_labels:\n        if label in text_1 or label in text_2:\n            labels.add(clean_text(label))\n    \n    literal_preds.append('|'.join(labels))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"literal_preds[:5]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## BERT predictions","metadata":{}},{"cell_type":"code","source":"MAX_LENGTH = 64 # max no. words for each sentence.\nOVERLAP = 20 # if a sentence exceeds MAX_LENGTH, we split it to multiple sentences with overlapping\n\nPREDICT_BATCH = 64000 \n\nPRETRAINED_PATH = '../input/coleridge-bert-models/output'\nTEST_INPUT_SAVE_PATH = './input_data'\nTEST_NER_DATA_FILE = 'test_ner_input.json'\nTRAIN_PATH = '../input/coleridge-bert-models/train_ner.json'\nVAL_PATH = '../input/coleridge-bert-models/train_ner.json'\n\nPREDICTION_SAVE_PATH = './pred'\nPREDICTION_FILE = 'test_predictions.txt'","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = train.groupby('Id').agg({\n    'pub_title': 'first',\n    'dataset_title': '|'.join,\n    'dataset_label': '|'.join,\n    'cleaned_label': '|'.join\n}).reset_index()\n\nprint(f'No. grouped training rows: {len(train)}')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def clean_training_text(txt):\n    \"\"\"\n    similar to the default clean_text function but without lowercasing.\n    \"\"\"\n    return re.sub('[^A-Za-z0-9]+', ' ', str(txt)).strip()\n\ndef shorten_sentences(sentences):\n    short_sentences = []\n    for sentence in sentences:\n        words = sentence.split()\n        if len(words) > MAX_LENGTH:\n            for p in range(0, len(words), MAX_LENGTH - OVERLAP):\n                short_sentences.append(' '.join(words[p:p+MAX_LENGTH]))\n        else:\n            short_sentences.append(sentence)\n    return short_sentences\n\ndef find_sublist(big_list, small_list):\n    all_positions = []\n    for i in range(len(big_list) - len(small_list) + 1):\n        if small_list == big_list[i:i+len(small_list)]:\n            all_positions.append(i)\n    \n    return all_positions\n\ndef tag_sentence(sentence, labels): # requirement: both sentence and labels are already cleaned\n    sentence_words = sentence.split()\n    \n    if labels is not None and any(re.findall(f'\\\\b{label}\\\\b', sentence)\n                                  for label in labels): # positive sample\n        nes = ['O'] * len(sentence_words)\n        for label in labels:\n            label_words = label.split()\n\n            all_pos = find_sublist(sentence_words, label_words)\n            for pos in all_pos:\n                nes[pos] = 'B'\n                for i in range(pos+1, pos+len(label_words)):\n                    nes[i] = 'I'\n\n        return True, list(zip(sentence_words, nes))\n        \n    else: # negative sample\n        nes = ['O'] * len(sentence_words)\n        return False, list(zip(sentence_words, nes))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cnt_pos, cnt_neg = 0, 0 # number of sentences that contain/not contain labels\nner_data = []\n\npbar = tqdm(total=len(train))\nfor i, id, dataset_label in train[['Id', 'dataset_label']].itertuples():\n    # paper\n    paper = papers[id]\n    \n    # labels\n    labels = dataset_label.split('|')\n    labels = [clean_training_text(label) for label in labels]\n    \n    # sentences\n    sentences = set([clean_training_text(sentence) for section in paper \n                 for sentence in section['text'].split('.') \n                ])\n    sentences = shorten_sentences(sentences) # make sentences short\n    sentences = [sentence for sentence in sentences if len(sentence) > 10] # only accept sentences with length > 10 chars\n    \n    # positive sample\n    for sentence in sentences:\n        is_positive, tags = tag_sentence(sentence, labels)\n        if is_positive:\n            cnt_pos += 1\n            ner_data.append(tags)\n        elif any(word in sentence.lower() for word in ['data', 'study']): \n            ner_data.append(tags)\n            cnt_neg += 1\n    \n    # process bar\n    pbar.update(1)\n    pbar.set_description(f\"Training data size: {cnt_pos} positives + {cnt_neg} negatives\")\n\n# shuffling\nrandom.shuffle(ner_data)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with open('train_ner.json', 'w') as f:\n    for row in ner_data:\n        words, nes = list(zip(*row))\n        row_json = {'tokens' : words, 'tags' : nes}\n        json.dump(row_json, f)\n        f.write('\\n')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Fine tuning bert","metadata":{}},{"cell_type":"code","source":"!python ../input/kaggle-ner-utils/kaggle_run_ner.py \\\n--model_name_or_path 'bert-base-cased' \\\n--train_file './train_ner.json' \\\n--validation_file './train_ner.json' \\\n--num_train_epochs 1 \\\n--per_device_train_batch_size 8 \\\n--per_device_eval_batch_size 8 \\\n--save_steps 15000 \\\n--output_dir './output' \\\n--report_to 'none' \\\n--seed 123 \\\n--do_train ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_rows = [] # test data in NER format\npaper_length = [] # store the number of sentences each paper has\n\nfor paper_id in sample_submission['Id']:\n    # load paper\n    paper = papers[paper_id]\n    \n    # extract sentences\n    sentences = [clean_training_text(sentence) for section in paper \n                 for sentence in section['text'].split('.')\n                ]\n    sentences = shorten_sentences(sentences) # make sentences short\n    sentences = [sentence for sentence in sentences if len(sentence) > 10] # only accept sentences with length > 10 chars\n    sentences = [sentence for sentence in sentences if any(word in sentence.lower() for word in ['data', 'study'])]\n        \n    # collect all sentences in json\n    for sentence in sentences:\n        sentence_words = sentence.split()\n        dummy_tags = ['O']*len(sentence_words)\n        test_rows.append({'tokens' : sentence_words, 'tags' : dummy_tags})\n    \n    # track which sentence belongs to which data point\n    paper_length.append(len(sentences))\n    \nprint(f'total number of sentences: {len(test_rows)}')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"os.environ[\"MODEL_PATH\"] = f\"{PRETRAINED_PATH}\"\nos.environ[\"TRAIN_FILE\"] = f\"{TRAIN_PATH}\"\nos.environ[\"VALIDATION_FILE\"] = f\"{VAL_PATH}\"\nos.environ[\"TEST_FILE\"] = f\"{TEST_INPUT_SAVE_PATH}/{TEST_NER_DATA_FILE}\"\nos.environ[\"OUTPUT_DIR\"] = f\"{PREDICTION_SAVE_PATH}\"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# copy my_seqeval.py to the working directory because the input directory is non-writable\n!cp /kaggle/input/coleridge-packages/my_seqeval.py ./\n\n# make necessart directories and files\nos.makedirs(TEST_INPUT_SAVE_PATH, exist_ok=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def bert_predict():\n    !python ../input/kaggle-ner-utils/kaggle_run_ner.py \\\n    --model_name_or_path \"$MODEL_PATH\" \\\n    --train_file \"$TRAIN_FILE\" \\\n    --validation_file \"$VALIDATION_FILE\" \\\n    --test_file \"$TEST_FILE\" \\\n    --output_dir \"$OUTPUT_DIR\" \\\n    --report_to 'none' \\\n    --seed 123 \\\n    --do_predict","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"bert_outputs = []\n\nfor batch_begin in range(0, len(test_rows), PREDICT_BATCH):\n    # write data rows to input file\n    with open(f'{TEST_INPUT_SAVE_PATH}/{TEST_NER_DATA_FILE}', 'w') as f:\n        for row in test_rows[batch_begin:batch_begin+PREDICT_BATCH]:\n            json.dump(row, f)\n            f.write('\\n')\n    \n    # remove output dir\n    !rm -r \"$OUTPUT_DIR\"\n    \n    # do predict\n    bert_predict()\n    \n    # read predictions\n    with open(f'{PREDICTION_SAVE_PATH}/{PREDICTION_FILE}') as f:\n        this_preds = f.read().split('\\n')[:-1]\n        bert_outputs += [pred.split() for pred in this_preds]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# get test sentences\ntest_sentences = [row['tokens'] for row in test_rows]\n\ndel test_rows","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"bert_dataset_labels = [] # store all dataset labels for each publication\n\nfor length in paper_length:\n    labels = set()\n    for sentence, pred in zip(test_sentences[:length], bert_outputs[:length]):\n        curr_phrase = ''\n        for word, tag in zip(sentence, pred):\n            if tag == 'B': # start a new phrase\n                if curr_phrase:\n                    labels.add(curr_phrase)\n                    curr_phrase = ''\n                curr_phrase = word\n            elif tag == 'I' and curr_phrase: # continue the phrase\n                curr_phrase += ' ' + word\n            else: # end last phrase (if any)\n                if curr_phrase:\n                    labels.add(curr_phrase)\n                    curr_phrase = ''\n        # check if the label is the suffix of the sentence\n        if curr_phrase:\n            labels.add(curr_phrase)\n            curr_phrase = ''\n    \n    # record dataset labels for this publication\n    bert_dataset_labels.append(labels)\n    \n    del test_sentences[:length], bert_outputs[:length]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"bert_dataset_labels[:5]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def jaccard_similarity(s1, s2):\n    l1 = s1.split(\" \")\n    l2 = s2.split(\" \")    \n    intersection = len(list(set(l1).intersection(l2)))\n    union = (len(l1) + len(l2)) - intersection\n    return float(intersection) / union\n\nfiltered_bert_labels = []\n\nfor labels in bert_dataset_labels:\n    filtered = []\n    \n    for label in sorted(labels, key=len):\n        label = clean_text(label)\n        if len(filtered) == 0 or all(jaccard_similarity(label, got_label) < 0.75 for got_label in filtered):\n            filtered.append(label)\n    \n    filtered_bert_labels.append('|'.join(filtered))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"filtered_bert_labels[:5]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Aggrigate","metadata":{}},{"cell_type":"code","source":"final_predictions = []\nfor literal_match, bert_pred in zip(literal_preds, filtered_bert_labels):\n    if literal_match:\n        final_predictions.append(literal_match)\n    else:\n        final_predictions.append(bert_pred)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission['PredictionString'] = final_predictions\nsample_submission.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission.to_csv(f'submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}