{"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":"markdown","source":"This notebook gives a simple combination of literal matching and Named Entity Recognition using BERT (base model from huggingface).\n\nThe training phase of the BERT model was done in another kernel: Pytorch BERT for Named Entity Recognition.","metadata":{}},{"cell_type":"code","source":"MAX_SAMPLE = None # set a small number for experimentation, set None for production.","metadata":{"execution":{"iopub.status.busy":"2021-06-12T09:55:39.927443Z","iopub.execute_input":"2021-06-12T09:55:39.928019Z","iopub.status.idle":"2021-06-12T09:55:39.934021Z","shell.execute_reply.started":"2021-06-12T09:55:39.927841Z","shell.execute_reply":"2021-06-12T09:55:39.933182Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Install packages","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2021-06-12T09:55:39.936634Z","iopub.execute_input":"2021-06-12T09:55:39.937391Z","iopub.status.idle":"2021-06-12T09:57:08.237923Z","shell.execute_reply.started":"2021-06-12T09:55:39.937347Z","shell.execute_reply":"2021-06-12T09:57:08.237121Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Import","metadata":{}},{"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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2021-06-12T09:57:08.241416Z","iopub.execute_input":"2021-06-12T09:57:08.241673Z","iopub.status.idle":"2021-06-12T09:57:08.942235Z","shell.execute_reply.started":"2021-06-12T09:57:08.241646Z","shell.execute_reply":"2021-06-12T09:57:08.941487Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load data","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2021-06-12T09:57:08.943406Z","iopub.execute_input":"2021-06-12T09:57:08.943754Z","iopub.status.idle":"2021-06-12T09:58:09.838246Z","shell.execute_reply.started":"2021-06-12T09:57:08.943716Z","shell.execute_reply":"2021-06-12T09:58:09.837448Z"},"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":{"execution":{"iopub.status.busy":"2021-06-12T09:58:09.841881Z","iopub.execute_input":"2021-06-12T09:58:09.842231Z","iopub.status.idle":"2021-06-12T09:58:09.871905Z","shell.execute_reply.started":"2021-06-12T09:58:09.842194Z","shell.execute_reply":"2021-06-12T09:58:09.871223Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Literal matching","metadata":{}},{"cell_type":"markdown","source":"### Create a knowledge bank","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":{"execution":{"iopub.status.busy":"2021-06-12T09:58:09.874772Z","iopub.execute_input":"2021-06-12T09:58:09.875146Z","iopub.status.idle":"2021-06-12T09:58:09.932000Z","shell.execute_reply.started":"2021-06-12T09:58:09.875109Z","shell.execute_reply":"2021-06-12T09:58:09.931107Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Matching on test data","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2021-06-12T09:58:09.933492Z","iopub.execute_input":"2021-06-12T09:58:09.933953Z","iopub.status.idle":"2021-06-12T09:58:09.939402Z","shell.execute_reply.started":"2021-06-12T09:58:09.933910Z","shell.execute_reply":"2021-06-12T09:58:09.938583Z"},"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))\n","metadata":{"execution":{"iopub.status.busy":"2021-06-12T09:58:09.940803Z","iopub.execute_input":"2021-06-12T09:58:09.941288Z","iopub.status.idle":"2021-06-12T09:58:10.061430Z","shell.execute_reply.started":"2021-06-12T09:58:09.941227Z","shell.execute_reply":"2021-06-12T09:58:10.060625Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"literal_preds[:5]","metadata":{"execution":{"iopub.status.busy":"2021-06-12T09:58:10.064822Z","iopub.execute_input":"2021-06-12T09:58:10.065084Z","iopub.status.idle":"2021-06-12T09:58:10.075626Z","shell.execute_reply.started":"2021-06-12T09:58:10.065057Z","shell.execute_reply":"2021-06-12T09:58:10.074889Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Bert prediction","metadata":{"trusted":true}},{"cell_type":"markdown","source":"### Paths and Hyperparameters","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":{"execution":{"iopub.status.busy":"2021-06-12T09:58:10.076827Z","iopub.execute_input":"2021-06-12T09:58:10.077284Z","iopub.status.idle":"2021-06-12T09:58:10.086302Z","shell.execute_reply.started":"2021-06-12T09:58:10.077233Z","shell.execute_reply":"2021-06-12T09:58:10.085589Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Transform data to NER format","metadata":{}},{"cell_type":"markdown","source":"Group by publication, training labels should have the same form as expected output.","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2021-06-12T09:58:10.087746Z","iopub.execute_input":"2021-06-12T09:58:10.088096Z","iopub.status.idle":"2021-06-12T09:58:10.455600Z","shell.execute_reply.started":"2021-06-12T09:58:10.088059Z","shell.execute_reply":"2021-06-12T09:58:10.454694Z"},"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","metadata":{"execution":{"iopub.status.busy":"2021-06-12T09:58:10.456755Z","iopub.execute_input":"2021-06-12T09:58:10.457071Z","iopub.status.idle":"2021-06-12T09:58:10.466531Z","shell.execute_reply.started":"2021-06-12T09:58:10.457040Z","shell.execute_reply":"2021-06-12T09:58:10.465501Z"},"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 \n                 if len(sentence) > 10] # only accept sentences with length > 10 chars\n    sentences = [sentence for sentence in sentences \n                 if any(word in sentence.lower() for word in \n                        ['data', 'information', 'benchmark', 'evaluation', \n                         'experiment', 'study', 'work', 'subject', 'discipline',\n                         'subject_area', 'field_of_study', 'field', 'subject_field',\n                         'analyze', 'analyse', 'examine', 'initial', 'image', 'cohort',\n                         'participle', 'dataset', 'database', 'cognit', 'clinic', 'sample',\n                         'years', 'age', 'long_time', 'measure', 'include', 'obtain',\n                         'follow', 'test', 'nation', 'year', 'biomark', 'analysis',\n                         'group', 'land', 'state', 'country', 'res_publica', 'body_politic',\n                         'institute', 'differ', 'rouping', 'investigate', 'protocol',\n                         'method', 'pet', 'result', 'perform', 'scan', 'patient',\n                         'association', 'available', 'baseline', 'assess', 'vailable',\n                         'recruit', 'longitudinal', 'control', 'normal', 'model', 'pose',\n                         'lay', 'place', 'put', 'position', 'set', 'provide', 'brain'])]\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":{"execution":{"iopub.status.busy":"2021-06-12T09:58:10.468099Z","iopub.execute_input":"2021-06-12T09:58:10.468545Z","iopub.status.idle":"2021-06-12T09:58:10.547170Z","shell.execute_reply.started":"2021-06-12T09:58:10.468506Z","shell.execute_reply":"2021-06-12T09:58:10.546380Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Do predict and collect results","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2021-06-12T09:58:10.548472Z","iopub.execute_input":"2021-06-12T09:58:10.548804Z","iopub.status.idle":"2021-06-12T09:58:10.554032Z","shell.execute_reply.started":"2021-06-12T09:58:10.548768Z","shell.execute_reply":"2021-06-12T09:58:10.552913Z"},"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":{"execution":{"iopub.status.busy":"2021-06-12T09:58:10.555545Z","iopub.execute_input":"2021-06-12T09:58:10.556374Z","iopub.status.idle":"2021-06-12T09:58:11.320220Z","shell.execute_reply.started":"2021-06-12T09:58:10.556325Z","shell.execute_reply":"2021-06-12T09:58:11.319032Z"},"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 \"roberta-base\" \\\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":{"execution":{"iopub.status.busy":"2021-06-12T09:58:11.321929Z","iopub.execute_input":"2021-06-12T09:58:11.322313Z","iopub.status.idle":"2021-06-12T09:58:11.328819Z","shell.execute_reply.started":"2021-06-12T09:58:11.322252Z","shell.execute_reply":"2021-06-12T09:58:11.327254Z"},"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":{"execution":{"iopub.status.busy":"2021-06-12T09:58:11.330365Z","iopub.execute_input":"2021-06-12T09:58:11.330985Z","iopub.status.idle":"2021-06-12T09:59:30.380764Z","shell.execute_reply.started":"2021-06-12T09:58:11.330932Z","shell.execute_reply":"2021-06-12T09:59:30.378823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Restore Dataset labels from predictions","metadata":{}},{"cell_type":"code","source":"# get test sentences\ntest_sentences = [row['tokens'] for row in test_rows]\n\ndel test_rows","metadata":{"execution":{"iopub.status.busy":"2021-06-12T09:59:30.381761Z","iopub.status.idle":"2021-06-12T09:59:30.382156Z"},"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":{"execution":{"iopub.status.busy":"2021-06-12T09:59:30.383150Z","iopub.status.idle":"2021-06-12T09:59:30.383702Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"bert_dataset_labels[:5]","metadata":{"execution":{"iopub.status.busy":"2021-06-12T09:59:30.384661Z","iopub.status.idle":"2021-06-12T09:59:30.385188Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Filter based on Jaccard score and clean","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2021-06-12T09:59:30.386355Z","iopub.status.idle":"2021-06-12T09:59:30.386881Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"filtered_bert_labels[:5]","metadata":{"execution":{"iopub.status.busy":"2021-06-12T09:59:30.387824Z","iopub.status.idle":"2021-06-12T09:59:30.388460Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Aggregate final predictions and write submission file","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":{"execution":{"iopub.status.busy":"2021-06-12T09:59:30.389531Z","iopub.status.idle":"2021-06-12T09:59:30.390180Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission['PredictionString'] = final_predictions\nsample_submission.head()","metadata":{"execution":{"iopub.status.busy":"2021-06-12T09:59:30.391377Z","iopub.status.idle":"2021-06-12T09:59:30.391999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission.to_csv(f'submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2021-06-12T09:59:30.393121Z","iopub.status.idle":"2021-06-12T09:59:30.393748Z"},"trusted":true},"execution_count":null,"outputs":[]}]}