{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install transformers","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from transformers import BertConfig, BertForSequenceClassification, BertTokenizer\nimport torch # importing torch before transformers causes errors\n\nfrom tqdm import tqdm, tqdm_notebook","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"test_df = pd.read_csv('../input/quora-insincere-questions-classification/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pretrained_weights = 'bert-base-uncased'\n\nconfig = BertConfig.from_pretrained(pretrained_weights, num_labels=2)\nmodel = BertForSequenceClassification.from_pretrained(pretrained_weights, config=config)\ntokenizer = BertTokenizer.from_pretrained(pretrained_weights, do_lower_case=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"MAX_LENGTH = 320\nBATCH_SIZE = 24","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def encode_text(texts):\n    \n    # encoding\n    X = [tokenizer.encode(text, add_special_tokens=True, max_length=MAX_LENGTH) \n         for text in tqdm_notebook(texts)]\n           \n    # padding\n    X = [x + [0 for _ in range(MAX_LENGTH-len(x))] for x in X]            \n    \n    return X\n\ntest_X = encode_text(test_df['question_text'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"device = torch.device('cuda')\nmodel = model.to(device)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_dataset = torch.utils.data.TensorDataset(torch.tensor(test_X, dtype=torch.long))\ntest_sampler = torch.utils.data.SequentialSampler(test_dataset)\ntest_loader = torch.utils.data.DataLoader(test_dataset, sampler=test_sampler, batch_size=BATCH_SIZE)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_state_dict = torch.load('../input/quora-bert-models/pytorch_model.bin')\nmodel = BertForSequenceClassification.from_pretrained(pretrained_weights, state_dict=model_state_dict)\nmodel.to(device)\n\npreds = None\n\nfor batch in tqdm_notebook(test_loader, desc=\"testing\"):\n    model.eval()\n    batch = tuple(t.to(device) for t in batch)\n\n    with torch.no_grad():\n        inputs = {'input_ids': batch[0]}\n        outputs = model(**inputs)\n        logits = outputs[0]\n\n    if preds is None:\n        preds = logits.detach().cpu().numpy()\n    else:\n        preds = np.append(preds, logits.detach().cpu().numpy(), axis=0)\n\npreds = np.argmax(preds, axis=1)\n\nsubmission = test_df[['qid']]\nsubmission['prediction'] = preds\nsubmission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.sum(preds)/len(preds) # a ratio of 1","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":1}