{"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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Imports"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"from fastai.text import *\nfrom fastai.datasets import URLs\nimport torch\nimport pandas as pd\nimport numpy as np\nimport logging\nimport os\nimport random","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Utils"},{"metadata":{"trusted":true},"cell_type":"code","source":"!( head -5000 ../input/train.csv ) > train.csv # reducing size to train to quickly run the entire code and submit \n!cp ../input/test.csv test.csv\ntrain_file = 'train.csv'\ntest_file = 'test.csv'\nfolder = '.'","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Load language model"},{"metadata":{"trusted":true},"cell_type":"code","source":"data_lm = TextLMDataBunch.from_csv(folder, \n                                   train_file, \n                                   text_cols='question_text', \n                                   label_cols='target')\nassert data_lm.device == torch.device('cuda')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Save language model"},{"metadata":{"trusted":true},"cell_type":"code","source":"data_lm.save('data_lm_export.pkl')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Load classifier model"},{"metadata":{"trusted":true},"cell_type":"code","source":"data_clas = TextClasDataBunch.from_csv(folder, \n                                       train_file,\n                                       test=test_file,\n                                       valid_pct=0.1,\n                                       vocab=data_lm.train_ds.vocab, \n                                       bs=32,\n                                       text_cols='question_text', \n                                       label_cols='target')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Save classifier model"},{"metadata":{"trusted":true},"cell_type":"code","source":"data_clas.save('data_clas_export.pkl')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Fine tune language model"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Language model trainer (66 min with whole training set)\nlearn = language_model_learner(data_lm, AWD_LSTM,\n                           drop_mult=0.5)\nlearn.fit_one_cycle(1 , 1e-2)\nlearn.save_encoder('encoder')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Fine tune classifier model"},{"metadata":{"trusted":true},"cell_type":"code","source":"learn_classifier = text_classifier_learner(data_clas, AWD_LSTM, drop_mult=0.5)\nlearn_classifier.load_encoder('encoder')\nlearn_classifier.fit_one_cycle(1, 1e-2) ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Prediction"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Language model prediction\nlearn.predict(\"This is a review about\", n_words=10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Classifier model prediction\nlearn_classifier.predict(\"This is a review about a question\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds,_ = learn_classifier.get_preds(ds_type=DatasetType.Test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"result_df = pd.read_csv(\"../input/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"result_df.prediction = preds.numpy()[:, 0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"result_df.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"result_df['prediction'] = (result_df['prediction'] > 0.98).astype(int)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"result_df.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}