{"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/embeddings\"))\nimport codecs\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7ba748699e39db1d02b3597f9882f3fb8f6bd709"},"cell_type":"code","source":"def sample_tokens(fname, n=200, encoding='utf-8'):\n    with codecs.open(fname, 'r', encoding=encoding) as f:\n        lines = []\n\n        for i in range(n):\n            lines.append(f.readline().split(' ', 2)[0])\n    return lines","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"' | '.join(sample_tokens('../input/embeddings/glove.840B.300d/glove.840B.300d.txt'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"1a324534a07ce593b42739c0fc7abc587103a37c"},"cell_type":"code","source":"' | '.join(sample_tokens('../input/embeddings/paragram_300_sl999/paragram_300_sl999.txt'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"19a6c4199cb765862c186dea1b2010e73624c0f7"},"cell_type":"code","source":"' | '.join(sample_tokens('../input/embeddings/wiki-news-300d-1M/wiki-news-300d-1M.vec'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"406cf9d499541bb4b6652b1d64931a7718e693e9"},"cell_type":"code","source":"from gensim.models import KeyedVectors","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"86b31cd0b92472cc80483c4779ec194ebad4e326"},"cell_type":"code","source":"google_news = KeyedVectors.load_word2vec_format('../input/embeddings/GoogleNews-vectors-negative300/GoogleNews-vectors-negative300.bin', binary=True, limit=200)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2385099bf36494c0a62ff6de603eac7b966057c0"},"cell_type":"code","source":"' | '.join(google_news.vocab.keys())","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}