{"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\"))\nprint(os.listdir(\"../input/embeddings\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"from gensim.models import KeyedVectors\npath='../input/embeddings/GoogleNews-vectors-negative300/GoogleNews-vectors-negative300.bin'\nword2vec=KeyedVectors.load_word2vec_format(path,binary=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"87516c97482e5a94a3dc02a660e95da93790d65a"},"cell_type":"code","source":"word2vec['politics']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"35ac70a0300b8bd598a2755ac9a843b3492ec23f"},"cell_type":"code","source":"data=pd.read_csv('../input/train.csv')\ntrain=data.sample(10000)\nvalidate=data.sample(20000)\ndel data","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0654a348462e3d81cd7948eb075d9a5b2964045d"},"cell_type":"code","source":"def get_doc_vector(doc):\n    words=doc.split(' ')\n    df_words_vec=pd.DataFrame()\n    for word in words:\n        try:\n            word_vec=word2vec[word]\n            #print(word)\n            #print(word_vec[:5])\n           # df_words_vec[word]=word_vec\n            df_words_vec=df_words_vec.append(pd.Series(word_vec), ignore_index=True)\n        except:\n            pass\n    return df_words_vec.mean()\n\n\ndf_docs_vector=train['question_text'].str.lower().apply(get_doc_vector)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f1db17f8c3d9a020f558b821b002628ebec98eed"},"cell_type":"code","source":"df_docs_vector.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b0b63e3d4b443aa14b52aff7fb661b7ae3613a8e"},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}