{"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\nimport gensim\nimport nltk\nprint(os.listdir(\"../input/embeddings/GoogleNews-vectors-negative300/\"))\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":"url=\"../input/embeddings/GoogleNews-vectors-negative300/GoogleNews-vectors-negative300.bin\"\nembeddings=gensim.models.KeyedVectors.load_word2vec_format(url,binary=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5bde3e9e45411f1817138ed37664e761de8fa7d4"},"cell_type":"code","source":"# To get most similar words for a given particular word\nembeddings.most_similar(\"ravi\",topn=10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"eb150da98352af49014c152ea79858ca4537f264"},"cell_type":"code","source":"#Words that are odd man out\nembeddings.doesnt_match(['rahul','gandhi','music'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a90bf06402388ba9657be7925530c47d1a15508d"},"cell_type":"code","source":"embeddings.most_similar(positive =['king','woman'],negative=['man'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2aea2848bd090312cd44be4a5bee6e0be774ee7e"},"cell_type":"code","source":"url='https://bit.ly/2S2yXEd'\nimdb=pd.read_csv(url)\nimdb.shape","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"26b14d0be82de913036ef2fa4fbf3035c7594b7c"},"cell_type":"markdown","source":"Document classification"},{"metadata":{"trusted":true,"_uuid":"ddf6973b6bebec9c94af63e2ca6df2a58e57f3f5"},"cell_type":"code","source":"imdb.loc[0,'review']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"fd91c651c1c75ccc4bac37b991d47c5464a48387"},"cell_type":"code","source":"len(embeddings[\"A\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"68aae4f3e65b562596e3134d8b94c11b364c8bcb"},"cell_type":"code","source":"embeddings[\"slow\"]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b34a61898b8355593cc476f4935e604e9d4aef3d"},"cell_type":"code","source":"import nltk\nstopwords =nltk.corpus.stopwords.words('english')\ndocs_vectors=pd.DataFrame()\nfor doc in imdb['review'].str.lower().str.replace('[^a-z ]',''):\n    temp=pd.DataFrame()\n    for word in nltk.word_tokenize(doc):\n        if word not in stopwords:\n            try:\n                word_vec=embeddings[word]\n                temp=temp.append(pd.Series(word_vec),ignore_index=True)\n            except:\n                pass\n    doc_vector=temp.mean()\n    docs_vectors=docs_vectors.append(doc_vector,ignore_index=True)\ndocs_vectors.shape\n\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9b158e7fda257bc2344fc7ece0bb1d74630176d4"},"cell_type":"code","source":"docs_vectors","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"4fef1a6c6c9fc8287606d091c1ec7523d46af2e3"},"cell_type":"code","source":"pd.isnull(docs_vectors).sum().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d56d54757cbccde9db6afad1fc310d5aca5f2d66"},"cell_type":"code","source":"docs_vectors['sentiment']=imdb['sentiment']\ndocs_vectors=docs_vectors.dropna()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a1ef04b3709a24af8706bd522ac1dc3b246d4aef"},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import AdaBoostClassifier\ntrain_x,test_x,train_y,test_y=train_test_split(docs_vectors.drop('sentiment',axis=1),\n                                              docs_vectors['sentiment'],\n                                              test_size=0.2,\n                                              random_state=100)\ntrain_x.shape,test_x.shape,train_y.shape,test_y.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"452f2e8a2e872967d0146f126afbb49c46f3c25e"},"cell_type":"code","source":"model = AdaBoostClassifier(n_estimators=800,random_state=1)\nmodel.fit(train_x,train_y)\ntest_pred =model.predict(test_x)\nfrom sklearn.metrics import accuracy_score\naccuracy_score(test_y,test_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"400a8d977e13b00d940e4c23799c7fa21f6ea0fd"},"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}