{"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/GoogleNews-vectors-negative300\"))\nimport gensim\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7f961fdb0bbaef1932542270743f4c724462c206"},"cell_type":"code","source":"import nltk","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":"a6e008ec1117df2da28a164a8b562991a883d5c6"},"cell_type":"code","source":"# embeddings.most_similar('hyundai', topn=10)\n# embeddings.doesnt_match(['rahul','gandhi','sonia','modi','sachin'])\n# embeddings.most_similar(positive=['king','woman'],negative=['man'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"becedde7f1854a9897928b6a5957887a498dbbc5"},"cell_type":"code","source":"url='https://bit.ly/2U7mLmC'\nyelp = pd.read_csv(url,sep=\"\\t\",delimiter=\"\\t\")\nyelp.reset_index(level=0, inplace=True)\nyelp.columns=[\"review\",\"sentiment\"]\nyelp.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"badad15b0e5e9ad4358814e59b5abf56ea98c3bf"},"cell_type":"code","source":"yelp.loc[1,'review']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f300c38e702bc81b309114233c70b5e2fa9aa9de"},"cell_type":"code","source":"embeddings['Not'].shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"4495682c6517986bc1627648bc9ab8ed3c25d453"},"cell_type":"code","source":"docs_vectors = pd.DataFrame()\nimport nltk\nstopwords=nltk.corpus.stopwords.words('english')\nfor doc in yelp['review'].str.lower().str.replace('[^a-z ]', ''):\n    temp = pd.DataFrame()\n    for word in doc.split(' '):\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    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"20ea51cce63445a6cce8188324da31fcb0aebc39"},"cell_type":"code","source":"docs_vectors","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a09e4913e07f4fc1fc90349004c0c9e8003fe3b2"},"cell_type":"code","source":"pd.isnull(docs_vectors).sum().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"71e9876e0f85e6b987e84ea6119e1de2ec78d9bc"},"cell_type":"code","source":"docs_vectors['sentiment'] = yelp['sentiment']\ndocs_vectors = docs_vectors.dropna()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"49062652595e04c059a554d7490077c30318518b"},"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\n                                                  \n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ce52bf992969373f32177782c247c2284f2fe26c"},"cell_type":"code","source":"model = AdaBoostClassifier(n_estimators=500, 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":"637b2c2cc4001d7ec9900ece355e2832c9047dec"},"cell_type":"code","source":" ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"aed38c23f49f78ba93cfb0006dcb64d8bb4d723c"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d04fd5a32ea0784ac3ccc4fc16ea811088596d99"},"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}