{"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\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":{"trusted":true,"_uuid":"7f410b2d567471bbd70b598b40b9d7be2afd9f00"},"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":"27341140712e04ac2609fd474a919ab4f93eada3"},"cell_type":"code","source":"url = 'https://raw.githubusercontent.com/vivektop/Unstructrured-Data-Anaysis/master/yelp_labelled.csv'\nyelp = pd.read_csv(url,sep='\\t',header=None)\nyelp = yelp.rename(columns={0:'Review', 1: 'Sentiment'})\nyelp.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"be762c4a83270655d8fd2f4f71142c8e7961a84e"},"cell_type":"code","source":"import nltk\ndocs_vectors = pd.DataFrame() # Final DF\nstopwords = nltk.corpus.stopwords.words('english')\nfor doc in yelp['Review'].str.lower().str.replace('[^a-z ]',''): # For every document\n    temp = pd.DataFrame() # temp df for every word\n    for word in doc.split(' '):\n        if word not in stopwords: #one word at a time\n            try:\n                word_vec = embeddings[word] #If available in embeddings append it to temp\n                temp = temp.append(pd.Series(word_vec),ignore_index = True) # convert to seriesto append easier\n            except: # if not then pass\n                pass\n    doc_vector = temp.mean() # Find the column sum \n    docs_vectors = docs_vectors.append(doc_vector,ignore_index = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0164c6c741e5e2d51358c8824c10f584f044cc8b"},"cell_type":"code","source":"docs_vectors['sentiment'] = yelp['Sentiment']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"41c7034b1717bc1ad22609af2219b5e355c6ac6b"},"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":"9fbc17543903080c555828e1f759c1e6a1906fcd"},"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":"60b703261c6576bebf6eeffe7e707128f416fcd9"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"33ba9e7af8dc732fb8f1a3b47d1eacb58fefd33a"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"076a7066e78c2b64f97b3f38079cf02537c8c55f"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"13d7201a0b3053ff5f174d3c890590cbfcf4fa93"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"68a8cdfa3884976d9c0e4087ed633d089f855659"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","collapsed":true,"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":false},"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}