{"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\"))\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":{"_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":"80c932cb06d10f2065f5f16f758e78bf5c41e847"},"cell_type":"code","source":"url='https://raw.githubusercontent.com/gaya3reddy/Datasets/master/yelp_labelled.csv'\nimport numpy as np\nimport pandas as pd\nimport gensim\n#url='https://raw.githubusercontent.com/skathirmani/datasets/master/yelp_labelled.csv'\nyelp_reviews = pd.read_csv(url, sep='\\t',header=None)\nyelp_reviews.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"351fe4e4d50981022c03a5fa8c8c19f2394e91cf"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7c6035e3bc45146916ef4af028d3bd529ff4bc34"},"cell_type":"code","source":"yelp_reviews.columns = ['Reviews','Sentiment']\nyelp_reviews.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9cc837288cac87f8f9b28c152cd90074ddb66747"},"cell_type":"code","source":"import nltk\nstopwords = nltk.corpus.stopwords.words('english')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2b8a9cb0cdc904b5cd937d487ca213f54a389123"},"cell_type":"code","source":"docs_vectors = pd.DataFrame()\n\nfor doc in yelp_reviews['Reviews'].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()   # Column mean of each doc\n    docs_vectors = docs_vectors.append(doc_vector, ignore_index=True)\ndocs_vectors.shape\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9c9f71d281da0c8b16b33331e2e9169ab40981a3"},"cell_type":"code","source":"docs_vectors['Sentiment'] = yelp_reviews['Sentiment']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5b214f345bf2a4c778834456a8b2265107004b75"},"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,random_state=1)\ntrain_x.shape ,test_x.shape,train_y.shape,test_y.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ea1afbc8fb6a277881e0fd996cbd22e3294ae339"},"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":"376e56caf4abc5063ade17cfcfbfe778b8ab4055"},"cell_type":"code","source":"\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5fd0b8af748a4a4ef78701c450d2142e0c422b2e"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"23ad3797850df29568058cc8b1e5fc237b30a776"},"cell_type":"code","source":"\n","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}