{"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)\nimport gensim\nimport nltk\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/\"))\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":"9dbd4336d68f48401d6fd5a15d4dccbc74214b4a"},"cell_type":"code","source":"url1 = 'https://raw.githubusercontent.com/skathirmani/datasets/master/yelp_labelled.csv'\nyelp = pd.read_csv(url1, sep = '\\t',names=['review','sentiment'])\nyelp = yelp.drop(yelp.index[0])\nyelp.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c483f7012335f86d3d22507a4c23772760d4504f"},"cell_type":"code","source":"stopwords = nltk.corpus.stopwords.words('english')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"97285cdce57701bca253717ad61b3394ed55059c"},"cell_type":"code","source":"docs_vectors = pd.DataFrame()\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    #print(doc_vector)\n    docs_vectors = docs_vectors.append(doc_vector,ignore_index=True)\ndocs_vectors.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7d992e9fa5e4eb1364cfcc79d4566b2f355077b7"},"cell_type":"code","source":"docs_vectors['sentiment'] = yelp['sentiment']\ndocs_vectors = docs_vectors.dropna()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ef285060eef50984d3c9684cf1612214d0583b9d"},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import AdaBoostClassifier\nfrom sklearn.metrics import accuracy_score\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":"7ddb4cd8357eb941e4cf66eb071f89317f168b98"},"cell_type":"code","source":"model = AdaBoostClassifier(n_estimators=500, random_state=100)\nmodel.fit(train_x,train_y)\nmodel_pred = model.predict(test_x)\naccuracy_score(test_y,model_pred)","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}