{"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# Any results you write to the current directory are saved as output.\n\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9013a1db1c956364280178da8e55f1ed7fe64ab4"},"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":"a184cb570c19ce1f8853a6a6a92578e9e94001b8"},"cell_type":"code","source":"url1 = 'https://raw.githubusercontent.com/skathirmani/datasets/master/yelp_labelled.csv'\nurl1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"cd83ee2419e6b8c7a6639e815052698c5646682e"},"cell_type":"code","source":"yelp = 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":"4e8cb8b1b5aaf8c3a51d211520bab9406f3b709c"},"cell_type":"code","source":"docs_vectors = pd.DataFrame()\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(' '): #for loop for goin through all words in the document\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 average\n    docs_vectors = docs_vectors.append(doc_vector, ignore_index=True)\ndocs_vectors.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"30b6cd37fbf21c308567fc074ea30ba97b29bc36"},"cell_type":"code","source":"pd.isnull(docs_vectors).sum().sum()\ndocs_vectors['sentiment'] = yelp['sentiment']\ndocs_vectors = docs_vectors.dropna()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"570e85f50e3992d2c444838855a0c0184a0de90d"},"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":"26613ce6036923f67e4aa0ccc3263bf0120c8224"},"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":{"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}