{"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/\"))\n\n# Any results you write to the current directory are saved as output.\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":"import gensim\nurl = \"../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":"713e416a8eee2a4c5cbafe526699cf55b5ad40c8"},"cell_type":"code","source":"import pandas as pd\nurl = 'https://raw.githubusercontent.com/vbethams/Datasets/master/reviews.csv'\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c2721b745deea51c7069b4bf4df679ca164adb5f"},"cell_type":"code","source":"imdb= pd.read_csv('https://raw.githubusercontent.com/vbethams/Datasets/master/reviews.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"89ebb862aff960d02d0ce594305bd9dda90591e1"},"cell_type":"code","source":"docs_vectors = pd.DataFrame()\nimport nltk\nstopwords = nltk.corpus.stopwords.words('english')\nfor doc in imdb['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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"076f930c41fbf11a5fca760b196b90a3be9d4014"},"cell_type":"code","source":"docs_vectors.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"97248fcda46af8fc74ac23c07e3decc434737827"},"cell_type":"code","source":"docs_vectors['sentiment'] = imdb['sentiment']\ndocs_vectors = docs_vectors.dropna()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"6b2cfb95a8f3b1c9247721cf6fe3c902c8e7fc43"},"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'],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":"a80d53bf0d469b1b1e027450590f5f4fe7a9249d"},"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}