{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import 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/\"))# 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","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":"73e41fc211cf11da1aa22960d9c612a4a97836fb"},"cell_type":"code","source":"import pandas as pd\nurl1 = 'https://raw.githubusercontent.com/skathirmani/datasets/master/imdb_sentiment.csv'\nimdb=pd.read_csv(url1,encoding='utf-8')\nimdb.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"6b14004804f7c25a898ad0d85698ec1cf179da5a"},"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":"2f4d8da93e92f8c927ceb45a4c556fc40f2a39c2"},"cell_type":"code","source":"docs_vectors['sentiment'] = imdb['sentiment']\ndocs_vectors = docs_vectors.dropna()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e136d349c37e86a065befd0d33839d0cb3c14316"},"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":"6e902fdd0a173597e1a71cd921e7614ae65ddc5a"},"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":"9a2bd1252e47cc4df045549fba95be010d46af38"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ca159c4e528cb9e76eb2dd7d840b43059cc63b5d"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0c82217c11fd6ae78c4e0dca66498e30bceb7cd0"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"846f8fc85d63394feb05259eb7a5e2d2fdc71c14"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"04025cea34e868300cbb874ef867fab07b740633"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8107a9d4f10da4e783044dd16777a7ad5ab5312c"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"880a43332feacf5161210e49c285651d1336045c"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a85ef881fa22da1969be533f942c733de6ef51d1"},"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}