{"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/\"))\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)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"820d08432f0a8385e8f4531937b09200e02e3da8"},"cell_type":"code","source":"import pandas as pd\nurl = 'https://raw.githubusercontent.com/skathirmani/datasets/master/imdb_sentiment.csv'\nimdb=pd.read_csv(url)\nimdb.shape\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"629a1e81b154bcf6312a6646f6d041269c515e40"},"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)\n \n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f873b1b4801fea33e67d0e426bb62a9c911fa83f"},"cell_type":"code","source":"docs_vectors['sentiment'] = imdb['sentiment']\ndocs_vectors = docs_vectors.dropna()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"96c11edf13ac9cc3d486cdb5962229a557ae3e10"},"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\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2c41efb3b4fbad06dc7b916909369d5d980b6fe6"},"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)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"75eb51a61717f1ef5523e9a7a59864d69c4597a2"},"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}