{"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\"))\nprint(os.listdir(\"../input/embeddings\"))\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":"from gensim.models import KeyedVectors\npath='../input/embeddings/GoogleNews-vectors-negative300/GoogleNews-vectors-negative300.bin'\nword2vec=KeyedVectors.load_word2vec_format(path,binary=True)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5d3a48181b38ea19bc11df8490ea4a4239356284"},"cell_type":"code","source":"url='https://raw.githubusercontent.com/AnaswaraElizabethAnt/Datasets/master/yelp_labelled.csv'\nyelp = pd.read_csv(url, sep='\\t',header=None)\nyelp.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7d682e53e7507bb5678c88c9b5e24565200c5b15"},"cell_type":"code","source":"yelp.columns = ['reviews','sentiment']\nyelp.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3814577fb24018fc76c4c913b2ffe2935e630bb0"},"cell_type":"code","source":"import nltk\nstopwords = nltk.corpus.stopwords.words('english')\ndocs_vectors = pd.DataFrame()\nfor doc in yelp['reviews'].str.lower().str.replace('[^a-z ]',''):\n    words = nltk.word_tokenize(doc)\n    words_clean = [word for word in words if word not in stopwords]\n    temp = pd.DataFrame()\n    for word in words_clean:\n        try:\n            word_vec = pd.Series(word2vec[word])\n            temp = temp.append(word_vec, ignore_index = True)\n        except:\n            pass\n    # coming out of first doc\n    temp_avg = temp.mean()\n    docs_vectors = docs_vectors.append(temp_avg, ignore_index = True)\ndocs_vectors.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e23ebb88ec39b093f66c0b7271cc65b062c2c2c6"},"cell_type":"code","source":"docs_vectors['Sentiment'] = yelp['sentiment']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a3a22e15e612c0df6f62a06fa8ca6ab39f5d1491"},"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,random_state=100)\ntrain_x.shape ,test_x.shape,train_y.shape,test_y.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"701b1656b64abf51f40261e17849da70741410ce"},"cell_type":"code","source":"model = AdaBoostClassifier(n_estimators=800, random_state=100)\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":"d6f13bb386cc2f55bb866e312a8518c9aaf77dd1"},"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}