{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom sklearn.multiclass import OneVsRestClassifier\nfrom sklearn.linear_model import SGDClassifier\nfrom sklearn import metrics\nfrom sklearn.metrics import f1_score,precision_score,recall_score\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from scipy import sparse\nx_train=sparse.load_npz('../input/stackoverflow-featurizing-preprocessed-data-tags/train_bi_gram.npz')\nx_test=sparse.load_npz('../input/stackoverflow-featurizing-preprocessed-data-tags/test_ni_gram.npz')\ny_train=sparse.load_npz('../input/stackoverflow-featurizing-preprocessed-data-tags/tags_vec_train.npz')\ny_test=sparse.load_npz('../input/stackoverflow-featurizing-preprocessed-data-tags/tags_vec_test.npz')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.shape,x_test.shape,y_train.shape,y_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"classifier=OneVsRestClassifier(SGDClassifier(loss='log',alpha=0.00001,penalty='l1'),n_jobs=-1)\nclassifier.fit(x_train,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.externals import joblib\njoblib.dump(classifier,'logistic_reg_equal_wt.pkl')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# prediction=classifier.predict(x_test)\n# metrics.accuracy(y_test,prediction)\n# f1_score(y_test,prediction,average='macro')\n# f1_score(y_test,prediction,average='micro')\n# metrics.hamming_loss(y_test,prediction)\n# metrics.classification_report(y_test,prediction)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}