{"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)\n\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":"train_toxic = pd.read_csv(\"../input/jigsaw-multilingual-toxic-comment-classification/jigsaw-toxic-comment-train.csv\")\ntrain_unintended = pd.read_csv(\"../input/jigsaw-multilingual-toxic-comment-classification/jigsaw-unintended-bias-train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_col = 'comment_text'\ny_cols = ['toxic', 'severe_toxic', 'obscene', 'threat', 'insult', 'identity_hate']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.feature_extraction.text import TfidfVectorizer\n\nvectorizer = TfidfVectorizer()\n\nX = vectorizer.fit_transform(train_toxic[x_col])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import cross_val_score\nfrom sklearn.linear_model import SGDClassifier\n\nsc = []\nfor i in range(len(y_cols)):\n    y = train_toxic[y_cols[i]]\n    model = SGDClassifier(loss=\"hinge\", penalty=\"l2\", max_iter=5)\n    scores = cross_val_score(model, X, y, cv=3)\n    sc.append(scores.mean()*100)\n    print(str(y_cols[i]) + \" : \" + str(scores.mean()*100))\n    print(scores)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sum(sc) / len(sc)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}