{"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\"))\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":"test_df = pd.read_csv('../input/test.csv')\n# parse errorが発生したため、下記URLを参考にengine='python'を変数に追加\n# https://www.shanelynn.ie/pandas-csv-error-error-tokenizing-data-c-error-eof-inside-string-starting-at-line/\ntrain_df = pd.read_csv('../input/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9a514d3fea96cdad30d0eb9ad5272679feaa935e"},"cell_type":"code","source":"train_df.count()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"0803db20b73d503119acb1819aaa1141b69aac47"},"cell_type":"markdown","source":"# 特徴量の抽出"},{"metadata":{"trusted":true,"_uuid":"e0b54e192bddbb919d1f178f366dc6e5f71b4583"},"cell_type":"code","source":"from sklearn.feature_extraction.text import CountVectorizer\nfrom sklearn.ensemble import RandomForestClassifier\n# BoWを作るための単語抽出器\nvectorizer = CountVectorizer(min_df=2, stop_words='english')\n\nall_content = list(train_df['question_text']) + list(test_df['question_text'])\ntrain_content = list(train_df['question_text'])\ntest_content = list(test_df['question_text'])\n# 訓練セット、テストセットすべてのBoW行列をベースとして作成\nX_feat = vectorizer.fit(all_content)\n\n# 訓練セットのBoWを作成\nX_train = vectorizer.transform(train_content)\nX_test = vectorizer.transform(test_content)\ny_train = train_df['target']","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8408bb737dcf24a48b9b2f2ac6221517d5629e83"},"cell_type":"markdown","source":"# 分類器による学習"},{"metadata":{"trusted":true,"_uuid":"74e348cf920277d7366eef5dbb29ec413941aa1e"},"cell_type":"code","source":"# ランダムフォレスト\nfrom sklearn.ensemble import RandomForestClassifier\nRF = RandomForestClassifier(min_samples_leaf=3, random_state=0)\nRF.fit(X_train, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"6fe9a19f68f842daeaefe225dface6ebfe38270f"},"cell_type":"code","source":"y_test = (RF.predict_proba(X_test)[:, 0] < 0.78).astype(int)\nsub = pd.read_csv('../input/sample_submission.csv')\nsub['prediction'] = list(y_test)\nsub.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b8b79a9185999e5e09410fce5dfbf21ed16e44e5"},"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}