{"cells":[{"metadata":{},"cell_type":"markdown","source":"# This notebook is for beginners who want to understand basic machine learning modelling"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-input":true,"_kg_hide-output":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 20GB 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":"full_train = pd.read_csv(\"/kaggle/input/riiid-test-answer-prediction/train.csv\",nrows=20000)\nquestions = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/questions.csv')\nlectures = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/lectures.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"full_train = full_train.dropna()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"full_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"full_train = full_train[['row_id','user_id','content_id','content_type_id','answered_correctly']]\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"feature_col = ['row_id','user_id','content_id','content_type_id']\ntarget_col = ['answered_correctly']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = full_train[feature_col]\ny = full_train[target_col]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\nrfclf = RandomForestClassifier()\nrfclf.fit(X_train,y_train)\npred = rfclf.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import roc_auc_score\nprint(roc_auc_score(y_test,pred))","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"from xgboost import XGBClassifier\nxgbclf = XGBClassifier()\nxgbclf.fit(X_train,y_train)\nxgb_pred = xgbclf.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(roc_auc_score(y_test,xgb_pred))","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"from sklearn.neural_network import MLPClassifier\nmlp = MLPClassifier()\nmlp.fit(X_train,y_train)\nmlp_pred = mlp.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(roc_auc_score(y_test,mlp_pred))","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}