{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"610688e5-81e2-93a4-bcae-5c5ba681ef8f"},"outputs":[],"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\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.model_selection import train_test_split\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\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"b4772b2d-0a82-d03b-b00e-7a4ddda4eae2"},"outputs":[],"source":"train_df = pd.read_csv(\"../input/train.csv\")\ntest_df = pd.read_csv(\"../input/test.csv\")"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"7ef692e1-e2c9-658b-1226-1dfff9af0ee7"},"outputs":[],"source":"train_df.head()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"ee08fe79-59ba-4728-fe85-4ccbd4d2c16a"},"outputs":[],"source":"train_df.info()\ntest_df.info()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"dae8e71f-fd2c-6a0a-ca5c-452b47131c4f"},"outputs":[],"source":"test_df.head()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"25ec110c-aaef-da22-5572-da8f358a3e14"},"outputs":[],"source":"train = train_df.values\ntest = test_df.values"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"ef92c586-5b0c-8975-3b04-812ff1f2b74c"},"outputs":[],"source":"X_train, X_test, y_train, y_test = train_test_split(\n    train[0::,1::], train[0::,0], test_size=0.2, random_state=0)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"ee11465e-12b7-106c-1ada-8c0411f873a9"},"outputs":[],"source":"forest = RandomForestClassifier(n_estimators = 500)\nforest = forest.fit(X_train,y_train)\nforest_output = forest.predict(X_test)\n\nprint(accuracy_score(y_test, forest_output))"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"6ee6ea1b-d6c8-c439-60bc-53249615e0fc"},"outputs":[],"source":""}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.5.2"}},"nbformat":4,"nbformat_minor":0}