{"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_minor":4,"nbformat":4,"cells":[{"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-07-07T15:21:16.120883Z","iopub.execute_input":"2022-07-07T15:21:16.121479Z","iopub.status.idle":"2022-07-07T15:21:16.158290Z","shell.execute_reply.started":"2022-07-07T15:21:16.121374Z","shell.execute_reply":"2022-07-07T15:21:16.157416Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import accuracy_score, precision_score, recall_score","metadata":{"execution":{"iopub.status.busy":"2022-07-07T15:21:16.160352Z","iopub.execute_input":"2022-07-07T15:21:16.161093Z","iopub.status.idle":"2022-07-07T15:21:17.919954Z","shell.execute_reply.started":"2022-07-07T15:21:16.160998Z","shell.execute_reply":"2022-07-07T15:21:17.918809Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = pd.read_csv('../input/titanic/train.csv')\ntest_data = pd.read_csv('../input/titanic/test.csv')","metadata":{"execution":{"iopub.status.busy":"2022-07-07T15:21:17.923438Z","iopub.execute_input":"2022-07-07T15:21:17.923933Z","iopub.status.idle":"2022-07-07T15:21:17.957073Z","shell.execute_reply.started":"2022-07-07T15:21:17.923887Z","shell.execute_reply":"2022-07-07T15:21:17.955554Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-07T15:21:17.958805Z","iopub.execute_input":"2022-07-07T15:21:17.959505Z","iopub.status.idle":"2022-07-07T15:21:17.989124Z","shell.execute_reply.started":"2022-07-07T15:21:17.959456Z","shell.execute_reply":"2022-07-07T15:21:17.987936Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.info()","metadata":{"execution":{"iopub.status.busy":"2022-07-07T15:21:17.992329Z","iopub.execute_input":"2022-07-07T15:21:17.993036Z","iopub.status.idle":"2022-07-07T15:21:18.023638Z","shell.execute_reply.started":"2022-07-07T15:21:17.993002Z","shell.execute_reply":"2022-07-07T15:21:18.022071Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2022-07-07T15:21:18.025136Z","iopub.execute_input":"2022-07-07T15:21:18.025567Z","iopub.status.idle":"2022-07-07T15:21:18.037478Z","shell.execute_reply.started":"2022-07-07T15:21:18.025519Z","shell.execute_reply":"2022-07-07T15:21:18.036343Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-07T15:21:18.039258Z","iopub.execute_input":"2022-07-07T15:21:18.040575Z","iopub.status.idle":"2022-07-07T15:21:18.059356Z","shell.execute_reply.started":"2022-07-07T15:21:18.040529Z","shell.execute_reply":"2022-07-07T15:21:18.058193Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y = train_data['Survived']\n\nfeatures = ['Pclass', 'Sex', 'SibSp', 'Parch']\n\nX = pd.get_dummies(train_data[features])\nX_test = pd.get_dummies(test_data[features])\n\nmodel = RandomForestClassifier(n_estimators=100, max_depth=5, random_state=1)\nmodel.fit(X, y)\n\npredictions = model.predict(X_test)","metadata":{"execution":{"iopub.status.busy":"2022-07-07T15:21:18.060932Z","iopub.execute_input":"2022-07-07T15:21:18.063074Z","iopub.status.idle":"2022-07-07T15:21:18.327510Z","shell.execute_reply.started":"2022-07-07T15:21:18.063024Z","shell.execute_reply":"2022-07-07T15:21:18.326722Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"output = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': predictions})\noutput.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2022-07-07T15:21:18.329344Z","iopub.execute_input":"2022-07-07T15:21:18.330163Z","iopub.status.idle":"2022-07-07T15:21:18.339502Z","shell.execute_reply.started":"2022-07-07T15:21:18.330120Z","shell.execute_reply":"2022-07-07T15:21:18.338716Z"},"trusted":true},"execution_count":null,"outputs":[]}]}