{"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":"2022-07-26T01:58:17.059673Z","iopub.execute_input":"2022-07-26T01:58:17.060509Z","iopub.status.idle":"2022-07-26T01:58:17.093800Z","shell.execute_reply.started":"2022-07-26T01:58:17.060380Z","shell.execute_reply":"2022-07-26T01:58:17.092608Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = pd.read_csv(\"/kaggle/input/titanic/train.csv\")\ntrain_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-26T01:58:17.097616Z","iopub.execute_input":"2022-07-26T01:58:17.097981Z","iopub.status.idle":"2022-07-26T01:58:17.135569Z","shell.execute_reply.started":"2022-07-26T01:58:17.097949Z","shell.execute_reply":"2022-07-26T01:58:17.134396Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data = pd.read_csv(\"/kaggle/input/titanic/test.csv\")\ntest_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-26T01:59:23.317476Z","iopub.execute_input":"2022-07-26T01:59:23.317878Z","iopub.status.idle":"2022-07-26T01:59:23.342557Z","shell.execute_reply.started":"2022-07-26T01:59:23.317845Z","shell.execute_reply":"2022-07-26T01:59:23.341412Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(train_data.shape)\nprint(test_data.shape)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T02:00:57.934174Z","iopub.execute_input":"2022-07-26T02:00:57.934692Z","iopub.status.idle":"2022-07-26T02:00:57.950010Z","shell.execute_reply.started":"2022-07-26T02:00:57.934645Z","shell.execute_reply":"2022-07-26T02:00:57.948525Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Percentage of female survivours\nwomen = train_data.loc[train_data.Sex == 'female'][\"Survived\"]\nrate_women = sum(women)/len(women)\n\nprint(\"% of women who survived:\", rate_women)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T02:02:39.616989Z","iopub.execute_input":"2022-07-26T02:02:39.617413Z","iopub.status.idle":"2022-07-26T02:02:39.626348Z","shell.execute_reply.started":"2022-07-26T02:02:39.617376Z","shell.execute_reply":"2022-07-26T02:02:39.625066Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Percentage of Male survivours\nmen = train_data.loc[train_data.Sex == 'male'][\"Survived\"]\nrate_men = sum(men)/len(men)\n\nprint(\"% of men who survived:\", rate_men)","metadata":{"execution":{"iopub.status.busy":"2022-07-26T02:02:41.829366Z","iopub.execute_input":"2022-07-26T02:02:41.829732Z","iopub.status.idle":"2022-07-26T02:02:41.837631Z","shell.execute_reply.started":"2022-07-26T02:02:41.829702Z","shell.execute_reply":"2022-07-26T02:02:41.836642Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Random Forest model using 4 variables","metadata":{}},{"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\n\ny = train_data[\"Survived\"]\n\nfeatures = [\"Pclass\", \"Sex\", \"SibSp\", \"Parch\"]\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)\npredictions = model.predict(X_test)\n\noutput = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': predictions})\noutput.to_csv('submission.csv', index=False)\nprint(\"Your submission was successfully saved!\")","metadata":{"execution":{"iopub.status.busy":"2022-07-26T02:04:57.831129Z","iopub.execute_input":"2022-07-26T02:04:57.831527Z","iopub.status.idle":"2022-07-26T02:04:58.673028Z","shell.execute_reply.started":"2022-07-26T02:04:57.831496Z","shell.execute_reply":"2022-07-26T02:04:58.671844Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}