{"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":"2022-07-17T16:23:59.574963Z","iopub.execute_input":"2022-07-17T16:23:59.575853Z","iopub.status.idle":"2022-07-17T16:23:59.613247Z","shell.execute_reply.started":"2022-07-17T16:23:59.575708Z","shell.execute_reply":"2022-07-17T16:23:59.611908Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = pd.read_csv('/kaggle/input/titanic/train.csv')\ntest_data = pd.read_csv('/kaggle/input/titanic/test.csv')\ntrain_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-17T16:23:59.615447Z","iopub.execute_input":"2022-07-17T16:23:59.615820Z","iopub.status.idle":"2022-07-17T16:23:59.667509Z","shell.execute_reply.started":"2022-07-17T16:23:59.615786Z","shell.execute_reply":"2022-07-17T16:23:59.666654Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns\n%matplotlib inline\nsns.countplot(x='Survived', data=train_data)","metadata":{"execution":{"iopub.status.busy":"2022-07-17T16:23:59.668947Z","iopub.execute_input":"2022-07-17T16:23:59.669490Z","iopub.status.idle":"2022-07-17T16:24:01.112624Z","shell.execute_reply.started":"2022-07-17T16:23:59.669456Z","shell.execute_reply":"2022-07-17T16:24:01.111686Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.countplot(x='Survived', hue='Sex', data=train_data)","metadata":{"execution":{"iopub.status.busy":"2022-07-17T16:24:01.114569Z","iopub.execute_input":"2022-07-17T16:24:01.115103Z","iopub.status.idle":"2022-07-17T16:24:01.298789Z","shell.execute_reply.started":"2022-07-17T16:24:01.115071Z","shell.execute_reply":"2022-07-17T16:24:01.297357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"features = ['Sex', 'Pclass', 'SibSp', 'Parch']\ny = train_data['Survived']\nX = pd.get_dummies(train_data[features])\nX_test = pd.get_dummies(test_data[features])","metadata":{"execution":{"iopub.status.busy":"2022-07-17T16:24:01.300296Z","iopub.execute_input":"2022-07-17T16:24:01.300711Z","iopub.status.idle":"2022-07-17T16:24:01.321134Z","shell.execute_reply.started":"2022-07-17T16:24:01.300668Z","shell.execute_reply":"2022-07-17T16:24:01.320192Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.countplot(x='Survived', hue='Pclass', data=train_data) ","metadata":{"execution":{"iopub.status.busy":"2022-07-17T16:24:01.322224Z","iopub.execute_input":"2022-07-17T16:24:01.323015Z","iopub.status.idle":"2022-07-17T16:24:01.527761Z","shell.execute_reply.started":"2022-07-17T16:24:01.322980Z","shell.execute_reply":"2022-07-17T16:24:01.526636Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\nmodel = RandomForestClassifier(n_estimators=100, max_depth=5, random_state=1)\nmodel.fit(X, y)  \nprediction = model.predict(X_test)  \noutput = pd.DataFrame({'PassengerId':test_data.PassengerId, 'Survived':prediction})\noutput.to_csv('my_submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2022-07-17T16:24:01.528968Z","iopub.execute_input":"2022-07-17T16:24:01.529285Z","iopub.status.idle":"2022-07-17T16:24:02.222622Z","shell.execute_reply.started":"2022-07-17T16:24:01.529255Z","shell.execute_reply":"2022-07-17T16:24:02.221414Z"},"trusted":true},"execution_count":null,"outputs":[]}]}