{"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 5GB 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":"2022-07-20T12:03:05.430827Z","iopub.execute_input":"2022-07-20T12:03:05.431462Z","iopub.status.idle":"2022-07-20T12:03:05.440295Z","shell.execute_reply.started":"2022-07-20T12:03:05.431412Z","shell.execute_reply":"2022-07-20T12:03:05.438879Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = pd.read_csv(\"/kaggle/input/titanic/train.csv\")","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","execution":{"iopub.status.busy":"2022-07-20T12:03:05.442714Z","iopub.execute_input":"2022-07-20T12:03:05.443216Z","iopub.status.idle":"2022-07-20T12:03:05.474132Z","shell.execute_reply.started":"2022-07-20T12:03:05.443168Z","shell.execute_reply":"2022-07-20T12:03:05.473377Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-20T12:03:05.475575Z","iopub.execute_input":"2022-07-20T12:03:05.475999Z","iopub.status.idle":"2022-07-20T12:03:05.508582Z","shell.execute_reply.started":"2022-07-20T12:03:05.475952Z","shell.execute_reply":"2022-07-20T12:03:05.507822Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data = pd.read_csv(\"/kaggle/input/titanic/test.csv\")","metadata":{"execution":{"iopub.status.busy":"2022-07-20T12:03:05.511239Z","iopub.execute_input":"2022-07-20T12:03:05.511534Z","iopub.status.idle":"2022-07-20T12:03:05.522630Z","shell.execute_reply.started":"2022-07-20T12:03:05.511507Z","shell.execute_reply":"2022-07-20T12:03:05.521715Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-20T12:03:05.524355Z","iopub.execute_input":"2022-07-20T12:03:05.524863Z","iopub.status.idle":"2022-07-20T12:03:05.543251Z","shell.execute_reply.started":"2022-07-20T12:03:05.524818Z","shell.execute_reply":"2022-07-20T12:03:05.542057Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"women = train_data.loc[train_data.Sex == 'female'][\"Survived\"]\nrate_women = sum(women)/len(women)\nprint(\"% of women who survived:\", rate_women)","metadata":{"execution":{"iopub.status.busy":"2022-07-20T12:03:05.544945Z","iopub.execute_input":"2022-07-20T12:03:05.545599Z","iopub.status.idle":"2022-07-20T12:03:05.556559Z","shell.execute_reply.started":"2022-07-20T12:03:05.545550Z","shell.execute_reply":"2022-07-20T12:03:05.555346Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"men = train_data.loc[train_data.Sex == 'male'][\"Survived\"]\nrate_men = sum(men)/len(men)\nprint(\"% of men who survived:\", rate_men)","metadata":{"execution":{"iopub.status.busy":"2022-07-20T12:03:05.559613Z","iopub.execute_input":"2022-07-20T12:03:05.560418Z","iopub.status.idle":"2022-07-20T12:03:05.569705Z","shell.execute_reply.started":"2022-07-20T12:03:05.560357Z","shell.execute_reply":"2022-07-20T12:03:05.568527Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(men), sum(men), len(women), sum(women)","metadata":{"execution":{"iopub.status.busy":"2022-07-20T12:03:05.596779Z","iopub.execute_input":"2022-07-20T12:03:05.597175Z","iopub.status.idle":"2022-07-20T12:03:05.605823Z","shell.execute_reply.started":"2022-07-20T12:03:05.597139Z","shell.execute_reply":"2022-07-20T12:03:05.604495Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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)\nmodel.score\n\noutput = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': predictions})\noutput.to_csv('my_submission.csv', index=None)\nprint(\"Your submission was successfully saved!\")","metadata":{"execution":{"iopub.status.busy":"2022-07-20T12:31:58.578833Z","iopub.execute_input":"2022-07-20T12:31:58.579350Z","iopub.status.idle":"2022-07-20T12:31:58.766466Z","shell.execute_reply.started":"2022-07-20T12:31:58.579315Z","shell.execute_reply":"2022-07-20T12:31:58.765542Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# import csv\n# with open('output.csv', 'r') as file:\n#     reader = csv.reader(file)\n#     for row in reader:\n#         print(row)","metadata":{"execution":{"iopub.status.busy":"2022-07-20T12:32:01.165251Z","iopub.execute_input":"2022-07-20T12:32:01.165794Z","iopub.status.idle":"2022-07-20T12:32:01.170009Z","shell.execute_reply.started":"2022-07-20T12:32:01.165758Z","shell.execute_reply":"2022-07-20T12:32:01.168987Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pd.read_csv(\"my_submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2022-07-20T12:32:01.282029Z","iopub.execute_input":"2022-07-20T12:32:01.282557Z","iopub.status.idle":"2022-07-20T12:32:01.295358Z","shell.execute_reply.started":"2022-07-20T12:32:01.282522Z","shell.execute_reply":"2022-07-20T12:32:01.294510Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}