{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.metrics import classification_report, confusion_matrix, accuracy_score\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"aa54be81c47b3c554bd316e0e4652d75d36f7f8f"},"cell_type":"code","source":"path = '../input/'\ntrain_data = pd.read_csv(path+'train.csv')\ntest = pd.read_csv(path+'test.csv')\ntrain_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"29c293dbb42bab504b48397bec84da6b6a8ab5d4"},"cell_type":"code","source":"train_data.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"889d0d8cf5c78f2aa3db7253c47f142c59bf32f1"},"cell_type":"code","source":"exclude_features = ['PassengerId','Name', 'SibSp','Cabin','Ticket']\ntrain_data = train_data.drop(exclude_features, axis= 1)\ntest = test.drop(exclude_features, axis =1)\ntrain_data = train_data.fillna(0, axis= 0)\ntest = test.fillna(0, axis=0)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5708662ab11c5275232ff0aac0772842c979bc73"},"cell_type":"code","source":"encoder = LabelEncoder()\nscaler = StandardScaler()\n\ntrain_data['Sex'] = encoder.fit_transform(train_data['Sex'])\ntrain_data['Embarked']= encoder.fit_transform(train_data['Embarked'].astype(str))\n\n\ntest['Sex'] = encoder.fit_transform(test['Sex'])\ntest['Embarked']= encoder.fit_transform(test['Embarked'].astype(str))\n\ntrain_data_features = train_data.drop('Survived', axis = 1)\ntrain_data_labels = train_data['Survived']\n\ntrain_data = scaler.fit_transform(train_data)\ntest = scaler.fit_transform(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f4ea14db9a3959d623349c307f1bd2b91a3e3cec"},"cell_type":"code","source":"model = RandomForestClassifier(n_estimators= 10)\n\nmodel.fit(train_data_features,train_data_labels)\npredictions =model.predict(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f0b1bf4c22830370d841ab6e5a9afd9e6ceaa3ab"},"cell_type":"code","source":"output = pd.read_csv(path+'gender_submission.csv')\n\nprint(confusion_matrix(output['Survived'], predictions))\nprint(classification_report(output['Survived'], predictions))\nprint(accuracy_score(output['Survived'], predictions))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"401d586effcf1c96fb7651eda573c1b5bc3a7e96"},"cell_type":"code","source":"output = pd.DataFrame({'PassengerId': output['PassengerId'], 'Survived': predictions})\noutput.to_csv('submission.csv', index=False)\n","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}