{"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":"markdown","source":"<div style=\"border-radius:10px;\n            border: #0b0265 solid;\n           background-color:#e8efff;\n           font-size:110%;\n           letter-spacing:0.5px;\n            text-align: center\">\n\n<center><h1 style=\"padding: 25px 0px; color:#0b0265; font-weight: bold; font-family: Cursive\">\nTitanic 🚢</h1></center>\n<center><h3 style=\"padding-bottom: 25px; color:#0b0265; font-weight: bold; font-style:italic; font-family: Cursive\">\n(With Ensemble algorithms)</h3></center>     \n\n</div>","metadata":{}},{"cell_type":"code","source":"import numpy as np \nimport pandas as pd \n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-07-15T09:35:41.846752Z","iopub.execute_input":"2022-07-15T09:35:41.847395Z","iopub.status.idle":"2022-07-15T09:35:41.856291Z","shell.execute_reply.started":"2022-07-15T09:35:41.847361Z","shell.execute_reply":"2022-07-15T09:35:41.855155Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Import Libraries","metadata":{}},{"cell_type":"code","source":"import numpy as np \nimport pandas as pd\n\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.preprocessing import MinMaxScaler\nfrom sklearn.preprocessing import RobustScaler\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.model_selection import KFold\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.model_selection import GridSearchCV, RandomizedSearchCV\n\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.metrics import average_precision_score\nfrom sklearn.metrics import precision_recall_curve\nfrom sklearn.metrics import f1_score\nfrom sklearn.metrics import roc_curve, roc_auc_score\nfrom sklearn.metrics import auc\nfrom sklearn.metrics import recall_score\nfrom sklearn.metrics import precision_score\n\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.linear_model import Ridge, Lasso, ElasticNet\nfrom sklearn.linear_model import LassoCV, Ridge, ElasticNet, LogisticRegressionCV\n\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.naive_bayes import BernoulliNB, GaussianNB\nfrom sklearn.neural_network import MLPClassifier\nfrom sklearn.svm import SVC\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.ensemble import ExtraTreesClassifier\nfrom sklearn.ensemble import GradientBoostingClassifier\nfrom sklearn.ensemble import StackingClassifier\nfrom xgboost import XGBClassifier\n\nfrom imblearn.over_sampling import SMOTE\n\nfrom statsmodels.stats.outliers_influence import variance_inflation_factor\n\nimport warnings\nwarnings.filterwarnings(\"ignore\")","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:41.879521Z","iopub.execute_input":"2022-07-15T09:35:41.879913Z","iopub.status.idle":"2022-07-15T09:35:43.676043Z","shell.execute_reply.started":"2022-07-15T09:35:41.879881Z","shell.execute_reply":"2022-07-15T09:35:43.674873Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Define Functions","metadata":{}},{"cell_type":"code","source":"def checkVIF(X):\n    vif = pd.DataFrame()\n    vif['Features'] = X.columns\n    vif['VIF'] = [variance_inflation_factor(X.values, i) for i in range(X.shape[1])]\n    vif['VIF'] = round(vif['VIF'], 2)\n    vif = vif.sort_values(by = \"VIF\", ascending = False,)\n    return(vif)\n\n# ------------------------------------------------------------------\ndef Cls_model_RndSrch_Tune(model, Data, X, y, params):\n    \n    clf = RandomizedSearchCV(model, params, scoring ='accuracy', cv = 5, n_jobs=-1, random_state=100)\n    clf.fit(X, y)\n    \n    print(\"best score is :\" , clf.best_score_)\n    print(\"best estimator is :\" , clf.best_estimator_)\n    print(\"best Params is :\" , clf.best_params_)\n    \n    return (clf.best_score_)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:43.678740Z","iopub.execute_input":"2022-07-15T09:35:43.679045Z","iopub.status.idle":"2022-07-15T09:35:43.688646Z","shell.execute_reply.started":"2022-07-15T09:35:43.679016Z","shell.execute_reply":"2022-07-15T09:35:43.687531Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Data Understanding","metadata":{}},{"cell_type":"code","source":"train_data = pd.read_csv(\"/kaggle/input/titanic/train.csv\")\ntrain_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:43.690836Z","iopub.execute_input":"2022-07-15T09:35:43.691434Z","iopub.status.idle":"2022-07-15T09:35:43.752581Z","shell.execute_reply.started":"2022-07-15T09:35:43.691386Z","shell.execute_reply":"2022-07-15T09:35:43.751813Z"},"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":"2022-07-15T09:35:43.753899Z","iopub.execute_input":"2022-07-15T09:35:43.754317Z","iopub.status.idle":"2022-07-15T09:35:43.780738Z","shell.execute_reply.started":"2022-07-15T09:35:43.754273Z","shell.execute_reply":"2022-07-15T09:35:43.779750Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(train_data.shape)\nprint(test_data.shape)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:43.782014Z","iopub.execute_input":"2022-07-15T09:35:43.782297Z","iopub.status.idle":"2022-07-15T09:35:43.787014Z","shell.execute_reply.started":"2022-07-15T09:35:43.782270Z","shell.execute_reply":"2022-07-15T09:35:43.785817Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.columns","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:43.788493Z","iopub.execute_input":"2022-07-15T09:35:43.789238Z","iopub.status.idle":"2022-07-15T09:35:43.800670Z","shell.execute_reply.started":"2022-07-15T09:35:43.789175Z","shell.execute_reply":"2022-07-15T09:35:43.799642Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.info()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:43.801856Z","iopub.execute_input":"2022-07-15T09:35:43.802320Z","iopub.status.idle":"2022-07-15T09:35:43.827874Z","shell.execute_reply.started":"2022-07-15T09:35:43.802288Z","shell.execute_reply":"2022-07-15T09:35:43.827102Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data.info()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:43.829980Z","iopub.execute_input":"2022-07-15T09:35:43.830439Z","iopub.status.idle":"2022-07-15T09:35:43.846496Z","shell.execute_reply.started":"2022-07-15T09:35:43.830392Z","shell.execute_reply":"2022-07-15T09:35:43.845448Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.countplot(x = \"Survived\", data = train_data)\ntrain_data.loc[:, 'Survived'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:43.848113Z","iopub.execute_input":"2022-07-15T09:35:43.848565Z","iopub.status.idle":"2022-07-15T09:35:44.120236Z","shell.execute_reply.started":"2022-07-15T09:35:43.848514Z","shell.execute_reply":"2022-07-15T09:35:44.119296Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.describe().T","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:44.121491Z","iopub.execute_input":"2022-07-15T09:35:44.121813Z","iopub.status.idle":"2022-07-15T09:35:44.160916Z","shell.execute_reply.started":"2022-07-15T09:35:44.121775Z","shell.execute_reply":"2022-07-15T09:35:44.159821Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"p = train_data.hist(figsize = (20,20))","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:44.162052Z","iopub.execute_input":"2022-07-15T09:35:44.162488Z","iopub.status.idle":"2022-07-15T09:35:45.599584Z","shell.execute_reply.started":"2022-07-15T09:35:44.162455Z","shell.execute_reply":"2022-07-15T09:35:45.598616Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Preproccessing","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize=(12,10), dpi= 80)\nax = sns.boxplot(data=train_data, orient=\"h\", palette=\"husl\", whis=1.5)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:45.600897Z","iopub.execute_input":"2022-07-15T09:35:45.601198Z","iopub.status.idle":"2022-07-15T09:35:45.873180Z","shell.execute_reply.started":"2022-07-15T09:35:45.601168Z","shell.execute_reply":"2022-07-15T09:35:45.872236Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:45.874521Z","iopub.execute_input":"2022-07-15T09:35:45.874832Z","iopub.status.idle":"2022-07-15T09:35:45.883411Z","shell.execute_reply.started":"2022-07-15T09:35:45.874803Z","shell.execute_reply":"2022-07-15T09:35:45.882786Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.drop(['Cabin'], axis=1, inplace=True)\ntest_data.drop(['Cabin'], axis=1, inplace=True)\ntrain_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:45.884629Z","iopub.execute_input":"2022-07-15T09:35:45.885069Z","iopub.status.idle":"2022-07-15T09:35:45.909404Z","shell.execute_reply.started":"2022-07-15T09:35:45.885037Z","shell.execute_reply":"2022-07-15T09:35:45.908596Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.columns","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:45.910715Z","iopub.execute_input":"2022-07-15T09:35:45.911289Z","iopub.status.idle":"2022-07-15T09:35:45.917898Z","shell.execute_reply.started":"2022-07-15T09:35:45.911245Z","shell.execute_reply":"2022-07-15T09:35:45.917206Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Mode: {}\".format(train_data.Age.mode()))\nprint(\"Mean: {}\".format(train_data.Age.mean()))\nprint(\"Median: {}\".format(train_data.Age.median()))\nprint(\"25%: {}\".format(train_data.Age.quantile(0.25)))\nprint(\"75%: {}\".format(train_data.Age.quantile(0.75)))\nprint(\"10%: {}\".format(train_data.Age.quantile(0.10)))\nprint(\"90%: {}\".format(train_data.Age.quantile(0.90)))\nprint(\"min: {}\".format(train_data.Age.min()))\nprint(\"max: {}\".format(train_data.Age.max()))\n\nQ1 = train_data.quantile(0.25)\nQ3 = train_data.quantile(0.75)\nIQR = Q3 - Q1\n\nprint(\"lower: {}\".format(Q1['Age']-(1.5*IQR['Age'])))\nprint(\"upper: {}\".format(Q3['Age']+(1.5*IQR['Age'])))","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:45.918936Z","iopub.execute_input":"2022-07-15T09:35:45.919318Z","iopub.status.idle":"2022-07-15T09:35:45.955591Z","shell.execute_reply.started":"2022-07-15T09:35:45.919291Z","shell.execute_reply":"2022-07-15T09:35:45.954485Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data['Age'] = train_data['Age'].fillna(train_data.Age.median())\ntest_data['Age'] = test_data['Age'].fillna(test_data.Age.median())","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:45.956954Z","iopub.execute_input":"2022-07-15T09:35:45.957566Z","iopub.status.idle":"2022-07-15T09:35:45.964888Z","shell.execute_reply.started":"2022-07-15T09:35:45.957501Z","shell.execute_reply":"2022-07-15T09:35:45.963737Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = train_data.dropna(how='any', axis= 0)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:45.966342Z","iopub.execute_input":"2022-07-15T09:35:45.967091Z","iopub.status.idle":"2022-07-15T09:35:45.979851Z","shell.execute_reply.started":"2022-07-15T09:35:45.967017Z","shell.execute_reply":"2022-07-15T09:35:45.978853Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Mode: {}\".format(test_data.Fare.mode()))\nprint(\"Mean: {}\".format(test_data.Fare.mean()))\nprint(\"Median: {}\".format(test_data.Fare.median()))\nprint(\"25%: {}\".format(test_data.Fare.quantile(0.25)))\nprint(\"75%: {}\".format(test_data.Fare.quantile(0.75)))\nprint(\"10%: {}\".format(test_data.Fare.quantile(0.10)))\nprint(\"90%: {}\".format(test_data.Fare.quantile(0.90)))\nprint(\"min: {}\".format(test_data.Fare.min()))\nprint(\"max: {}\".format(test_data.Fare.max()))\n\nQ1 = test_data.quantile(0.25)\nQ3 = test_data.quantile(0.75)\nIQR = Q3 - Q1\n\nprint(\"lower: {}\".format(Q1['Fare']-(1.5*IQR['Fare'])))\nprint(\"upper: {}\".format(Q3['Fare']+(1.5*IQR['Fare'])))","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:45.981505Z","iopub.execute_input":"2022-07-15T09:35:45.982197Z","iopub.status.idle":"2022-07-15T09:35:46.005564Z","shell.execute_reply.started":"2022-07-15T09:35:45.982151Z","shell.execute_reply":"2022-07-15T09:35:46.004472Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data['Fare'] = test_data['Fare'].fillna(test_data.Fare.median())","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.007091Z","iopub.execute_input":"2022-07-15T09:35:46.007682Z","iopub.status.idle":"2022-07-15T09:35:46.013888Z","shell.execute_reply.started":"2022-07-15T09:35:46.007636Z","shell.execute_reply":"2022-07-15T09:35:46.012865Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.015316Z","iopub.execute_input":"2022-07-15T09:35:46.015969Z","iopub.status.idle":"2022-07-15T09:35:46.028689Z","shell.execute_reply.started":"2022-07-15T09:35:46.015884Z","shell.execute_reply":"2022-07-15T09:35:46.027506Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.030150Z","iopub.execute_input":"2022-07-15T09:35:46.030761Z","iopub.status.idle":"2022-07-15T09:35:46.040636Z","shell.execute_reply.started":"2022-07-15T09:35:46.030718Z","shell.execute_reply":"2022-07-15T09:35:46.039591Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.loc[train_data.duplicated()].shape","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.044934Z","iopub.execute_input":"2022-07-15T09:35:46.045321Z","iopub.status.idle":"2022-07-15T09:35:46.061328Z","shell.execute_reply.started":"2022-07-15T09:35:46.045288Z","shell.execute_reply":"2022-07-15T09:35:46.060215Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data.loc[test_data.duplicated()].shape","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.063381Z","iopub.execute_input":"2022-07-15T09:35:46.063814Z","iopub.status.idle":"2022-07-15T09:35:46.073878Z","shell.execute_reply.started":"2022-07-15T09:35:46.063774Z","shell.execute_reply":"2022-07-15T09:35:46.072967Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.columns","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.075456Z","iopub.execute_input":"2022-07-15T09:35:46.076115Z","iopub.status.idle":"2022-07-15T09:35:46.084257Z","shell.execute_reply.started":"2022-07-15T09:35:46.076066Z","shell.execute_reply":"2022-07-15T09:35:46.083519Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.drop(['Name','Ticket'], axis=1, inplace=True)\ntest_data.drop(['Name','Ticket'], axis=1, inplace=True)\ntrain_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.085578Z","iopub.execute_input":"2022-07-15T09:35:46.086160Z","iopub.status.idle":"2022-07-15T09:35:46.108292Z","shell.execute_reply.started":"2022-07-15T09:35:46.086115Z","shell.execute_reply":"2022-07-15T09:35:46.107259Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"mask = np.triu(np.ones_like(train_data.corr()))\nfig, ax = plt.subplots(figsize=(30,25),dpi=80, facecolor='w', edgecolor='k')\nsns.heatmap(train_data.corr(), mask= mask, cmap=\"YlGnBu\", vmax=.3, annot = True, center = 0,annot_kws={\"fontsize\":22})","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.110034Z","iopub.execute_input":"2022-07-15T09:35:46.110374Z","iopub.status.idle":"2022-07-15T09:35:46.693874Z","shell.execute_reply.started":"2022-07-15T09:35:46.110340Z","shell.execute_reply":"2022-07-15T09:35:46.693025Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.columns","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.694896Z","iopub.execute_input":"2022-07-15T09:35:46.695283Z","iopub.status.idle":"2022-07-15T09:35:46.700812Z","shell.execute_reply.started":"2022-07-15T09:35:46.695253Z","shell.execute_reply":"2022-07-15T09:35:46.699927Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"categorical_feature = ['Sex','Embarked']","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.702099Z","iopub.execute_input":"2022-07-15T09:35:46.702421Z","iopub.status.idle":"2022-07-15T09:35:46.713463Z","shell.execute_reply.started":"2022-07-15T09:35:46.702392Z","shell.execute_reply":"2022-07-15T09:35:46.712345Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"le = LabelEncoder() \ntrain_data[categorical_feature] = train_data[categorical_feature].apply(lambda col: le.fit_transform(col)) \ntest_data[categorical_feature] = test_data[categorical_feature].apply(lambda col: le.fit_transform(col)) \ntrain_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.715385Z","iopub.execute_input":"2022-07-15T09:35:46.716439Z","iopub.status.idle":"2022-07-15T09:35:46.744613Z","shell.execute_reply.started":"2022-07-15T09:35:46.716328Z","shell.execute_reply":"2022-07-15T09:35:46.743618Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x = train_data.drop(\"Survived\", axis = 1)\ny = train_data['Survived']","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.746049Z","iopub.execute_input":"2022-07-15T09:35:46.746658Z","iopub.status.idle":"2022-07-15T09:35:46.754013Z","shell.execute_reply.started":"2022-07-15T09:35:46.746612Z","shell.execute_reply":"2022-07-15T09:35:46.753036Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train, x_test, y_train, y_test = train_test_split(x, y, random_state = 100,stratify=y, test_size = 0.2)\nprint(y_train.value_counts())","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.755264Z","iopub.execute_input":"2022-07-15T09:35:46.755897Z","iopub.status.idle":"2022-07-15T09:35:46.768525Z","shell.execute_reply.started":"2022-07-15T09:35:46.755852Z","shell.execute_reply":"2022-07-15T09:35:46.767628Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"scale = MinMaxScaler()\n\ncol = ['Pclass', 'Age', 'SibSp', 'Parch','Fare', 'Embarked']\n\nx_train[col] = scale.fit_transform(x_train[col])\nx_train.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.769819Z","iopub.execute_input":"2022-07-15T09:35:46.770314Z","iopub.status.idle":"2022-07-15T09:35:46.797388Z","shell.execute_reply.started":"2022-07-15T09:35:46.770275Z","shell.execute_reply":"2022-07-15T09:35:46.796632Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_test[col] = scale.transform(x_test[col])\ntest_data[col] = scale.transform(test_data[col])\nx_test.head()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.798633Z","iopub.execute_input":"2022-07-15T09:35:46.799004Z","iopub.status.idle":"2022-07-15T09:35:46.833440Z","shell.execute_reply.started":"2022-07-15T09:35:46.798974Z","shell.execute_reply":"2022-07-15T09:35:46.832501Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Manage Imbalance Data","metadata":{}},{"cell_type":"code","source":"smt = SMOTE(random_state=100)\nx_train, y_train = smt.fit_resample(x_train, y_train)\nnp.bincount(y_train)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.834604Z","iopub.execute_input":"2022-07-15T09:35:46.835056Z","iopub.status.idle":"2022-07-15T09:35:46.856867Z","shell.execute_reply.started":"2022-07-15T09:35:46.835015Z","shell.execute_reply":"2022-07-15T09:35:46.855829Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature Selection","metadata":{}},{"cell_type":"code","source":"checkVIF(x).reset_index(drop=True)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.858128Z","iopub.execute_input":"2022-07-15T09:35:46.858440Z","iopub.status.idle":"2022-07-15T09:35:46.915039Z","shell.execute_reply.started":"2022-07-15T09:35:46.858410Z","shell.execute_reply":"2022-07-15T09:35:46.914000Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dt=DecisionTreeClassifier()\ndt.fit(x_train,y_train)\nfeat_importances1 = pd.Series(dt.feature_importances_, index=x_train.columns)\nfeat_importances1.sort_values(ascending=True).plot(kind='barh')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:46.916363Z","iopub.execute_input":"2022-07-15T09:35:46.916989Z","iopub.status.idle":"2022-07-15T09:35:47.094296Z","shell.execute_reply.started":"2022-07-15T09:35:46.916942Z","shell.execute_reply":"2022-07-15T09:35:47.093397Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"rf = RandomForestClassifier()\nrf.fit(x_train,y_train)\nfeat_importances1 = pd.Series(rf.feature_importances_, index=x_train.columns)\nfeat_importances1.sort_values(ascending=True).plot(kind='barh')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:47.095418Z","iopub.execute_input":"2022-07-15T09:35:47.095720Z","iopub.status.idle":"2022-07-15T09:35:47.497455Z","shell.execute_reply.started":"2022-07-15T09:35:47.095683Z","shell.execute_reply":"2022-07-15T09:35:47.496512Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"gb = GradientBoostingClassifier()\ngb.fit(x_train,y_train)\nfeat_importances1 = pd.Series(gb.feature_importances_, index=x_train.columns)\nfeat_importances1.sort_values(ascending=True).plot(kind='barh')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:47.500307Z","iopub.execute_input":"2022-07-15T09:35:47.500652Z","iopub.status.idle":"2022-07-15T09:35:47.821632Z","shell.execute_reply.started":"2022-07-15T09:35:47.500622Z","shell.execute_reply":"2022-07-15T09:35:47.820645Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"et = ExtraTreesClassifier()\net.fit(x_train,y_train)\nfeat_importances1 = pd.Series(et.feature_importances_, index=x_train.columns)\nfeat_importances1.sort_values(ascending=True).plot(kind='barh')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:47.822893Z","iopub.execute_input":"2022-07-15T09:35:47.823158Z","iopub.status.idle":"2022-07-15T09:35:48.171819Z","shell.execute_reply.started":"2022-07-15T09:35:47.823133Z","shell.execute_reply":"2022-07-15T09:35:48.170600Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ls = LassoCV(max_iter=100, random_state=100, n_jobs=-1)\nclf = ls.fit(x_train, y_train)\nimportance = np.abs(clf.coef_)\nframe = pd.Series(importance, x_train.columns)\nframe.sort_values(ascending = True).plot(kind='barh')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:48.173269Z","iopub.execute_input":"2022-07-15T09:35:48.173685Z","iopub.status.idle":"2022-07-15T09:35:48.782284Z","shell.execute_reply.started":"2022-07-15T09:35:48.173642Z","shell.execute_reply":"2022-07-15T09:35:48.781432Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"en = ElasticNet(max_iter=100, alpha=0.0001, random_state=100, selection='cyclic')\nclf = en.fit(x_train, y_train)\nimportance = np.abs(clf.coef_)\nframe = pd.Series(importance, x_train.columns)\nframe.sort_values(ascending = True).plot(kind='barh')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:48.783309Z","iopub.execute_input":"2022-07-15T09:35:48.783736Z","iopub.status.idle":"2022-07-15T09:35:48.946283Z","shell.execute_reply.started":"2022-07-15T09:35:48.783699Z","shell.execute_reply":"2022-07-15T09:35:48.944795Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"r = Ridge(max_iter=100, random_state=100, normalize=True)\nclf = r.fit(x_train, y_train)\nimportance = np.abs(clf.coef_)\nframe = pd.Series(importance, x_train.columns)\nframe.sort_values(ascending = True).plot(kind='barh', )\nplt.title(\"Feature Selection with Ridge\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:48.947813Z","iopub.execute_input":"2022-07-15T09:35:48.948161Z","iopub.status.idle":"2022-07-15T09:35:49.153826Z","shell.execute_reply.started":"2022-07-15T09:35:48.948128Z","shell.execute_reply":"2022-07-15T09:35:49.152695Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"correlation=(train_data.corr()['Survived'])\ndel correlation['Survived']\ncorrelation.sort_values(ascending=True).plot(kind='barh',color = \"darkgreen\")\nplt.title(\"correlation\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:49.155124Z","iopub.execute_input":"2022-07-15T09:35:49.155436Z","iopub.status.idle":"2022-07-15T09:35:49.325975Z","shell.execute_reply.started":"2022-07-15T09:35:49.155406Z","shell.execute_reply":"2022-07-15T09:35:49.324939Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# new Features\nx_train_new = x_train[['Pclass', 'Sex', 'Age', 'Fare','Embarked']]\nx_test_new = x_test[['Pclass', 'Sex', 'Age', 'Fare','Embarked']]","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:49.327406Z","iopub.execute_input":"2022-07-15T09:35:49.328001Z","iopub.status.idle":"2022-07-15T09:35:49.336635Z","shell.execute_reply.started":"2022-07-15T09:35:49.327958Z","shell.execute_reply":"2022-07-15T09:35:49.335664Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Hyperparameter Tuning and Build Models","metadata":{}},{"cell_type":"code","source":"param_DT = {'criterion':['gini', 'entropy'] ,\n            'max_depth':[None,3,4,5] ,\n            'min_samples_split':[2,3,4,5,6] ,\n            'min_samples_leaf':[2,3,4,5,6]}\n\nCls_model_RndSrch_Tune(DecisionTreeClassifier(random_state = 0), train_data, x_train_new, y_train, param_DT)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:49.338015Z","iopub.execute_input":"2022-07-15T09:35:49.338419Z","iopub.status.idle":"2022-07-15T09:35:52.355244Z","shell.execute_reply.started":"2022-07-15T09:35:49.338373Z","shell.execute_reply":"2022-07-15T09:35:52.354391Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"param_RF = {'criterion':['gini', 'entropy'] ,\n            'max_depth':[ None,3,4,5] ,\n            'min_samples_split':[2,3,4,5,6] ,\n            'min_samples_leaf':[2,3,4,5,6],\n            'n_estimators':[25,50,75,100,200,300]}\n\nCls_model_RndSrch_Tune(RandomForestClassifier(random_state = 0), train_data, x_train_new, y_train, param_RF)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:52.356729Z","iopub.execute_input":"2022-07-15T09:35:52.357247Z","iopub.status.idle":"2022-07-15T09:35:57.433676Z","shell.execute_reply.started":"2022-07-15T09:35:52.357210Z","shell.execute_reply":"2022-07-15T09:35:57.432610Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"param_ET = {'criterion':['gini', 'entropy'] ,\n            'max_depth':[3,4,5] ,\n            'min_samples_split':[2,3,4,5,6] ,\n            'min_samples_leaf':[2,3,4,5,6],\n            'n_estimators':[25,50,75,100,200,300],\n            'max_features' : ['auto', 'sqrt', 'log2']}\n\nCls_model_RndSrch_Tune(ExtraTreesClassifier(random_state = 0), train_data, x_train_new, y_train, param_ET)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:35:57.434925Z","iopub.execute_input":"2022-07-15T09:35:57.435205Z","iopub.status.idle":"2022-07-15T09:36:01.763607Z","shell.execute_reply.started":"2022-07-15T09:35:57.435177Z","shell.execute_reply":"2022-07-15T09:36:01.762615Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"param_MLP = {'activation' : ['relu' , 'logistic' , 'tanh'],\n            'hidden_layer_sizes':[(10), (20), (20,30)],\n            'max_iter' : [10, 50, 100, 200],\n            'solver': ['sgd', 'adam'],\n            'learning_rate_init': [0.01, 0.001, 0.0001, 0.025, 0.1, 0.2]}\n\nCls_model_RndSrch_Tune(MLPClassifier(random_state = 0), train_data, x_train_new, y_train, param_MLP)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:01.764878Z","iopub.execute_input":"2022-07-15T09:36:01.765175Z","iopub.status.idle":"2022-07-15T09:36:05.719731Z","shell.execute_reply.started":"2022-07-15T09:36:01.765144Z","shell.execute_reply":"2022-07-15T09:36:05.718942Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"param_SVM = {'kernel' : ['linear', 'rbf', 'poly'],\n            'gamma' : [0.01, 0.1, 0.2, 0.3, 0.4,0.5, 0.6,0.7], \n            'C':  [0.01 , 0.1, 1, 10, 100],\n            'degree': [2, 3, 4, 5, 6]}\n\n\nCls_model_RndSrch_Tune(SVC(random_state = 0), train_data, x_train_new, y_train, param_SVM)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:05.720773Z","iopub.execute_input":"2022-07-15T09:36:05.721177Z","iopub.status.idle":"2022-07-15T09:36:06.634122Z","shell.execute_reply.started":"2022-07-15T09:36:05.721146Z","shell.execute_reply":"2022-07-15T09:36:06.633097Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"param_GB = {'loss' : ['deviance', 'exponential'],\n            'n_estimators':[25,50,75,100,200,300],\n            'criterion' : ['friedman_mse', 'mse', 'mae'],\n            'min_samples_split':[2,3,4,5,6] ,\n            'min_samples_leaf':[2,3,4,5,6],\n            'max_depth':[3,4,5]}\n\nCls_model_RndSrch_Tune(GradientBoostingClassifier(random_state = 0), train_data, x_train_new, y_train, param_GB)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:06.635641Z","iopub.execute_input":"2022-07-15T09:36:06.636072Z","iopub.status.idle":"2022-07-15T09:36:18.871692Z","shell.execute_reply.started":"2022-07-15T09:36:06.636025Z","shell.execute_reply":"2022-07-15T09:36:18.870673Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"param_LR = {'penalty' : ['l1', 'l2', 'elasticnet', 'none'],\n            'C': range(1,11),\n            'solver' : ['newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga'],\n            'multi_class' : ['auto', 'ovr', 'multinomial']}\n\n\nCls_model_RndSrch_Tune(LogisticRegression(random_state = 0), train_data, x_train_new, y_train, param_LR)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:18.872910Z","iopub.execute_input":"2022-07-15T09:36:18.873215Z","iopub.status.idle":"2022-07-15T09:36:19.178383Z","shell.execute_reply.started":"2022-07-15T09:36:18.873184Z","shell.execute_reply":"2022-07-15T09:36:19.177707Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            background-color:#ffffff;\n            border-style: solid;\n            border-color: #0b0265;\n            letter-spacing:0.5px;\">\n\n<center><h3 style=\"padding: 5px 0px; color:#0b0265; font-weight: bold; font-family: Cursive\">\nModels</h3></center>\n</div>","metadata":{}},{"cell_type":"code","source":"DT = DecisionTreeClassifier(max_depth=5, min_samples_leaf=5, min_samples_split=4,\n                       random_state=0)\n\nDT.fit(x_train_new, y_train)\n\ny_test_pred_DT = DT.predict(x_test_new)\ny_train_pred_DT = DT.predict(x_train_new)\n\ntest_acc_DT = accuracy_score(y_test, y_test_pred_DT)\ntrain_acc_DT = accuracy_score(y_train, y_train_pred_DT)\n\nprecision_score_DT = precision_score(y_test, y_test_pred_DT)\nrecall_score_DT = recall_score(y_test, y_test_pred_DT)\nf1_score_DT = f1_score(y_test, y_test_pred_DT)\n\nprint(\"Tain set Accuracy: \", train_acc_DT)\nprint(\"Test set Accuracy: \", test_acc_DT)\nprint(\"************************************************\")\nprint(\"precision_score: \", precision_score_DT)\nprint(\"recall_score: \", recall_score_DT)\nprint(\"f1_score: \", f1_score_DT)","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:19.179637Z","iopub.execute_input":"2022-07-15T09:36:19.180112Z","iopub.status.idle":"2022-07-15T09:36:19.203733Z","shell.execute_reply.started":"2022-07-15T09:36:19.180081Z","shell.execute_reply":"2022-07-15T09:36:19.202489Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"MLP = MLPClassifier(hidden_layer_sizes=(20, 30), learning_rate_init=0.1,\n              random_state=0, solver='sgd')\n\nMLP.fit(x_train_new, y_train)\n\ny_test_pred_MLP = MLP.predict(x_test_new)\ny_train_pred_MLP = MLP.predict(x_train_new)\n\ntest_acc_MLP = accuracy_score(y_test, y_test_pred_MLP)\ntrain_acc_MLP = accuracy_score(y_train, y_train_pred_MLP)\n\nprecision_score_MLP = precision_score(y_test, y_test_pred_MLP)\nrecall_score_MLP = recall_score(y_test, y_test_pred_MLP)\nf1_score_MLP = f1_score(y_test, y_test_pred_MLP)\nconf_MLP = confusion_matrix(y_test, y_test_pred_MLP)\n\nprint(\"Tain set Accuracy: \", train_acc_MLP)\nprint(\"Test set Accuracy: \", test_acc_MLP)\nprint(\"************************************************\")\nprint(\"precision_score: \", precision_score_MLP)\nprint(\"recall_score: \", recall_score_MLP)\nprint(\"f1_score: \", f1_score_MLP)\nprint(\"************************************************\")","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:19.204994Z","iopub.execute_input":"2022-07-15T09:36:19.205280Z","iopub.status.idle":"2022-07-15T09:36:19.534051Z","shell.execute_reply.started":"2022-07-15T09:36:19.205251Z","shell.execute_reply":"2022-07-15T09:36:19.532854Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"RF = RandomForestClassifier(criterion='entropy', max_depth=5, min_samples_leaf=4,\n                       min_samples_split=3, n_estimators=50, random_state=0)\n\nRF.fit(x_train_new, y_train)\n\ny_test_pred_RF = RF.predict(x_test_new)\ny_train_pred_RF = RF.predict(x_train_new)\n\ntest_acc_RF = accuracy_score(y_test, y_test_pred_RF)\ntrain_acc_RF = accuracy_score(y_train, y_train_pred_RF)\n\nprecision_score_RF = precision_score(y_test, y_test_pred_RF)\nrecall_score_RF = recall_score(y_test, y_test_pred_RF)\nf1_score_RF = f1_score(y_test, y_test_pred_RF)\nconf_RF = confusion_matrix(y_test, y_test_pred_RF)\n\nprint(\"Tain set Accuracy: \", train_acc_RF)\nprint(\"Test set Accuracy: \", test_acc_RF)\nprint(\"************************************************\")\nprint(\"precision_score: \", precision_score_RF)\nprint(\"recall_score: \", recall_score_RF)\nprint(\"f1_score: \", f1_score_RF)\nprint(\"************************************************\")","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:19.535805Z","iopub.execute_input":"2022-07-15T09:36:19.536507Z","iopub.status.idle":"2022-07-15T09:36:19.736917Z","shell.execute_reply.started":"2022-07-15T09:36:19.536456Z","shell.execute_reply":"2022-07-15T09:36:19.735859Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GB = GradientBoostingClassifier(criterion='mse', loss='exponential', max_depth=3,\n                           min_samples_leaf=3, min_samples_split=4,\n                           n_estimators=25, random_state=0)\n\nGB.fit(x_train_new, y_train)\n\ny_test_pred_GB = GB.predict(x_test_new)\ny_train_pred_GB = GB.predict(x_train_new)\n\ntest_acc_GB = accuracy_score(y_test, y_test_pred_GB)\ntrain_acc_GB = accuracy_score(y_train, y_train_pred_GB)\n\nprecision_score_GB = precision_score(y_test, y_test_pred_GB)\nrecall_score_GB = recall_score(y_test, y_test_pred_GB)\nf1_score_GB = f1_score(y_test, y_test_pred_GB)\nconf_GB = confusion_matrix(y_test, y_test_pred_GB)\n\nprint(\"Tain set Accuracy: \", train_acc_GB)\nprint(\"Test set Accuracy: \", test_acc_GB)\nprint(\"************************************************\")\nprint(\"precision_score: \", precision_score_GB)\nprint(\"recall_score: \", recall_score_GB)\nprint(\"f1_score: \", f1_score_GB)\nprint(\"************************************************\")","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:19.740424Z","iopub.execute_input":"2022-07-15T09:36:19.740761Z","iopub.status.idle":"2022-07-15T09:36:19.802175Z","shell.execute_reply.started":"2022-07-15T09:36:19.740728Z","shell.execute_reply":"2022-07-15T09:36:19.801186Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"SVM = SVC(C=100, degree=5, gamma=0.7, kernel='poly', random_state=0, probability=True)\n\nSVM.fit(x_train_new, y_train)\n\ny_test_pred_SVM = SVM.predict(x_test_new)\ny_train_pred_SVM = SVM.predict(x_train_new)\n\ntest_acc_SVM = accuracy_score(y_test, y_test_pred_SVM)\ntrain_acc_SVM = accuracy_score(y_train, y_train_pred_SVM)\n\nprecision_score_SVM = precision_score(y_test, y_test_pred_SVM)\nrecall_score_SVM = recall_score(y_test, y_test_pred_SVM)\nf1_score_SVM = f1_score(y_test, y_test_pred_SVM)\nconf_SVM = confusion_matrix(y_test, y_test_pred_SVM)\n\nroc_test_SVM = roc_auc_score(y_test, y_test_pred_SVM)\nroc_train_SVM = roc_auc_score(y_train, y_train_pred_SVM)\n\n\nprint(\"Tain set Accuracy: \", train_acc_SVM)\nprint(\"Test set Accuracy: \", test_acc_SVM)\nprint(\"************************************************\")\nprint(\"precision_score: \", precision_score_SVM)\nprint(\"recall_score: \", recall_score_SVM)\nprint(\"f1_score: \", f1_score_SVM)\nprint(\"************************************************\")","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:19.803366Z","iopub.execute_input":"2022-07-15T09:36:19.803665Z","iopub.status.idle":"2022-07-15T09:36:20.836339Z","shell.execute_reply.started":"2022-07-15T09:36:19.803637Z","shell.execute_reply":"2022-07-15T09:36:20.835360Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ET = ExtraTreesClassifier(criterion='entropy', max_depth=3, max_features='sqrt',\n                     min_samples_leaf=3, min_samples_split=4, n_estimators=75,\n                     random_state=0)\nET.fit(x_train_new, y_train)\n\ny_test_pred_ET = ET.predict(x_test_new)\ny_train_pred_ET = ET.predict(x_train_new)\n\ntest_acc_ET = accuracy_score(y_test, y_test_pred_ET)\ntrain_acc_ET = accuracy_score(y_train, y_train_pred_ET)\n\nprecision_score_ET = precision_score(y_test, y_test_pred_ET)\nrecall_score_ET = recall_score(y_test, y_test_pred_ET)\nf1_score_ET = f1_score(y_test, y_test_pred_ET)\nconf_ET = confusion_matrix(y_test, y_test_pred_ET)\n\nprint(\"Tain set Accuracy: \", train_acc_ET)\nprint(\"Test set Accuracy: \", test_acc_ET)\nprint(\"************************************************\")\nprint(\"precision_score: \", precision_score_ET)\nprint(\"recall_score: \", recall_score_ET)\nprint(\"f1_score: \", f1_score_ET)\nprint(\"************************************************\")","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:20.837945Z","iopub.execute_input":"2022-07-15T09:36:20.838315Z","iopub.status.idle":"2022-07-15T09:36:20.989589Z","shell.execute_reply.started":"2022-07-15T09:36:20.838275Z","shell.execute_reply":"2022-07-15T09:36:20.988489Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"LR = LogisticRegression(C=7, random_state=0, solver='newton-cg')\nLR.fit(x_train_new, y_train)\n\ny_test_pred_LR = LR.predict(x_test_new)\ny_train_pred_LR = LR.predict(x_train_new)\n\ntest_acc_LR = accuracy_score(y_test, y_test_pred_LR)\ntrain_acc_LR = accuracy_score(y_train, y_train_pred_LR)\n\nprecision_score_LR = precision_score(y_test, y_test_pred_LR)\nrecall_score_LR = recall_score(y_test, y_test_pred_LR)\nf1_score_LR = f1_score(y_test, y_test_pred_LR)\nconf_LR = confusion_matrix(y_test, y_test_pred_LR)\n\nprint(\"Tain set Accuracy: \", train_acc_LR)\nprint(\"Test set Accuracy: \", test_acc_LR)\nprint(\"************************************************\")\nprint(\"precision_score: \", precision_score_LR)\nprint(\"recall_score: \", recall_score_LR)\nprint(\"f1_score: \", f1_score_LR)\nprint(\"************************************************\")","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:20.991095Z","iopub.execute_input":"2022-07-15T09:36:20.991481Z","iopub.status.idle":"2022-07-15T09:36:21.025992Z","shell.execute_reply.started":"2022-07-15T09:36:20.991439Z","shell.execute_reply":"2022-07-15T09:36:21.024981Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Compare Models ","metadata":{}},{"cell_type":"code","source":"models = [('Decision Tree', train_acc_DT, test_acc_DT, precision_score_DT, recall_score_DT, f1_score_DT, 'Good'),\n          ('Random Forest', train_acc_RF, test_acc_RF, precision_score_RF, recall_score_RF, f1_score_RF, 'Good'),\n          ('Neural Network', train_acc_MLP, test_acc_MLP, precision_score_MLP, recall_score_MLP, f1_score_MLP,'Good'),\n          ('SVC', train_acc_SVM, test_acc_SVM, precision_score_SVM, recall_score_SVM, f1_score_SVM,'Good'),\n          ('Extra Tree', train_acc_ET, test_acc_ET, precision_score_ET, recall_score_ET, f1_score_ET,'Good'),          \n          ('Gradient Boosting', train_acc_GB, test_acc_GB, precision_score_GB, recall_score_GB, f1_score_GB,'*** The Best ***'),\n          \n         ]","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:21.027092Z","iopub.execute_input":"2022-07-15T09:36:21.027367Z","iopub.status.idle":"2022-07-15T09:36:21.034149Z","shell.execute_reply.started":"2022-07-15T09:36:21.027341Z","shell.execute_reply":"2022-07-15T09:36:21.033186Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predict_IR = pd.DataFrame(data = models, columns=['Model', 'Train_accuracy', 'Test_accuracy','precision_score', 'recall_score', 'f1_score', 'Description'])\npredict_IR.style.background_gradient(cmap='YlGn')","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:21.035162Z","iopub.execute_input":"2022-07-15T09:36:21.035513Z","iopub.status.idle":"2022-07-15T09:36:21.097904Z","shell.execute_reply.started":"2022-07-15T09:36:21.035480Z","shell.execute_reply":"2022-07-15T09:36:21.097144Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prediction","metadata":{}},{"cell_type":"code","source":"test_data.shape","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:21.099081Z","iopub.execute_input":"2022-07-15T09:36:21.099354Z","iopub.status.idle":"2022-07-15T09:36:21.104512Z","shell.execute_reply.started":"2022-07-15T09:36:21.099327Z","shell.execute_reply":"2022-07-15T09:36:21.103871Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# new\ntest_data_new = test_data[['Pclass', 'Sex', 'Age', 'Fare','Embarked']]","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:21.105651Z","iopub.execute_input":"2022-07-15T09:36:21.106117Z","iopub.status.idle":"2022-07-15T09:36:21.118997Z","shell.execute_reply.started":"2022-07-15T09:36:21.106088Z","shell.execute_reply":"2022-07-15T09:36:21.117979Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = GB.predict(test_data_new)\noutput = pd.DataFrame({'PassengerId': test_data.PassengerId, 'Survived': predictions})\noutput.to_csv('my_submission.csv', index=False)\nprint(\"Your submission was successfully saved!\")","metadata":{"execution":{"iopub.status.busy":"2022-07-15T09:36:21.120336Z","iopub.execute_input":"2022-07-15T09:36:21.120671Z","iopub.status.idle":"2022-07-15T09:36:21.139057Z","shell.execute_reply.started":"2022-07-15T09:36:21.120640Z","shell.execute_reply":"2022-07-15T09:36:21.138045Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            background-color:#ffffff;\n            border-style:solid;\n            border-color: #0b0265;\n            letter-spacing:0.5px;\">\n\n<center><h4 style=\"padding: 5px 0px; color:#0b0265; font-weight: bold; font-family: Cursive\">\n    Thanks for your attention and for reviewing my notebook.🙌 <br><br>Please write your comments for me.📝</h4></center>\n<center><h4 style=\"padding: 5px 0px; color:#0b0265; font-weight: bold; font-family: Cursive\">\nIf you liked my work and found it useful, please upvote. Thank you🙏</h4></center>\n</div>","metadata":{}}]}