kaggle titanic tutorial
import pandas as pd import numpy as np import seaborn as sns import matplotlib.pyplot as plt %matplotlib inline from sklearn.preprocessing import OrdinalEncoder, OneHotEncoder from sklearn.impute import SimpleImputer from sklearn.compose import make_column_transformer, ColumnTransformer from sklearn.pipeline import Pipeline, make_pipeline from sklearn.linear_model import LogisticRegression from sklearn.svm import SVC from sklearn.tree import DecisionTreeClassifier from sklearn.neighbors import KNeighborsClassifier from sklearn.naive_bayes import GaussianNB from xgboost import XGBClassifier from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier, ExtraTreesClassifier, VotingClassifier from sklearn.model_selection import cross_val_score, StratifiedKFold, train_test_split, GridSearchCV train_df = pd.read_csv('/kaggle/input/titanic/train.csv') test_df = pd.read_csv('/kaggle/input/titanic/test.csv') train_df.head() 
train_df.info() 
train_df.describe() 
train_df.describe(include=['O']) 
train_df.groupby(['Pclass'], as_index=False)['Survived'].mean() 
train_df.groupby(['Sex'], as_index=False)['Survived'].mean() 
train_df.groupby(['SibSp'], as_index=False)['Survived'].mean() 
train_df.groupby(['Parch'], as_index=False)['Survived'].mean() 
train_df['Family_Size'] = train_df['SibSp'] + train_df['Parch'] + 1 test_df['Family_Size'] = test_df['SibSp'] + test_df['Parch'] + 1 train_df.groupby(['Family_Size'], as_index=False)['Survived'].mean() 
family_map = {1: 'Alone', 2: 'Small', 3: 'Small', 4: 'Small', 5: 'Medium', 6: 'Medium', 7: 'Large', 8: 'Large', 11: 'Large'} train_df['Family_Size_Grouped'] = train_df['Family_Size'].map(family_map) test_df['Family_Size_Grouped'] = train_df['Family_Size'].map(family_map) train_df.groupby(['Family_Size_Grouped'], as_index=False)['Survived'].mean() 
train_df.groupby(['Embarked'], as_index=False)['Survived'].mean() 
sns.displot(train_df, x='Age', col='Survived', binwidth=10, height=5) 
train_df['Age_Cut'] = pd.qcut(train_df['Age'], 5) test_df['Age_Cut'] = pd.qcut(test_df['Age'], 5) train_df.groupby(['Age_Cut'], as_index=False)['Survived'].mean() 
train_df.loc[train_df['Age'] <= 19, 'Age'] = 0 train_df.loc[(train_df['Age'] > 19) & (train_df['Age'] <= 25), 'Age'] = 1 train_df.loc[(train_df['Age'] > 25) & (train_df['Age'] <= 31.8), 'Age'] = 2 train_df.loc[(train_df['Age'] > 31.8) & (train_df['Age'] <= 41), 'Age'] = 3 train_df.loc[(train_df['Age'] > 41) & (train_df['Age'] <= 80), 'Age'] = 4 train_df.loc[train_df['Age'] > 80, 'Age'] test_df.loc[test_df['Age'] <= 19, 'Age'] = 0 test_df.loc[(test_df['Age'] > 19) & (test_df['Age'] <= 25), 'Age'] = 1 test_df.loc[(test_df['Age'] > 25) & (test_df['Age'] <= 31.8), 'Age'] = 2 test_df.loc[(test_df['Age'] > 31.8) & (test_df['Age'] <= 41), 'Age'] = 3 test_df.loc[(test_df['Age'] > 41) & (test_df['Age'] <= 80), 'Age'] = 4 test_df.loc[test_df['Age'] > 80, 'Age'] 
train_df.head() 
sns.displot(train_df, x='Fare', col='Survived', binwidth=80, height=5) 
train_df['Fare_Cut'] = pd.qcut(train_df['Fare'], 5) test_df['Fare_Cut'] = pd.qcut(test_df['Fare'], 5) train_df.groupby(['Fare_Cut'], as_index=False)['Survived'].mean() 
train_df.loc[train_df['Fare'] <= 7.854, 'Fare'] = 0 train_df.loc[(train_df['Fare'] > 7.854) & (train_df['Fare'] <= 10.5), 'Fare'] = 1 train_df.loc[(train_df['Fare'] > 10.5) & (train_df['Fare'] <= 21.679), 'Fare'] = 2 train_df.loc[(train_df['Fare'] > 21.679) & (train_df['Fare'] <= 39.688), 'Fare'] = 3 train_df.loc[(train_df['Fare'] > 39.688) & (train_df['Fare'] <= 512.329), 'Fare'] = 4 train_df.loc[train_df['Fare'] > 512.329, 'Fare'] test_df.loc[test_df['Fare'] <= 7.854, 'Fare'] = 0 test_df.loc[(test_df['Fare'] > 7.854) & (test_df['Fare'] <= 10.5), 'Fare'] = 1 test_df.loc[(test_df['Fare'] > 10.5) & (test_df['Fare'] <= 21.679), 'Fare'] = 2 test_df.loc[(test_df['Fare'] > 21.679) & (test_df['Fare'] <= 39.688), 'Fare'] = 3 test_df.loc[(test_df['Fare'] > 39.688) & (test_df['Fare'] <= 512.329), 'Fare'] = 4 test_df.loc[test_df['Fare'] > 512.329, 'Fare'] 
train_df['Name'] 
train_df['Title'] = train_df['Name'].str.split(pat= ",", expand=True)[1].str.split(pat= ".", expand=True)[0].apply(lambda x: x.strip()) test_df['Title'] = test_df['Name'].str.split(pat= ",", expand=True)[1].str.split(pat= ".", expand=True)[0].apply(lambda x: x.strip()) train_df.groupby(['Title'], as_index=False)['Survived'].mean() 
#military - Capt, Col, Major #noble - Jonkheer, the Countess, Don, Lady, Sir #unmaried Female - Mlle, Ms, Mme
train_df['Title'] = train_df['Title'].replace({ 'Capt': 'Military', 'Col': 'Military', 'Major': 'Military', 'Jonkheer': 'Noble', 'the Countess': 'Noble', 'Don': 'Noble', 'Lady': 'Noble', 'Sir': 'Noble', 'Mlle': 'Noble', 'Ms': 'Noble', 'Mme': 'Noble' }) test_df['Title'] = test_df['Title'].replace({ 'Capt': 'Military', 'Col': 'Military', 'Major': 'Military', 'Jonkheer': 'Noble', 'the Countess': 'Noble', 'Don': 'Noble', 'Lady': 'Noble', 'Sir': 'Noble', 'Mlle': 'Noble', 'Ms': 'Noble', 'Mme': 'Noble' }) train_df.groupby(['Title'], as_index=False)['Survived'].agg(['count', 'mean']) 
train_df['Name_Length'] = train_df['Name'].apply(lambda x: len(x)) test_df['Name_Length'] = test_df['Name'].apply(lambda x: len(x)) g = sns.kdeplot(train_df['Name_Length'][(train_df['Survived']==0) & (train_df['Name_Length'].notnull())], color='Red', fill=True) g = sns.kdeplot(train_df['Name_Length'][(train_df['Survived']==1) & (train_df['Name_Length'].notnull())], ax=g, color='Blue', fill=True) g.set_xlabel('Name_Length') g.set_ylabel('Frequency') g = g.legend(['Not Survived', 'Survived']) 
train_df['Name_LengthGB'] = pd.qcut(train_df['Name_Length'], 3) test_df['Name_LengthGB'] = pd.qcut(test_df['Name_Length'], 3) train_df.groupby(['Name_LengthGB'], as_index=False)['Survived'].mean() 
train_df.loc[train_df['Name_Length'] <= 22, 'Name_Size'] = 0 train_df.loc[(train_df['Name_Length'] > 22) & (train_df['Name_Length'] <= 28), 'Name_Size'] = 1 train_df.loc[(train_df['Name_Length'] > 28) & (train_df['Name_Length'] <= 82), 'Name_Size'] = 2 train_df.loc[train_df['Name_Length'] > 82, 'Name_Size'] test_df.loc[test_df['Name_Length'] <= 22, 'Name_Size'] = 0 test_df.loc[(test_df['Name_Length'] > 22) & (test_df['Name_Length'] <= 28), 'Name_Size'] = 1 test_df.loc[(test_df['Name_Length'] > 28) & (test_df['Name_Length'] <= 82), 'Name_Size'] = 2 test_df.loc[test_df['Name_Length'] > 82, 'Name_Size'] 
train_df.head() 
train_df['Ticket'] 
train_df['TicketNumber'] = train_df['Ticket'].apply(lambda x: pd.Series({'Ticket': x.split()[-1]})) test_df['TicketNumber'] = test_df['Ticket'].apply(lambda x: pd.Series({'Ticket': x.split()[-1]})) train_df.groupby(['TicketNumber'], as_index=False)['Survived'].agg(['count', 'mean']).sort_values('count', ascending=False) 
train_df.groupby('TicketNumber')['TicketNumber'].transform('count') 
train_df['TicketNumberCounts'] = train_df.groupby('TicketNumber')['TicketNumber'].transform('count') test_df['TicketNumberCounts'] = test_df.groupby('TicketNumber')['TicketNumber'].transform('count') train_df.groupby(['TicketNumberCounts'], as_index=False)['Survived'].agg(['count', 'mean']).sort_values('count', ascending=False) 
train_df['Ticket'] 
train_df['Ticket'].str.split(pat=" ", expand=True) 
train_df['TicketLocation'] = np.where(train_df['Ticket'].str.split(pat=" ", expand=True)[1].notna(), train_df['Ticket'].str.split(pat=" ", expand=True)[0].apply(lambda x: x.strip()), 'Blank') test_df['TicketLocation'] = np.where(test_df['Ticket'].str.split(pat=" ", expand=True)[1].notna(), test_df['Ticket'].str.split(pat=" ", expand=True)[0].apply(lambda x: x.strip()), 'Blank') train_df['TicketLocation'].value_counts() 
train_df['TicketLocation'] = train_df['TicketLocation'].replace({ 'SOTON/O.Q.':'SOTON/OQ', 'C.A.':'CA', 'CA.':'CA', 'SC/PARIS':'SC/Paris', 'S.C./PARIS':'SC/Paris', 'A/4.':'A/4', 'A/5.':'A/5', 'A.5.':'A/5', 'A./5.':'A/5', 'W./C.':'W/C', }) test_df['TicketLocation'] = test_df['TicketLocation'].replace({ 'SOTON/O.Q.':'SOTON/OQ', 'C.A.':'CA', 'CA.':'CA', 'SC/PARIS':'SC/Paris', 'S.C./PARIS':'SC/Paris', 'A/4.':'A/4', 'A/5.':'A/5', 'A.5.':'A/5', 'A./5.':'A/5', 'W./C.':'W/C', }) train_df.groupby(['TicketLocation'], as_index=False)['Survived'].agg(['count', 'mean']) 
train_df['Cabin'] = train_df['Cabin'].fillna('U') train_df['Cabin'] = pd.Series([i[0] if not pd.isnull(i) else 'x' for i in train_df['Cabin']]) test_df['Cabin'] = test_df['Cabin'].fillna('U') test_df['Cabin'] = pd.Series([i[0] if not pd.isnull(i) else 'x' for i in test_df['Cabin']]) train_df.groupby(['Cabin'], as_index=False)['Survived'].agg(['count', 'mean']) 
train_df['Cabin_Assigned'] = train_df['Cabin'].apply(lambda x: 0 if x in ['U'] else 1) test_df['Cabin_Assigned'] = test_df['Cabin'].apply(lambda x: 0 if x in ['U'] else 1) train_df.groupby(['Cabin_Assigned'], as_index=False)['Survived'].agg(['count', 'mean']) 
train_df.head() 
train_df.shape 
test_df.shape 
train_df.info() 
train_df.columns 
test_df.info() 
train_df['Age'].fillna(train_df['Age'].mean(), inplace=True) test_df['Age'].fillna(test_df['Age'].mean(), inplace=True) test_df['Fare'].fillna(test_df['Fare'].mean(), inplace=True) ohe = OneHotEncoder(sparse_output=False) ode = OrdinalEncoder SI = SimpleImputer(strategy='most_frequent') ode_cols = ['Family_Size_Grouped'] ohe_cols = ['Sex', 'Embarked'] correlation_matrix = train_df.corr(numeric_only=True) # Create a heatmap using Seaborn plt.figure(figsize=(8, 6)) # Adjust the figure size as needed sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt=".2f") 
#NEW Drop Sibsp, Parch, TicketNumberCounts #new X = train_df.drop(['Survived', 'SibSp', 'Parch'], axis=1) y = train_df['Survived'] X_test = test_df.drop(['Age_Cut', 'Fare_Cut', 'SibSp', 'Parch'], axis=1) #OLD #X = train_df.drop(['Survived'], axis=1) #y = train_df['Survived'] #X_test = test_df.drop(['Age_Cut', 'Fare_Cut'], axis=1)
X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.2, stratify = y, random_state=21) ordinal_pipeline = Pipeline(steps=[ ('impute', SimpleImputer(strategy='most_frequent')), ('ord', OrdinalEncoder(handle_unknown='use_encoded_value', unknown_value=-1)) ]) ohe_pipeline = Pipeline(steps=[ ('impute', SimpleImputer(strategy='most_frequent')), ('one-hot', OneHotEncoder(handle_unknown = 'ignore', sparse_output=False)) ]) col_trans = ColumnTransformer(transformers=[ ('impute', SI, ['Age']), ('ord_pipeline', ordinal_pipeline, ode_cols), ('ohe_pipeline', ohe_pipeline, ohe_cols), # ('passthrough', 'passthrough', ['Pclass', 'TicketNumberCounts', 'Cabin_Assigned', 'Name_Size', 'Age', 'Fare']) ('passthrough', 'passthrough', ['Pclass', 'Cabin_Assigned', 'Name_Size', 'Age', 'Fare', 'TicketNumberCounts']) ], remainder='drop', n_jobs=-1) rfc = RandomForestClassifier() param_grid = { 'n_estimators': [150, 200, 300, 500], 'min_samples_split': [5, 10, 15], 'max_depth': [10, 13, 15, 17, 20], 'min_samples_leaf': [2, 4, 5, 6], 'criterion': ['gini', 'entropy'], } CV_rfc = GridSearchCV(estimator=rfc, param_grid=param_grid, cv=StratifiedKFold(n_splits=5)) pipefinalrfc = make_pipeline(col_trans, CV_rfc) pipefinalrfc.fit(X_train, y_train) 
print(CV_rfc.best_params_) print(CV_rfc.best_score_) 
dtc = DecisionTreeClassifier() param_grid = { 'min_samples_split': [5, 10, 15], 'max_depth': [10, 20, 30], 'min_samples_leaf': [1, 2, 4], 'criterion': ['gini', 'entropy'], } CV_dtc = GridSearchCV(estimator=dtc, param_grid=param_grid, cv=StratifiedKFold(n_splits=5)) pipefinaldtc = make_pipeline(col_trans, CV_dtc) pipefinaldtc.fit(X_train, y_train) 
print(CV_dtc.best_params_) print(CV_dtc.best_score_) 
knn = KNeighborsClassifier() param_grid = { 'n_neighbors': [3, 5, 7, 9, 11], 'weights': ['uniform', 'distance'], 'algorithm': ['auto', 'ball_tree', 'kd_tree', 'brute'], 'p': [1,2], } CV_knn = GridSearchCV(estimator=knn, param_grid=param_grid, cv=StratifiedKFold(n_splits=5)) pipefinalknn = make_pipeline(col_trans, CV_knn) pipefinalknn.fit(X_train, y_train) 
print(CV_knn.best_params_) print(CV_knn.best_score_) 
svc = SVC(probability=True) param_grid = { 'C': [100,10, 1.0, 0.1, 0.001, 0.001], 'kernel':['linear', 'poly', 'rbf', 'sigmoid'], } CV_svc = GridSearchCV(estimator=svc, param_grid=param_grid, cv=StratifiedKFold(n_splits=5)) pipefinalsvc = make_pipeline(col_trans, CV_svc) pipefinalsvc.fit(X_train, y_train) 
print(CV_svc.best_params_) print(CV_svc.best_score_) 
lr = LogisticRegression() param_grid = { 'C': [100,10, 1.0, 0.1, 0.001, 0.001], } CV_lr = GridSearchCV(estimator=lr, param_grid=param_grid, cv=StratifiedKFold(n_splits=5)) pipefinallr= make_pipeline(col_trans, CV_lr) pipefinallr.fit(X_train, y_train) 
print(CV_lr.best_params_) print(CV_lr.best_score_) 
gnb = GaussianNB() param_grid = { 'var_smoothing': [0.00000001, 0.000000001, 0.00000001], } CV_gnb = GridSearchCV(estimator=gnb, param_grid=param_grid, cv=StratifiedKFold(n_splits=5)) pipefinalgnb= make_pipeline(col_trans, CV_gnb) pipefinalgnb.fit(X_train, y_train) 
print(CV_gnb.best_params_) print(CV_gnb.best_score_) 
xg = XGBClassifier() param_grid = { 'booster': ['gbtree', 'gblinear','dart'], } CV_xg = GridSearchCV(estimator=xg, param_grid=param_grid, cv=StratifiedKFold(n_splits=5)) pipefinalxg= make_pipeline(col_trans, CV_xg) pipefinalxg.fit(X_train, y_train) 
print(CV_xg.best_params_) print(CV_xg.best_score_) 
abc = AdaBoostClassifier() dtc_2 = DecisionTreeClassifier(criterion = 'entropy', max_depth=10,min_samples_leaf=4, min_samples_split=10) svc_2 = SVC(probability=True, C=10, kernel='rbf') lr_2 = LogisticRegression(C=0.1) lr_3 = LogisticRegression(C=0.2) lr_4 = LogisticRegression(C=0.05) param_grid = { 'estimator': [dtc_2, svc_2, lr_2], 'n_estimators': [5, 10, 25, 50, 100], 'algorithm': ['SAMME', 'SAMME.R'], 'learning_rate': [(0.97 + x / 100) for x in range(1, 7)] } CV_abc = GridSearchCV(estimator=abc, param_grid=param_grid, cv=StratifiedKFold(n_splits=5)) pipefinalabc= make_pipeline(col_trans, CV_abc) pipefinalabc.fit(X_train, y_train) 
print(CV_abc.best_params_) print(CV_abc.best_score_) 
etc = ExtraTreesClassifier() param_grid = { "max_features": [1, 3, 10], "min_samples_split": [2, 3, 10], "min_samples_leaf": [1, 3, 10], "n_estimators" :[100,300], } CV_etc = GridSearchCV(estimator=etc, param_grid=param_grid, cv=StratifiedKFold(n_splits=5)) pipefinaletc= make_pipeline(col_trans, CV_etc) pipefinaletc.fit(X_train, y_train) 
print(CV_etc.best_params_) print(CV_etc.best_score_) 
GBC = GradientBoostingClassifier() param_grid = { 'n_estimators' : [300, 400, 500], 'learning_rate': [ 0.1, 0.3, 0.6, 1.0], 'max_depth': [8, 10, 12], 'min_samples_leaf': [50, 100, 120, 150], 'max_features': [0.1, 0.3, 0.5] } CV_gbc = GridSearchCV(estimator=GBC, param_grid=param_grid, cv=StratifiedKFold(n_splits=5)) pipefinalgbc= make_pipeline(col_trans, CV_gbc) pipefinalgbc.fit(X_train, y_train) 
print(CV_gbc.best_params_) print(CV_gbc.best_score_) 
vc1 = VotingClassifier([('gbc', CV_gbc.best_estimator_), ('etc', CV_etc.best_estimator_), ('nb', CV_gnb.best_estimator_) ], voting='hard', weights=[1,2,3] ) vc2 = VotingClassifier([('abc', CV_abc.best_estimator_), ('etc', CV_etc.best_estimator_), ('nb', CV_gnb.best_estimator_) ], voting='hard', weights=[1,2,3] ) #1,2,3 is the best performing one pipefinalcv1 = make_pipeline(col_trans, vc1) pipefinalcv2 = make_pipeline(col_trans, vc2) pipefinalcv1.fit(X_train, y_train) 
pipefinalcv2.fit(X_train, y_train) 
Y_pred = pipefinalrfc.predict(X_test) Y_pred2 = pipefinaldtc.predict(X_test) Y_pred3 = pipefinalknn.predict(X_test) Y_pred4 = pipefinalsvc.predict(X_test) Y_pred5 = pipefinallr.predict(X_test) Y_pred6 = pipefinalgnb.predict(X_test) Y_pred7 = pipefinalxg.predict(X_test) Y_pred8 = pipefinalabc.predict(X_test) Y_pred9 = pipefinaletc.predict(X_test) Y_pred10 = pipefinalgbc.predict(X_test) Y_pred11 = pipefinalcv1.predict(X_test) Y_pred12 = pipefinalcv2.predict(X_test) submission = pd.DataFrame({ 'PassengerId': test_df['PassengerId'], 'Survived': Y_pred }) submission2 = pd.DataFrame({ 'PassengerId': test_df['PassengerId'], 'Survived': Y_pred2 }) submission3 = pd.DataFrame({ 'PassengerId': test_df['PassengerId'], 'Survived': Y_pred3 }) submission4 = pd.DataFrame({ 'PassengerId': test_df['PassengerId'], 'Survived': Y_pred4 }) submission5 = pd.DataFrame({ 'PassengerId': test_df['PassengerId'], 'Survived': Y_pred5 }) submission6 = pd.DataFrame({ 'PassengerId': test_df['PassengerId'], 'Survived': Y_pred6 }) submission7 = pd.DataFrame({ 'PassengerId': test_df['PassengerId'], 'Survived': Y_pred7 }) submission8 = pd.DataFrame({ 'PassengerId': test_df['PassengerId'], 'Survived': Y_pred8 }) submission9 = pd.DataFrame({ 'PassengerId': test_df['PassengerId'], 'Survived': Y_pred9 }) submission10 = pd.DataFrame({ 'PassengerId': test_df['PassengerId'], 'Survived': Y_pred10 }) submission11 = pd.DataFrame({ "PassengerId": test_df["PassengerId"], "Survived": Y_pred11 }) submission12 = pd.DataFrame({ "PassengerId": test_df["PassengerId"], "Survived": Y_pred12 }) submission.to_csv('/kaggle/working/submission929_1.csv', index=False) submission2.to_csv('/kaggle/working/submission929_2.csv', index=False) submission3.to_csv('/kaggle/working/submission929_3.csv', index=False) submission4.to_csv('/kaggle/working/submission929_4.csv', index=False) submission5.to_csv('/kaggle/working/submission929_5.csv', index=False) submission6.to_csv('/kaggle/working/submission929_6.csv', index=False) submission7.to_csv('/kaggle/working/submission929_7.csv', index=False) submission8.to_csv('/kaggle/working/submission101_8.csv', index=False) submission9.to_csv('/kaggle/working/submission101_9.csv', index=False) submission10.to_csv('/kaggle/working/submission101_10.csv', index=False) submission11.to_csv('/kaggle/working/submission101_11.csv', index=False) submission12.to_csv('/kaggle/working/submission101_12.csv', index=False) 