In [ ]:

    

# data analysis and wrangling
import pandas as pd
import numpy as np
import random as rnd

# visualization
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline


    

In [ ]:

    

train_df = pd.read_csv('./train.csv')
test_df = pd.read_csv('./test.csv')
combine = [train_df, test_df]


    

In [ ]:

    

## Add Title
for dataset in combine:
    dataset['Title'] = dataset.Name.str.extract(' ([A-Za-z]+)\.', expand=False)

pd.crosstab(train_df['Title'], train_df['Survived'])


    

In [ ]:

    

## Add Title
for dataset in combine:
    dataset['Title'] = dataset.Name.str.extract(' ([A-Za-z]+)\.', expand=False)

    dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col', 'Don', 'Dr', 'Sir', 'Major', 'Jonkheer', 'Dona'], 'Rare')

    dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')

print(train_df[['Title', 'Survived']].groupby(['Title'], as_index=False).mean())

title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Rare": 5, "Rev": 6}
for dataset in combine:
    dataset['Title'] = dataset['Title'].map(title_mapping)
    dataset['Title'] = dataset['Title'].fillna(0)


    

In [ ]:

    

## Convert Sex to int
for dataset in combine:
    dataset['SexType'] = dataset['Sex'].map( {'female': 1, 'male': 0} ).astype(int)

pd.crosstab(train_df['SexType'], train_df['Survived'])


    

In [ ]:

    

guess_ages = np.zeros((2,3))
guess_ages

for dataset in combine:
    for i in range(0, 2): # Sex
        for j in range(0, 3): # Pclass
            guess_df = dataset[(dataset['SexType'] == i) & (dataset['Pclass'] == j+1)]['Age'].dropna()

            age_guess = guess_df.median()

            # Convert random age float to nearest .5 age
            guess_ages[i,j] = int( age_guess/0.5 + 0.5 ) * 0.5
            
    for i in range(0, 2):
        for j in range(0, 3):
            dataset.loc[ dataset.Age.isnull() & (dataset.SexType == i) & (dataset.Pclass == j + 1), 'Age'] = guess_ages[i,j]

    dataset['Age'] = dataset['Age'].astype(int)

train_df.Age


    

In [ ]:

    

for dataset in combine:
    dataset['FamilySize'] = dataset['SibSp'] + dataset['Parch']

train_df[['FamilySize', 'Survived']].groupby(['FamilySize'], as_index=False).mean().sort_values(by='Survived', ascending=False)


    

In [ ]:

    

## Add family features
for dataset in combine:
    dataset['IsAlone'] = 0
    dataset.loc[dataset['FamilySize'] == 0, 'IsAlone'] = 1

train_df[['IsAlone', 'Survived']].groupby(['IsAlone'], as_index=False).mean()


    

In [ ]:

    

for dataset in combine:    
    dataset.loc[ dataset['Age'] <= 16, 'Age'] = 0
    dataset.loc[(dataset['Age'] > 16) & (dataset['Age'] <= 32), 'Age'] = 1
    dataset.loc[(dataset['Age'] > 32) & (dataset['Age'] <= 48), 'Age'] = 2
    dataset.loc[(dataset['Age'] > 48) & (dataset['Age'] <= 64), 'Age'] = 3
    dataset.loc[ dataset['Age'] > 64, 'Age']
train_df.head()


    

In [ ]:

    

## Add Age*Class
for dataset in combine:
    dataset['Age*Class'] = dataset.Age * dataset.Pclass

train_df.loc[:, ['Age*Class', 'Age', 'Pclass']].head(10)


    

In [ ]:

    

for dataset in combine:
    dataset['Embarked'] = dataset['Embarked'].fillna('S')
    
train_df[['Embarked', 'Survived']].groupby(['Embarked'], as_index=False).mean().sort_values(by='Survived', ascending=False)


    

In [ ]:

    

for dataset in combine:
    dataset['EmbarkedType'] = dataset['Embarked'].map( {'S': 0, 'C': 1, 'Q': 2} ).astype(int)

train_df.head()


    

In [ ]:

    

test_df['Fare'].fillna(test_df['Fare'].dropna().median(), inplace=True)


    

In [ ]:

    

train_df['FareBand'] = pd.qcut(train_df['Fare'], 4)
train_df[['FareBand', 'Survived']].groupby(['FareBand'], as_index=False).mean().sort_values(by='FareBand', ascending=True)

for dataset in combine:
    dataset.loc[ dataset['Fare'] <= 7.91, 'Fare'] = 0
    dataset.loc[(dataset['Fare'] > 7.91) & (dataset['Fare'] <= 14.454), 'Fare'] = 1
    dataset.loc[(dataset['Fare'] > 14.454) & (dataset['Fare'] <= 31), 'Fare']   = 2
    dataset.loc[ dataset['Fare'] > 31, 'Fare'] = 3
    dataset['Fare'] = dataset['Fare'].astype(int)

train_df = train_df.drop(['FareBand'], axis=1)
combine = [train_df, test_df]


    

In [ ]:

    

train_df


    

In [ ]:

    

##
## Predict
##

### cross validation
from sklearn.model_selection import cross_val_score

### 
from sklearn.ensemble import RandomForestClassifier
import xgboost as xgb


    

In [ ]:

    

X_train = train_df.drop(["PassengerId", "Survived", "Name", "Sex", "FamilySize", "SibSp", "Parch", "Ticket", "Cabin", "Embarked", "EmbarkedType"], axis=1)
Y_train = train_df["Survived"]
X_test  = test_df.drop(["PassengerId",                      "Name", "Sex", "FamilySize", "SibSp", "Parch", "Ticket", "Cabin", "Embarked", "EmbarkedType"], axis=1).copy()
print(X_train.shape, Y_train.shape, X_test.shape)
X_train


    

In [ ]:

    

# Random Forest

random_forest = RandomForestClassifier(n_estimators=200, max_depth=5)
random_forest.fit(X_train, Y_train)
Y_pred = random_forest.predict(X_test)
random_forest.score(X_train, Y_train)
acc_random_forest = round(random_forest.score(X_train, Y_train) * 100, 2)
print("Training Accuracy = %s" % acc_random_forest)

print("Cross Validation Accuracy = %s " % cross_val_score(random_forest, X_train, Y_train, cv=4).mean())


    

In [ ]:

    

gbm = xgb.XGBClassifier(max_depth=5, n_estimators=200, learning_rate=0.05).fit(X_train, Y_train)
Y_pred = gbm.predict(X_test)

acc_xgboost= round(gbm.score(X_train, Y_train) * 100, 2)
print("Training Accuracy = %s" % acc_xgboost)
print("Cross Validation Accuracy = %s " % cross_val_score(gbm, X_train, Y_train, cv=4).mean())


    

In [ ]:

    

submission = pd.DataFrame({
        "PassengerId": test_df["PassengerId"],
        "Survived": Y_pred
    })
print(submission)

submission.to_csv('./my_submission2.csv', index=False)

## This gets score 0.77033


    

In [ ]: