# preview the data
train_df.head()  # 默认前5行

train_df.tail() # 默认后5行

train_df.describe()  # 数据的描述（总数、均值、标准差、最大、最小、25%、50%、75%）
# Review survived rate using `percentiles=[.61, .62]` knowing our problem description mentions 38% survival rate.
# Review Parch distribution using `percentiles=[.75, .8]`
# SibSp distribution `[.68, .69]`
# Age and Fare `[.1, .2, .3, .4, .5, .6, .7, .8, .9, .99]`

train_df.describe(include=[‘O‘])  # 找出特征中几个出现的不同值和频率最高

# 通过groupby找出该特征与目标之间的关联
train_df[[‘Pclass‘, ‘Survived‘]].groupby([‘Pclass‘], as_index=False).mean().sort_values(by=‘Survived‘, ascending=False)

train_df[["Sex", "Survived"]].groupby([‘Sex‘], as_index=False).mean().sort_values(by=‘Survived‘, ascending=False)

train_df[["SibSp", "Survived"]].groupby([‘SibSp‘], as_index=False).mean().sort_values(by=‘Survived‘, ascending=False)

train_df[["Parch", "Survived"]].groupby([‘Parch‘], as_index=False).mean().sort_values(by=‘Survived‘, ascending=False)

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

pd.crosstab(train_df[‘Title‘], train_df[‘Sex‘])

for dataset in combine:
    dataset[‘Title‘] = dataset[‘Title‘].replace([‘Lady‘, ‘Countess‘,‘Capt‘, ‘Col‘, 	‘Don‘, ‘Dr‘, ‘Major‘, ‘Rev‘, ‘Sir‘, ‘Jonkheer‘, ‘Dona‘], ‘Rare‘)

    dataset[‘Title‘] = dataset[‘Title‘].replace(‘Mlle‘, ‘Miss‘)
    dataset[‘Title‘] = dataset[‘Title‘].replace(‘Ms‘, ‘Miss‘)
    dataset[‘Title‘] = dataset[‘Title‘].replace(‘Mme‘, ‘Mrs‘)
    
train_df[[‘Title‘, ‘Survived‘]].groupby([‘Title‘], as_index=False).mean()

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

train_df.head()

for dataset in combine:
    dataset[‘Sex‘] = dataset[‘Sex‘].map( {‘female‘: 1, ‘male‘: 0} ).astype(int)

train_df.head()

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

            # age_mean = guess_df.mean()
            # age_std = guess_df.std()
            # age_guess = rnd.uniform(age_mean - age_std, age_mean + age_std)

            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.Sex == i) & (dataset.Pclass == j+1),                    ‘Age‘] = guess_ages[i,j]

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

train_df.head()

train_df[‘AgeBand‘] = pd.cut(train_df[‘Age‘], 5)
train_df[[‘AgeBand‘, ‘Survived‘]].groupby([‘AgeBand‘], as_index=False).mean().sort_values(by=‘AgeBand‘, ascending=True)

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()

train_df = train_df.drop([‘AgeBand‘], axis=1)
combine = [train_df, test_df]
train_df.head()

for dataset in combine:
    dataset[‘FamilySize‘] = dataset[‘SibSp‘] + dataset[‘Parch‘] + 1

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

for dataset in combine:
    dataset[‘IsAlone‘] = 0
    dataset.loc[dataset[‘FamilySize‘] == 1, ‘IsAlone‘] = 1

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

train_df = train_df.drop([‘Parch‘, ‘SibSp‘, ‘FamilySize‘], axis=1)
test_df = test_df.drop([‘Parch‘, ‘SibSp‘, ‘FamilySize‘], axis=1)
combine = [train_df, test_df]

train_df.head()

for dataset in combine:
    dataset[‘Age*Class‘] = dataset.Age * dataset.Pclass

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

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

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

train_df.head()

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

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]
    
train_df.head(10)

test_df.head(10)

coeff_df = pd.DataFrame(train_df.columns.delete(0))
coeff_df.columns = [‘Feature‘]
coeff_df["Correlation"] = pd.Series(logreg.coef_[0])

coeff_df.sort_values(by=‘Correlation‘, ascending=False)

models = pd.DataFrame({
    ‘Model‘: [‘Support Vector Machines‘, ‘KNN‘, ‘Logistic Regression‘, 
              ‘Random Forest‘, ‘Naive Bayes‘, ‘Perceptron‘, 
              ‘Stochastic Gradient Decent‘, ‘Linear SVC‘, 
              ‘Decision Tree‘],
    ‘Score‘: [acc_svc, acc_knn, acc_log, 
              acc_random_forest, acc_gaussian, acc_perceptron, 
              acc_sgd, acc_linear_svc, acc_decision_tree]})
models.sort_values(by=‘Score‘, ascending=False)