使用级联预测模型 完整代码

import pandas as pd
import numpy as np
import re
import sklearn
import seaborn as sns
import matplotlib.pyplot as plt
import xgboost as xgb
import plotly.offline as py
py.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import plotly.tools as tls
 
import warnings
warnings.filterwarnings('ignore')
 
# Going to use these 5 base models for the stacking
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier, ExtraTreesClassifier
from sklearn.svm import SVC
from sklearn.cross_validation import KFold;
# Load in the train and test datasets
train = pd.read_csv('titanic_train.csv')
test = pd.read_csv('test.csv')
# Store our passenger ID for easy access
PassengerId = test['PassengerId']
# print(train.head(3))
full_data = [train, test]
 
# 额外添加一些需要从已有数据中计算得到的其他特征
# 例如姓名的长度
train['Name_length'] = train['Name'].apply(len)
test['Name_length'] = test['Name'].apply(len)
# 是否有Cabin
train['Has_Cabin'] = train["Cabin"].apply(lambda x: 0 if type(x) == float else 1)
test['Has_Cabin'] = test["Cabin"].apply(lambda x: 0 if type(x) == float else 1)
 
# 计算全部家人的数目
for dataset in full_data:
    dataset['FamilySize'] = dataset['SibSp'] + dataset['Parch'] + 1
# 是否是一个人
for dataset in full_data:
    dataset['IsAlone'] = 0
    dataset.loc[dataset['FamilySize'] == 1, 'IsAlone'] = 1
# 对Embarked列的空数据进行处理
for dataset in full_data:
    dataset['Embarked'] = dataset['Embarked'].fillna('S')
# 用训练集数据的Fare的中值来填充所有Fare为空的数据
for dataset in full_data:
    dataset['Fare'] = dataset['Fare'].fillna(train['Fare'].median())
train['CategoricalFare'] = pd.qcut(train['Fare'], 4)
# 创建一个新的特征CategoricalAge
for dataset in full_data:
    age_avg = dataset['Age'].mean()
    age_std = dataset['Age'].std()
    age_null_count = dataset['Age'].isnull().sum()
    age_null_random_list = np.random.randint(age_avg - age_std, age_avg + age_std, size=age_null_count)
    dataset['Age'][np.isnan(dataset['Age'])] = age_null_random_list
    dataset['Age'] = dataset['Age'].astype(int)
train['CategoricalAge'] = pd.cut(train['Age'], 5)
# 定义一个函数，用于寻找姓名中的Title
def get_title(name):
    title_search = re.search(' ([A-Za-z]+)\.', name)
    # If the title exists, extract and return it.
    if title_search:
        return title_search.group(1)
    return ""
# 创建一个新的变量Title
for dataset in full_data:
    dataset['Title'] = dataset['Name'].apply(get_title)
# 将一些不常见的Title转换为一些对应的常见Title种类
for dataset in full_data:
    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')
 
for dataset in full_data:
    # 将性别映射至0,1
    dataset['Sex'] = dataset['Sex'].map( {'female': 0, 'male': 1} ).astype(int)
    
    # 将Title映射至0-5。
    title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, &#