集成学习：XGBoost

r囧r小猫 2023-07-11 06:23 58阅读 0赞

# ![20191009191333910.png][][日萌社][Link 1] #

[人工智能AI：Keras PyTorch MXNet TensorFlow PaddlePaddle 深度学习实战（不定时更新）][AI_Keras PyTorch MXNet TensorFlow PaddlePaddle]

--------------------

[集成学习：Bagging、随机森林、Boosting、GBDT][Bagging_Boosting_GBDT]

[集成学习：XGBoost][XGBoost]

[集成学习：lightGBM（一）][lightGBM]

[集成学习：lightGBM（二）][lightGBM 1]

--------------------

# 5.1 xgboost算法原理 #

XGBoost（Extreme Gradient Boosting）全名叫极端梯度提升树，XGBoost是集成学习方法的王牌，在Kaggle数据挖掘比赛中，大部分获胜者用了XGBoost。

XGBoost在绝大多数的回归和分类问题上表现的十分顶尖，本节将较详细的介绍XGBoost的算法原理。

## 1 最优模型的构建方法 ##

我们在前面已经知道，构建最优模型的一般方法是**最小化训练数据的损失函数**。

我们用字母 L表示损失，如下式：

![2020030417501622.png][]

> 其中，F是假设空间
> 
> 假设空间是在已知属性和属性可能取值的情况下，对所有可能满足目标的情况的一种毫无遗漏的假设集合。

式（1.1）称为**经验风险最小化**，训练得到的模型复杂度较高。当训练数据较小时，模型很容易出现过拟合问题。

因此，为了降低模型的复杂度，常采用下式：

![20200304175026284.png][]

> 其中J(f)J(f)为模型的复杂度，

式（2.1）称为**结构风险最小化**，结构风险最小化的模型往往对训练数据以及未知的测试数据都有较好的预测 。

应用：

*  决策树的生成和剪枝分别对应了经验风险最小化和结构风险最小化，
 *  XGBoost的决策树生成是结构风险最小化的结果，后续会详细介绍。

## 2 XGBoost的目标函数推导 ##

### 2.1 目标函数确定 ###

目标函数，即损失函数，通过最小化损失函数来构建最优模型。

由前面可知， 损失函数应加上表示模型复杂度的正则项，且XGBoost对应的模型包含了多个CART树，因此，模型的目标函数为：

![20200304175044512.png][]

![20200304175053821.png][]

### 2.2 CART树的介绍 ###

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70][]

### 2.3 树的复杂度定义 ###

2.3.1 定义每课树的复杂度

XGBoost法对应的模型包含了多棵cart树，定义每棵树的复杂度：

![20200304175137797.png][]

2.3.2 树的复杂度举例

假设我们要预测一家人对电子游戏的喜好程度，考虑到年轻和年老相比，年轻更可能喜欢电子游戏，以及男性和女性相比，男性更喜欢电子游戏，故先根据年龄大小区分小孩和大人，然后再通过性别区分开是男是女，逐一给各人在电子游戏喜好程度上打分，如下图所示：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 1][]

就这样，训练出了2棵树tree1和tree2，类似之前gbdt的原理，两棵树的结论累加起来便是最终的结论，所以：

*  小男孩的预测分数就是两棵树中小孩所落到的结点的分数相加：2 + 0.9 = 2.9。
 *  爷爷的预测分数同理：-1 + （-0.9）= -1.9。

具体如下图所示：![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 2][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 3][]

### 2.4 目标函数推导 ###

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 4][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 5][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 6][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 7][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 8][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 9][]

## 3 XGBoost的回归树构建方法 ##

### 3.1 计算分裂节点 ###

在实际训练过程中，当建立第 t 棵树时，XGBoost采用贪心法进行树结点的分裂：

从树深为0时开始：

*  对树中的每个叶子结点尝试进行分裂；
 *  每次分裂后，原来的一个叶子结点继续分裂为左右两个子叶子结点，原叶子结点中的样本集将根据该结点的判断规则分散到左右两个叶子结点中；
 *  新分裂一个结点后，我们需要检测这次分裂是否会给损失函数带来增益，增益的定义如下：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 10][]

如果增益Gain>0，即分裂为两个叶子节点后，目标函数下降了，那么我们会考虑此次分裂的结果。

那么一直这样分裂，什么时候才会停止呢？

### 3.2 停止分裂条件判断 ###

情况一：上节推导得到的打分函数是衡量树结构好坏的标准，因此，可用打分函数来选择最佳切分点。首先确定样本特征的所有切分点，对每一个确定的切分点进行切分，切分好坏的标准如下：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 11][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 12][]

## 4 XGBoost与GDBT的区别 ##

*  区别一：
    
     *  XGBoost生成CART树考虑了树的复杂度，
     *  GDBT未考虑，GDBT在树的剪枝步骤中考虑了树的复杂度。
 *  区别二：
    
     *  XGBoost是拟合上一轮损失函数的二阶导展开，GDBT是拟合上一轮损失函数的一阶导展开，因此，XGBoost的准确性更高，且满足相同的训练效果，需要的迭代次数更少。
 *  区别三：
    
     *  XGBoost与GDBT都是逐次迭代来提高模型性能，但是XGBoost在选取最佳切分点时可以开启多线程进行，大大提高了运行速度。

## 5 小结 ##

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 13][]

--------------------

# 5.2 xgboost算法api介绍 #

## 1 xgboost的安装： ##

官网链接：[https://xgboost.readthedocs.io/en/latest/][https_xgboost.readthedocs.io_en_latest]

pip3 install xgboost

## 2 xgboost参数介绍 ##

xgboost虽然被称为kaggle比赛神奇，但是，我们要想训练出不错的模型，必须要给参数传递合适的值。

xgboost中封装了很多参数，主要由三种类型构成：**通用参数（general parameters），Booster 参数（booster parameters）和学习目标参数（task parameters）**

*  通用参数：主要是**宏观函数控制；**
 *  Booster参数：取决于选择的Booster类型，**用于控制每一步的booster（tree, regressiong）**；
 *  学习目标参数：**控制训练目标的表现**。

### 2.1 通用参数（general parameters） ###

1.  **booster** \[缺省值=gbtree\]
2.  决定使用哪个booster，可以是gbtree，gblinear或者dart。
    
     *  g**btree和dart使用基于树的模型(dart 主要多了 Dropout)，而gblinear 使用线性函数.**
3.  **silent** \[缺省值=0\]
    
     *  设置为0打印运行信息；设置为1静默模式，不打印
4.  **nthread** \[缺省值=设置为最大可能的线程数\]
    
     *  并行运行xgboost的线程数，输入的参数应该<=系统的CPU核心数，若是没有设置算法会检测将其设置为CPU的全部核心数

> 下面的两个参数不需要设置，使用默认的就好了

1.  **num\_pbuffer** \[xgboost自动设置，不需要用户设置\]
    
     *  预测结果缓存大小，通常设置为训练实例的个数。该缓存用于保存最后boosting操作的预测结果。
2.  **num\_feature** \[xgboost自动设置，不需要用户设置\]
    
     *  在boosting中使用特征的维度，设置为特征的最大维度

### 2.2 Booster 参数（booster parameters） ###

2.2.1 Parameters for Tree Booster

1.  **eta** \[缺省值=0.3，别名：learning\_rate\]
    
     *  更新中减少的步长来防止过拟合。
     *  在每次boosting之后，可以直接获得新的特征权值，这样可以使得boosting更加鲁棒。
     *  范围： \[0,1\]
2.  **gamma** \[缺省值=0，别名: min\_split\_loss\]（分裂最小loss）
    
     *  在节点分裂时，只有分裂后损失函数的值下降了，才会分裂这个节点。
     *  Gamma指定了节点分裂所需的最小损失函数下降值。 这个参数的值越大，算法越保守。这个参数的值和损失函数息息相关，所以是需要调整的。
     *  范围: \[0,∞\]
3.  **max\_depth** \[缺省值=6\]
    
     *  这个值为树的最大深度。 这个值也是用来避免过拟合的。max\_depth越大，模型会学到更具体更局部的样本。设置为0代表没有限制
     *  范围: \[0,∞\]
4.  **min\_child\_weight** \[缺省值=1\]
    
     *  决定最小叶子节点样本权重和。XGBoost的这个参数是最小样本权重的和.
     *  当它的值较大时，可以避免模型学习到局部的特殊样本。 但是如果这个值过高，会导致欠拟合。这个参数需要使用CV来调整。.
     *  范围: \[0,∞\]
5.  **subsample** \[缺省值=1\]
    
     *  这个参数控制对于每棵树，随机采样的比例。
     *  减小这个参数的值，算法会更加保守，避免过拟合。但是，如果这个值设置得过小，它可能会导致欠拟合。
     *  典型值：0.5-1，0.5代表平均采样，防止过拟合.
     *  范围: (0,1\]
6.  **colsample\_bytree** \[缺省值=1\]
    
     *  用来控制每棵随机采样的列数的占比(每一列是一个特征)。
     *  典型值：0.5-1
     *  范围: (0,1\]
7.  **colsample\_bylevel** \[缺省值=1\]
    
     *  用来控制树的每一级的每一次分裂，对列数的采样的占比。
     *  我个人一般不太用这个参数，因为subsample参数和colsample\_bytree参数可以起到相同的作用。但是如果感兴趣，可以挖掘这个参数更多的用处。
     *  范围: (0,1\]
8.  **lambda** \[缺省值=1，别名: reg\_lambda\]
    
     *  权重的L2正则化项(和Ridge regression类似)。
     *  这个参数是用来控制XGBoost的正则化部分的。虽然大部分数据科学家很少用到这个参数，但是这个参数
     *  在减少过拟合上还是可以挖掘出更多用处的。.
9.  **alpha** \[缺省值=0，别名: reg\_alpha\]
    
     *  权重的L1正则化项。(和Lasso regression类似)。 可以应用在很高维度的情况下，使得算法的速度更快。
10. **scale\_pos\_weight**\[缺省值=1\]
    
     *  在各类别样本十分不平衡时，把这个参数设定为一个正值，可以使算法更快收敛。通常可以将其设置为负
     *  样本的数目与正样本数目的比值。

2.2.2 Parameters for Linear Booster

> linear booster一般很少用到。

1.  **lambda** \[缺省值=0，别称: reg\_lambda\]
    
     *  L2正则化惩罚系数，增加该值会使得模型更加保守。
2.  **alpha** \[缺省值=0，别称: reg\_alpha\]
    
     *  L1正则化惩罚系数，增加该值会使得模型更加保守。
3.  **lambda\_bias** \[缺省值=0，别称: reg\_lambda\_bias\]
    
     *  偏置上的L2正则化(没有在L1上加偏置，因为并不重要)

### 2.3 学习目标参数（task parameters） ###

1.  **objective** \[缺省值=reg:linear\]
    
    1.  “**reg:linear**” – 线性回归
    2.  **“reg:logistic**” – 逻辑回归
    3.  “**binary:logistic**” – 二分类逻辑回归，输出为概率
    4.  “**multi:softmax**” – 使用softmax的多分类器，返回预测的类别(不是概率)。在这种情况下，你还需要多设一个参数：num\_class(类别数目)
    5.  “**multi:softprob**” – 和multi:softmax参数一样，但是返回的是每个数据属于各个类别的概率。
2.  **eval\_metric** \[缺省值=通过目标函数选择\]
    
    可供选择的如下所示：
    
    1.  “**rmse**”: 均方根误差
    2.  “**mae**”: 平均绝对值误差
    3.  “**logloss**”: 负对数似然函数值
    4.  “**error”**: 二分类错误率。
        
         *  其值通过错误分类数目与全部分类数目比值得到。对于预测，预测值大于0.5被认为是正类，其它归为负类。
    5.  “**error@t**”: 不同的划分阈值可以通过 ‘t’进行设置
    6.  “**merror**”: 多分类错误率，计算公式为(wrong cases)/(all cases)
    7.  “**mlogloss**”: 多分类log损失
    8.  “**auc**”: 曲线下的面积
3.  seed \[缺省值=0\]
    
     *  随机数的种子

*  设置它可以复现随机数据的结果，也可以用于调整参数

--------------------

# 5.3 xgboost案例介绍 #

## 1 案例背景 ##

> 该案例和前面决策树中所用案例一样。

泰坦尼克号沉没是历史上最臭名昭着的沉船事件之一。1912年4月15日，在她的处女航中，泰坦尼克号在与冰山相撞后沉没，在2224名乘客和机组人员中造成1502人死亡。这场耸人听闻的悲剧震惊了国际社会，并为船舶制定了更好的安全规定。 造成海难失事的原因之一是乘客和机组人员没有足够的救生艇。尽管幸存下沉有一些运气因素，但有些人比其他人更容易生存，例如妇女，儿童和上流社会。 在这个案例中，我们要求您完成对哪些人可能存活的分析。特别是，我们要求您运用机器学习工具来预测哪些乘客幸免于悲剧。

> 案例：[https://www.kaggle.com/c/titanic/overview][https_www.kaggle.com_c_titanic_overview]

我们提取到的数据集中的特征包括票的类别，是否存活，乘坐班次，年龄，登陆home.dest，房间，船和性别等。

> 数据：[http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt][http_biostat.mc.vanderbilt.edu_wiki_pub_Main_DataSets_titanic.txt]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 14][]

经过观察数据得到:

*  **1 乘坐班是指乘客班（1，2，3），是社会经济阶层的代表。**
 *  **2 其中age数据存在缺失。**

## 2 步骤分析 ##

*  1.获取数据
 *  2.数据基本处理
    
     *  2.1 确定特征值,目标值
     *  2.2 缺失值处理
     *  2.3 数据集划分
 *  3.特征工程(字典特征抽取)
 *  4.机器学习(xgboost)
 *  5.模型评估

## 3 代码实现 ##

*  导入需要的模块

import pandas as pd
    import numpy as np
    from sklearn.feature_extraction import DictVectorizer
    from sklearn.model_selection import train_test_split

*  1.获取数据

# 1、获取数据
    titan = pd.read_csv("http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt")

*  2.数据基本处理
    
     *  2.1 确定特征值,目标值
    
        x = titan[["pclass", "age", "sex"]]
        y = titan["survived"]
    
     *  2.2 缺失值处理
    
        # 缺失值需要处理，将特征当中有类别的这些特征进行字典特征抽取
        x['age'].fillna(x['age'].mean(), inplace=True)
    
     *  2.3 数据集划分
    
        x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=22)
 *  3.特征工程(字典特征抽取)

特征中出现类别符号，需要进行one-hot编码处理(DictVectorizer)

x.to\_dict(orient="records") 需要将数组特征转换成字典数据

# 对于x转换成字典数据x.to_dict(orient="records")
    # [{"pclass": "1st", "age": 29.00, "sex": "female"}, {}]
    
    transfer = DictVectorizer(sparse=False)
    
    x_train = transfer.fit_transform(x_train.to_dict(orient="records"))
    x_test = transfer.fit_transform(x_test.to_dict(orient="records"))

--------------------

*  4.xgboost模型训练和模型评估

# 模型初步训练
    from xgboost import XGBClassifier
    xg = XGBClassifier()
    
    xg.fit(x_train, y_train)
    
    xg.score(x_test, y_test)

# 针对max_depth进行模型调优
    depth_range = range(10)
    score = []
    for i in depth_range:
        xg = XGBClassifier(eta=1, gamma=0, max_depth=i)
        xg.fit(x_train, y_train)
        s = xg.score(x_test, y_test)
        print(s)
        score.append(s)

# 结果可视化
    import matplotlib.pyplot as plt
    
    plt.plot(depth_range, score)
    
    plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 15][]

--------------------

In \[1\]:

\# 1.获取数据  
\# 2.数据基本处理  
\# 2.1 确定特征值,目标值  
\# 2.2 缺失值处理  
\# 2.3 数据集划分  
\# 3.特征工程(字典特征抽取)  
\# 4.机器学习(xgboost)  
\# 5.模型评估

In \[2\]:

import pandas as pd  
import numpy as np  
from sklearn.model\_selection import train\_test\_split  
from sklearn.feature\_extraction import DictVectorizer  
from sklearn.tree import DecisionTreeClassifier, export\_graphviz

In \[3\]:

\# 1.获取数据  
titan = pd.read\_csv("http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt")

In \[4\]:

titan

Out\[4\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>row.names</th> 
   <th>pclass</th> 
   <th>survived</th> 
   <th>name</th> 
   <th>age</th> 
   <th>embarked</th> 
   <th>home.dest</th> 
   <th>room</th> 
   <th>ticket</th> 
   <th>boat</th> 
   <th>sex</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>1</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Allen, Miss Elisabeth Walton</td> 
   <td>29.0000</td> 
   <td>Southampton</td> 
   <td>St Louis, MO</td> 
   <td>B-5</td> 
   <td>24160 L221</td> 
   <td>2</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>2</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Allison, Miss Helen Loraine</td> 
   <td>2.0000</td> 
   <td>Southampton</td> 
   <td>Montreal, PQ / Chesterville, ON</td> 
   <td>C26</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>3</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Allison, Mr Hudson Joshua Creighton</td> 
   <td>30.0000</td> 
   <td>Southampton</td> 
   <td>Montreal, PQ / Chesterville, ON</td> 
   <td>C26</td> 
   <td>NaN</td> 
   <td>(135)</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>4</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Allison, Mrs Hudson J.C. (Bessie Waldo Daniels)</td> 
   <td>25.0000</td> 
   <td>Southampton</td> 
   <td>Montreal, PQ / Chesterville, ON</td> 
   <td>C26</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>5</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Allison, Master Hudson Trevor</td> 
   <td>0.9167</td> 
   <td>Southampton</td> 
   <td>Montreal, PQ / Chesterville, ON</td> 
   <td>C22</td> 
   <td>NaN</td> 
   <td>11</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>5</th> 
   <td>6</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Anderson, Mr Harry</td> 
   <td>47.0000</td> 
   <td>Southampton</td> 
   <td>New York, NY</td> 
   <td>E-12</td> 
   <td>NaN</td> 
   <td>3</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>6</th> 
   <td>7</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Andrews, Miss Kornelia Theodosia</td> 
   <td>63.0000</td> 
   <td>Southampton</td> 
   <td>Hudson, NY</td> 
   <td>D-7</td> 
   <td>13502 L77</td> 
   <td>10</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>7</th> 
   <td>8</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Andrews, Mr Thomas, jr</td> 
   <td>39.0000</td> 
   <td>Southampton</td> 
   <td>Belfast, NI</td> 
   <td>A-36</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>8</th> 
   <td>9</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Appleton, Mrs Edward Dale (Charlotte Lamson)</td> 
   <td>58.0000</td> 
   <td>Southampton</td> 
   <td>Bayside, Queens, NY</td> 
   <td>C-101</td> 
   <td>NaN</td> 
   <td>2</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>9</th> 
   <td>10</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Artagaveytia, Mr Ramon</td> 
   <td>71.0000</td> 
   <td>Cherbourg</td> 
   <td>Montevideo, Uruguay</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>(22)</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>10</th> 
   <td>11</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Astor, Colonel John Jacob</td> 
   <td>47.0000</td> 
   <td>Cherbourg</td> 
   <td>New York, NY</td> 
   <td>NaN</td> 
   <td>17754 L224 10s 6d</td> 
   <td>(124)</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>11</th> 
   <td>12</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Astor, Mrs John Jacob (Madeleine Talmadge Force)</td> 
   <td>19.0000</td> 
   <td>Cherbourg</td> 
   <td>New York, NY</td> 
   <td>NaN</td> 
   <td>17754 L224 10s 6d</td> 
   <td>4</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>12</th> 
   <td>13</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Aubert, Mrs Leontine Pauline</td> 
   <td>NaN</td> 
   <td>Cherbourg</td> 
   <td>Paris, France</td> 
   <td>B-35</td> 
   <td>17477 L69 6s</td> 
   <td>9</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>13</th> 
   <td>14</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Barkworth, Mr Algernon H.</td> 
   <td>NaN</td> 
   <td>Southampton</td> 
   <td>Hessle, Yorks</td> 
   <td>A-23</td> 
   <td>NaN</td> 
   <td>B</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>14</th> 
   <td>15</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Baumann, Mr John D.</td> 
   <td>NaN</td> 
   <td>Southampton</td> 
   <td>New York, NY</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>15</th> 
   <td>16</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Baxter, Mrs James (Helene DeLaudeniere Chaput)</td> 
   <td>50.0000</td> 
   <td>Cherbourg</td> 
   <td>Montreal, PQ</td> 
   <td>B-58/60</td> 
   <td>NaN</td> 
   <td>6</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>16</th> 
   <td>17</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Baxter, Mr Quigg Edmond</td> 
   <td>24.0000</td> 
   <td>Cherbourg</td> 
   <td>Montreal, PQ</td> 
   <td>B-58/60</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>17</th> 
   <td>18</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Beattie, Mr Thomson</td> 
   <td>36.0000</td> 
   <td>Cherbourg</td> 
   <td>Winnipeg, MN</td> 
   <td>C-6</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>18</th> 
   <td>19</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Beckwith, Mr Richard Leonard</td> 
   <td>37.0000</td> 
   <td>Southampton</td> 
   <td>New York, NY</td> 
   <td>D-35</td> 
   <td>NaN</td> 
   <td>5</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>19</th> 
   <td>20</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Beckwith, Mrs Richard Leonard (Sallie Monypeny)</td> 
   <td>47.0000</td> 
   <td>Southampton</td> 
   <td>New York, NY</td> 
   <td>D-35</td> 
   <td>NaN</td> 
   <td>5</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>20</th> 
   <td>21</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Behr, Mr Karl Howell</td> 
   <td>26.0000</td> 
   <td>Cherbourg</td> 
   <td>New York, NY</td> 
   <td>C-148</td> 
   <td>NaN</td> 
   <td>5</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>21</th> 
   <td>22</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Birnbaum, Mr Jakob</td> 
   <td>25.0000</td> 
   <td>Cherbourg</td> 
   <td>San Francisco, CA</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>(148)</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>22</th> 
   <td>23</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Bishop, Mr Dickinson H.</td> 
   <td>25.0000</td> 
   <td>Cherbourg</td> 
   <td>Dowagiac, MI</td> 
   <td>B-49</td> 
   <td>NaN</td> 
   <td>7</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>23</th> 
   <td>24</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Bishop, Mrs Dickinson H. (Helen Walton)</td> 
   <td>19.0000</td> 
   <td>Cherbourg</td> 
   <td>Dowagiac, MI</td> 
   <td>B-49</td> 
   <td>NaN</td> 
   <td>7</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>24</th> 
   <td>25</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Bjornstrm-Steffansson, Mr Mauritz Hakan</td> 
   <td>28.0000</td> 
   <td>Southampton</td> 
   <td>Stockholm, Sweden / Washington, DC</td> 
   <td>NaN</td> 
   <td></td> 
   <td>D</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>25</th> 
   <td>26</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Blackwell, Mr Stephen Weart</td> 
   <td>45.0000</td> 
   <td>Southampton</td> 
   <td>Trenton, NJ</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>(241)</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>26</th> 
   <td>27</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Blank, Mr Henry</td> 
   <td>39.0000</td> 
   <td>Cherbourg</td> 
   <td>Glen Ridge, NJ</td> 
   <td>A-31</td> 
   <td>NaN</td> 
   <td>7</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>27</th> 
   <td>28</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Bonnell, Miss Caroline</td> 
   <td>30.0000</td> 
   <td>Southampton</td> 
   <td>Youngstown, OH</td> 
   <td>C-7</td> 
   <td>NaN</td> 
   <td>8</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>28</th> 
   <td>29</td> 
   <td>1st</td> 
   <td>1</td> 
   <td>Bonnell, Miss Elizabeth</td> 
   <td>58.0000</td> 
   <td>Southampton</td> 
   <td>Birkdale, England Cleveland, Ohio</td> 
   <td>C-103</td> 
   <td>NaN</td> 
   <td>8</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>29</th> 
   <td>30</td> 
   <td>1st</td> 
   <td>0</td> 
   <td>Borebank, Mr John James</td> 
   <td>NaN</td> 
   <td>Southampton</td> 
   <td>London / Winnipeg, MB</td> 
   <td>D-21/2</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>...</th> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
  </tr> 
  <tr> 
   <th>1283</th> 
   <td>1284</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Vestrom, Miss Hulda Amanda Adolfina</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>1284</th> 
   <td>1285</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Vonk, Mr Jenko</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1285</th> 
   <td>1286</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Ware, Mr Frederick</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1286</th> 
   <td>1287</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Warren, Mr Charles William</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1287</th> 
   <td>1288</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Wazli, Mr Yousif</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1288</th> 
   <td>1289</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Webber, Mr James</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1289</th> 
   <td>1290</td> 
   <td>3rd</td> 
   <td>1</td> 
   <td>Wennerstrom, Mr August Edvard</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1290</th> 
   <td>1291</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Wenzel, Mr Linhart</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1291</th> 
   <td>1292</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Widegren, Mr Charles Peter</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1292</th> 
   <td>1293</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Wiklund, Mr Jacob Alfred</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1293</th> 
   <td>1294</td> 
   <td>3rd</td> 
   <td>1</td> 
   <td>Wilkes, Mrs Ellen</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>1294</th> 
   <td>1295</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Willer, Mr Aaron</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1295</th> 
   <td>1296</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Willey, Mr Edward</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1296</th> 
   <td>1297</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Williams, Mr Howard Hugh</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1297</th> 
   <td>1298</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Williams, Mr Leslie</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1298</th> 
   <td>1299</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Windelov, Mr Einar</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1299</th> 
   <td>1300</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Wirz, Mr Albert</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1300</th> 
   <td>1301</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Wiseman, Mr Phillippe</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1301</th> 
   <td>1302</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Wittevrongel, Mr Camiel</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1302</th> 
   <td>1303</td> 
   <td>3rd</td> 
   <td>1</td> 
   <td>Yalsevac, Mr Ivan</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1303</th> 
   <td>1304</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Yasbeck, Mr Antoni</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1304</th> 
   <td>1305</td> 
   <td>3rd</td> 
   <td>1</td> 
   <td>Yasbeck, Mrs Antoni</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>1305</th> 
   <td>1306</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Youssef, Mr Gerios</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1306</th> 
   <td>1307</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Zabour, Miss Hileni</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>1307</th> 
   <td>1308</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Zabour, Miss Tamini</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>1308</th> 
   <td>1309</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Zakarian, Mr Artun</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1309</th> 
   <td>1310</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Zakarian, Mr Maprieder</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1310</th> 
   <td>1311</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Zenn, Mr Philip</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>1311</th> 
   <td>1312</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Zievens, Rene</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>1312</th> 
   <td>1313</td> 
   <td>3rd</td> 
   <td>0</td> 
   <td>Zimmerman, Leo</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>male</td> 
  </tr> 
 </tbody> 
</table>

1313 rows × 11 columns

In \[5\]:

titan.describe()

Out\[5\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>row.names</th> 
   <th>survived</th> 
   <th>age</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>count</th> 
   <td>1313.000000</td> 
   <td>1313.000000</td> 
   <td>633.000000</td> 
  </tr> 
  <tr> 
   <th>mean</th> 
   <td>657.000000</td> 
   <td>0.341965</td> 
   <td>31.194181</td> 
  </tr> 
  <tr> 
   <th>std</th> 
   <td>379.174762</td> 
   <td>0.474549</td> 
   <td>14.747525</td> 
  </tr> 
  <tr> 
   <th>min</th> 
   <td>1.000000</td> 
   <td>0.000000</td> 
   <td>0.166700</td> 
  </tr> 
  <tr> 
   <th>25%</th> 
   <td>329.000000</td> 
   <td>0.000000</td> 
   <td>21.000000</td> 
  </tr> 
  <tr> 
   <th>50%</th> 
   <td>657.000000</td> 
   <td>0.000000</td> 
   <td>30.000000</td> 
  </tr> 
  <tr> 
   <th>75%</th> 
   <td>985.000000</td> 
   <td>1.000000</td> 
   <td>41.000000</td> 
  </tr> 
  <tr> 
   <th>max</th> 
   <td>1313.000000</td> 
   <td>1.000000</td> 
   <td>71.000000</td> 
  </tr> 
 </tbody> 
</table>

In \[6\]:

\# 2.数据基本处理  
\# 2.1 确定特征值,目标值  
x = titan\[\["pclass", "age", "sex"\]\]  
y = titan\["survived"\]

In \[7\]:

x.head()

Out\[7\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>pclass</th> 
   <th>age</th> 
   <th>sex</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>1st</td> 
   <td>29.0000</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>1st</td> 
   <td>2.0000</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>1st</td> 
   <td>30.0000</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>1st</td> 
   <td>25.0000</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>1st</td> 
   <td>0.9167</td> 
   <td>male</td> 
  </tr> 
 </tbody> 
</table>

In \[8\]:

y.head()

Out\[8\]:

0    1
    1    0
    2    0
    3    0
    4    1
    Name: survived, dtype: int64

In \[9\]:

\# 2.2 缺失值处理  
x\['age'\].fillna(value=titan\["age"\].mean(), inplace=True)

In \[10\]:

x.head()

Out\[10\]:

In \[11\]:

\# 2.3 数据集划分  
x\_train, x\_test, y\_train, y\_test = train\_test\_split(x, y, random\_state=22, test\_size=0.2)

In \[12\]:

\# 3.特征工程(字典特征抽取)

In \[13\]:

x\_train.head()

Out\[13\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>pclass</th> 
   <th>age</th> 
   <th>sex</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>649</th> 
   <td>3rd</td> 
   <td>45.000000</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>1078</th> 
   <td>3rd</td> 
   <td>31.194181</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>59</th> 
   <td>1st</td> 
   <td>31.194181</td> 
   <td>female</td> 
  </tr> 
  <tr> 
   <th>201</th> 
   <td>1st</td> 
   <td>18.000000</td> 
   <td>male</td> 
  </tr> 
  <tr> 
   <th>61</th> 
   <td>1st</td> 
   <td>31.194181</td> 
   <td>female</td> 
  </tr> 
 </tbody> 
</table>

In \[14\]:

x\_train = x\_train.to\_dict(orient="records")  
x\_test = x\_test.to\_dict(orient="records")

In \[15\]:

x\_train

Out\[15\]:

[{'pclass': '3rd', 'age': 45.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 18.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 6.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 27.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 21.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 4.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 13.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 30.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 50.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 22.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 49.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 62.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 32.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 64.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 23.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 55.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 24.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 6.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 10.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 53.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 18.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 36.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 19.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 28.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 17.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 21.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 25.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 19.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 21.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 48.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 27.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 46.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 29.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 35.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 38.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 32.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 16.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 18.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 16.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 33.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 17.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 18.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 36.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 33.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 52.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 35.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 25.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 45.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 50.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 52.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 20.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 32.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 34.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 33.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 21.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 45.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 43.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 59.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 47.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 38.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 51.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 36.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 23.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 6.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 58.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 4.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 35.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 12.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 19.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 64.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 27.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 34.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 18.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 48.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 50.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 18.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 34.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 21.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 44.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 19.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 39.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 42.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 69.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 2.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 22.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 47.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 22.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 42.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 21.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 48.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 45.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 45.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 39.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 14.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 30.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 32.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 54.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 36.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 47.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 0.8333, 'sex': 'male'},
     {'pclass': '1st', 'age': 53.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 24.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 37.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 25.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 23.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 40.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 20.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 23.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 22.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 29.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 55.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 49.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 18.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 24.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 22.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 54.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 38.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 42.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 52.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 19.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 8.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 57.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 22.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 16.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 45.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 28.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 19.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 28.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 24.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 38.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 36.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 55.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 25.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 32.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 9.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 29.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 40.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 39.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 25.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 49.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 36.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 23.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 23.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 17.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 24.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 28.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 40.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 6.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 17.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 34.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 41.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 28.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 61.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 17.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 3.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 24.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 30.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 41.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 42.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 28.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 48.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 50.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 16.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 40.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 23.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 34.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 39.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 34.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 22.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 9.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 22.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 30.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 25.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 24.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 26.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 57.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 39.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 35.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 41.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 67.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 11.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 22.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 20.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 50.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 33.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 36.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 48.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 59.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 25.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 17.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 45.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 49.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 33.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 46.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 52.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 36.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 28.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 28.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 19.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 43.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 36.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 51.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 36.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 3.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 48.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 48.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 16.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 36.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 44.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 36.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 37.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 32.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 30.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 22.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 40.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 24.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 65.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 37.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 52.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 23.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 0.8333, 'sex': 'male'},
     {'pclass': '2nd', 'age': 35.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 27.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 27.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 41.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 18.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 33.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 56.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 40.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 9.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 28.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 30.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 25.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 48.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 36.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 35.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 1.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 2.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 32.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 25.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 29.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 21.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 27.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 38.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 28.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 0.9167, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 39.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 9.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 45.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 36.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 14.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 30.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 22.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 60.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 48.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 28.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 23.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 32.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 30.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 46.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 32.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 27.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 61.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 39.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 0.1667, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 15.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 18.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 24.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 17.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 42.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 20.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 62.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 49.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 23.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 33.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 19.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 45.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 70.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 37.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 28.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 54.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 51.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 21.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 64.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 29.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 33.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 50.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 19.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 59.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 18.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 49.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 38.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 48.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 54.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 19.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 3.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 18.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 22.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 34.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 28.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 15.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 40.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 46.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 8.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 63.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 43.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 16.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 38.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 1.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 35.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 42.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 38.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 17.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 40.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 4.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 29.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 22.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 57.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 40.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 47.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 37.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 42.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 21.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 5.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 21.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 40.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 9.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 41.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 36.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 28.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 39.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 35.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 24.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 45.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 24.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 50.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 56.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 32.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 19.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 18.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 45.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 22.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 20.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 50.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 24.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 40.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 21.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 52.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 45.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 11.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 23.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 26.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 40.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 49.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 18.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 18.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 9.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 25.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 35.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 32.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 21.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 32.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 45.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 26.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 21.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 25.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 36.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 27.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 24.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 18.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 56.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 16.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 18.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 64.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 46.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 18.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 46.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 29.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 18.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 33.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 34.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 0.8333, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 58.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 60.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 23.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 44.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 71.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 13.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 58.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 4.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 16.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 33.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 33.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 48.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 28.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 55.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 54.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 71.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 47.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 21.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 21.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 24.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 23.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 18.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 54.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 17.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 6.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 45.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 36.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 55.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 26.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '1st', 'age': 65.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 27.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 22.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '2nd', 'age': 7.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 30.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 39.0, 'sex': 'female'},
     {'pclass': '1st', 'age': 19.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 19.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 20.0, 'sex': 'male'},
     {'pclass': '1st', 'age': 56.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 38.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 23.0, 'sex': 'female'},
     {'pclass': '2nd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 42.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 23.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 25.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '2nd', 'age': 16.0, 'sex': 'male'},
     {'pclass': '2nd', 'age': 42.0, 'sex': 'male'},
     {'pclass': '3rd', 'age': 2.0, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'female'},
     {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
     {'pclass': '1st', 'age': 36.0, 'sex': 'male'},
     ...]

In \[16\]:

transfer = DictVectorizer()

x\_train = transfer.fit\_transform(x\_train)  
x\_test = transfer.fit\_transform(x\_test)

In \[21\]:

\# 4.xgboost模型训练  
\# 4.1 初步模型训练  
from xgboost import XGBClassifier

xg = XGBClassifier()

xg.fit(x\_train, y\_train)

Out\[21\]:

XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
                  colsample_bynode=1, colsample_bytree=1, gamma=0,
                  learning_rate=0.1, max_delta_step=0, max_depth=3,
                  min_child_weight=1, missing=None, n_estimators=100, n_jobs=1,
                  nthread=None, objective='binary:logistic', random_state=0,
                  reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,
                  silent=None, subsample=1, verbosity=1)

In \[22\]:

xg.score(x\_test, y\_test)

Out\[22\]:

0.7832699619771863

In \[23\]:

\# 4.2 对max\_depth进行调优

depth\_range  = range(10)  
score = \[\]

for i in depth\_range:  
    xg = XGBClassifier(eta=1, gamma=0, max\_depth=i)  
    xg.fit(x\_train, y\_train)  
      
    s = xg.score(x\_test, y\_test)  
      
    print(s)  
    score.append(s)

0.6311787072243346
    0.7908745247148289
    0.7870722433460076
    0.7832699619771863
    0.7870722433460076
    0.7908745247148289
    0.7908745247148289
    0.7946768060836502
    0.7908745247148289
    0.7946768060836502

In \[25\]:

\# 4.3 调优结果可视化  
import matplotlib.pyplot as plt

plt.plot(depth\_range, score)

plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 16][]

--------------------

# 5.4 otto案例介绍 -- Otto Group Product Classification Challenge【xgboost实现】 #

## 1 背景介绍 ##

奥托集团是世界上最大的电子商务公司之一，在20多个国家设有子公司。该公司每天都在世界各地销售数百万种产品,所以对其产品根据性能合理的分类非常重要。

不过,在实际工作中,工作人员发现,许多相同的产品得到了不同的分类。本案例要求,你对奥拓集团的产品进行正确的分分类。尽可能的提供分类的准确性。

链接：[https://www.kaggle.com/c/otto-group-product-classification-challenge/overview][https_www.kaggle.com_c_otto-group-product-classification-challenge_overview]

## 2 思路分析 ##

*  1.数据获取
 *  2.数据基本处理
    
     *  2.1 截取部分数据
     *  2.2 把标签纸转换为数字
     *  **2.3 分割数据(使用StratifiedShuffleSplit)**
     *  **2.4 数据标准化**
     *  **2.5 数据pca降维**
 *  **3.模型训练**
    
     *  **3.1 基本模型训练**
     *  **3.2 模型调优**
        
         *  **3.2.1 调优参数:**
            
             *  **n\_estimator,**
             *  **max\_depth,**
             *  **min\_child\_weights,**
             *  **subsamples,**
             *  **consample\_bytrees,**
             *  **etas**
         *  **3.2.2 确定最后最优参数**

## 3 部分代码实现 ##

*  2.数据基本处理
    
     *  2.1 截取部分数据
     *  2.2 把标签纸转换为数字
     *  **2.3 分割数据(使用StratifiedShuffleSplit)**
        
            # 使用StratifiedShuffleSplit对数据集进行分割
            from sklearn.model_selection import StratifiedShuffleSplit
            
            sss = StratifiedShuffleSplit(n_splits=1, test_size=0.2, random_state=0)
            for train_index, test_index in sss.split(X_resampled.values, y_resampled):
                print(len(train_index))
                print(len(test_index))
            
                x_train = X_resampled.values[train_index]
                x_val = X_resampled.values[test_index]
            
                y_train = y_resampled[train_index]
                y_val = y_resampled[test_index]
        
            # 分割数据图形可视化
            import seaborn as sns
            
            sns.countplot(y_val)
            
            plt.show()
     *  **2.4 数据标准化**
        
            from sklearn.preprocessing import StandardScaler
            
            scaler = StandardScaler()
            scaler.fit(x_train)
            
            x_train_scaled = scaler.transform(x_train)
            x_val_scaled = scaler.transform(x_val)
     *  **2.5 数据pca降维**
        
            print(x_train_scaled.shape)
            # (13888, 93)
            
            from sklearn.decomposition import PCA
            
            pca = PCA(n_components=0.9)
            x_train_pca = pca.fit_transform(x_train_scaled)
            x_val_pca = pca.transform(x_val_scaled)
            
            print(x_train_pca.shape, x_val_pca.shape)
            (13888, 65) (3473, 65)
        
        从上面输出的数据可以看出,只选择65个元素,就可以表达出特征中90%的信息
        
            # 降维数据可视化
            plt.plot(np.cumsum(pca.explained_variance_ratio_))
            
            plt.xlabel("元素数量")
            plt.ylabel("可表达信息的百分占比")
            
            plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 17][]

*  **3.模型训练**
    
     *  **3.1 基本模型训练**
        
            from xgboost import XGBClassifier
            
            xgb = XGBClassifier()
            xgb.fit(x_train_pca, y_train)
            
            # 改变预测值的输出模式,让输出结果为百分占比,降低logloss值
            y_pre_proba = xgb.predict_proba(x_val_pca)
        
            # logloss进行模型评估
            from sklearn.metrics import log_loss
            log_loss(y_val, y_pre_proba, eps=1e-15, normalize=True)
            
            xgb.get_params

*  **3.2 模型调优**
    
     *  **3.2.1 调优参数:**
        
         *  **n\_estimator,**
            
                scores_ne = []
                n_estimators = [100,200,400,450,500,550,600,700]
                
                for nes in n_estimators:
                    print("n_estimators:", nes)
                    xgb = XGBClassifier(max_depth=3, 
                                        learning_rate=0.1, 
                                        n_estimators=nes, 
                                        objective="multi:softprob", 
                                        n_jobs=-1, 
                                        nthread=4, 
                                        min_child_weight=1, 
                                        subsample=1, 
                                        colsample_bytree=1,
                                        seed=42)
                
                    xgb.fit(x_train_pca, y_train)
                    y_pre = xgb.predict_proba(x_val_pca)
                    score = log_loss(y_val, y_pre)
                    scores_ne.append(score)
                    print("测试数据的logloss值为:{}".format(score))
            
                # 数据变化可视化
                plt.plot(n_estimators, scores_ne, "o-")
                
                plt.ylabel("log_loss")
                plt.xlabel("n_estimators")
                print("n_estimators的最优值为:{}".format(n_estimators[np.argmin(scores_ne)]))

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 18][]

*   *   *  **max\_depth,**
            
                scores_md = []
                max_depths = [1,3,5,6,7]
                
                for md in max_depths:  # 修改
                    xgb = XGBClassifier(max_depth=md, # 修改
                                        learning_rate=0.1, 
                                        n_estimators=n_estimators[np.argmin(scores_ne)],   # 修改 
                                        objective="multi:softprob", 
                                        n_jobs=-1, 
                                        nthread=4, 
                                        min_child_weight=1, 
                                        subsample=1, 
                                        colsample_bytree=1,
                                        seed=42)
                
                    xgb.fit(x_train_pca, y_train)
                    y_pre = xgb.predict_proba(x_val_pca)
                    score = log_loss(y_val, y_pre)
                    scores_md.append(score)  # 修改
                    print("测试数据的logloss值为:{}".format(log_loss(y_val, y_pre)))
            
                # 数据变化可视化
                plt.plot(max_depths, scores_md, "o-")  # 修改
                
                plt.ylabel("log_loss")
                plt.xlabel("max_depths")  # 修改
                print("max_depths的最优值为:{}".format(max_depths[np.argmin(scores_md)]))  # 修改
         *  **min\_child\_weights,**
            
             *  依据上面模式进行调整
         *  **subsamples,**
         *  **consample\_bytrees,**
         *  **etas**
     *  **3.2.2 确定最后最优参数**
        
            xgb = XGBClassifier(learning_rate =0.1, 
                                n_estimators=550, 
                                max_depth=3, 
                                min_child_weight=3, 
                                subsample=0.7, 
                                colsample_bytree=0.7, 
                                nthread=4, 
                                seed=42, 
                                objective='multi:softprob')
            xgb.fit(x_train_scaled, y_train)
            
            y_pre = xgb.predict_proba(x_val_scaled)
            
            print("测试数据的logloss值为 : {}".format(log_loss(y_val, y_pre, eps=1e-15, normalize=True)))

--------------------

In \[1\]:

import numpy as np  
import pandas as pd  
import matplotlib.pyplot as plt

# 数据获取 #

In \[2\]:

data = pd.read\_csv("./data/otto/train.csv")

In \[3\]:

data.head()

Out\[3\]:

5 rows × 95 columns

In \[4\]:

data.shape

Out\[4\]:

(61878, 95)

In \[5\]:

data.describe()

Out\[5\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>id</th> 
   <th>feat_1</th> 
   <th>feat_2</th> 
   <th>feat_3</th> 
   <th>feat_4</th> 
   <th>feat_5</th> 
   <th>feat_6</th> 
   <th>feat_7</th> 
   <th>feat_8</th> 
   <th>feat_9</th> 
   <th>...</th> 
   <th>feat_84</th> 
   <th>feat_85</th> 
   <th>feat_86</th> 
   <th>feat_87</th> 
   <th>feat_88</th> 
   <th>feat_89</th> 
   <th>feat_90</th> 
   <th>feat_91</th> 
   <th>feat_92</th> 
   <th>feat_93</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>count</th> 
   <td>61878.000000</td> 
   <td>61878.00000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>...</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
   <td>61878.000000</td> 
  </tr> 
  <tr> 
   <th>mean</th> 
   <td>30939.500000</td> 
   <td>0.38668</td> 
   <td>0.263066</td> 
   <td>0.901467</td> 
   <td>0.779081</td> 
   <td>0.071043</td> 
   <td>0.025696</td> 
   <td>0.193704</td> 
   <td>0.662433</td> 
   <td>1.011296</td> 
   <td>...</td> 
   <td>0.070752</td> 
   <td>0.532306</td> 
   <td>1.128576</td> 
   <td>0.393549</td> 
   <td>0.874915</td> 
   <td>0.457772</td> 
   <td>0.812421</td> 
   <td>0.264941</td> 
   <td>0.380119</td> 
   <td>0.126135</td> 
  </tr> 
  <tr> 
   <th>std</th> 
   <td>17862.784315</td> 
   <td>1.52533</td> 
   <td>1.252073</td> 
   <td>2.934818</td> 
   <td>2.788005</td> 
   <td>0.438902</td> 
   <td>0.215333</td> 
   <td>1.030102</td> 
   <td>2.255770</td> 
   <td>3.474822</td> 
   <td>...</td> 
   <td>1.151460</td> 
   <td>1.900438</td> 
   <td>2.681554</td> 
   <td>1.575455</td> 
   <td>2.115466</td> 
   <td>1.527385</td> 
   <td>4.597804</td> 
   <td>2.045646</td> 
   <td>0.982385</td> 
   <td>1.201720</td> 
  </tr> 
  <tr> 
   <th>min</th> 
   <td>1.000000</td> 
   <td>0.00000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>...</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
  </tr> 
  <tr> 
   <th>25%</th> 
   <td>15470.250000</td> 
   <td>0.00000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>...</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
  </tr> 
  <tr> 
   <th>50%</th> 
   <td>30939.500000</td> 
   <td>0.00000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>...</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
  </tr> 
  <tr> 
   <th>75%</th> 
   <td>46408.750000</td> 
   <td>0.00000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>1.000000</td> 
   <td>0.000000</td> 
   <td>...</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>1.000000</td> 
   <td>0.000000</td> 
   <td>1.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
   <td>0.000000</td> 
  </tr> 
  <tr> 
   <th>max</th> 
   <td>61878.000000</td> 
   <td>61.00000</td> 
   <td>51.000000</td> 
   <td>64.000000</td> 
   <td>70.000000</td> 
   <td>19.000000</td> 
   <td>10.000000</td> 
   <td>38.000000</td> 
   <td>76.000000</td> 
   <td>43.000000</td> 
   <td>...</td> 
   <td>76.000000</td> 
   <td>55.000000</td> 
   <td>65.000000</td> 
   <td>67.000000</td> 
   <td>30.000000</td> 
   <td>61.000000</td> 
   <td>130.000000</td> 
   <td>52.000000</td> 
   <td>19.000000</td> 
   <td>87.000000</td> 
  </tr> 
 </tbody> 
</table>

8 rows × 94 columns

In \[6\]:

\# 图形可视化,查看数据分布  
import seaborn as sns

sns.countplot(data.target)

plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 19][]

由上图可以看出,该数据类别不均衡,所以需要后期处理

# 数据基本处理 #

数据已经经过脱敏,不再需要特殊处理

## 截取部分数据 ##

In \[7\]:

new1\_data = data\[:10000\]  
new1\_data.shape

Out\[7\]:

(10000, 95)

In \[8\]:

\# 图形可视化,查看数据分布  
import seaborn as sns

sns.countplot(new1\_data.target)

plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 19][]

使用上面方式获取数据不可行,然后使用随机欠采样获取响应的数据

In \[9\]:

\# 随机欠采样获取数据  
\# 首先需要确定特征值\\标签值

y = data\["target"\]  
x = data.drop(\["id", "target"\], axis=1)

In \[10\]:

x.head()

Out\[10\]:

5 rows × 93 columns

In \[11\]:

y.head()

Out\[11\]:

0    Class_1
    1    Class_1
    2    Class_1
    3    Class_1
    4    Class_1
    Name: target, dtype: object

In \[12\]:

\# 欠采样获取数据  
from imblearn.under\_sampling import RandomUnderSampler

rus = RandomUnderSampler(random\_state=0)

X\_resampled, y\_resampled = rus.fit\_resample(x, y)

In \[13\]:

x.shape, y.shape

Out\[13\]:

((61878, 93), (61878,))

In \[14\]:

X\_resampled.shape, y\_resampled.shape

Out\[14\]:

((17361, 93), (17361,))

In \[15\]:

\# 图形可视化,查看数据分布  
import seaborn as sns

sns.countplot(y\_resampled)

plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 20][]

## 把标签值转换为数字 ##

In \[16\]:

y\_resampled.head()

Out\[16\]:

0    Class_1
    1    Class_1
    2    Class_1
    3    Class_1
    4    Class_1
    Name: target, dtype: object

In \[17\]:

from sklearn.preprocessing import LabelEncoder

le = LabelEncoder()  
y\_resampled = le.fit\_transform(y\_resampled)

In \[18\]:

y\_resampled

Out\[18\]:

array([0, 0, 0, ..., 8, 8, 8])

## 分割数据 ##

In \[19\]:

from sklearn.model\_selection import train\_test\_split

x\_train, x\_test, y\_train, y\_test = train\_test\_split(X\_resampled, y\_resampled, test\_size=0.2)

In \[20\]:

x_train.shape, y_train.shape

Out\[20\]:

((13888, 93), (13888,))

In \[21\]:

x\_test.shape, y\_test.shape

Out\[21\]:

((3473, 93), (3473,))

In \[22\]:

\# 1.数据获取

\# 2.数据基本处理

\# 2.1 截取部分数据  
    \# 2.2 把标签纸转换为数字  
    \# 2.3 分割数据(使用StratifiedShuffleSplit)  
    \# 2.4 数据标准化  
    \# 2.5 数据pca降维

\# 3.模型训练  
    \# 3.1 基本模型训练  
    \# 3.2 模型调优  
        \# 3.2.1 调优参数:  
            \# n\_estimator,  
            \# max\_depth,  
            \# min\_child\_weights,  
            \# subsamples,  
            \# consample\_bytrees,  
            \# etas  
        \# 3.2.2 确定最后最优参数

In \[23\]:

\# 图形可视化  
import seaborn as sns

sns.countplot(y\_test)  
plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 21][]

In \[28\]:

\# 通过StratifiedShuffleSplit实现数据分割

from sklearn.model\_selection import StratifiedShuffleSplit

sss = StratifiedShuffleSplit(n\_splits=1, test\_size=0.2, random\_state=0)

for train\_index, test\_index in sss.split(X\_resampled.values, y\_resampled):  
    print(len(train\_index))  
    print(len(test\_index))  
      
    x\_train = X\_resampled.values\[train\_index\]  
    x\_val = X\_resampled.values\[test\_index\]  
      
    y\_train = y\_resampled\[train\_index\]  
    y\_val = y\_resampled\[test\_index\]

13888
    3473

In \[29\]:

print(x\_train.shape, x\_val.shape)

(13888, 93) (3473, 93)

In \[30\]:

\# 图形可视化  
import seaborn as sns

sns.countplot(y\_val)  
plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 22][]

## 数据标准化 ##

In \[31\]:

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()  
scaler.fit(x\_train)

x\_train\_scaled = scaler.transform(x\_train)  
x\_val\_scaled = scaler.transform(x\_val)

## 数据PCA降维 ##

In \[33\]:

x\_train\_scaled.shape

Out\[33\]:

(13888, 93)

In \[34\]:

from sklearn.decomposition import PCA

pca = PCA(n\_components=0.9)

x\_train\_pca = pca.fit\_transform(x\_train\_scaled)  
x\_val\_pca = pca.transform(x\_val\_scaled)

In \[35\]:

print(x\_train\_pca.shape, x\_val\_pca.shape)

(13888, 65) (3473, 65)

In \[37\]:

\# 可视化数据降维信息变化程度  
plt.plot(np.cumsum(pca.explained\_variance\_ratio\_))

plt.xlabel("元素数量")  
plt.ylabel("表达信息百分占比")

plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 23][]

# 模型训练 #

## 基本模型训练 ##

In \[38\]:

from xgboost import XGBClassifier

xgb = XGBClassifier()  
xgb.fit(x\_train\_pca, y\_train)

Out\[38\]:

XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
                  colsample_bynode=1, colsample_bytree=1, gamma=0,
                  learning_rate=0.1, max_delta_step=0, max_depth=3,
                  min_child_weight=1, missing=None, n_estimators=100, n_jobs=1,
                  nthread=None, objective='multi:softprob', random_state=0,
                  reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,
                  silent=None, subsample=1, verbosity=1)

In \[39\]:

\# 输出预测值,一定输出带有百分占比的预测值  
y\_pre\_proba = xgb.predict\_proba(x\_val\_pca)

In \[40\]:

y\_pre\_proba

Out\[40\]:

array([[0.4893983 , 0.00375719, 0.00225278, ..., 0.06179977, 0.17131925,
            0.03980364],
           [0.14336601, 0.01110009, 0.01018962, ..., 0.00691424, 0.02062171,
            0.7525783 ],
           [0.00834821, 0.14602502, 0.65013766, ..., 0.01385602, 0.00602207,
            0.00240582],
           ...,
           [0.09568001, 0.00293341, 0.00582061, ..., 0.1031019 , 0.7587154 ,
            0.02730099],
           [0.40236628, 0.12317444, 0.03567632, ..., 0.18818544, 0.13276173,
            0.07105519],
           [0.00473167, 0.01536749, 0.02546864, ..., 0.00882399, 0.88531935,
            0.00384397]], dtype=float32)

In \[42\]:

\# logloss评估  
from sklearn.metrics import log\_loss

log\_loss(y\_val, y\_pre\_proba, eps=1e-15, normalize=True)

Out\[42\]:

0.7845457684689274

In \[43\]:

xgb.get\_params

Out\[43\]:

## 模型调优 ##

### 确定最优的estimators ###

In \[44\]:

scores\_ne = \[\]  
n\_estimators = \[100, 200, 300, 400, 500, 550, 600, 700\]

In \[49\]:

for nes in n\_estimators:  
    print("n\_estimators:", nes)  
    xgb = XGBClassifier(max\_depth=3,  
                        learning\_rate=0.1,   
                        n\_estimators=nes,   
                        objective="multi:softprob",   
                        n\_jobs=-1,   
                        nthread=4,   
                        min\_child\_weight=1,  
                        subsample=1,  
                        colsample\_bytree=1,  
                        seed=42)  
      
    xgb.fit(x\_train\_pca, y\_train)  
    y\_pre = xgb.predict\_proba(x\_val\_pca)  
    score = log\_loss(y\_val, y\_pre)  
    scores\_ne.append(score)  
      
    print("每次测试的logloss值是:\{\}".format(score))

n_estimators: 100
    每次测试的logloss值是:0.7845457684689274
    n_estimators: 200
    每次测试的logloss值是:0.7163659085830947
    n_estimators: 300
    每次测试的logloss值是:0.6933389946023942
    n_estimators: 400
    每次测试的logloss值是:0.68119252278615
    n_estimators: 500
    每次测试的logloss值是:0.67700775120196
    n_estimators: 550
    每次测试的logloss值是:0.6756911007299885
    n_estimators: 600
    每次测试的logloss值是:0.6757532660164814
    n_estimators: 700
    每次测试的logloss值是:0.6778721089881976

In \[50\]:

\# 图形化展示相应的logloss值  
plt.plot(n\_estimators, scores\_ne, "o-")

plt.xlabel("n\_estimators")  
plt.ylabel("log\_loss")  
plt.show()

print("最优的n\_estimators值是:\{\}".format(n\_estimators\[np.argmin(scores\_ne)\]))

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 24][]

最优的n_estimators值是:550

### 确定最优的max\_depth ###

In \[63\]:

scores\_md = \[\]  
max\_depths = \[1,3,5,6,7\]

In \[64\]:

for md in max\_depths:  
    print("max\_depth:", md)  
    xgb = XGBClassifier(max\_depth=md,  
                        learning\_rate=0.1,   
                        n\_estimators=n\_estimators\[np.argmin(scores\_ne)\],   
                        objective="multi:softprob",   
                        n\_jobs=-1,   
                        nthread=4,   
                        min\_child\_weight=1,  
                        subsample=1,  
                        colsample\_bytree=1,  
                        seed=42)  
      
    xgb.fit(x\_train\_pca, y\_train)  
    y\_pre = xgb.predict\_proba(x\_val\_pca)  
    score = log\_loss(y\_val, y\_pre)  
    scores\_md.append(score)  
      
    print("每次测试的logloss值是:\{\}".format(score))

max_depth: 1
    每次测试的logloss值是:0.8186777106711784
    max_depth: 3
    每次测试的logloss值是:0.6756911007299885
    max_depth: 5
    每次测试的logloss值是:0.730323661087053
    max_depth: 6
    每次测试的logloss值是:0.7693314501840949
    max_depth: 7
    每次测试的logloss值是:0.7889236364892144

In \[67\]:

\# 图形化展示相应的logloss值  
plt.plot(max\_depths, scores\_md, "o-")

plt.xlabel("max\_depths")  
plt.ylabel("log\_loss")  
plt.show()

print("最优的max\_depths值是:\{\}".format(max\_depths\[np.argmin(scores\_md)\]))

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 19][]

最优的max_depths值是:3

### 依据上面模式,运行调试下面参数 ###

min\_child\_weights,

subsamples,

consample\_bytrees,

etas

In \[69\]:

xgb = XGBClassifier(learning\_rate =0.1,   
                    n\_estimators=550,   
                    max\_depth=3,   
                    min\_child\_weight=3,   
                    subsample=0.7,   
                    colsample\_bytree=0.7,   
                    nthread=4,   
                    seed=42,   
                    objective='multi:softprob')

xgb.fit(x\_train\_scaled, y\_train)

y\_pre = xgb.predict\_proba(x\_val\_scaled)

print("测试数据的log\_loss值为 : \{\}".format(log\_loss(y\_val, y\_pre, eps=1e-15, normalize=True)))

测试数据的log_loss值为 : 0.5944022517380477

[20191009191333910.png]: https://img-blog.csdnimg.cn/20191009191333910.png
[Link 1]: http://www.rimengshe.com/
[AI_Keras PyTorch MXNet TensorFlow PaddlePaddle]: https://blog.csdn.net/zimiao552147572/article/details/88867161
[Bagging_Boosting_GBDT]: https://blog.csdn.net/zimiao552147572/article/details/104529615
[XGBoost]: https://blog.csdn.net/zimiao552147572/article/details/104658658
[lightGBM]: https://blog.csdn.net/zimiao552147572/article/details/104659336
[lightGBM 1]: https://blog.csdn.net/zimiao552147572/article/details/104659386
[2020030417501622.png]: https://img-blog.csdnimg.cn/2020030417501622.png
[20200304175026284.png]: https://img-blog.csdnimg.cn/20200304175026284.png
[20200304175044512.png]: https://img-blog.csdnimg.cn/20200304175044512.png
[20200304175053821.png]: https://img-blog.csdnimg.cn/20200304175053821.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200304175107641.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[20200304175137797.png]: https://img-blog.csdnimg.cn/20200304175137797.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20200304175145190.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/2020030417520054.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 3]: https://img-blog.csdnimg.cn/20200304175205852.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 4]: https://img-blog.csdnimg.cn/20200304175232123.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 5]: https://img-blog.csdnimg.cn/20200304175241300.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 6]: https://img-blog.csdnimg.cn/2020030417525642.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 7]: https://img-blog.csdnimg.cn/20200304175308393.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 8]: https://img-blog.csdnimg.cn/20200304175321803.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 9]: https://img-blog.csdnimg.cn/20200304175336823.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 10]: https://img-blog.csdnimg.cn/20200304175354590.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 11]: https://img-blog.csdnimg.cn/20200304175416643.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 12]: https://img-blog.csdnimg.cn/20200304175423563.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 13]: https://img-blog.csdnimg.cn/20200304175443429.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[https_xgboost.readthedocs.io_en_latest]: https://xgboost.readthedocs.io/en/latest/
[https_www.kaggle.com_c_titanic_overview]: https://www.kaggle.com/c/titanic/overview
[http_biostat.mc.vanderbilt.edu_wiki_pub_Main_DataSets_titanic.txt]: http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 14]: https://img-blog.csdnimg.cn/20200304175555922.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 15]: https://img-blog.csdnimg.cn/20200304175618155.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 16]: https://img-blog.csdnimg.cn/20200304175640119.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[https_www.kaggle.com_c_otto-group-product-classification-challenge_overview]: https://www.kaggle.com/c/otto-group-product-classification-challenge/overview
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 17]: https://img-blog.csdnimg.cn/20200304180003239.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 18]: https://img-blog.csdnimg.cn/20200304180016929.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 19]: https://img-blog.csdnimg.cn/20200304180034636.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 20]: https://img-blog.csdnimg.cn/20200304180034637.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 21]: https://img-blog.csdnimg.cn/20200304180034639.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 22]: https://img-blog.csdnimg.cn/20200304180034644.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 23]: https://img-blog.csdnimg.cn/20200304180034645.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 24]: https://img-blog.csdnimg.cn/20200304180034640.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70