【Python】学习笔记总结8（经典算法）

冷不防 2023-03-01 13:29 4阅读 0赞

### 文章目录 ###

*  八、Python经典算法
 *   *  0.Python画图
     *  1.回归-线性回归
     *  2.分类-k最近邻
     *  3.聚类
     *   *  3.1.Kmeans(k均值聚类算法)
         *  3.2.DBSCAN(基于密度的聚类算法)
         *  3.3.层次聚类算法
     *  4.降维
     *   *  4.1.PCA算法
         *  4.2.FA算法
     *  5.学习（神经网络）
     *   *  5.1.BP神经网络
     *  6.推荐算法
     *  7.时间序列（视频学习）

# 八、Python经典算法 #

## 0.Python画图 ##

[Python画图][Python]

## 1.回归-线性回归 ##

[回归-课程回顾][-]  
**目的**：找一条线，尽可能地拟合数据点，生成线性回归模型，并进行预测  
**解决什么样的问题**：要完成的任务是预测一个连续值的话，那这个任务就是回归。是离散值的话就是分类  
**拟合（Fitting）**：就是说这个曲线能不能很好的描述某些样本，并且有比较好的泛化能力。  
**过拟合（Overfitting）**：就是太过贴近于训练数据的特征了，在训练集上表现非常优秀，近乎完美的预测/区分了所有的数据，但是在新的测试集上却表现平平，不具泛化性，拿到新样本后没有办法去准确的判断。  
**欠拟合（UnderFitting）**：测试样本的特性没有学到，或者是模型过于简单无法拟合或区分样本。  
[过拟合和欠拟合的形象解释][Link 1]

import matplotlib.pyplot as plt
    import numpy as np
    t = np.arange(1,10,1)
    y = 0.9 * t + np.sin(t)
    # plt.plot(t,y,"o")
    # plt.show()
    model = np.polyfit(t,y,deg = 3)#生成三阶模型
    t2 = np.arange(-2,12,0.5)
    y2predict = np.polyval(model,t2)
    plt.plot(t,y,"o",t2,y2predict,"x")
    plt.show()

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70]

## 2.分类-k最近邻 ##

[分类-课程回顾][- 1]  
**目的**：根据已知样本进行分类学习，生成模型，并对测试样本进行预测  
**解决什么样的问题**：了解单个样本信息特征以及其标签值，根据其生成模型，并对测试样本进行预测

#分类算法
    #k最近邻：近朱者赤近墨者黑原理
    import os
    import pandas as pd
    from sklearn import  neighbors
    thisFilePath = os.path.abspath('.')
    os.chdir(thisFilePath)
    # print(os.getcwd())
    df = pd.read_csv('ScoreData.csv')
    # print(df.head())
    
    train_x = df.iloc[0:8,2:4]
    # print(train_x.head())
    train_y= df.iloc[0:8,4]
    # print(train_y.head())
    
    model = neighbors.KNeighborsClassifier()
    model.fit(train_x,train_y)
    test_x = df.iloc[8:11,2:4]
    test_y= df.iloc[8:11,4].values
    
    test_p = model.predict(test_x)
    print(test_p)
    print(test_y)
    
    print(model.score(test_x, test_y))

## 3.聚类 ##

[聚类-课程回顾][- 2]  
**目的**：根据已知样本进行分类学习，生成模型，并对测试样本进行预测  
**解决什么样的问题**：不了解单个样本信息特征以及其标签值，根据其生成模型，并对测试样本进行预测

### 3.1.Kmeans(k均值聚类算法) ###

(k-means clustering algorithm)  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 1]

import numpy as np
    train_x2 = np.array(train_x[['yuwen','shuxue']])
    print(train_x2)
    from sklearn.cluster import KMeans
    model2 = KMeans(n_clusters=3)
    model2 = model2.fit(train_x2)
    clusterResult = pd.DataFrame(model2.labels_,index=train_x.index,columns=['clusterResult'])
    print(clusterResult.head())

### 3.2.DBSCAN(基于密度的聚类算法) ###

[(Density-Based Spatial Clustering of Applications with Noise)][Density-Based Spatial Clustering of Applications with Noise]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 2]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 3]

### 3.3.层次聚类算法 ###

[一篇][Link 2]  
[二篇][Link 3]  
[三篇][Link 4]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 4]

## 4.降维 ##

[降维-课程回顾][- 3]  
**目的**：某种映射方法，将原高维空间中的数据点映射到低维度的空间中  
**解决什么样的问题**：通过映射将数据降维后进行分类，案例征友考量，案例文科指数，理科指数(可以使用因子分析得到与原数据相关系数)

### 4.1.PCA算法 ###

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 5]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 6]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 7]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 8]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 9]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 10]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 11]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 12]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 13]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 14]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 15]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 16]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 17]

### 4.2.FA算法 ###

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 18]

## 5.学习（神经网络） ##

[学习-课程回顾][- 4]  
**目的**：某种映射方法，将原高维空间中的数据点映射到低维度的空间中  
**解决什么样的问题**：案例图像识别

### 5.1.BP神经网络 ###

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 19]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 20]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 21]

## 6.推荐算法 ##

[推荐-课程回顾][- 5]  
**目的**：利用用户的一些行为，通过一些数学算法，推测出用户可能喜欢的东西  
**解决什么样的问题**：案例推荐  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 22]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 23]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 24]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 25]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 26]

## 7.时间序列（视频学习） ##

[时间序列-课程回顾][- 6]  
**目的**：根据已有的历史数据对未来进行预测  
**解决什么样的问题**：案例股票  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 27]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 28]  
ADF检验  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 29]  
差分  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 30]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 31]  
ADF检验  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 32]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 33]  
反差分  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 34]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 35]

[Python]: https://blog.csdn.net/w576233728/article/details/86538060
[-]: https://www.bilibili.com/video/BV12p4y1X7JS?p=59
[Link 1]: https://blog.csdn.net/xuaho0907/article/details/88649141
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70]: /images/20230208/34b976a15b454da59c389635ffc20d10.png
[- 1]: https://www.bilibili.com/video/BV12p4y1X7JS?p=60
[- 2]: https://www.bilibili.com/video/BV12p4y1X7JS?p=61
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20200729145944480.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[Density-Based Spatial Clustering of Applications with Noise]: https://zhuanlan.zhihu.com/p/23504573
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/20200729150509807.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 3]: https://img-blog.csdnimg.cn/20200729150646877.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[Link 2]: https://zhuanlan.zhihu.com/p/22452157
[Link 3]: https://zhuanlan.zhihu.com/p/22458092
[Link 4]: https://zhuanlan.zhihu.com/p/22498257
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 4]: https://img-blog.csdnimg.cn/20200729150946825.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[- 3]: https://www.bilibili.com/video/BV12p4y1X7JS?p=62
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 5]: https://img-blog.csdnimg.cn/20200729160520896.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 6]: https://img-blog.csdnimg.cn/20200729160550268.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 7]: https://img-blog.csdnimg.cn/20200729160842818.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 8]: https://img-blog.csdnimg.cn/20200729161147931.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 9]: https://img-blog.csdnimg.cn/20200729161213125.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 10]: https://img-blog.csdnimg.cn/20200729161243643.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 11]: https://img-blog.csdnimg.cn/20200729161332894.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 12]: https://img-blog.csdnimg.cn/2020072916141736.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 13]: https://img-blog.csdnimg.cn/20200729161440321.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 14]: https://img-blog.csdnimg.cn/20200729161511662.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 15]: https://img-blog.csdnimg.cn/20200729161538866.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 16]: https://img-blog.csdnimg.cn/20200729161616336.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 17]: https://img-blog.csdnimg.cn/20200729161631132.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 18]: https://img-blog.csdnimg.cn/20200729160852720.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[- 4]: https://www.bilibili.com/video/BV12p4y1X7JS?p=63
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 19]: https://img-blog.csdnimg.cn/20200729161956703.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 20]: https://img-blog.csdnimg.cn/2020072916263782.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 21]: https://img-blog.csdnimg.cn/20200729162810759.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[- 5]: https://www.bilibili.com/video/BV12p4y1X7JS?p=64
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 22]: https://img-blog.csdnimg.cn/20200729163127853.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 23]: https://img-blog.csdnimg.cn/20200729163418948.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 24]: https://img-blog.csdnimg.cn/2020072916364755.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 25]: https://img-blog.csdnimg.cn/20200729163741782.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 26]: https://img-blog.csdnimg.cn/20200729163839136.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[- 6]: https://www.bilibili.com/video/BV12p4y1X7JS?p=65
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 27]: https://img-blog.csdnimg.cn/2020072916435099.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 28]: https://img-blog.csdnimg.cn/20200729164406887.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 29]: https://img-blog.csdnimg.cn/20200729164433909.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 30]: https://img-blog.csdnimg.cn/20200729164446917.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 31]: https://img-blog.csdnimg.cn/20200729164543239.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 32]: https://img-blog.csdnimg.cn/20200729164624773.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 33]: https://img-blog.csdnimg.cn/20200729164718101.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 34]: https://img-blog.csdnimg.cn/20200729164834756.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1_size_16_color_FFFFFF_t_70 35]: https://img-blog.csdnimg.cn/20200729164911640.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI1NjAxMzQ1,size_16,color_FFFFFF,t_70