Pandas

Dear 丶 2023-07-06 06:25 33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]

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

# **1 Pandas介绍** #

![20200216213926720.png][]

**  **

*  2008年WesMcKinney开发出的库
 *  专门用于数据挖掘的开源python库
 *  **以Numpy为基础，借力Numpy模块在计算方面性能高的优势**
 *  **基于matplotlib，能够简便的画图**
 *  **独特的数据结构**

## 2 为什么使用Pandas ##

Numpy已经能够帮助我们处理数据，能够结合matplotlib解决部分数据展示等问题，那么pandas学习的目的在什么地方呢？

*  **增强图表可读性**
    
     *  回忆我们在numpy当中创建学生成绩表样式：
     *  返回结果：

array([[92, 55, 78, 50, 50],
           [71, 76, 50, 48, 96],
           [45, 84, 78, 51, 68],
           [81, 91, 56, 54, 76],
           [86, 66, 77, 67, 95],
           [46, 86, 56, 61, 99],
           [46, 95, 44, 46, 56],
           [80, 50, 45, 65, 57],
           [41, 93, 90, 41, 97],
           [65, 83, 57, 57, 40]])

如果数据展示为这样，可读性就会更友好：

![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 1][]

## 3 小结 ##

*  pandas的优势【了解】
    
     *  增强图表可读性
     *  便捷的数据处理能力
     *  读取文件方便
     *  封装了Matplotlib、Numpy的画图和计算

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

# 5.2 Pandas数据结构 #

Pandas中一共有三种数据结构，分别为：Series、DataFrame和MultiIndex（老版本中叫Panel ）。

其中Series是一维数据结构，DataFrame是二维的表格型数据结构，MultiIndex是三维的数据结构。

## 1.Series ##

Series是一个类似于一维数组的数据结构，它能够保存任何类型的数据，比如整数、字符串、浮点数等，**主要由一组数据和与之相关的索引两部分构成。**

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 2][]

### 1.1 Series的创建 ###

# 导入pandas
    import pandas as pd
    
    pd.Series(data=None, index=None, dtype=None)

*  参数：
    
     *  data：传入的数据，可以是ndarray、list等
     *  index：索引，必须是唯一的，且与数据的长度相等。如果没有传入索引参数，则默认会自动创建一个从0-N的整数索引。
     *  dtype：数据的类型

通过已有数据创建

*  指定内容，默认索引

pd.Series(np.arange(10))

# 运行结果
    0    0
    1    1
    2    2
    3    3
    4    4
    5    5
    6    6
    7    7
    8    8
    9    9
    dtype: int64

*  指定索引

pd.Series([6.7,5.6,3,10,2], index=[1,2,3,4,5])

# 运行结果
    1     6.7
    2     5.6
    3     3.0
    4    10.0
    5     2.0
    dtype: float64

*  通过字典数据创建

color_count = pd.Series({'red':100, 'blue':200, 'green': 500, 'yellow':1000})
    color_count

# 运行结果
    blue       200
    green      500
    red        100
    yellow    1000
    dtype: int64

### 1.2 Series的属性 ###

为了更方便地操作Series对象中的索引和数据，**Series中提供了两个属性index和values**

*  index

color_count.index
    
    # 结果
    Index(['blue', 'green', 'red', 'yellow'], dtype='object')

*  values

color_count.values
    
    # 结果
    array([ 200,  500,  100, 1000])

也可以使用索引来获取数据：

color_count[2]
    
    # 结果
    100

## 2.DataFrame ##

DataFrame是一个类似于二维数组或表格(如excel)的对象，既有行索引，又有列索引

*  行索引，表明不同行，横向索引，叫index，0轴，axis=0
 *  列索引，表名不同列，纵向索引，叫columns，1轴，axis=1

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 3][]

### 2.1 DataFrame的创建 ###

# 导入pandas
    import pandas as pd
    
    pd.DataFrame(data=None, index=None, columns=None)

*  参数：
    
     *  index：行标签。如果没有传入索引参数，则默认会自动创建一个从0-N的整数索引。
     *  columns：列标签。如果没有传入索引参数，则默认会自动创建一个从0-N的整数索引。
 *  通过已有数据创建

举例一：

pd.DataFrame(np.random.randn(2,3))

![20200216214110785.png][]

回忆咱们在前面直接使用np创建的数组显示方式，比较两者的区别。

举例二：创建学生成绩表

# 生成10名同学，5门功课的数据
    score = np.random.randint(40, 100, (10, 5))
    
    # 结果
    array([[92, 55, 78, 50, 50],
           [71, 76, 50, 48, 96],
           [45, 84, 78, 51, 68],
           [81, 91, 56, 54, 76],
           [86, 66, 77, 67, 95],
           [46, 86, 56, 61, 99],
           [46, 95, 44, 46, 56],
           [80, 50, 45, 65, 57],
           [41, 93, 90, 41, 97],
           [65, 83, 57, 57, 40]])

**但是这样的数据形式很难看到存储的是什么的样的数据，可读性比较差！！**

**问题：如何让数据更有意义的显示**？

# 使用Pandas中的数据结构
    score_df = pd.DataFrame(score)

![2020021621412229.png][]

给分数数据增加行列索引,显示效果更佳

效果：

![20200216214131404.png][]

*  增加行、列索引

# 构造行索引序列
    subjects = ["语文", "数学", "英语", "政治", "体育"]
    
    # 构造列索引序列
    stu = ['同学' + str(i) for i in range(score_df.shape[0])]
    
    # 添加行索引
    data = pd.DataFrame(score, columns=subjects, index=stu)

### 2.2 DataFrame的属性 ###

*  **shape**

data.shape
    
    # 结果
    (10, 5)

*  **index**

DataFrame的行索引列表

data.index
    
    # 结果
    Index(['同学0', '同学1', '同学2', '同学3', '同学4', '同学5', '同学6', '同学7', '同学8', '同学9'], dtype='object')

*  **columns**

DataFrame的列索引列表

data.columns
    
    # 结果
    Index(['语文', '数学', '英语', '政治', '体育'], dtype='object')

*  **values**

直接获取其中array的值

data.values
    
    array([[92, 55, 78, 50, 50],
           [71, 76, 50, 48, 96],
           [45, 84, 78, 51, 68],
           [81, 91, 56, 54, 76],
           [86, 66, 77, 67, 95],
           [46, 86, 56, 61, 99],
           [46, 95, 44, 46, 56],
           [80, 50, 45, 65, 57],
           [41, 93, 90, 41, 97],
           [65, 83, 57, 57, 40]])

*  **T**

转置

data.T

结果

![20200216214144910.png][]

*  **head(5)**：显示前5行内容

如果不补充参数，默认5行。填入参数N则显示前N行

data.head(5)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 4][]

*  **tail(5)**:显示后5行内容

如果不补充参数，默认5行。填入参数N则显示后N行

data.tail(5)

### 2.3 DatatFrame索引的设置 ###

需求：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 5][]

2.3.1 修改行列索引值

stu = ["学生_" + str(i) for i in range(score_df.shape[0])]
    
    # 必须整体全部修改
    data.index = stu

注意：以下修改方式是错误的

# 错误修改方式
    data.index[3] = '学生_3'

2.3.2 重设索引

*  reset\_index(drop=False)
    
     *  设置新的下标索引
     *  drop:默认为False，不删除原来索引，如果为True,删除原来的索引值

# 重置索引,drop=False
    data.reset_index()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 6][]

# 重置索引,drop=True
    data.reset_index(drop=True)

2.3.3 以某列值设置为新的索引

*  set\_index(keys, drop=True)
    
     *  **keys** : 列索引名成或者列索引名称的列表
     *  **drop** : boolean, default True.当做新的索引，删除原来的列

设置新索引案例

1、创建

df = pd.DataFrame({'month': [1, 4, 7, 10],
                        'year': [2012, 2014, 2013, 2014],
                        'sale':[55, 40, 84, 31]})
    
       month  sale  year
    0  1      55    2012
    1  4      40    2014
    2  7      84    2013
    3  10     31    2014

2、以月份设置新的索引

df.set_index('month')
           sale  year
    month
    1      55    2012
    4      40    2014
    7      84    2013
    10     31    2014

3、设置多个索引，以年和月份

df = df.set_index(['year', 'month'])
    df
                sale
    year  month
    2012  1     55
    2014  4     40
    2013  7     84
    2014  10    31

> 注：通过刚才的设置，这样DataFrame就变成了一个具有MultiIndex的DataFrame。

## 3.MultiIndex与Panel ##

### 3.1 MultiIndex ###

MultiIndex是三维的数据结构;

多级索引（也称层次化索引）是pandas的重要功能，可以在Series、DataFrame对象上拥有2个以及2个以上的索引。

3.1.1 multiIndex的特性

打印刚才的df的行索引结果

df.index
    
    MultiIndex(levels=[[2012, 2013, 2014], [1, 4, 7, 10]],
               labels=[[0, 2, 1, 2], [0, 1, 2, 3]],
               names=['year', 'month'])

多级或分层索引对象。

*  index属性
    
     *  names:levels的名称
     *  levels：每个level的元组值

df.index.names
    # FrozenList(['year', 'month'])
    
    df.index.levels
    # FrozenList([[1, 2], [1, 4, 7, 10]])

3.1.2 multiIndex的创建

arrays = [[1, 1, 2, 2], ['red', 'blue', 'red', 'blue']]
    pd.MultiIndex.from_arrays(arrays, names=('number', 'color'))
    
    # 结果
    MultiIndex(levels=[[1, 2], ['blue', 'red']],
               codes=[[0, 0, 1, 1], [1, 0, 1, 0]],
               names=['number', 'color'])

### 3.2 Panel ###

3.2.1 panel的创建

*  *class* `pandas.Panel`(*data=None*, *items=None*, *major\_axis=None*, *minor\_axis=None*)
    
     *  作用：存储3维数组的Panel结构
     *  参数：
        
         *  **data** : ndarray或者dataframe
         *  **items** : 索引或类似数组的对象，axis=0
         *  **major\_axis** : 索引或类似数组的对象，axis=1
         *  **minor\_axis** : 索引或类似数组的对象，axis=2

p = pd.Panel(data=np.arange(24).reshape(4,3,2),
                     items=list('ABCD'),
                     major_axis=pd.date_range('20130101', periods=3),
                     minor_axis=['first', 'second'])
    
    # 结果
    <class 'pandas.core.panel.Panel'>
    Dimensions: 4 (items) x 3 (major_axis) x 2 (minor_axis)
    Items axis: A to D
    Major_axis axis: 2013-01-01 00:00:00 to 2013-01-03 00:00:00
    Minor_axis axis: first to second

3.2.2 查看panel数据

p[:,:,"first"]
    p["B",:,:]

> **注：Pandas从版本0.20.0开始弃用：推荐的用于表示3D数据的方法是通过DataFrame上的MultiIndex方法**

## 4 小结 ##

*  pandas的优势【了解】
    
     *  增强图表可读性
     *  便捷的数据处理能力
     *  读取文件方便
     *  封装了Matplotlib、Numpy的画图和计算
 *  series【知道】
    
     *  创建
        
         *  pd.Series(\[\], index=\[\])
         *  pd.Series(\{\})
     *  属性
        
         *  对象.index
         *  对象.values
 *  DataFrame【掌握】
    
     *  创建
        
         *  pd.DataFrame(data=None, index=None, columns=None)
     *  属性
        
         *  shape -- 形状
         *  index -- 行索引
         *  columns -- 列索引
         *  values -- 查看值
         *  T -- 转置
         *  head() -- 查看头部内容
         *  tail() -- 查看尾部内容
     *  DataFrame索引
        
         *  修改的时候,需要进行全局修改
         *  对象.reset\_index()
         *  对象.set\_index(keys)
 *  MultiIndex与Panel【了解】
    
     *  multiIndex:
        
         *  类似ndarray中的三维数组
         *  创建：
            
             *  pd.MultiIndex.from\_arrays()
         *  属性：
            
             *  对象.index
     *  panel：
        
         *  pd.Panel(data, items, major\_axis, minor\_axis)
         *  panel数据要是想看到,则需要进行索引到dataframe或者series才可以

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

# **5.3 基本数据操作** #

为了更好的理解这些基本操作，我们将读取一个真实的股票数据。关于文件操作，后面在介绍，这里只先用一下API

# 读取文件
    data = pd.read_csv("./data/stock_day.csv")
    
    # 删除一些列，让数据更简单些，再去做后面的操作
    data = data.drop(["ma5","ma10","ma20","v_ma5","v_ma10","v_ma20"], axis=1)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 7][]

## 1 索引操作 ##

Numpy当中我们已经讲过使用索引选取序列和切片选择，pandas也支持类似的操作，也可以直接使用列名、行名

称，甚至组合使用。

### 1.1 **直接使用行列索引(先列后行)** ###

获取'2018-02-27'这天的'close'的结果

# 直接使用行列索引名字的方式（先列后行）
    data['open']['2018-02-27']
    23.53
    
    # 不支持的操作
    # 错误
    data['2018-02-27']['open']
    # 错误
    data[:1, :2]

### 1.2 **结合loc或者iloc使用索引** ###

获取从'2018-02-27':'2018-02-22'，'open'的结果

# 使用loc:只能指定行列索引的名字
    data.loc['2018-02-27':'2018-02-22', 'open']
    
    2018-02-27    23.53
    2018-02-26    22.80
    2018-02-23    22.88
    Name: open, dtype: float64
    
    # 使用iloc可以通过索引的下标去获取
    # 获取前3天数据,前5列的结果
    data.iloc[:3, :5]
    
                open    high    close    low
    2018-02-27    23.53    25.88    24.16    23.53
    2018-02-26    22.80    23.78    23.53    22.80
    2018-02-23    22.88    23.37    22.82    22.71

### 1.3 **使用ix组合索引** ###

> Warning:Starting in 0.20.0, the `.ix` indexer is deprecated, in favor of the more strict `.iloc` and `.loc` indexers.

获取行第1天到第4天，\['open', 'close', 'high', 'low'\]这个四个指标的结果

# 使用ix进行下表和名称组合做引
    data.ix[0:4, ['open', 'close', 'high', 'low']]
    
    # 推荐使用loc和iloc来获取的方式
    data.loc[data.index[0:4], ['open', 'close', 'high', 'low']]
    data.iloc[0:4, data.columns.get_indexer(['open', 'close', 'high', 'low'])]
    
                open    close    high    low
    2018-02-27    23.53    24.16    25.88    23.53
    2018-02-26    22.80    23.53    23.78    22.80
    2018-02-23    22.88    22.82    23.37    22.71
    2018-02-22    22.25    22.28    22.76    22.02

## 2 赋值操作 ##

对DataFrame当中的close列进行重新赋值为1

# 直接修改原来的值
    data['close'] = 1
    # 或者
    data.close = 1

## 3 排序 ##

排序有两种形式，一种对于索引进行排序，一种对于内容进行排序

### 3.1 DataFrame排序 ###

*  使用df.sort\_values(by=, ascending=)
    
     *  单个键或者多个键进行排序,
     *  参数：
        
         *  by：指定排序参考的键
         *  ascending:默认升序
            
             *  ascending=False:降序
             *  ascending=True:升序

# 按照开盘价大小进行排序 , 使用ascending指定按照大小排序
    data.sort_values(by="open", ascending=True).head()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 8][]

# 按照多个键进行排序
    data.sort_values(by=['open', 'high'])

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 9][]

*  使用df.sort\_index给索引进行排序

这个股票的日期索引原来是从大到小，现在重新排序，从小到大

# 对索引进行排序
    data.sort_index()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 10][]

### 3.2 Series排序 ###

*  使用series.sort\_values(ascending=True)进行排序

series排序时，只有一列，不需要参数

data['p_change'].sort_values(ascending=True).head()
    
    2015-09-01   -10.03
    2015-09-14   -10.02
    2016-01-11   -10.02
    2015-07-15   -10.02
    2015-08-26   -10.01
    Name: p_change, dtype: float64

*  使用series.sort\_index()进行排序

与df一致

# 对索引进行排序
    data['p_change'].sort_index().head()
    
    2015-03-02    2.62
    2015-03-03    1.44
    2015-03-04    1.57
    2015-03-05    2.02
    2015-03-06    8.51
    Name: p_change, dtype: float64

## 4 总结 ##

*  1.索引【掌握】
    
     *  直接索引 -- 先列后行,是需要通过索引的字符串进行获取
     *  loc -- 先行后列,是需要通过索引的字符串进行获取
     *  iloc -- 先行后列,是通过下标进行索引
     *  ix -- 先行后列, 可以用上面两种方法混合进行索引
 *  2.赋值【知道】
    
     *  data\[""\] = \*\*
     *  data.** =**
 *  3.排序【知道】
    
     *  dataframe
        
         *  对象.sort\_values()
         *  对象.sort\_index()
     *  series
        
         *  对象.sort\_values()
         *  对象.sort\_index()

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

# 5.4 DataFrame运算 #

## 1 算术运算 ##

*  add(other)

比如进行数学运算加上具体的一个数字

data['open'].add(1)
    
    2018-02-27    24.53
    2018-02-26    23.80
    2018-02-23    23.88
    2018-02-22    23.25
    2018-02-14    22.49

*  sub(other)'

## 2 逻辑运算 ##

### 2.1 逻辑运算符号 ###

*  例如筛选data\["open"\] > 23的日期数据
    
     *  data\["open"\] > 23返回逻辑结果

data["open"] > 23
    
    2018-02-27     True
    2018-02-26    False
    2018-02-23    False
    2018-02-22    False
    2018-02-14    False

# 逻辑判断的结果可以作为筛选的依据
    data[data["open"] > 23].head()

![20200216214708539.png][]

*  完成多个逻辑判断，

data[(data["open"] > 23) & (data["open"] < 24)].head()

![20200216214718460.png][]

### 2.2 逻辑运算函数 ###

*  query(expr)
    
     *  expr:查询字符串

通过query使得刚才的过程更加方便简单

data.query("open<24 & open>23").head()

*  isin(values)

例如判断'open'是否为23.53和23.85

# 可以指定值进行一个判断，从而进行筛选操作
    data[data["open"].isin([23.53, 23.85])]

![20200216214735561.png][]

## 3 统计运算 ##

### 3.1 describe ###

综合分析: 能够直接得出很多统计结果,`count`, `mean`, `std`, `min`, `max` 等

# 计算平均值、标准差、最大值、最小值
    data.describe()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 11][]

### 3.2 统计函数 ###

Numpy当中已经详细介绍，在这里我们演示min(最小值), max(最大值), mean(平均值), median(中位数), var(方差), std(标准差),mode(众数)结果:

<table> 
 <thead> 
  <tr> 
   <th><code>count</code></th> 
   <th>Number of non-NA observations</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <td><code>sum</code></td> 
   <td><strong>Sum of values</strong></td> 
  </tr> 
  <tr> 
   <td><code>mean</code></td> 
   <td><strong>Mean of values</strong></td> 
  </tr> 
  <tr> 
   <td><code>median</code></td> 
   <td>Arithmetic median of values</td> 
  </tr> 
  <tr> 
   <td><code>min</code></td> 
   <td><strong>Minimum</strong></td> 
  </tr> 
  <tr> 
   <td><code>max</code></td> 
   <td><strong>Maximum</strong></td> 
  </tr> 
  <tr> 
   <td><code>mode</code></td> 
   <td>Mode</td> 
  </tr> 
  <tr> 
   <td><code>abs</code></td> 
   <td>Absolute Value</td> 
  </tr> 
  <tr> 
   <td><code>prod</code></td> 
   <td>Product of values</td> 
  </tr> 
  <tr> 
   <td><code>std</code></td> 
   <td><strong>Bessel-corrected sample standard deviation</strong></td> 
  </tr> 
  <tr> 
   <td><code>var</code></td> 
   <td><strong>Unbiased variance</strong></td> 
  </tr> 
  <tr> 
   <td><code>idxmax</code></td> 
   <td>compute the index labels with the maximum</td> 
  </tr> 
  <tr> 
   <td><code>idxmin</code></td> 
   <td>compute the index labels with the minimum</td> 
  </tr> 
 </tbody> 
</table>

**对于单个函数去进行统计的时候，坐标轴还是按照默认列“columns” (axis=0, default)，如果要对行“index” 需要指定(axis=1)**

*  max()、min()

# 使用统计函数：0 代表列求结果， 1 代表行求统计结果
    data.max(0)
    
    open                   34.99
    high                   36.35
    close                  35.21
    low                    34.01
    volume             501915.41
    price_change            3.03
    p_change               10.03
    turnover               12.56
    my_price_change         3.41
    dtype: float64

*  std()、var()

# 方差
    data.var(0)
    
    open               1.545255e+01
    high               1.662665e+01
    close              1.554572e+01
    low                1.437902e+01
    volume             5.458124e+09
    price_change       8.072595e-01
    p_change           1.664394e+01
    turnover           4.323800e+00
    my_price_change    6.409037e-01
    dtype: float64
    
    # 标准差
    data.std(0)
    
    open                   3.930973
    high                   4.077578
    close                  3.942806
    low                    3.791968
    volume             73879.119354
    price_change           0.898476
    p_change               4.079698
    turnover               2.079375
    my_price_change        0.800565
    dtype: float64

*  **median()：中位数**

中位数为将数据从小到大排列，在最中间的那个数为中位数。如果没有中间数，取中间两个数的平均值。

df = pd.DataFrame({'COL1' : [2,3,4,5,4,2],
                       'COL2' : [0,1,2,3,4,2]})
    
    df.median()
    
    COL1    3.5
    COL2    2.0
    dtype: float64

*  idxmax()、idxmin()

# 求出最大值的位置
    data.idxmax(axis=0)
    
    open               2015-06-15
    high               2015-06-10
    close              2015-06-12
    low                2015-06-12
    volume             2017-10-26
    price_change       2015-06-09
    p_change           2015-08-28
    turnover           2017-10-26
    my_price_change    2015-07-10
    dtype: object
    
    
    # 求出最小值的位置
    data.idxmin(axis=0)
    
    open               2015-03-02
    high               2015-03-02
    close              2015-09-02
    low                2015-03-02
    volume             2016-07-06
    price_change       2015-06-15
    p_change           2015-09-01
    turnover           2016-07-06
    my_price_change    2015-06-15
    dtype: object

### 3.3 累计统计函数 ###

<table> 
 <thead> 
  <tr> 
   <th>函数</th> 
   <th>作用</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <td><code>cumsum</code></td> 
   <td><strong>计算前1/2/3/…/n个数的和</strong></td> 
  </tr> 
  <tr> 
   <td><code>cummax</code></td> 
   <td>计算前1/2/3/…/n个数的最大值</td> 
  </tr> 
  <tr> 
   <td><code>cummin</code></td> 
   <td>计算前1/2/3/…/n个数的最小值</td> 
  </tr> 
  <tr> 
   <td><code>cumprod</code></td> 
   <td>计算前1/2/3/…/n个数的积</td> 
  </tr> 
 </tbody> 
</table>

**那么这些累计统计函数怎么用？**

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 12][]

以上这些函数可以对series和dataframe操作

这里我们按照时间的从前往后来进行累计

*  排序

# 排序之后，进行累计求和
    data = data.sort_index()

*  对p\_change进行求和

stock_rise = data['p_change']
    # plot方法集成了前面直方图、条形图、饼图、折线图
    stock_rise.cumsum()
    
    2015-03-02      2.62
    2015-03-03      4.06
    2015-03-04      5.63
    2015-03-05      7.65
    2015-03-06     16.16
    2015-03-09     16.37
    2015-03-10     18.75
    2015-03-11     16.36
    2015-03-12     15.03
    2015-03-13     17.58
    2015-03-16     20.34
    2015-03-17     22.42
    2015-03-18     23.28
    2015-03-19     23.74
    2015-03-20     23.48
    2015-03-23     23.74

**那么如何让这个连续求和的结果更好的显示呢？**

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 13][]

如果要使用plot函数，需要导入matplotlib.

import matplotlib.pyplot as plt
    # plot显示图形
    stock_rise.cumsum().plot()
    # 需要调用show，才能显示出结果
    plt.show()

> 关于plot，稍后会介绍API的选择

## 4 自定义运算 ##

*  apply(func, axis=0)
    
     *  func:自定义函数
     *  axis=0:默认是列，axis=1为行进行运算
 *  定义一个对列，最大值-最小值的函数

data[['open', 'close']].apply(lambda x: x.max() - x.min(), axis=0)
    
    open     22.74
    close    22.85
    dtype: float64

## 5 小结 ##

*  算术运算【知道】
 *  逻辑运算【知道】
    
     *  1.逻辑运算符号
     *  2.逻辑运算函数
        
         *  对象.query()
         *  对象.isin()
 *  统计运算【知道】
    
     *  1.对象.describe()
     *  2.统计函数
     *  3.累积统计函数
 *  自定义运算【知道】
    
     *  apply(func, axis=0)

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

# 5.5 Pandas画图 #

## 1 pandas.DataFrame.plot ##

*  `DataFrame.plot`(*kind='line'*)
 *  kind : str，需要绘制图形的种类
    
     *  **‘line’ : line plot (default)**
     *  ‘bar’ : vertical bar plot
     *  ‘barh’ : horizontal bar plot
        
         *  关于“barh”的解释：
         *  [http://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.plot.barh.html][http_pandas.pydata.org_pandas-docs_stable_reference_api_pandas.DataFrame.plot.barh.html]
     *  ‘hist’ : histogram
     *  ‘pie’ : pie plot
     *  ‘scatter’ : scatter plot

> 更多细节：[https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.plot.html?highlight=plot\#pandas.DataFrame.plot][https_pandas.pydata.org_pandas-docs_stable_generated_pandas.DataFrame.plot.html_highlight_plot_pandas.DataFrame.plot]

## 2 pandas.Series.plot ##

> 更多细节：[https://pandas.pydata.org/pandas-docs/stable/generated/pandas.Series.plot.html?highlight=plot\#pandas.Series.plot][https_pandas.pydata.org_pandas-docs_stable_generated_pandas.Series.plot.html_highlight_plot_pandas.Series.plot]

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

# 5.6 文件读取与存储 #

我们的数据大部分存在于文件当中，所以pandas会支持复杂的IO操作，pandas的API支持众多的文件格式，如CSV、SQL、XLS、JSON、HDF5。

> 注：最常用的HDF5和CSV文件

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 14][]

## 1 CSV ##

### 1.1 read\_csv ###

*  pandas.read\_csv(filepath\_or\_buffer, sep =',', usecols )
    
     *  filepath\_or\_buffer:文件路径
     *  sep :分隔符，默认用","隔开
     *  usecols:指定读取的列名，列表形式
 *  举例：读取之前的股票的数据

# 读取文件,并且指定只获取'open', 'close'指标
    data = pd.read_csv("./data/stock_day.csv", usecols=['open', 'close'])
    
                open    close
    2018-02-27    23.53    24.16
    2018-02-26    22.80    23.53
    2018-02-23    22.88    22.82
    2018-02-22    22.25    22.28
    2018-02-14    21.49    21.92

### 1.2 to\_csv ###

*  DataFrame.to\_csv(path\_or\_buf=None, sep=', ’, columns=None, header=True, index=True, mode='w', encoding=None)
    
     *  path\_or\_buf :文件路径
     *  sep :分隔符，默认用","隔开
     *  columns :选择需要的列索引
     *  header :boolean or list of string, default True,是否写进列索引值
     *  index:是否写进行索引
     *  mode:'w'：重写, 'a' 追加
 *  举例：保存读取出来的股票数据
    
     *  保存'open'列的数据，然后读取查看结果

# 选取10行数据保存,便于观察数据
    data[:10].to_csv("./data/test.csv", columns=['open'])

# 读取，查看结果
    pd.read_csv("./data/test.csv")
    
         Unnamed: 0    open
    0    2018-02-27    23.53
    1    2018-02-26    22.80
    2    2018-02-23    22.88
    3    2018-02-22    22.25
    4    2018-02-14    21.49
    5    2018-02-13    21.40
    6    2018-02-12    20.70
    7    2018-02-09    21.20
    8    2018-02-08    21.79
    9    2018-02-07    22.69

会发现将索引存入到文件当中，变成单独的一列数据。如果需要删除，可以指定index参数,删除原来的文件，重新保存一次。

# index:存储不会讲索引值变成一列数据
    data[:10].to_csv("./data/test.csv", columns=['open'], index=False)

## 2 HDF5 ##

### 2.1 read\_hdf与to\_hdf ###

**HDF5文件的读取和存储需要指定一个键，值为要存储的DataFrame**

*  pandas.read\_hdf(path\_or\_buf，key =None，\*\* kwargs)
    
    从h5文件当中读取数据
    
     *  path\_or\_buffer:文件路径
     *  key:读取的键
     *  return:Theselected object
 *  DataFrame.to\_hdf(path\_or\_buf, *key*, *\*\\*kwargs\*)

### 2.2 案例 ###

*  读取文件

day_close = pd.read_hdf("./data/day_close.h5")

如果读取的时候出现以下错误

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 15][]

需要安装安装tables模块避免不能读取HDF5文件

pip install tables

![2020021621494246.png][]

*  存储文件

day_close.to_hdf("./data/test.h5", key="day_close")

再次读取的时候, 需要指定键的名字

new_close = pd.read_hdf("./data/test.h5", key="day_close")

**注意：优先选择使用HDF5文件存储**

*  HDF5在存储的时候支持压缩，**使用的方式是blosc，这个是速度最快**的也是pandas默认支持的
 *  使用压缩可以**提磁盘利用率，节省空间**
 *  HDF5还是跨平台的，可以轻松迁移到hadoop 上面

## 3 JSON ##

JSON是我们常用的一种数据交换格式，前面在前后端的交互经常用到，也会在存储的时候选择这种格式。所以我们需要知道Pandas如何进行读取和存储JSON格式。

### 3.1 read\_json ###

*  pandas.read\_json(path\_or\_buf=None, orient=None, typ='frame', lines=False)
    
     *  将JSON格式准换成默认的Pandas DataFrame格式
     *  orient : string,Indication of expected JSON string format.
        
         *  'split' : dict like \{index -> \[index\], columns -> \[columns\], data -> \[values\]\}
            
             *  split 将索引总结到索引，列名到列名，数据到数据。将三部分都分开了
         *  **'records' : list like \[\{column -> value\}, ... , \{column -> value\}\]**
            
             *  records 以`columns：values`的形式输出
         *  'index' : dict like \{index -> \{column -> value\}\}
            
             *  index 以`index：{columns：values}...`的形式输出
         *  **'columns' : dict like \{column -> \{index -> value\}\}**,默认该格式
            
             *  colums 以`columns:{index:values}`的形式输出
         *  'values' : just the values array
            
             *  values 直接输出值
     *  lines : boolean, default False
        
         *  按照每行读取json对象
     *  typ : default ‘frame’， 指定转换成的对象类型series或者dataframe
    
    ### 3.2 read\_josn 案例 ###
 *  数据介绍

这里使用一个新闻标题讽刺数据集，格式为json。`is_sarcastic`：1讽刺的，否则为0；`headline`：新闻报道的标题；`article_link`：链接到原始新闻文章。存储格式为：

{"article_link": "https://www.huffingtonpost.com/entry/versace-black-code_us_5861fbefe4b0de3a08f600d5", "headline": "former versace store clerk sues over secret 'black code' for minority shoppers", "is_sarcastic": 0}
    {"article_link": "https://www.huffingtonpost.com/entry/roseanne-revival-review_us_5ab3a497e4b054d118e04365", "headline": "the 'roseanne' revival catches up to our thorny political mood, for better and worse", "is_sarcastic": 0}

*  读取

orient指定存储的json格式，lines指定按照行去变成一个样本

json_read = pd.read_json("./data/Sarcasm_Headlines_Dataset.json", orient="records", lines=True)

结果为：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 16][]

### 3.3 to\_json ###

*  DataFrame.to\_json(*path\_or\_buf=None*, *orient=None*, *lines=False*)
    
     *  将Pandas 对象存储为json格式
     *  *path\_or\_buf=None*：文件地址
     *  orient:存储的json形式，\{‘split’,’records’,’index’,’columns’,’values’\}
     *  lines:一个对象存储为一行

### 3.4 案例 ###

*  存储文件

json_read.to_json("./data/test.json", orient='records')

结果

[{"article_link":"https:\/\/www.huffingtonpost.com\/entry\/versace-black-code_us_5861fbefe4b0de3a08f600d5","headline":"former versace store clerk sues over secret 'black code' for minority shoppers","is_sarcastic":0},{"article_link":"https:\/\/www.huffingtonpost.com\/entry\/roseanne-revival-review_us_5ab3a497e4b054d118e04365","headline":"the 'roseanne' revival catches up to our thorny political mood, for better and worse","is_sarcastic":0},{"article_link":"https:\/\/local.theonion.com\/mom-starting-to-fear-son-s-web-series-closest-thing-she-1819576697","headline":"mom starting to fear son's web series closest thing she will have to grandchild","is_sarcastic":1},{"article_link":"https:\/\/politics.theonion.com\/boehner-just-wants-wife-to-listen-not-come-up-with-alt-1819574302","headline":"boehner just wants wife to listen, not come up with alternative debt-reduction ideas","is_sarcastic":1},{"article_link":"https:\/\/www.huffingtonpost.com\/entry\/jk-rowling-wishes-snape-happy-birthday_us_569117c4e4b0cad15e64fdcb","headline":"j.k. rowling wishes snape happy birthday in the most magical way","is_sarcastic":0},{"article_link":"https:\/\/www.huffingtonpost.com\/entry\/advancing-the-worlds-women_b_6810038.html","headline":"advancing the world's women","is_sarcastic":0},....]

*  修改lines参数为True

json_read.to_json("./data/test.json", orient='records', lines=True)

结果

{"article_link":"https:\/\/www.huffingtonpost.com\/entry\/versace-black-code_us_5861fbefe4b0de3a08f600d5","headline":"former versace store clerk sues over secret 'black code' for minority shoppers","is_sarcastic":0}
    {"article_link":"https:\/\/www.huffingtonpost.com\/entry\/roseanne-revival-review_us_5ab3a497e4b054d118e04365","headline":"the 'roseanne' revival catches up to our thorny political mood, for better and worse","is_sarcastic":0}
    {"article_link":"https:\/\/local.theonion.com\/mom-starting-to-fear-son-s-web-series-closest-thing-she-1819576697","headline":"mom starting to fear son's web series closest thing she will have to grandchild","is_sarcastic":1}
    {"article_link":"https:\/\/politics.theonion.com\/boehner-just-wants-wife-to-listen-not-come-up-with-alt-1819574302","headline":"boehner just wants wife to listen, not come up with alternative debt-reduction ideas","is_sarcastic":1}
    {"article_link":"https:\/\/www.huffingtonpost.com\/entry\/jk-rowling-wishes-snape-happy-birthday_us_569117c4e4b0cad15e64fdcb","headline":"j.k. rowling wishes snape happy birthday in the most magical way","is_sarcastic":0}...

## 4 小结 ##

*  pandas的CSV、HDF5、JSON文件的读取【知道】
    
     *  对象.read\_\*\*()
     *  对象.to\_\*\*()

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

# 5.7 高级处理-缺失值处理 #

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 17][]

## 1 如何处理nan ##

*  获取缺失值的标记方式(NaN或者其他标记方式)
 *  如果缺失值的标记方式是NaN
    
     *  判断数据中是否包含NaN：
        
         *  pd.isnull(df),
         *  pd.notnull(df)
     *  存在缺失值nan:
        
         *  1、删除存在缺失值的:dropna(axis='rows')
            
             *  注：不会修改原数据，需要接受返回值
         *  2、替换缺失值:fillna(value, inplace=True)
            
             *  value:替换成的值
             *  inplace:True:会修改原数据，False:不替换修改原数据，生成新的对象
 *  如果缺失值没有使用NaN标记，比如使用"？"
    
     *  先替换‘?’为np.nan，然后继续处理

## 2 电影数据的缺失值处理 ##

*  电影数据文件获取

# 读取电影数据
    movie = pd.read_csv("./data/IMDB-Movie-Data.csv")

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 18][]

### 2.1 判断缺失值是否存在 ###

*  pd.notnull()

pd.notnull(movie)

Rank    Title    Genre    Description    Director    Actors    Year    Runtime (Minutes)    Rating    Votes    Revenue (Millions)    Metascore
    0    True    True    True    True    True    True    True    True    True    True    True    True
    1    True    True    True    True    True    True    True    True    True    True    True    True
    2    True    True    True    True    True    True    True    True    True    True    True    True
    3    True    True    True    True    True    True    True    True    True    True    True    True
    4    True    True    True    True    True    True    True    True    True    True    True    True
    5    True    True    True    True    True    True    True    True    True    True    True    True
    6    True    True    True    True    True    True    True    True    True    True    True    True
    7    True    True    True    True    True    True    True    True    True    True    False    True

np.all(pd.notnull(movie))

*  pd.isnull()

### 2.2 存在缺失值nan,并且是np.nan ###

*  1、删除

pandas删除缺失值，使用dropna的前提是，缺失值的类型必须是np.nan

# 不修改原数据
    movie.dropna()
    
    # 可以定义新的变量接受或者用原来的变量名
    data = movie.dropna()

*  2、替换缺失值

# 替换存在缺失值的样本的两列
    # 替换填充平均值，中位数
    # movie['Revenue (Millions)'].fillna(movie['Revenue (Millions)'].mean(), inplace=True)

替换所有缺失值：

for i in movie.columns:
        if np.all(pd.notnull(movie[i])) == False:
            print(i)
            movie[i].fillna(movie[i].mean(), inplace=True)

### 2.3 不是缺失值nan，有默认标记的 ###

数据是这样的：![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 19][]

wis = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data")

以上数据在读取时，可能会报如下错误：

URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:833)>

解决办法：

# 全局取消证书验证
    import ssl
    ssl._create_default_https_context = ssl._create_unverified_context

**处理思路分析：**

*  1、先替换‘?’为np.nan
    
     *  df.replace(to\_replace=, value=)
        
         *  to\_replace:替换前的值
         *  value:替换后的值

# 把一些其它值标记的缺失值，替换成np.nan
    wis = wis.replace(to_replace='?', value=np.nan)

*  2、在进行缺失值的处理

# 删除
    wis = wis.dropna()

## 3 小结 ##

*  isnull、notnull判断是否存在缺失值【知道】
    
     *  np.any(pd.isnull(movie)) \# 里面如果有一个缺失值,就返回True
     *  np.all(pd.notnull(movie)) \# 里面如果有一个缺失值,就返回False
 *  dropna删除np.nan标记的缺失值【知道】
    
     *  movie.dropna()
 *  fillna填充缺失值【知道】
    
     *  movie\[i\].fillna(value=movie\[i\].mean(), inplace=True)
 *  replace替换具体某些值【知道】
    
     *  wis.replace(to\_replace="?", value=np.NaN)

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

# 5.8 高级处理-数据离散化![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 20][] #

## 1 为什么要离散化 ##

连续属性离散化的目的是为了简化数据结构，**数据离散化技术可以用来减少给定连续属性值的个数**。离散化方法经常作为数据挖掘的工具。

## 2 什么是数据的离散化 ##

**连续属性的离散化就是在连续属性的值域上，将值域划分为若干个离散的区间，最后用不同的符号或整数** **值代表落在每个子区间中的属性值。**

离散化有很多种方法，这使用一种最简单的方式去操作

*  原始人的身高数据：165，174，160，180，159，163，192，184
 *  假设按照身高分几个区间段：150~165, 165~180,180~195

这样我们将数据分到了三个区间段，我可以对应的标记为矮、中、高三个类别，最终要处理成一个"哑变量"矩阵

## 3 股票的涨跌幅离散化 ##

我们对股票每日的"p\_change"进行离散化

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 21][]

### 3.1 读取股票的数据 ###

先读取股票的数据，筛选出p\_change数据

data = pd.read_csv("./data/stock_day.csv")
    p_change= data['p_change']

### 3.2 将股票涨跌幅数据进行分组 ###

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 22][]

使用的工具：

*  pd.qcut(data, q)：
    
     *  对数据进行分组将数据分组，一般会与value\_counts搭配使用，统计每组的个数
 *  series.value\_counts()：统计分组次数

# 自行分组
    qcut = pd.qcut(p_change, 10)
    # 计算分到每个组数据个数
    qcut.value_counts()

自定义区间分组：

*  pd.cut(data, bins)

# 自己指定分组区间
    bins = [-100, -7, -5, -3, 0, 3, 5, 7, 100]
    p_counts = pd.cut(p_change, bins)

### 3.3 股票涨跌幅分组数据变成one-hot编码 ###

*  **什么是one-hot编码**

把每个类别生成一个布尔列，这些列中只有一列可以为这个样本取值为1.其又被称为独热编码。

把下图中左边的表格转化为使用右边形式进行表示：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 23][]

*  pandas.get\_dummies(*data*, *prefix=None*)
    
     *  data:array-like, Series, or DataFrame
     *  prefix:分组名字

# 得出one-hot编码矩阵
    dummies = pd.get_dummies(p_counts, prefix="rise")

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 24][]

## 4 小结 ##

*  数据离散化【知道】
    
     *  可以用来减少给定连续属性值的个数
     *  在连续属性的值域上，将值域划分为若干个离散的区间，最后用不同的符号或整数值代表落在每个子区间中的属性值。
 *  qcut、cut实现数据分组【知道】
    
     *  qcut:大致分为相同的几组
     *  cut:自定义分组区间
 *  get\_dummies实现哑变量矩阵【知道】

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

# 5.9 高级处理-合并 #

如果你的数据由多张表组成，那么有时候需要将不同的内容合并在一起分析

## 1 pd.concat实现数据合并 ##

*  pd.concat(\[data1, data2\], axis=1)
    
     *  按照行或列进行合并,axis=0为列索引，axis=1为行索引

比如我们将刚才处理好的one-hot编码与原数据合并

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 25][]

# 按照行索引进行
    pd.concat([data, dummies], axis=1)

## 2 pd.merge ##

*  pd.merge(left, right, how='inner', on=None)
    
     *  可以指定按照两组数据的共同键值对合并或者左右各自
     *  `left`: DataFrame
     *  `right`: 另一个DataFrame
     *  `on`: 指定的共同键
     *  how:按照什么方式连接

<table> 
 <thead> 
  <tr> 
   <th>Merge method</th> 
   <th>SQL Join Name</th> 
   <th>Description</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <td><code>left</code></td> 
   <td><code>LEFT OUTER JOIN</code></td> 
   <td>Use keys from left frame only</td> 
  </tr> 
  <tr> 
   <td><code>right</code></td> 
   <td><code>RIGHT OUTER JOIN</code></td> 
   <td>Use keys from right frame only</td> 
  </tr> 
  <tr> 
   <td><code>outer</code></td> 
   <td><code>FULL OUTER JOIN</code></td> 
   <td>Use union of keys from both frames</td> 
  </tr> 
  <tr> 
   <td><code>inner</code></td> 
   <td><code>INNER JOIN</code></td> 
   <td>Use intersection of keys from both frames</td> 
  </tr> 
 </tbody> 
</table>

### 2.1 pd.merge合并 ###

left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
                            'key2': ['K0', 'K1', 'K0', 'K1'],
                            'A': ['A0', 'A1', 'A2', 'A3'],
                            'B': ['B0', 'B1', 'B2', 'B3']})
    
    right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
                            'key2': ['K0', 'K0', 'K0', 'K0'],
                            'C': ['C0', 'C1', 'C2', 'C3'],
                            'D': ['D0', 'D1', 'D2', 'D3']})
    
    # 默认内连接
    result = pd.merge(left, right, on=['key1', 'key2'])

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 26][]

*  左连接

result = pd.merge(left, right, how='left', on=['key1', 'key2'])

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 27][]

*  右连接

result = pd.merge(left, right, how='right', on=['key1', 'key2'])

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 28][]

*  外链接

result = pd.merge(left, right, how='outer', on=['key1', 'key2'])

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 29][]

## 3 总结 ##

*  pd.concat(\[数据1, 数据2\], axis=\*\*)【知道】
 *  pd.merge(left, right, how=, on=)【知道】
    
     *  how -- 以何种方式连接
     *  on -- 连接的键的依据是哪几个

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

# 5.10 高级处理-交叉表与透视表 #

## 1 交叉表与透视表什么作用 ##

**探究股票的涨跌与星期几有关？**

**以下图当中表示，week代表星期几，1,0代表这一天股票的涨跌幅是好还是坏，里面的数据代表比例**

**可以理解为所有时间为星期一等等的数据当中涨跌幅好坏的比例**

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 30][]

*  交叉表：**交叉表用于计算一列数据对于另外一列数据的分组个数(用于统计分组频率的特殊透视表)**
    
     *  pd.crosstab(value1, value2)
 *  透视表：**透视表是将原有的DataFrame的列分别作为行索引和列索引，然后对指定的列应用聚集函数**
    
     *  data.pivot\_table(）
 *   *  DataFrame.pivot\_table(\[\], index=\[\])

## 2 案例分析 ##

### 2.1 数据准备 ###

*  准备两列数据，星期数据以及涨跌幅是好是坏数据
 *  进行交叉表计算

# 寻找星期几跟股票张得的关系
    # 1、先把对应的日期找到星期几
    date = pd.to_datetime(data.index).weekday
    data['week'] = date
    
    # 2、假如把p_change按照大小去分个类0为界限
    data['posi_neg'] = np.where(data['p_change'] > 0, 1, 0)
    
    # 通过交叉表找寻两列数据的关系
    count = pd.crosstab(data['week'], data['posi_neg'])

但是我们看到count只是每个星期日子的好坏天数，并没有得到比例，该怎么去做？

*  对于每个星期一等的总天数求和，运用除法运算求出比例

# 算数运算，先求和
    sum = count.sum(axis=1).astype(np.float32)
    
    # 进行相除操作，得出比例
    pro = count.div(sum, axis=0)

### 2.2 查看效果 ###

使用plot画出这个比例，使用stacked的柱状图

pro.plot(kind='bar', stacked=True)
    plt.show()

### 2.3 使用pivot\_table(透视表)实现 ###

使用透视表，刚才的过程更加简单

# 通过透视表，将整个过程变成更简单一些
    data.pivot_table(['posi_neg'], index='week')

## 3 小结 ##

*  交叉表与透视表的作用【知道】
    
     *  交叉表：计算一列数据对于另外一列数据的分组个数
     *  透视表：指定某一列对另一列的关系

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

# 5.11 高级处理-分组与聚合![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 31][] #

**分组与聚合通常是分析数据的一种方式，通常与一些统计函数一起使用，查看数据的分组情况**

想一想其实刚才的交叉表与透视表也有分组的功能，所以算是分组的一种形式，只不过他们主要是计算次数或者计算比例！！看其中的效果：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 32][]

## 1 什么分组与聚合 ##

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 33][]

## 2 分组API ##

*  DataFrame.groupby(key, as\_index=False)
    
     *  key:分组的列数据，可以多个
 *  案例:不同颜色的不同笔的价格数据

col =pd.DataFrame({'color': ['white','red','green','red','green'], 'object': ['pen','pencil','pencil','ashtray','pen'],'price1':[5.56,4.20,1.30,0.56,2.75],'price2':[4.75,4.12,1.60,0.75,3.15]})
    
    color    object    price1    price2
    0    white    pen    5.56    4.75
    1    red    pencil    4.20    4.12
    2    green    pencil    1.30    1.60
    3    red    ashtray    0.56    0.75
    4    green    pen    2.75    3.15

*  进行分组，对颜色分组，price进行聚合

# 分组，求平均值
    col.groupby(['color'])['price1'].mean()
    col['price1'].groupby(col['color']).mean()
    
    color
    green    2.025
    red      2.380
    white    5.560
    Name: price1, dtype: float64
    
    # 分组，数据的结构不变
    col.groupby(['color'], as_index=False)['price1'].mean()
    
    color    price1
    0    green    2.025
    1    red    2.380
    2    white    5.560

## 3 星巴克零售店铺数据 ##

现在我们有一组关于全球星巴克店铺的统计数据，如果我想知道美国的星巴克数量和中国的哪个多，或者我想知道中国每个省份星巴克的数量的情况，那么应该怎么办？

> 数据来源：[https://www.kaggle.com/starbucks/store-locations/data][https_www.kaggle.com_starbucks_store-locations_data]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 34][]

### 3.1 数据获取 ###

从文件中读取星巴克店铺数据

# 导入星巴克店的数据
    starbucks = pd.read_csv("./data/starbucks/directory.csv")

### 3.2 进行分组聚合 ###

# 按照国家分组，求出每个国家的星巴克零售店数量
    count = starbucks.groupby(['Country']).count()

**画图显示结果**

count['Brand'].plot(kind='bar', figsize=(20, 8))
    plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 35][]

假设我们加入省市一起进行分组

# 设置多个索引，set_index()
    starbucks.groupby(['Country', 'State/Province']).count()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 36][]

**仔细观察这个结构，与我们前面讲的哪个结构类似？？**

与前面的MultiIndex结构类似

## 4 小结 ##

*  groupby进行数据的分组【知道】
    
     *  pandas中，抛开聚合谈分组，无意义

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

# 案例 #

## 1 需求 ##

现在我们有一组从2006年到2016年1000部最流行的电影数据

数据来源：[https://www.kaggle.com/damianpanek/sunday-eda/data][https_www.kaggle.com_damianpanek_sunday-eda_data]

*  问题1：我们想知道这些电影数据中评分的平均分，导演的人数等信息，我们应该怎么获取？
 *  问题2：对于这一组电影数据，如果我们想rating，runtime的分布情况，应该如何呈现数据？
 *  问题3：对于这一组电影数据，如果我们希望统计电影分类(genre)的情况，应该如何处理数据？

## 2 实现 ##

首先获取导入包，获取数据

%matplotlib inline
    import pandas  as pd 
    import numpy as np
    from matplotlib import pyplot as plt

#文件的路径
    path = "./data/IMDB-Movie-Data.csv"
    #读取文件
    df = pd.read_csv(path)

### 2.1 问题一： ###

**我们想知道这些电影数据中评分的平均分，导演的人数等信息，我们应该怎么获取？**

*  得出评分的平均分

使用mean函数

df["Rating"].mean()

*  得出导演人数信息

求出唯一值，然后进行形状获取

## 导演的人数
    # df["Director"].unique().shape[0]
    np.unique(df["Director"]).shape[0]
    
    644

### 2.2 问题二： ###

**对于这一组电影数据，如果我们想Rating，Runtime (Minutes)的分布情况，应该如何呈现数据？**

*  直接呈现，以直方图的形式

选择分数列数据，进行plot

df["Rating"].plot(kind='hist',figsize=(20,8))

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 37][]

*  Rating进行分布展示

进行绘制直方图

plt.figure(figsize=(20,8),dpi=80)
    plt.hist(df["Rating"].values,bins=20)
    plt.show()

修改刻度的间隔

# 求出最大最小值
    max_ = df["Rating"].max()
    min_ = df["Rating"].min()
    
    # 生成刻度列表
    t1 = np.linspace(min_,max_,num=21)
    
    # [ 1.9    2.255  2.61   2.965  3.32   3.675  4.03   4.385  4.74   5.095  5.45   5.805  6.16   6.515  6.87   7.225  7.58   7.935  8.29   8.645  9.   ]
    
    # 修改刻度
    plt.xticks(t1)
    
    # 添加网格
    plt.grid()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 38][]

*  Runtime (Minutes)进行分布展示

进行绘制直方图

plt.figure(figsize=(20,8),dpi=80)
    plt.hist(df["Runtime (Minutes)"].values,bins=20)
    plt.show()

修改间隔

# 求出最大最小值
    max_ = df["Runtime (Minutes)"].max()
    min_ = df["Runtime (Minutes)"].min()
    
    # # 生成刻度列表
    t1 = np.linspace(min_,max_,num=21)
    
    # 修改刻度
    plt.xticks(np.linspace(min_,max_,num=21))
    
    # 添加网格
    plt.grid()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 39][]

### 2.3 问题三： ###

**对于这一组电影数据，如果我们希望统计电影分类(genre)的情况，应该如何处理数据？**

*  思路分析
    
     *  思路
        
         *  1、创建一个全为0的dataframe，列索引置为电影的分类，temp\_df
         *  2、遍历每一部电影，temp\_df中把分类出现的列的值置为1
         *  3、求和
 *  1、创建一个全为0的dataframe，列索引置为电影的分类，temp\_df

# 进行字符串分割
    temp_list = [i.split(",") for i in df["Genre"]]
    # 获取电影的分类
    genre_list = np.unique([i for j in temp_list for i in j]) 
    
    # 增加新的列
    temp_df = pd.DataFrame(np.zeros([df.shape[0],genre_list.shape[0]]),columns=genre_list)

*  2、遍历每一部电影，temp\_df中把分类出现的列的值置为1

for i in range(1000):
        #temp_list[i] ['Action','Adventure','Animation']
        temp_df.ix[i,temp_list[i]]=1
    print(temp_df.sum().sort_values())

*  3、求和,绘图

temp_df.sum().sort_values(ascending=False).plot(kind="bar",figsize=(20,8),fontsize=20,colormap="cool")
    
    
    Musical        5.0
    Western        7.0
    War           13.0
    Music         16.0
    Sport         18.0
    History       29.0
    Animation     49.0
    Family        51.0
    Biography     81.0
    Fantasy      101.0
    Mystery      106.0
    Horror       119.0
    Sci-Fi       120.0
    Romance      141.0
    Crime        150.0
    Thriller     195.0
    Adventure    259.0
    Comedy       279.0
    Action       303.0
    Drama        513.0
    dtype: float64

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 40][]

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

series
    series的创建
    import pandas as pd
    import numpy as np
    pd.Series(np.arange(9))
    0    0
    1    1
    2    2
    3    3
    4    4
    5    5
    6    6
    7    7
    8    8
    dtype: int64
    pd.Series([1.2, 2.3, 4.5, 5.0], index=[1, 2, 3, 4])
    1    1.2
    2    2.3
    3    4.5
    4    5.0
    dtype: float64
    color_count = pd.Series({"red":10, "green":20, "blue":100})
    color_count
    blue     100
    green     20
    red       10
    dtype: int64
    series的属性
    color_count.index
    Index(['blue', 'green', 'red'], dtype='object')
    color_count.values
    array([100,  20,  10])
    color_count[0]
    100
    color_count[1]
    20
    DataFrame
    DataFrame创建
    pd.DataFrame(np.random.randn(2,3))

![20200217210309220.png][]

score = np.random.randint(40, 100, (10, 5))
    score
    array([[98, 85, 84, 93, 83],
           [73, 68, 64, 47, 87],
           [91, 58, 86, 92, 46],
           [62, 86, 99, 75, 66],
           [49, 73, 46, 61, 81],
           [43, 96, 47, 65, 90],
           [98, 84, 60, 73, 54],
           [59, 93, 58, 83, 43],
           [62, 66, 51, 88, 89],
           [66, 60, 63, 57, 51]])
    score_df = pd.DataFrame(score)
    score_df

![20200217210407216.png][]

subjects = ["语文", "数学", "英语", "政治", "体育"]
    
    stu = ["同学"+ str(i) for i in range(score_df.shape[0])]
    
    data = pd.DataFrame(score, columns=subjects, index=stu)
    stu
    ['同学0', '同学1', '同学2', '同学3', '同学4', '同学5', '同学6', '同学7', '同学8', '同学9']
    data

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 41][]

DataFrame的属性
    data.shape
    (10, 5)
    data.index
    Index(['同学0', '同学1', '同学2', '同学3', '同学4', '同学5', '同学6', '同学7', '同学8', '同学9'], dtype='object')
    data.columns
    Index(['语文', '数学', '英语', '政治', '体育'], dtype='object')
    data.values
    array([[98, 85, 84, 93, 83],
           [73, 68, 64, 47, 87],
           [91, 58, 86, 92, 46],
           [62, 86, 99, 75, 66],
           [49, 73, 46, 61, 81],
           [43, 96, 47, 65, 90],
           [98, 84, 60, 73, 54],
           [59, 93, 58, 83, 43],
           [62, 66, 51, 88, 89],
           [66, 60, 63, 57, 51]])
    data.T

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 42][]![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 43][]

DataFrame索引值的设置
    stu = ["同学_"+ str(i) for i in range(score_df.shape[0])]
    
    data.index = stu
    # stu
    data

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 44][]

# data.index[2] = "同学__"
    
    data.reset_index()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 45][]

data.reset_index(drop=True)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 46][]

df = pd.DataFrame({'month': [1, 4, 7, 10],
                        'year': [2012, 2014, 2013, 2014],
                        'sale':[55, 40, 84, 31]})
    df

![20200217210621373.png][]

df.set_index("year")

![20200217210631687.png][]

df = df.set_index(["year", "month"])
    df

![20200217210646103.png][]

MultiIndex与Panel
    MultiIndex
    df

![20200217210701467.png][]

df.index
    MultiIndex(levels=[[2012, 2013, 2014], [1, 4, 7, 10]],
               labels=[[0, 2, 1, 2], [0, 1, 2, 3]],
               names=['year', 'month'])
    df.index.names
    FrozenList(['year', 'month'])
    df.index.levels
    FrozenList([[2012, 2013, 2014], [1, 4, 7, 10]])
    arrays = [[1, 1, 2, 2], ["r", "b", "r","b"]]
    pd.MultiIndex.from_arrays(arrays, names=("num", "col"))
    MultiIndex(levels=[[1, 2], ['b', 'r']],
               labels=[[0, 0, 1, 1], [1, 0, 1, 0]],
               names=['num', 'col'])

panel
    p = pd.Panel(data=np.arange(24).reshape(4,3,2),
                     items=list('ABCD'),
                     major_axis=pd.date_range('20130101', periods=3),
                     minor_axis=['first', 'second'])
    p
    <class 'pandas.core.panel.Panel'>
    Dimensions: 4 (items) x 3 (major_axis) x 2 (minor_axis)
    Items axis: A to D
    Major_axis axis: 2013-01-01 00:00:00 to 2013-01-03 00:00:00
    Minor_axis axis: first to second

![20200217210739197.png][]

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

In \[1\]:

import pandas as pd

In \[2\]:

data = pd.read\_csv("./data/stock\_day.csv")

In \[4\]:

data.head()

Out\[4\]:

In \[5\]:

data = data.drop(\["ma5","ma10","ma20","v\_ma5","v\_ma10","v\_ma20"\], axis=1)

In \[7\]:

data.head()

Out\[7\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>turnover</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2018-02-27</th> 
   <td>23.53</td> 
   <td>25.88</td> 
   <td>24.16</td> 
   <td>23.53</td> 
   <td>95578.03</td> 
   <td>0.63</td> 
   <td>2.68</td> 
   <td>2.39</td> 
  </tr> 
  <tr> 
   <th>2018-02-26</th> 
   <td>22.80</td> 
   <td>23.78</td> 
   <td>23.53</td> 
   <td>22.80</td> 
   <td>60985.11</td> 
   <td>0.69</td> 
   <td>3.02</td> 
   <td>1.53</td> 
  </tr> 
  <tr> 
   <th>2018-02-23</th> 
   <td>22.88</td> 
   <td>23.37</td> 
   <td>22.82</td> 
   <td>22.71</td> 
   <td>52914.01</td> 
   <td>0.54</td> 
   <td>2.42</td> 
   <td>1.32</td> 
  </tr> 
  <tr> 
   <th>2018-02-22</th> 
   <td>22.25</td> 
   <td>22.76</td> 
   <td>22.28</td> 
   <td>22.02</td> 
   <td>36105.01</td> 
   <td>0.36</td> 
   <td>1.64</td> 
   <td>0.90</td> 
  </tr> 
  <tr> 
   <th>2018-02-14</th> 
   <td>21.49</td> 
   <td>21.99</td> 
   <td>21.92</td> 
   <td>21.48</td> 
   <td>23331.04</td> 
   <td>0.44</td> 
   <td>2.05</td> 
   <td>0.58</td> 
  </tr> 
 </tbody> 
</table>

# 索引操作 #

In \[8\]:

data\["open"\]\["2018-02-27"\] \# 直接索引,必须是先列后行

Out\[8\]:

23.53

In \[11\]:

\# data\["2018-02-27"\]\["open"\]

In \[13\]:

\# data\[:1 ,:2\]

In \[14\]:

data.loc\["2018-02-27":"2018-02-14", "open":"close"\]

Out\[14\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2018-02-27</th> 
   <td>23.53</td> 
   <td>25.88</td> 
   <td>24.16</td> 
  </tr> 
  <tr> 
   <th>2018-02-26</th> 
   <td>22.80</td> 
   <td>23.78</td> 
   <td>23.53</td> 
  </tr> 
  <tr> 
   <th>2018-02-23</th> 
   <td>22.88</td> 
   <td>23.37</td> 
   <td>22.82</td> 
  </tr> 
  <tr> 
   <th>2018-02-22</th> 
   <td>22.25</td> 
   <td>22.76</td> 
   <td>22.28</td> 
  </tr> 
  <tr> 
   <th>2018-02-14</th> 
   <td>21.49</td> 
   <td>21.99</td> 
   <td>21.92</td> 
  </tr> 
 </tbody> 
</table>

In \[15\]:

data.iloc\[:5, :3\]

Out\[15\]:

In \[16\]:

data.ix\[0:5, \["open", "close"\]\]

Out\[16\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>close</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2018-02-27</th> 
   <td>23.53</td> 
   <td>24.16</td> 
  </tr> 
  <tr> 
   <th>2018-02-26</th> 
   <td>22.80</td> 
   <td>23.53</td> 
  </tr> 
  <tr> 
   <th>2018-02-23</th> 
   <td>22.88</td> 
   <td>22.82</td> 
  </tr> 
  <tr> 
   <th>2018-02-22</th> 
   <td>22.25</td> 
   <td>22.28</td> 
  </tr> 
  <tr> 
   <th>2018-02-14</th> 
   <td>21.49</td> 
   <td>21.92</td> 
  </tr> 
 </tbody> 
</table>

In \[17\]:

data.loc\[data.index\[0:5\], \["open", "close"\]\]

Out\[17\]:

In \[19\]:

data.columns.get\_indexer(\["open", "close"\])

Out\[19\]:

array([0, 2])

In \[20\]:

data.iloc\[0:5, data.columns.get\_indexer(\["open", "close"\])\]

Out\[20\]:

# 赋值操作 #

In \[22\]:

data\["close"\] = 1

In \[24\]:

data.head()

Out\[24\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>turnover</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2018-02-27</th> 
   <td>23.53</td> 
   <td>25.88</td> 
   <td>1</td> 
   <td>23.53</td> 
   <td>95578.03</td> 
   <td>0.63</td> 
   <td>2.68</td> 
   <td>2.39</td> 
  </tr> 
  <tr> 
   <th>2018-02-26</th> 
   <td>22.80</td> 
   <td>23.78</td> 
   <td>1</td> 
   <td>22.80</td> 
   <td>60985.11</td> 
   <td>0.69</td> 
   <td>3.02</td> 
   <td>1.53</td> 
  </tr> 
  <tr> 
   <th>2018-02-23</th> 
   <td>22.88</td> 
   <td>23.37</td> 
   <td>1</td> 
   <td>22.71</td> 
   <td>52914.01</td> 
   <td>0.54</td> 
   <td>2.42</td> 
   <td>1.32</td> 
  </tr> 
  <tr> 
   <th>2018-02-22</th> 
   <td>22.25</td> 
   <td>22.76</td> 
   <td>1</td> 
   <td>22.02</td> 
   <td>36105.01</td> 
   <td>0.36</td> 
   <td>1.64</td> 
   <td>0.90</td> 
  </tr> 
  <tr> 
   <th>2018-02-14</th> 
   <td>21.49</td> 
   <td>21.99</td> 
   <td>1</td> 
   <td>21.48</td> 
   <td>23331.04</td> 
   <td>0.44</td> 
   <td>2.05</td> 
   <td>0.58</td> 
  </tr> 
 </tbody> 
</table>

In \[26\]:

data.close = 10

In \[27\]:

data.head()

Out\[27\]:

# 排序 #

In \[30\]:

data.sort\_values(by="open", ascending=False).head()

Out\[30\]:

In \[32\]:

data.sort\_values(by=\["open", "high"\]).head()

Out\[32\]:

In \[34\]:

data.sort\_index().head()

Out\[34\]:

In \[37\]:

data\["high"\].sort\_values().head()

Out\[37\]:

2015-03-02    12.67
    2015-03-04    12.92
    2015-03-03    13.06
    2015-09-07    13.38
    2015-03-05    13.45
    Name: high, dtype: float64

In \[39\]:

data\["high"\].sort\_index().head()

Out\[39\]:

2015-03-02    12.67
    2015-03-03    13.06
    2015-03-04    12.92
    2015-03-05    13.45
    2015-03-06    14.48
    Name: high, dtype: float64

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

In \[79\]:

import pandas as pd

import matplotlib.pyplot as plt

In \[35\]:

data = pd.read\_csv("./data/stock\_day.csv")

In \[84\]:

data.head()

Out\[84\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>turnover</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2015-03-02</th> 
   <td>12.25</td> 
   <td>12.67</td> 
   <td>12.52</td> 
   <td>12.20</td> 
   <td>96291.73</td> 
   <td>0.32</td> 
   <td>2.62</td> 
   <td>3.30</td> 
  </tr> 
  <tr> 
   <th>2015-03-03</th> 
   <td>12.52</td> 
   <td>13.06</td> 
   <td>12.70</td> 
   <td>12.52</td> 
   <td>139071.61</td> 
   <td>0.18</td> 
   <td>1.44</td> 
   <td>4.76</td> 
  </tr> 
  <tr> 
   <th>2015-03-04</th> 
   <td>12.80</td> 
   <td>12.92</td> 
   <td>12.90</td> 
   <td>12.61</td> 
   <td>67075.44</td> 
   <td>0.20</td> 
   <td>1.57</td> 
   <td>2.30</td> 
  </tr> 
  <tr> 
   <th>2015-03-05</th> 
   <td>12.88</td> 
   <td>13.45</td> 
   <td>13.16</td> 
   <td>12.87</td> 
   <td>93180.39</td> 
   <td>0.26</td> 
   <td>2.02</td> 
   <td>3.19</td> 
  </tr> 
  <tr> 
   <th>2015-03-06</th> 
   <td>13.17</td> 
   <td>14.48</td> 
   <td>14.28</td> 
   <td>13.13</td> 
   <td>179831.72</td> 
   <td>1.12</td> 
   <td>8.51</td> 
   <td>6.16</td> 
  </tr> 
 </tbody> 
</table>

In \[37\]:

data = data.drop(\["ma5","ma10","ma20","v\_ma5","v\_ma10","v\_ma20"\], axis=1)

In \[38\]:

data.head()

Out\[38\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>turnover</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2018-02-27</th> 
   <td>23.53</td> 
   <td>25.88</td> 
   <td>24.16</td> 
   <td>23.53</td> 
   <td>95578.03</td> 
   <td>0.63</td> 
   <td>2.68</td> 
   <td>2.39</td> 
  </tr> 
  <tr> 
   <th>2018-02-26</th> 
   <td>22.80</td> 
   <td>23.78</td> 
   <td>23.53</td> 
   <td>22.80</td> 
   <td>60985.11</td> 
   <td>0.69</td> 
   <td>3.02</td> 
   <td>1.53</td> 
  </tr> 
  <tr> 
   <th>2018-02-23</th> 
   <td>22.88</td> 
   <td>23.37</td> 
   <td>22.82</td> 
   <td>22.71</td> 
   <td>52914.01</td> 
   <td>0.54</td> 
   <td>2.42</td> 
   <td>1.32</td> 
  </tr> 
  <tr> 
   <th>2018-02-22</th> 
   <td>22.25</td> 
   <td>22.76</td> 
   <td>22.28</td> 
   <td>22.02</td> 
   <td>36105.01</td> 
   <td>0.36</td> 
   <td>1.64</td> 
   <td>0.90</td> 
  </tr> 
  <tr> 
   <th>2018-02-14</th> 
   <td>21.49</td> 
   <td>21.99</td> 
   <td>21.92</td> 
   <td>21.48</td> 
   <td>23331.04</td> 
   <td>0.44</td> 
   <td>2.05</td> 
   <td>0.58</td> 
  </tr> 
 </tbody> 
</table>

# 算术运算 #

In \[41\]:

data\["open"\].add(10).head()

Out\[41\]:

2018-02-27    33.53
    2018-02-26    32.80
    2018-02-23    32.88
    2018-02-22    32.25
    2018-02-14    31.49
    Name: open, dtype: float64

In \[43\]:

\# data\["open"\]+10 \# 一般不会这么使用

# 逻辑运算 #

In \[45\]:

\# data\["close"\] > 20

In \[48\]:

data\[data\["open"\] > 23\].head()

Out\[48\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>turnover</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2018-02-27</th> 
   <td>23.53</td> 
   <td>25.88</td> 
   <td>24.16</td> 
   <td>23.53</td> 
   <td>95578.03</td> 
   <td>0.63</td> 
   <td>2.68</td> 
   <td>2.39</td> 
  </tr> 
  <tr> 
   <th>2018-02-01</th> 
   <td>23.71</td> 
   <td>23.86</td> 
   <td>22.42</td> 
   <td>22.22</td> 
   <td>66414.64</td> 
   <td>-1.30</td> 
   <td>-5.48</td> 
   <td>1.66</td> 
  </tr> 
  <tr> 
   <th>2018-01-31</th> 
   <td>23.85</td> 
   <td>23.98</td> 
   <td>23.72</td> 
   <td>23.31</td> 
   <td>49155.02</td> 
   <td>-0.11</td> 
   <td>-0.46</td> 
   <td>1.23</td> 
  </tr> 
  <tr> 
   <th>2018-01-30</th> 
   <td>23.71</td> 
   <td>24.08</td> 
   <td>23.83</td> 
   <td>23.70</td> 
   <td>32420.43</td> 
   <td>0.05</td> 
   <td>0.21</td> 
   <td>0.81</td> 
  </tr> 
  <tr> 
   <th>2018-01-29</th> 
   <td>24.40</td> 
   <td>24.63</td> 
   <td>23.77</td> 
   <td>23.72</td> 
   <td>65469.81</td> 
   <td>-0.73</td> 
   <td>-2.98</td> 
   <td>1.64</td> 
  </tr> 
 </tbody> 
</table>

In \[51\]:

data\[(data\["open"\]>23)&(data\["open"\]<24)\].head()

Out\[51\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>turnover</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2018-02-27</th> 
   <td>23.53</td> 
   <td>25.88</td> 
   <td>24.16</td> 
   <td>23.53</td> 
   <td>95578.03</td> 
   <td>0.63</td> 
   <td>2.68</td> 
   <td>2.39</td> 
  </tr> 
  <tr> 
   <th>2018-02-01</th> 
   <td>23.71</td> 
   <td>23.86</td> 
   <td>22.42</td> 
   <td>22.22</td> 
   <td>66414.64</td> 
   <td>-1.30</td> 
   <td>-5.48</td> 
   <td>1.66</td> 
  </tr> 
  <tr> 
   <th>2018-01-31</th> 
   <td>23.85</td> 
   <td>23.98</td> 
   <td>23.72</td> 
   <td>23.31</td> 
   <td>49155.02</td> 
   <td>-0.11</td> 
   <td>-0.46</td> 
   <td>1.23</td> 
  </tr> 
  <tr> 
   <th>2018-01-30</th> 
   <td>23.71</td> 
   <td>24.08</td> 
   <td>23.83</td> 
   <td>23.70</td> 
   <td>32420.43</td> 
   <td>0.05</td> 
   <td>0.21</td> 
   <td>0.81</td> 
  </tr> 
  <tr> 
   <th>2018-01-16</th> 
   <td>23.40</td> 
   <td>24.60</td> 
   <td>24.40</td> 
   <td>23.30</td> 
   <td>101295.42</td> 
   <td>0.96</td> 
   <td>4.10</td> 
   <td>2.54</td> 
  </tr> 
 </tbody> 
</table>

In \[53\]:

data.query("open<24 & open>23").head()

Out\[53\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>turnover</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2018-02-27</th> 
   <td>23.53</td> 
   <td>25.88</td> 
   <td>24.16</td> 
   <td>23.53</td> 
   <td>95578.03</td> 
   <td>0.63</td> 
   <td>2.68</td> 
   <td>2.39</td> 
  </tr> 
  <tr> 
   <th>2018-02-01</th> 
   <td>23.71</td> 
   <td>23.86</td> 
   <td>22.42</td> 
   <td>22.22</td> 
   <td>66414.64</td> 
   <td>-1.30</td> 
   <td>-5.48</td> 
   <td>1.66</td> 
  </tr> 
  <tr> 
   <th>2018-01-31</th> 
   <td>23.85</td> 
   <td>23.98</td> 
   <td>23.72</td> 
   <td>23.31</td> 
   <td>49155.02</td> 
   <td>-0.11</td> 
   <td>-0.46</td> 
   <td>1.23</td> 
  </tr> 
  <tr> 
   <th>2018-01-30</th> 
   <td>23.71</td> 
   <td>24.08</td> 
   <td>23.83</td> 
   <td>23.70</td> 
   <td>32420.43</td> 
   <td>0.05</td> 
   <td>0.21</td> 
   <td>0.81</td> 
  </tr> 
  <tr> 
   <th>2018-01-16</th> 
   <td>23.40</td> 
   <td>24.60</td> 
   <td>24.40</td> 
   <td>23.30</td> 
   <td>101295.42</td> 
   <td>0.96</td> 
   <td>4.10</td> 
   <td>2.54</td> 
  </tr> 
 </tbody> 
</table>

In \[57\]:

data\[data\["open"\].isin(\[23.23, 23.71\])\]

Out\[57\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>turnover</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2018-02-01</th> 
   <td>23.71</td> 
   <td>23.86</td> 
   <td>22.42</td> 
   <td>22.22</td> 
   <td>66414.64</td> 
   <td>-1.30</td> 
   <td>-5.48</td> 
   <td>1.66</td> 
  </tr> 
  <tr> 
   <th>2018-01-30</th> 
   <td>23.71</td> 
   <td>24.08</td> 
   <td>23.83</td> 
   <td>23.70</td> 
   <td>32420.43</td> 
   <td>0.05</td> 
   <td>0.21</td> 
   <td>0.81</td> 
  </tr> 
  <tr> 
   <th>2017-12-19</th> 
   <td>23.23</td> 
   <td>23.66</td> 
   <td>23.46</td> 
   <td>23.23</td> 
   <td>43068.70</td> 
   <td>0.31</td> 
   <td>1.34</td> 
   <td>1.08</td> 
  </tr> 
 </tbody> 
</table>

# 统计运算 #

In \[58\]:

data.describe()

Out\[58\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>turnover</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>count</th> 
   <td>643.000000</td> 
   <td>643.000000</td> 
   <td>643.000000</td> 
   <td>643.000000</td> 
   <td>643.000000</td> 
   <td>643.000000</td> 
   <td>643.000000</td> 
   <td>643.000000</td> 
  </tr> 
  <tr> 
   <th>mean</th> 
   <td>21.272706</td> 
   <td>21.900513</td> 
   <td>21.336267</td> 
   <td>20.771835</td> 
   <td>99905.519114</td> 
   <td>0.018802</td> 
   <td>0.190280</td> 
   <td>2.936190</td> 
  </tr> 
  <tr> 
   <th>std</th> 
   <td>3.930973</td> 
   <td>4.077578</td> 
   <td>3.942806</td> 
   <td>3.791968</td> 
   <td>73879.119354</td> 
   <td>0.898476</td> 
   <td>4.079698</td> 
   <td>2.079375</td> 
  </tr> 
  <tr> 
   <th>min</th> 
   <td>12.250000</td> 
   <td>12.670000</td> 
   <td>12.360000</td> 
   <td>12.200000</td> 
   <td>1158.120000</td> 
   <td>-3.520000</td> 
   <td>-10.030000</td> 
   <td>0.040000</td> 
  </tr> 
  <tr> 
   <th>25%</th> 
   <td>19.000000</td> 
   <td>19.500000</td> 
   <td>19.045000</td> 
   <td>18.525000</td> 
   <td>48533.210000</td> 
   <td>-0.390000</td> 
   <td>-1.850000</td> 
   <td>1.360000</td> 
  </tr> 
  <tr> 
   <th>50%</th> 
   <td>21.440000</td> 
   <td>21.970000</td> 
   <td>21.450000</td> 
   <td>20.980000</td> 
   <td>83175.930000</td> 
   <td>0.050000</td> 
   <td>0.260000</td> 
   <td>2.500000</td> 
  </tr> 
  <tr> 
   <th>75%</th> 
   <td>23.400000</td> 
   <td>24.065000</td> 
   <td>23.415000</td> 
   <td>22.850000</td> 
   <td>127580.055000</td> 
   <td>0.455000</td> 
   <td>2.305000</td> 
   <td>3.915000</td> 
  </tr> 
  <tr> 
   <th>max</th> 
   <td>34.990000</td> 
   <td>36.350000</td> 
   <td>35.210000</td> 
   <td>34.010000</td> 
   <td>501915.410000</td> 
   <td>3.030000</td> 
   <td>10.030000</td> 
   <td>12.560000</td> 
  </tr> 
 </tbody> 
</table>

In \[60\]:

data.max(0)

Out\[60\]:

open                34.99
    high                36.35
    close               35.21
    low                 34.01
    volume          501915.41
    price_change         3.03
    p_change            10.03
    turnover            12.56
    dtype: float64

In \[62\]:

\# data.max(1)

In \[63\]:

df = pd.DataFrame(\{'COL1' : \[2,3,4,5,4,2\],

'COL2' : [0,1,2,3,4,2]})

In \[64\]:

Out\[64\]:

In \[65\]:

df.median()

Out\[65\]:

COL1    3.5
    COL2    2.0
    dtype: float64

In \[66\]:

data.idxmax()

Out\[66\]:

open            2015-06-15
    high            2015-06-10
    close           2015-06-12
    low             2015-06-12
    volume          2017-10-26
    price_change    2015-06-09
    p_change        2015-08-28
    turnover        2017-10-26
    dtype: object

In \[67\]:

data.idxmin()

Out\[67\]:

open            2015-03-02
    high            2015-03-02
    close           2015-09-02
    low             2015-03-02
    volume          2016-07-06
    price_change    2015-06-15
    p_change        2015-09-01
    turnover        2016-07-06
    dtype: object

In \[70\]:

data = data.sort\_index()

In \[71\]:

data.head()

Out\[71\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>turnover</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2015-03-02</th> 
   <td>12.25</td> 
   <td>12.67</td> 
   <td>12.52</td> 
   <td>12.20</td> 
   <td>96291.73</td> 
   <td>0.32</td> 
   <td>2.62</td> 
   <td>3.30</td> 
  </tr> 
  <tr> 
   <th>2015-03-03</th> 
   <td>12.52</td> 
   <td>13.06</td> 
   <td>12.70</td> 
   <td>12.52</td> 
   <td>139071.61</td> 
   <td>0.18</td> 
   <td>1.44</td> 
   <td>4.76</td> 
  </tr> 
  <tr> 
   <th>2015-03-04</th> 
   <td>12.80</td> 
   <td>12.92</td> 
   <td>12.90</td> 
   <td>12.61</td> 
   <td>67075.44</td> 
   <td>0.20</td> 
   <td>1.57</td> 
   <td>2.30</td> 
  </tr> 
  <tr> 
   <th>2015-03-05</th> 
   <td>12.88</td> 
   <td>13.45</td> 
   <td>13.16</td> 
   <td>12.87</td> 
   <td>93180.39</td> 
   <td>0.26</td> 
   <td>2.02</td> 
   <td>3.19</td> 
  </tr> 
  <tr> 
   <th>2015-03-06</th> 
   <td>13.17</td> 
   <td>14.48</td> 
   <td>14.28</td> 
   <td>13.13</td> 
   <td>179831.72</td> 
   <td>1.12</td> 
   <td>8.51</td> 
   <td>6.16</td> 
  </tr> 
 </tbody> 
</table>

In \[73\]:

stock\_rise = data\["p\_change"\]

In \[75\]:

\# stock\_rise.cumsum()

In \[80\]:

stock\_rise.cumsum().plot()

plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 47][]

# 自定义运算 #

In \[88\]:

data\[\["open", "close"\]\].apply(lambda x: x.max()-x.min(), axis=0)

Out\[88\]:

open     22.74
    close    22.85
    dtype: float64

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

In \[1\]:

import pandas as pd

# csv #

In \[2\]:

data = pd.read\_csv("./data/stock\_day.csv", usecols=\["open","close"\])

In \[3\]:

data.head()

Out\[3\]:

In \[4\]:

\# data.to\_csv("./data/test.csv", columns=\["close"\])

data.to_csv("./data/test.csv", columns=["close"], index=False)

In \[5\]:

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

In \[6\]:

data.head()

Out\[6\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>close</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>24.16</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>23.53</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>22.82</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>22.28</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>21.92</td> 
  </tr> 
 </tbody> 
</table>

# hdf5 #

In \[7\]:

day\_close = pd.read\_hdf("./data/day\_close.h5")

In \[8\]:

day\_close.head()

Out\[8\]:

5 rows × 3562 columns

In \[9\]:

day\_close.to\_hdf("./data/test.h5", key="day\_close")

In \[10\]:

new\_data = pd.read\_hdf("./data/test.h5", key="day\_close")

In \[11\]:

new\_data.head()

Out\[11\]:

5 rows × 3562 columns

# json #

In \[12\]:

data = pd.read\_json("./data/Sarcasm\_Headlines\_Dataset.json", orient="records", lines=True)

In \[13\]:

data.head()

Out\[13\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>article_link</th> 
   <th>headline</th> 
   <th>is_sarcastic</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>https://www.huffingtonpost.com/entry/versace-b...</td> 
   <td>former versace store clerk sues over secret 'b...</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>https://www.huffingtonpost.com/entry/roseanne-...</td> 
   <td>the 'roseanne' revival catches up to our thorn...</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>https://local.theonion.com/mom-starting-to-fea...</td> 
   <td>mom starting to fear son's web series closest ...</td> 
   <td>1</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>https://politics.theonion.com/boehner-just-wan...</td> 
   <td>boehner just wants wife to listen, not come up...</td> 
   <td>1</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>https://www.huffingtonpost.com/entry/jk-rowlin...</td> 
   <td>j.k. rowling wishes snape happy birthday in th...</td> 
   <td>0</td> 
  </tr> 
 </tbody> 
</table>

In \[14\]:

data.to\_json("./data/test.json", orient="records")

In \[15\]:

data.to\_json("./data/test.json", orient="records", lines=True)

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

In \[1\]:

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

# 缺失值处理 #

In \[2\]:

movie = pd.read\_csv("./data/IMDB-Movie-Data.csv")

In \[3\]:

movie.head()

Out\[3\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>Rank</th> 
   <th>Title</th> 
   <th>Genre</th> 
   <th>Description</th> 
   <th>Director</th> 
   <th>Actors</th> 
   <th>Year</th> 
   <th>Runtime (Minutes)</th> 
   <th>Rating</th> 
   <th>Votes</th> 
   <th>Revenue (Millions)</th> 
   <th>Metascore</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>1</td> 
   <td>Guardians of the Galaxy</td> 
   <td>Action,Adventure,Sci-Fi</td> 
   <td>A group of intergalactic criminals are forced ...</td> 
   <td>James Gunn</td> 
   <td>Chris Pratt, Vin Diesel, Bradley Cooper, Zoe S...</td> 
   <td>2014</td> 
   <td>121</td> 
   <td>8.1</td> 
   <td>757074</td> 
   <td>333.13</td> 
   <td>76.0</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>2</td> 
   <td>Prometheus</td> 
   <td>Adventure,Mystery,Sci-Fi</td> 
   <td>Following clues to the origin of mankind, a te...</td> 
   <td>Ridley Scott</td> 
   <td>Noomi Rapace, Logan Marshall-Green, Michael Fa...</td> 
   <td>2012</td> 
   <td>124</td> 
   <td>7.0</td> 
   <td>485820</td> 
   <td>126.46</td> 
   <td>65.0</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>3</td> 
   <td>Split</td> 
   <td>Horror,Thriller</td> 
   <td>Three girls are kidnapped by a man with a diag...</td> 
   <td>M. Night Shyamalan</td> 
   <td>James McAvoy, Anya Taylor-Joy, Haley Lu Richar...</td> 
   <td>2016</td> 
   <td>117</td> 
   <td>7.3</td> 
   <td>157606</td> 
   <td>138.12</td> 
   <td>62.0</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>4</td> 
   <td>Sing</td> 
   <td>Animation,Comedy,Family</td> 
   <td>In a city of humanoid animals, a hustling thea...</td> 
   <td>Christophe Lourdelet</td> 
   <td>Matthew McConaughey,Reese Witherspoon, Seth Ma...</td> 
   <td>2016</td> 
   <td>108</td> 
   <td>7.2</td> 
   <td>60545</td> 
   <td>270.32</td> 
   <td>59.0</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>5</td> 
   <td>Suicide Squad</td> 
   <td>Action,Adventure,Fantasy</td> 
   <td>A secret government agency recruits some of th...</td> 
   <td>David Ayer</td> 
   <td>Will Smith, Jared Leto, Margot Robbie, Viola D...</td> 
   <td>2016</td> 
   <td>123</td> 
   <td>6.2</td> 
   <td>393727</td> 
   <td>325.02</td> 
   <td>40.0</td> 
  </tr> 
 </tbody> 
</table>

## 缺失值是nan ##

In \[4\]:

np.all(pd.notnull(movie)) \# 里面如果有一个缺失值,那么会返回False,说明有缺失值

Out\[4\]:

False

In \[5\]:

np.any(pd.isnull(movie)) \# 里面如果有一个缺失值,那么会返回True,说明有缺失值

Out\[5\]:

True

In \[6\]:

data = movie.dropna()

In \[7\]:

np.all(pd.notnull(data)) \# 里面如果有一个缺失值,那么会返回False,说明有缺失值

Out\[7\]:

True

In \[8\]:

movie\["Revenue (Millions)"\].mean()

Out\[8\]:

82.95637614678898

In \[9\]:

movie\["Revenue (Millions)"\].fillna(movie\["Revenue (Millions)"\].mean(), inplace=True)

In \[10\]:

movie.head()

Out\[10\]:

In \[11\]:

for i in movie.columns:

if np.any(pd.isnull(movie[i])) == True:

print(i)

movie[i].fillna(movie[i].mean(), inplace=True)

Metascore

In \[12\]:

np.any(pd.isnull(movie)) \# 里面如果有一个缺失值,那么会返回True,说明有缺失值

Out\[12\]:

False

In \[13\]:

wis = pd.read\_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data")

In \[14\]:

wis.head()

Out\[14\]:

## 缺失值是其他符号 ##

In \[15\]:

wis = wis.replace(to\_replace="?", value=np.nan)

In \[16\]:

wis.head()

Out\[16\]:

In \[17\]:

wis = wis.dropna()

In \[18\]:

np.any(pd.isnull(wis)) \# 里面如果有一个缺失值,那么会返回True,说明有缺失值

Out\[18\]:

False

# 数据离散化 #

In \[19\]:

data = pd.read\_csv("./data/stock\_day.csv")

In \[20\]:

data.head()

Out\[20\]:

In \[21\]:

p\_change = data\["p\_change"\]

In \[22\]:

p\_change.head()

Out\[22\]:

2018-02-27    2.68
    2018-02-26    3.02
    2018-02-23    2.42
    2018-02-22    1.64
    2018-02-14    2.05
    Name: p_change, dtype: float64

In \[23\]:

\# 自动分成差不多数量的类别

qcut = pd.qcut(p_change, 10)

qcut.value_counts()

Out\[23\]:

(5.27, 10.03]                    65
    (0.26, 0.94]                     65
    (-0.462, 0.26]                   65
    (-10.030999999999999, -4.836]    65
    (2.938, 5.27]                    64
    (1.738, 2.938]                   64
    (-1.352, -0.462]                 64
    (-2.444, -1.352]                 64
    (-4.836, -2.444]                 64
    (0.94, 1.738]                    63
    Name: p_change, dtype: int64

In \[24\]:

\# 指定分组区间

bins = [-100, -7, -5, -3, 0, 3, 5, 7, 100]

p_count = pd.cut(p_change, bins)

In \[25\]:

p\_count.value\_counts()

Out\[25\]:

(0, 3]        215
    (-3, 0]       188
    (3, 5]         57
    (-5, -3]       51
    (7, 100]       35
    (5, 7]         35
    (-100, -7]     34
    (-7, -5]       28
    Name: p_change, dtype: int64

In \[26\]:

dummies = pd.get\_dummies(p\_count, prefix="rise")

dummies.head()

Out\[26\]:

# 合并 #

In \[27\]:

pd.concat(\[data, dummies\],axis=1)

Out\[27\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>open</th> 
   <th>high</th> 
   <th>close</th> 
   <th>low</th> 
   <th>volume</th> 
   <th>price_change</th> 
   <th>p_change</th> 
   <th>ma5</th> 
   <th>ma10</th> 
   <th>ma20</th> 
   <th>...</th> 
   <th>v_ma20</th> 
   <th>turnover</th> 
   <th>rise_(-100, -7]</th> 
   <th>rise_(-7, -5]</th> 
   <th>rise_(-5, -3]</th> 
   <th>rise_(-3, 0]</th> 
   <th>rise_(0, 3]</th> 
   <th>rise_(3, 5]</th> 
   <th>rise_(5, 7]</th> 
   <th>rise_(7, 100]</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>2018-02-27</th> 
   <td>23.53</td> 
   <td>25.88</td> 
   <td>24.16</td> 
   <td>23.53</td> 
   <td>95578.03</td> 
   <td>0.63</td> 
   <td>2.68</td> 
   <td>22.942</td> 
   <td>22.142</td> 
   <td>22.875</td> 
   <td>...</td> 
   <td>55576.11</td> 
   <td>2.39</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-26</th> 
   <td>22.80</td> 
   <td>23.78</td> 
   <td>23.53</td> 
   <td>22.80</td> 
   <td>60985.11</td> 
   <td>0.69</td> 
   <td>3.02</td> 
   <td>22.406</td> 
   <td>21.955</td> 
   <td>22.942</td> 
   <td>...</td> 
   <td>56007.50</td> 
   <td>1.53</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-23</th> 
   <td>22.88</td> 
   <td>23.37</td> 
   <td>22.82</td> 
   <td>22.71</td> 
   <td>52914.01</td> 
   <td>0.54</td> 
   <td>2.42</td> 
   <td>21.938</td> 
   <td>21.929</td> 
   <td>23.022</td> 
   <td>...</td> 
   <td>56372.85</td> 
   <td>1.32</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-22</th> 
   <td>22.25</td> 
   <td>22.76</td> 
   <td>22.28</td> 
   <td>22.02</td> 
   <td>36105.01</td> 
   <td>0.36</td> 
   <td>1.64</td> 
   <td>21.446</td> 
   <td>21.909</td> 
   <td>23.137</td> 
   <td>...</td> 
   <td>60149.60</td> 
   <td>0.90</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-14</th> 
   <td>21.49</td> 
   <td>21.99</td> 
   <td>21.92</td> 
   <td>21.48</td> 
   <td>23331.04</td> 
   <td>0.44</td> 
   <td>2.05</td> 
   <td>21.366</td> 
   <td>21.923</td> 
   <td>23.253</td> 
   <td>...</td> 
   <td>61716.11</td> 
   <td>0.58</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-13</th> 
   <td>21.40</td> 
   <td>21.90</td> 
   <td>21.48</td> 
   <td>21.31</td> 
   <td>30802.45</td> 
   <td>0.28</td> 
   <td>1.32</td> 
   <td>21.342</td> 
   <td>22.103</td> 
   <td>23.387</td> 
   <td>...</td> 
   <td>65161.68</td> 
   <td>0.77</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-12</th> 
   <td>20.70</td> 
   <td>21.40</td> 
   <td>21.19</td> 
   <td>20.63</td> 
   <td>32445.39</td> 
   <td>0.82</td> 
   <td>4.03</td> 
   <td>21.504</td> 
   <td>22.338</td> 
   <td>23.533</td> 
   <td>...</td> 
   <td>68686.33</td> 
   <td>0.81</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-09</th> 
   <td>21.20</td> 
   <td>21.46</td> 
   <td>20.36</td> 
   <td>20.19</td> 
   <td>54304.01</td> 
   <td>-1.50</td> 
   <td>-6.86</td> 
   <td>21.920</td> 
   <td>22.596</td> 
   <td>23.645</td> 
   <td>...</td> 
   <td>70552.47</td> 
   <td>1.36</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-08</th> 
   <td>21.79</td> 
   <td>22.09</td> 
   <td>21.88</td> 
   <td>21.75</td> 
   <td>27068.16</td> 
   <td>0.09</td> 
   <td>0.41</td> 
   <td>22.372</td> 
   <td>23.009</td> 
   <td>23.839</td> 
   <td>...</td> 
   <td>73852.45</td> 
   <td>0.68</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-07</th> 
   <td>22.69</td> 
   <td>23.11</td> 
   <td>21.80</td> 
   <td>21.29</td> 
   <td>53853.25</td> 
   <td>-0.50</td> 
   <td>-2.24</td> 
   <td>22.480</td> 
   <td>23.258</td> 
   <td>23.929</td> 
   <td>...</td> 
   <td>74925.33</td> 
   <td>1.35</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-06</th> 
   <td>22.80</td> 
   <td>23.55</td> 
   <td>22.29</td> 
   <td>22.20</td> 
   <td>55555.00</td> 
   <td>-0.97</td> 
   <td>-4.17</td> 
   <td>22.864</td> 
   <td>23.607</td> 
   <td>24.029</td> 
   <td>...</td> 
   <td>75738.95</td> 
   <td>1.39</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-05</th> 
   <td>22.45</td> 
   <td>23.39</td> 
   <td>23.27</td> 
   <td>22.25</td> 
   <td>52341.39</td> 
   <td>0.65</td> 
   <td>2.87</td> 
   <td>23.172</td> 
   <td>23.928</td> 
   <td>24.112</td> 
   <td>...</td> 
   <td>77070.00</td> 
   <td>1.31</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-02</th> 
   <td>22.40</td> 
   <td>22.70</td> 
   <td>22.62</td> 
   <td>21.53</td> 
   <td>33242.11</td> 
   <td>0.20</td> 
   <td>0.89</td> 
   <td>23.272</td> 
   <td>24.114</td> 
   <td>24.184</td> 
   <td>...</td> 
   <td>79929.71</td> 
   <td>0.83</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-02-01</th> 
   <td>23.71</td> 
   <td>23.86</td> 
   <td>22.42</td> 
   <td>22.22</td> 
   <td>66414.64</td> 
   <td>-1.30</td> 
   <td>-5.48</td> 
   <td>23.646</td> 
   <td>24.365</td> 
   <td>24.279</td> 
   <td>...</td> 
   <td>88480.92</td> 
   <td>1.66</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-31</th> 
   <td>23.85</td> 
   <td>23.98</td> 
   <td>23.72</td> 
   <td>23.31</td> 
   <td>49155.02</td> 
   <td>-0.11</td> 
   <td>-0.46</td> 
   <td>24.036</td> 
   <td>24.583</td> 
   <td>24.411</td> 
   <td>...</td> 
   <td>91666.75</td> 
   <td>1.23</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-30</th> 
   <td>23.71</td> 
   <td>24.08</td> 
   <td>23.83</td> 
   <td>23.70</td> 
   <td>32420.43</td> 
   <td>0.05</td> 
   <td>0.21</td> 
   <td>24.350</td> 
   <td>24.671</td> 
   <td>24.365</td> 
   <td>...</td> 
   <td>92943.35</td> 
   <td>0.81</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-29</th> 
   <td>24.40</td> 
   <td>24.63</td> 
   <td>23.77</td> 
   <td>23.72</td> 
   <td>65469.81</td> 
   <td>-0.73</td> 
   <td>-2.98</td> 
   <td>24.684</td> 
   <td>24.728</td> 
   <td>24.294</td> 
   <td>...</td> 
   <td>93456.22</td> 
   <td>1.64</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-26</th> 
   <td>24.27</td> 
   <td>24.74</td> 
   <td>24.49</td> 
   <td>24.22</td> 
   <td>50601.83</td> 
   <td>0.11</td> 
   <td>0.45</td> 
   <td>24.956</td> 
   <td>24.694</td> 
   <td>24.221</td> 
   <td>...</td> 
   <td>91980.51</td> 
   <td>1.27</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-25</th> 
   <td>24.99</td> 
   <td>24.99</td> 
   <td>24.37</td> 
   <td>24.23</td> 
   <td>104097.59</td> 
   <td>-0.93</td> 
   <td>-3.68</td> 
   <td>25.084</td> 
   <td>24.669</td> 
   <td>24.109</td> 
   <td>...</td> 
   <td>92262.67</td> 
   <td>2.61</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-24</th> 
   <td>25.49</td> 
   <td>26.28</td> 
   <td>25.29</td> 
   <td>25.20</td> 
   <td>134838.00</td> 
   <td>-0.20</td> 
   <td>-0.79</td> 
   <td>25.130</td> 
   <td>24.599</td> 
   <td>23.997</td> 
   <td>...</td> 
   <td>89522.22</td> 
   <td>3.37</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-23</th> 
   <td>25.15</td> 
   <td>25.53</td> 
   <td>25.50</td> 
   <td>24.93</td> 
   <td>104205.76</td> 
   <td>0.39</td> 
   <td>1.55</td> 
   <td>24.992</td> 
   <td>24.450</td> 
   <td>23.844</td> 
   <td>...</td> 
   <td>85876.80</td> 
   <td>2.61</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-22</th> 
   <td>25.14</td> 
   <td>25.40</td> 
   <td>25.13</td> 
   <td>24.75</td> 
   <td>68292.08</td> 
   <td>-0.01</td> 
   <td>-0.04</td> 
   <td>24.772</td> 
   <td>24.296</td> 
   <td>23.644</td> 
   <td>...</td> 
   <td>84970.00</td> 
   <td>1.71</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-19</th> 
   <td>24.60</td> 
   <td>25.34</td> 
   <td>25.13</td> 
   <td>24.42</td> 
   <td>128449.11</td> 
   <td>0.53</td> 
   <td>2.15</td> 
   <td>24.432</td> 
   <td>24.254</td> 
   <td>23.537</td> 
   <td>...</td> 
   <td>82975.10</td> 
   <td>3.21</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-18</th> 
   <td>24.40</td> 
   <td>24.88</td> 
   <td>24.60</td> 
   <td>24.30</td> 
   <td>67435.14</td> 
   <td>0.01</td> 
   <td>0.04</td> 
   <td>24.254</td> 
   <td>24.192</td> 
   <td>23.441</td> 
   <td>...</td> 
   <td>78252.92</td> 
   <td>1.69</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-17</th> 
   <td>24.42</td> 
   <td>24.92</td> 
   <td>24.60</td> 
   <td>23.80</td> 
   <td>92242.51</td> 
   <td>0.20</td> 
   <td>0.82</td> 
   <td>24.068</td> 
   <td>24.239</td> 
   <td>23.378</td> 
   <td>...</td> 
   <td>77049.61</td> 
   <td>2.31</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-16</th> 
   <td>23.40</td> 
   <td>24.60</td> 
   <td>24.40</td> 
   <td>23.30</td> 
   <td>101295.42</td> 
   <td>0.96</td> 
   <td>4.10</td> 
   <td>23.908</td> 
   <td>24.058</td> 
   <td>23.321</td> 
   <td>...</td> 
   <td>74590.92</td> 
   <td>2.54</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-15</th> 
   <td>24.01</td> 
   <td>24.23</td> 
   <td>23.43</td> 
   <td>23.30</td> 
   <td>69768.17</td> 
   <td>-0.80</td> 
   <td>-3.30</td> 
   <td>23.820</td> 
   <td>23.860</td> 
   <td>23.257</td> 
   <td>...</td> 
   <td>71006.65</td> 
   <td>1.75</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-12</th> 
   <td>23.70</td> 
   <td>25.15</td> 
   <td>24.24</td> 
   <td>23.42</td> 
   <td>120303.53</td> 
   <td>0.56</td> 
   <td>2.37</td> 
   <td>24.076</td> 
   <td>23.748</td> 
   <td>23.236</td> 
   <td>...</td> 
   <td>69690.35</td> 
   <td>3.01</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-11</th> 
   <td>23.67</td> 
   <td>23.85</td> 
   <td>23.67</td> 
   <td>23.21</td> 
   <td>48525.75</td> 
   <td>-0.12</td> 
   <td>-0.50</td> 
   <td>24.130</td> 
   <td>23.548</td> 
   <td>23.197</td> 
   <td>...</td> 
   <td>65928.23</td> 
   <td>1.21</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2018-01-10</th> 
   <td>24.10</td> 
   <td>24.60</td> 
   <td>23.80</td> 
   <td>23.40</td> 
   <td>70125.79</td> 
   <td>-0.14</td> 
   <td>-0.58</td> 
   <td>24.410</td> 
   <td>23.394</td> 
   <td>23.204</td> 
   <td>...</td> 
   <td>66934.89</td> 
   <td>1.76</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</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> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
   <td>...</td> 
  </tr> 
  <tr> 
   <th>2015-04-13</th> 
   <td>19.60</td> 
   <td>21.30</td> 
   <td>21.13</td> 
   <td>19.50</td> 
   <td>171822.69</td> 
   <td>1.70</td> 
   <td>8.75</td> 
   <td>19.228</td> 
   <td>17.812</td> 
   <td>16.563</td> 
   <td>...</td> 
   <td>111752.31</td> 
   <td>5.88</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
  </tr> 
  <tr> 
   <th>2015-04-10</th> 
   <td>19.55</td> 
   <td>19.89</td> 
   <td>19.43</td> 
   <td>19.20</td> 
   <td>112962.15</td> 
   <td>-0.19</td> 
   <td>-0.97</td> 
   <td>18.334</td> 
   <td>17.276</td> 
   <td>16.230</td> 
   <td>...</td> 
   <td>106228.29</td> 
   <td>3.87</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-04-09</th> 
   <td>18.28</td> 
   <td>19.89</td> 
   <td>19.62</td> 
   <td>18.02</td> 
   <td>183119.05</td> 
   <td>1.20</td> 
   <td>6.51</td> 
   <td>17.736</td> 
   <td>16.826</td> 
   <td>15.964</td> 
   <td>...</td> 
   <td>104829.10</td> 
   <td>6.27</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-04-08</th> 
   <td>17.60</td> 
   <td>18.53</td> 
   <td>18.42</td> 
   <td>17.60</td> 
   <td>157725.97</td> 
   <td>0.88</td> 
   <td>5.02</td> 
   <td>17.070</td> 
   <td>16.394</td> 
   <td>15.698</td> 
   <td>...</td> 
   <td>101658.57</td> 
   <td>5.40</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-04-07</th> 
   <td>16.54</td> 
   <td>17.98</td> 
   <td>17.54</td> 
   <td>16.50</td> 
   <td>122471.85</td> 
   <td>0.88</td> 
   <td>5.28</td> 
   <td>16.620</td> 
   <td>16.120</td> 
   <td>15.510</td> 
   <td>...</td> 
   <td>98832.94</td> 
   <td>4.19</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-04-03</th> 
   <td>16.44</td> 
   <td>16.77</td> 
   <td>16.66</td> 
   <td>16.25</td> 
   <td>91962.88</td> 
   <td>0.22</td> 
   <td>1.34</td> 
   <td>16.396</td> 
   <td>15.904</td> 
   <td>15.348</td> 
   <td>...</td> 
   <td>99956.63</td> 
   <td>3.15</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-04-02</th> 
   <td>16.21</td> 
   <td>16.50</td> 
   <td>16.44</td> 
   <td>16.21</td> 
   <td>66336.32</td> 
   <td>0.15</td> 
   <td>0.92</td> 
   <td>16.218</td> 
   <td>15.772</td> 
   <td>15.229</td> 
   <td>...</td> 
   <td>104350.08</td> 
   <td>2.27</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-04-01</th> 
   <td>16.18</td> 
   <td>16.48</td> 
   <td>16.29</td> 
   <td>16.00</td> 
   <td>68609.42</td> 
   <td>0.12</td> 
   <td>0.74</td> 
   <td>15.916</td> 
   <td>15.666</td> 
   <td>15.065</td> 
   <td>...</td> 
   <td>105692.28</td> 
   <td>2.35</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-31</th> 
   <td>16.78</td> 
   <td>16.88</td> 
   <td>16.17</td> 
   <td>16.07</td> 
   <td>84467.62</td> 
   <td>-0.25</td> 
   <td>-1.52</td> 
   <td>15.718</td> 
   <td>15.568</td> 
   <td>14.896</td> 
   <td>...</td> 
   <td>105615.58</td> 
   <td>2.89</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-30</th> 
   <td>15.99</td> 
   <td>16.63</td> 
   <td>16.42</td> 
   <td>15.99</td> 
   <td>85090.45</td> 
   <td>0.65</td> 
   <td>4.12</td> 
   <td>15.620</td> 
   <td>15.469</td> 
   <td>14.722</td> 
   <td>...</td> 
   <td>108345.78</td> 
   <td>2.91</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-27</th> 
   <td>14.90</td> 
   <td>15.86</td> 
   <td>15.77</td> 
   <td>14.90</td> 
   <td>120352.13</td> 
   <td>0.84</td> 
   <td>5.63</td> 
   <td>15.412</td> 
   <td>15.314</td> 
   <td>14.527</td> 
   <td>...</td> 
   <td>108905.84</td> 
   <td>4.12</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-26</th> 
   <td>15.14</td> 
   <td>15.35</td> 
   <td>14.93</td> 
   <td>14.91</td> 
   <td>84877.75</td> 
   <td>-0.37</td> 
   <td>-2.42</td> 
   <td>15.326</td> 
   <td>15.184</td> 
   <td>14.462</td> 
   <td>...</td> 
   <td>108303.41</td> 
   <td>2.91</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-25</th> 
   <td>15.97</td> 
   <td>15.97</td> 
   <td>15.30</td> 
   <td>15.18</td> 
   <td>97174.40</td> 
   <td>-0.38</td> 
   <td>-2.42</td> 
   <td>15.416</td> 
   <td>15.102</td> 
   <td>14.436</td> 
   <td>...</td> 
   <td>109604.83</td> 
   <td>3.33</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-24</th> 
   <td>15.38</td> 
   <td>16.16</td> 
   <td>15.68</td> 
   <td>15.28</td> 
   <td>153390.08</td> 
   <td>0.30</td> 
   <td>1.95</td> 
   <td>15.418</td> 
   <td>15.002</td> 
   <td>14.385</td> 
   <td>...</td> 
   <td>110336.03</td> 
   <td>5.25</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-23</th> 
   <td>15.34</td> 
   <td>15.56</td> 
   <td>15.38</td> 
   <td>15.25</td> 
   <td>89461.32</td> 
   <td>0.04</td> 
   <td>0.26</td> 
   <td>15.318</td> 
   <td>14.899</td> 
   <td>14.304</td> 
   <td>...</td> 
   <td>107645.16</td> 
   <td>3.06</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-20</th> 
   <td>15.38</td> 
   <td>15.48</td> 
   <td>15.34</td> 
   <td>15.18</td> 
   <td>76800.13</td> 
   <td>-0.04</td> 
   <td>-0.26</td> 
   <td>15.216</td> 
   <td>14.792</td> 
   <td>14.232</td> 
   <td>...</td> 
   <td>108857.41</td> 
   <td>2.63</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-19</th> 
   <td>15.20</td> 
   <td>15.64</td> 
   <td>15.38</td> 
   <td>15.11</td> 
   <td>93644.19</td> 
   <td>0.07</td> 
   <td>0.46</td> 
   <td>15.042</td> 
   <td>14.686</td> 
   <td>14.153</td> 
   <td>...</td> 
   <td>111147.22</td> 
   <td>3.21</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-18</th> 
   <td>15.18</td> 
   <td>15.66</td> 
   <td>15.31</td> 
   <td>15.02</td> 
   <td>121538.71</td> 
   <td>0.13</td> 
   <td>0.86</td> 
   <td>14.788</td> 
   <td>14.464</td> 
   <td>14.058</td> 
   <td>...</td> 
   <td>112493.60</td> 
   <td>4.16</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-17</th> 
   <td>14.90</td> 
   <td>15.44</td> 
   <td>15.18</td> 
   <td>14.63</td> 
   <td>158770.77</td> 
   <td>0.31</td> 
   <td>2.08</td> 
   <td>14.586</td> 
   <td>14.223</td> 
   <td>13.954</td> 
   <td>...</td> 
   <td>111739.85</td> 
   <td>5.43</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-16</th> 
   <td>14.52</td> 
   <td>15.05</td> 
   <td>14.87</td> 
   <td>14.51</td> 
   <td>94468.30</td> 
   <td>0.40</td> 
   <td>2.76</td> 
   <td>14.480</td> 
   <td>13.975</td> 
   <td>13.843</td> 
   <td>...</td> 
   <td>107464.31</td> 
   <td>3.23</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-13</th> 
   <td>14.13</td> 
   <td>14.50</td> 
   <td>14.47</td> 
   <td>14.08</td> 
   <td>61342.22</td> 
   <td>0.36</td> 
   <td>2.55</td> 
   <td>14.368</td> 
   <td>13.740</td> 
   <td>13.740</td> 
   <td>...</td> 
   <td>108763.91</td> 
   <td>2.10</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-12</th> 
   <td>14.11</td> 
   <td>14.80</td> 
   <td>14.11</td> 
   <td>13.95</td> 
   <td>84978.37</td> 
   <td>-0.19</td> 
   <td>-1.33</td> 
   <td>14.330</td> 
   <td>13.659</td> 
   <td>13.659</td> 
   <td>...</td> 
   <td>114032.98</td> 
   <td>2.91</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-11</th> 
   <td>14.80</td> 
   <td>15.08</td> 
   <td>14.30</td> 
   <td>14.14</td> 
   <td>119708.43</td> 
   <td>-0.35</td> 
   <td>-2.39</td> 
   <td>14.140</td> 
   <td>13.603</td> 
   <td>13.603</td> 
   <td>...</td> 
   <td>117664.81</td> 
   <td>4.10</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-10</th> 
   <td>14.20</td> 
   <td>14.80</td> 
   <td>14.65</td> 
   <td>14.01</td> 
   <td>101213.51</td> 
   <td>0.34</td> 
   <td>2.38</td> 
   <td>13.860</td> 
   <td>13.503</td> 
   <td>13.503</td> 
   <td>...</td> 
   <td>117372.87</td> 
   <td>3.46</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-09</th> 
   <td>14.14</td> 
   <td>14.85</td> 
   <td>14.31</td> 
   <td>13.80</td> 
   <td>144945.66</td> 
   <td>0.03</td> 
   <td>0.21</td> 
   <td>13.470</td> 
   <td>13.312</td> 
   <td>13.312</td> 
   <td>...</td> 
   <td>120066.09</td> 
   <td>4.96</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-06</th> 
   <td>13.17</td> 
   <td>14.48</td> 
   <td>14.28</td> 
   <td>13.13</td> 
   <td>179831.72</td> 
   <td>1.12</td> 
   <td>8.51</td> 
   <td>13.112</td> 
   <td>13.112</td> 
   <td>13.112</td> 
   <td>...</td> 
   <td>115090.18</td> 
   <td>6.16</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
  </tr> 
  <tr> 
   <th>2015-03-05</th> 
   <td>12.88</td> 
   <td>13.45</td> 
   <td>13.16</td> 
   <td>12.87</td> 
   <td>93180.39</td> 
   <td>0.26</td> 
   <td>2.02</td> 
   <td>12.820</td> 
   <td>12.820</td> 
   <td>12.820</td> 
   <td>...</td> 
   <td>98904.79</td> 
   <td>3.19</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-04</th> 
   <td>12.80</td> 
   <td>12.92</td> 
   <td>12.90</td> 
   <td>12.61</td> 
   <td>67075.44</td> 
   <td>0.20</td> 
   <td>1.57</td> 
   <td>12.707</td> 
   <td>12.707</td> 
   <td>12.707</td> 
   <td>...</td> 
   <td>100812.93</td> 
   <td>2.30</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-03</th> 
   <td>12.52</td> 
   <td>13.06</td> 
   <td>12.70</td> 
   <td>12.52</td> 
   <td>139071.61</td> 
   <td>0.18</td> 
   <td>1.44</td> 
   <td>12.610</td> 
   <td>12.610</td> 
   <td>12.610</td> 
   <td>...</td> 
   <td>117681.67</td> 
   <td>4.76</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
  <tr> 
   <th>2015-03-02</th> 
   <td>12.25</td> 
   <td>12.67</td> 
   <td>12.52</td> 
   <td>12.20</td> 
   <td>96291.73</td> 
   <td>0.32</td> 
   <td>2.62</td> 
   <td>12.520</td> 
   <td>12.520</td> 
   <td>12.520</td> 
   <td>...</td> 
   <td>96291.73</td> 
   <td>3.30</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>0</td> 
  </tr> 
 </tbody> 
</table>

643 rows × 22 columns

In \[28\]:

left = pd.DataFrame(\{'key1': \['K0', 'K0', 'K1', 'K2'\],

'key2': ['K0', 'K1', 'K0', 'K1'],

'A': ['A0', 'A1', 'A2', 'A3'],

'B': ['B0', 'B1', 'B2', 'B3']})

right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],

'key2': ['K0', 'K0', 'K0', 'K0'],

'C': ['C0', 'C1', 'C2', 'C3'],

'D': ['D0', 'D1', 'D2', 'D3']})

In \[29\]:

left

Out\[29\]:

In \[30\]:

right

Out\[30\]:

In \[31\]:

pd.merge(left, right, on=\["key1", "key2"\])

Out\[31\]:

In \[32\]:

pd.merge(left, right, on=\["key1", "key2"\], how="inner")

Out\[32\]:

In \[33\]:

pd.merge(left, right, on=\["key1", "key2"\], how="left")

Out\[33\]:

In \[34\]:

pd.merge(left, right, on=\["key1", "key2"\], how="right")

Out\[34\]:

In \[35\]:

pd.merge(left, right, on=\["key1", "key2"\], how="outer")

Out\[35\]:

# 交叉表透视表 #

In \[36\]:

data.head()

Out\[36\]:

In \[37\]:

data.index

Out\[37\]:

Index(['2018-02-27', '2018-02-26', '2018-02-23', '2018-02-22', '2018-02-14',
           '2018-02-13', '2018-02-12', '2018-02-09', '2018-02-08', '2018-02-07',
           ...
           '2015-03-13', '2015-03-12', '2015-03-11', '2015-03-10', '2015-03-09',
           '2015-03-06', '2015-03-05', '2015-03-04', '2015-03-03', '2015-03-02'],
          dtype='object', length=643)

In \[38\]:

time = pd.to\_datetime(data.index)

In \[39\]:

time.weekday

Out\[39\]:

Int64Index([1, 0, 4, 3, 2, 1, 0, 4, 3, 2,
                ...
                4, 3, 2, 1, 0, 4, 3, 2, 1, 0],
               dtype='int64', length=643)

In \[40\]:

time.day

Out\[40\]:

Int64Index([27, 26, 23, 22, 14, 13, 12,  9,  8,  7,
                ...
                13, 12, 11, 10,  9,  6,  5,  4,  3,  2],
               dtype='int64', length=643)

In \[41\]:

data\["week"\] = time.weekday

In \[42\]:

data.head()

Out\[42\]:

In \[43\]:

data\["p\_n"\] = np.where(data\["p\_change"\] > 0, 1, 0)  
In \[44\]:

data.head()

Out\[44\]:

In \[45\]:

count = pd.crosstab(data\["week"\], data\["p\_n"\])

count

Out\[45\]:

In \[46\]:

sum = count.sum(axis=1).astype(np.float32)

sum

Out\[46\]:

week
    0    125.0
    1    131.0
    2    132.0
    3    128.0
    4    127.0
    dtype: float32

In \[47\]:

ret = count.div(sum, axis=0)

In \[48\]:

ret

Out\[48\]:

In \[49\]:

ret.plot(kind="bar", stacked=True)

plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 48][]

In \[50\]:

data.pivot\_table(\["p\_n"\], index="week")

Out\[50\]:

# 分组聚合 #

In \[51\]:

col =pd.DataFrame(\{'color': \['white','red','green','red','green'\], 'object': \['pen','pencil','pencil','ashtray','pen'\],'price1':\[5.56,4.20,1.30,0.56,2.75\],'price2':\[4.75,4.12,1.60,0.75,3.15\]\})

In [52]:

col

Out\[52\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>color</th> 
   <th>object</th> 
   <th>price1</th> 
   <th>price2</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>white</td> 
   <td>pen</td> 
   <td>5.56</td> 
   <td>4.75</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>red</td> 
   <td>pencil</td> 
   <td>4.20</td> 
   <td>4.12</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>green</td> 
   <td>pencil</td> 
   <td>1.30</td> 
   <td>1.60</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>red</td> 
   <td>ashtray</td> 
   <td>0.56</td> 
   <td>0.75</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>green</td> 
   <td>pen</td> 
   <td>2.75</td> 
   <td>3.15</td> 
  </tr> 
 </tbody> 
</table>

In \[53\]:

col.groupby(\["color"\])\["price1"\].mean()

Out\[53\]:

color
    green    2.025
    red      2.380
    white    5.560
    Name: price1, dtype: float64

In \[54\]:

col\["price1"\].groupby(col\["color"\]).mean()

Out\[54\]:

color
    green    2.025
    red      2.380
    white    5.560
    Name: price1, dtype: float64

In \[55\]:

col.groupby(\["color"\], as\_index=False)\["price1"\].mean()

Out\[55\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>color</th> 
   <th>price1</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>green</td> 
   <td>2.025</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>red</td> 
   <td>2.380</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>white</td> 
   <td>5.560</td> 
  </tr> 
 </tbody> 
</table>

In \[56\]:

starbucks = pd.read\_csv("./data/starbucks/directory.csv")

In \[57\]:

starbucks.head()

Out\[57\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>Brand</th> 
   <th>Store Number</th> 
   <th>Store Name</th> 
   <th>Ownership Type</th> 
   <th>Street Address</th> 
   <th>City</th> 
   <th>State/Province</th> 
   <th>Country</th> 
   <th>Postcode</th> 
   <th>Phone Number</th> 
   <th>Timezone</th> 
   <th>Longitude</th> 
   <th>Latitude</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>Starbucks</td> 
   <td>47370-257954</td> 
   <td>Meritxell, 96</td> 
   <td>Licensed</td> 
   <td>Av. Meritxell, 96</td> 
   <td>Andorra la Vella</td> 
   <td>7</td> 
   <td>AD</td> 
   <td>AD500</td> 
   <td>376818720</td> 
   <td>GMT+1:00 Europe/Andorra</td> 
   <td>1.53</td> 
   <td>42.51</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>Starbucks</td> 
   <td>22331-212325</td> 
   <td>Ajman Drive Thru</td> 
   <td>Licensed</td> 
   <td>1 Street 69, Al Jarf</td> 
   <td>Ajman</td> 
   <td>AJ</td> 
   <td>AE</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>GMT+04:00 Asia/Dubai</td> 
   <td>55.47</td> 
   <td>25.42</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>Starbucks</td> 
   <td>47089-256771</td> 
   <td>Dana Mall</td> 
   <td>Licensed</td> 
   <td>Sheikh Khalifa Bin Zayed St.</td> 
   <td>Ajman</td> 
   <td>AJ</td> 
   <td>AE</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>GMT+04:00 Asia/Dubai</td> 
   <td>55.47</td> 
   <td>25.39</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>Starbucks</td> 
   <td>22126-218024</td> 
   <td>Twofour 54</td> 
   <td>Licensed</td> 
   <td>Al Salam Street</td> 
   <td>Abu Dhabi</td> 
   <td>AZ</td> 
   <td>AE</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>GMT+04:00 Asia/Dubai</td> 
   <td>54.38</td> 
   <td>24.48</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>Starbucks</td> 
   <td>17127-178586</td> 
   <td>Al Ain Tower</td> 
   <td>Licensed</td> 
   <td>Khaldiya Area, Abu Dhabi Island</td> 
   <td>Abu Dhabi</td> 
   <td>AZ</td> 
   <td>AE</td> 
   <td>NaN</td> 
   <td>NaN</td> 
   <td>GMT+04:00 Asia/Dubai</td> 
   <td>54.54</td> 
   <td>24.51</td> 
  </tr> 
 </tbody> 
</table>

In \[58\]:

count = starbucks.groupby(\["Country"\]).count()

In \[59\]:

count\["Brand"\].plot(kind="bar", figsize=(20, 8))

plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 49][]

In \[60\]:

starbucks.groupby(\["Country", "State/Province"\]).count()

Out\[60\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th></th> 
   <th>Brand</th> 
   <th>Store Number</th> 
   <th>Store Name</th> 
   <th>Ownership Type</th> 
   <th>Street Address</th> 
   <th>City</th> 
   <th>Postcode</th> 
   <th>Phone Number</th> 
   <th>Timezone</th> 
   <th>Longitude</th> 
   <th>Latitude</th> 
  </tr> 
  <tr> 
   <th>Country</th> 
   <th>State/Province</th> 
   <th></th> 
   <th></th> 
   <th></th> 
   <th></th> 
   <th></th> 
   <th></th> 
   <th></th> 
   <th></th> 
   <th></th> 
   <th></th> 
   <th></th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>AD</th> 
   <th>7</th> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
  </tr> 
  <tr> 
   <th>AE</th> 
   <th>AJ</th> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>0</td> 
   <td>0</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
  </tr> 
  <tr> 
   <th>AZ</th> 
   <td>48</td> 
   <td>48</td> 
   <td>48</td> 
   <td>48</td> 
   <td>48</td> 
   <td>48</td> 
   <td>7</td> 
   <td>20</td> 
   <td>48</td> 
   <td>48</td> 
   <td>48</td> 
  </tr> 
  <tr> 
   <th>DU</th> 
   <td>82</td> 
   <td>82</td> 
   <td>82</td> 
   <td>82</td> 
   <td>82</td> 
   <td>82</td> 
   <td>16</td> 
   <td>50</td> 
   <td>82</td> 
   <td>82</td> 
   <td>82</td> 
  </tr> 
  <tr> 
   <th>FU</th> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>1</td> 
   <td>0</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
  </tr> 
  <tr> 
   <th>RK</th> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>0</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
  </tr> 
  <tr> 
   <th>SH</th> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>0</td> 
   <td>5</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
  </tr> 
  <tr> 
   <th>UQ</th> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
  </tr> 
  <tr> 
   <th>AR</th> 
   <th>B</th> 
   <td>21</td> 
   <td>21</td> 
   <td>21</td> 
   <td>21</td> 
   <td>21</td> 
   <td>21</td> 
   <td>18</td> 
   <td>5</td> 
   <td>21</td> 
   <td>21</td> 
   <td>21</td> 
  </tr> 
  <tr> 
   <th>C</th> 
   <td>73</td> 
   <td>73</td> 
   <td>73</td> 
   <td>73</td> 
   <td>73</td> 
   <td>73</td> 
   <td>71</td> 
   <td>24</td> 
   <td>73</td> 
   <td>73</td> 
   <td>73</td> 
  </tr> 
  <tr> 
   <th>M</th> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
   <td>2</td> 
   <td>0</td> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
  </tr> 
  <tr> 
   <th>S</th> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>0</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
  </tr> 
  <tr> 
   <th>X</th> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>0</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
  </tr> 
  <tr> 
   <th>AT</th> 
   <th>3</th> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
  </tr> 
  <tr> 
   <th>5</th> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
  </tr> 
  <tr> 
   <th>9</th> 
   <td>14</td> 
   <td>14</td> 
   <td>14</td> 
   <td>14</td> 
   <td>14</td> 
   <td>14</td> 
   <td>14</td> 
   <td>13</td> 
   <td>14</td> 
   <td>14</td> 
   <td>14</td> 
  </tr> 
  <tr> 
   <th>AU</th> 
   <th>NSW</th> 
   <td>9</td> 
   <td>9</td> 
   <td>9</td> 
   <td>9</td> 
   <td>9</td> 
   <td>9</td> 
   <td>9</td> 
   <td>0</td> 
   <td>9</td> 
   <td>9</td> 
   <td>9</td> 
  </tr> 
  <tr> 
   <th>QLD</th> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>0</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
  </tr> 
  <tr> 
   <th>VIC</th> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
   <td>0</td> 
   <td>5</td> 
   <td>5</td> 
   <td>5</td> 
  </tr> 
  <tr> 
   <th>AW</th> 
   <th>AW</th> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>0</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
  </tr> 
  <tr> 
   <th>AZ</th> 
   <th>BA</th> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>2</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
  </tr> 
  <tr> 
   <th>SAB</th> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
  </tr> 
  <tr> 
   <th>BE</th> 
   <th>BE</th> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
   <td>0</td> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
  </tr> 
  <tr> 
   <th>VAN</th> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>0</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
  </tr> 
  <tr> 
   <th>VBR</th> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>0</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
  </tr> 
  <tr> 
   <th>VLG</th> 
   <td>10</td> 
   <td>10</td> 
   <td>10</td> 
   <td>10</td> 
   <td>10</td> 
   <td>10</td> 
   <td>10</td> 
   <td>1</td> 
   <td>10</td> 
   <td>10</td> 
   <td>10</td> 
  </tr> 
  <tr> 
   <th>WAL</th> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
   <td>0</td> 
   <td>2</td> 
   <td>2</td> 
   <td>2</td> 
  </tr> 
  <tr> 
   <th>BG</th> 
   <th>2</th> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
   <td>0</td> 
   <td>0</td> 
   <td>1</td> 
   <td>1</td> 
   <td>1</td> 
  </tr> 
  <tr> 
   <th>23</th> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
   <td>1</td> 
   <td>0</td> 
   <td>4</td> 
   <td>4</td> 
   <td>4</td> 
  </tr> 
  <tr> 
   <th>BH</th> 
   <th>13</th> 
   <td>16</td> 
   <td>16</td> 
   <td>16</td> 
   <td>16</td> 
   <td>16</td> 
   <td>16</td> 
   <td>2</td> 
   <td>10</td> 
   <td>16</td> 
   <td>16</td> 
   <td>16</td> 
  </tr> 
  <tr> 
   <th>...</th> 
   <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>US</th> 
   <th>MO</th> 
   <td>188</td> 
   <td>188</td> 
   <td>188</td> 
   <td>188</td> 
   <td>188</td> 
   <td>188</td> 
   <td>188</td> 
   <td>175</td> 
   <td>188</td> 
   <td>188</td> 
   <td>188</td> 
  </tr> 
  <tr> 
   <th>MS</th> 
   <td>32</td> 
   <td>32</td> 
   <td>32</td> 
   <td>32</td> 
   <td>32</td> 
   <td>32</td> 
   <td>32</td> 
   <td>28</td> 
   <td>32</td> 
   <td>32</td> 
   <td>32</td> 
  </tr> 
  <tr> 
   <th>MT</th> 
   <td>36</td> 
   <td>36</td> 
   <td>36</td> 
   <td>36</td> 
   <td>36</td> 
   <td>36</td> 
   <td>36</td> 
   <td>36</td> 
   <td>36</td> 
   <td>36</td> 
   <td>36</td> 
  </tr> 
  <tr> 
   <th>NC</th> 
   <td>338</td> 
   <td>338</td> 
   <td>338</td> 
   <td>338</td> 
   <td>338</td> 
   <td>338</td> 
   <td>338</td> 
   <td>322</td> 
   <td>338</td> 
   <td>338</td> 
   <td>338</td> 
  </tr> 
  <tr> 
   <th>ND</th> 
   <td>13</td> 
   <td>13</td> 
   <td>13</td> 
   <td>13</td> 
   <td>13</td> 
   <td>13</td> 
   <td>13</td> 
   <td>13</td> 
   <td>13</td> 
   <td>13</td> 
   <td>13</td> 
  </tr> 
  <tr> 
   <th>NE</th> 
   <td>58</td> 
   <td>58</td> 
   <td>58</td> 
   <td>58</td> 
   <td>58</td> 
   <td>58</td> 
   <td>58</td> 
   <td>56</td> 
   <td>58</td> 
   <td>58</td> 
   <td>58</td> 
  </tr> 
  <tr> 
   <th>NH</th> 
   <td>29</td> 
   <td>29</td> 
   <td>29</td> 
   <td>29</td> 
   <td>29</td> 
   <td>29</td> 
   <td>29</td> 
   <td>27</td> 
   <td>29</td> 
   <td>29</td> 
   <td>29</td> 
  </tr> 
  <tr> 
   <th>NJ</th> 
   <td>261</td> 
   <td>261</td> 
   <td>261</td> 
   <td>261</td> 
   <td>261</td> 
   <td>261</td> 
   <td>261</td> 
   <td>250</td> 
   <td>261</td> 
   <td>261</td> 
   <td>261</td> 
  </tr> 
  <tr> 
   <th>NM</th> 
   <td>76</td> 
   <td>76</td> 
   <td>76</td> 
   <td>76</td> 
   <td>76</td> 
   <td>76</td> 
   <td>76</td> 
   <td>75</td> 
   <td>76</td> 
   <td>76</td> 
   <td>76</td> 
  </tr> 
  <tr> 
   <th>NV</th> 
   <td>253</td> 
   <td>253</td> 
   <td>253</td> 
   <td>253</td> 
   <td>253</td> 
   <td>253</td> 
   <td>253</td> 
   <td>230</td> 
   <td>253</td> 
   <td>253</td> 
   <td>253</td> 
  </tr> 
  <tr> 
   <th>NY</th> 
   <td>645</td> 
   <td>645</td> 
   <td>645</td> 
   <td>645</td> 
   <td>645</td> 
   <td>645</td> 
   <td>645</td> 
   <td>627</td> 
   <td>645</td> 
   <td>645</td> 
   <td>645</td> 
  </tr> 
  <tr> 
   <th>OH</th> 
   <td>378</td> 
   <td>378</td> 
   <td>378</td> 
   <td>378</td> 
   <td>378</td> 
   <td>378</td> 
   <td>377</td> 
   <td>357</td> 
   <td>378</td> 
   <td>378</td> 
   <td>378</td> 
  </tr> 
  <tr> 
   <th>OK</th> 
   <td>79</td> 
   <td>79</td> 
   <td>79</td> 
   <td>79</td> 
   <td>79</td> 
   <td>79</td> 
   <td>79</td> 
   <td>76</td> 
   <td>79</td> 
   <td>79</td> 
   <td>79</td> 
  </tr> 
  <tr> 
   <th>OR</th> 
   <td>359</td> 
   <td>359</td> 
   <td>359</td> 
   <td>359</td> 
   <td>359</td> 
   <td>359</td> 
   <td>359</td> 
   <td>343</td> 
   <td>359</td> 
   <td>359</td> 
   <td>359</td> 
  </tr> 
  <tr> 
   <th>PA</th> 
   <td>357</td> 
   <td>357</td> 
   <td>357</td> 
   <td>357</td> 
   <td>357</td> 
   <td>357</td> 
   <td>357</td> 
   <td>350</td> 
   <td>357</td> 
   <td>357</td> 
   <td>357</td> 
  </tr> 
  <tr> 
   <th>RI</th> 
   <td>27</td> 
   <td>27</td> 
   <td>27</td> 
   <td>27</td> 
   <td>27</td> 
   <td>27</td> 
   <td>27</td> 
   <td>27</td> 
   <td>27</td> 
   <td>27</td> 
   <td>27</td> 
  </tr> 
  <tr> 
   <th>SC</th> 
   <td>131</td> 
   <td>131</td> 
   <td>131</td> 
   <td>131</td> 
   <td>131</td> 
   <td>131</td> 
   <td>131</td> 
   <td>125</td> 
   <td>131</td> 
   <td>131</td> 
   <td>131</td> 
  </tr> 
  <tr> 
   <th>SD</th> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
  </tr> 
  <tr> 
   <th>TN</th> 
   <td>180</td> 
   <td>180</td> 
   <td>180</td> 
   <td>180</td> 
   <td>180</td> 
   <td>180</td> 
   <td>180</td> 
   <td>162</td> 
   <td>180</td> 
   <td>180</td> 
   <td>180</td> 
  </tr> 
  <tr> 
   <th>TX</th> 
   <td>1042</td> 
   <td>1042</td> 
   <td>1042</td> 
   <td>1042</td> 
   <td>1042</td> 
   <td>1042</td> 
   <td>1042</td> 
   <td>1002</td> 
   <td>1042</td> 
   <td>1042</td> 
   <td>1042</td> 
  </tr> 
  <tr> 
   <th>UT</th> 
   <td>101</td> 
   <td>101</td> 
   <td>101</td> 
   <td>101</td> 
   <td>101</td> 
   <td>101</td> 
   <td>101</td> 
   <td>99</td> 
   <td>101</td> 
   <td>101</td> 
   <td>101</td> 
  </tr> 
  <tr> 
   <th>VA</th> 
   <td>432</td> 
   <td>432</td> 
   <td>432</td> 
   <td>432</td> 
   <td>432</td> 
   <td>432</td> 
   <td>432</td> 
   <td>413</td> 
   <td>432</td> 
   <td>432</td> 
   <td>432</td> 
  </tr> 
  <tr> 
   <th>VT</th> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
   <td>8</td> 
  </tr> 
  <tr> 
   <th>WA</th> 
   <td>757</td> 
   <td>757</td> 
   <td>757</td> 
   <td>757</td> 
   <td>757</td> 
   <td>757</td> 
   <td>757</td> 
   <td>738</td> 
   <td>757</td> 
   <td>757</td> 
   <td>757</td> 
  </tr> 
  <tr> 
   <th>WI</th> 
   <td>145</td> 
   <td>145</td> 
   <td>145</td> 
   <td>145</td> 
   <td>145</td> 
   <td>145</td> 
   <td>145</td> 
   <td>144</td> 
   <td>145</td> 
   <td>145</td> 
   <td>145</td> 
  </tr> 
  <tr> 
   <th>WV</th> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
   <td>23</td> 
   <td>25</td> 
   <td>25</td> 
   <td>25</td> 
  </tr> 
  <tr> 
   <th>WY</th> 
   <td>23</td> 
   <td>23</td> 
   <td>23</td> 
   <td>23</td> 
   <td>23</td> 
   <td>23</td> 
   <td>23</td> 
   <td>22</td> 
   <td>23</td> 
   <td>23</td> 
   <td>23</td> 
  </tr> 
  <tr> 
   <th>VN</th> 
   <th>HN</th> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
   <td>6</td> 
  </tr> 
  <tr> 
   <th>SG</th> 
   <td>19</td> 
   <td>19</td> 
   <td>19</td> 
   <td>19</td> 
   <td>19</td> 
   <td>19</td> 
   <td>19</td> 
   <td>17</td> 
   <td>19</td> 
   <td>19</td> 
   <td>19</td> 
  </tr> 
  <tr> 
   <th>ZA</th> 
   <th>GT</th> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
   <td>2</td> 
   <td>3</td> 
   <td>3</td> 
   <td>3</td> 
  </tr> 
 </tbody> 
</table>

545 rows × 11 columns

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

In \[2\]:

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

In \[3\]:

movie = pd.read\_csv("./data/IMDB-Movie-Data.csv")

In \[4\]:

movie.head()

Out\[4\]:

# 我们想知道这些电影数据中评分的平均分，导演的人数等信息，我们应该怎么获取？ #

In \[8\]:

movie\["Rating"\].mean()

Out\[8\]:

6.723199999999999

In \[10\]:

np.unique(movie\["Director"\]).shape\[0\]

Out\[10\]:

644

# 对于这一组电影数据，如果我们想Rating，Runtime (Minutes)的分布情况，应该如何呈现数据？ #

In \[13\]:

\# Rating分布

movie["Rating"].plot(kind="hist")

Out\[13\]:

<matplotlib.axes._subplots.AxesSubplot at 0x123e2ccf8>

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 50][]

In \[16\]:

\# Rating分布

# 1.创建画布

plt.figure(figsize=(20, 8), dpi=100)

# 2.绘制图像

plt.hist(movie["Rating"].values, bins=20)

# 2.1 添加刻度

max_ = movie["Rating"].max()

min_ = movie["Rating"].min()

t1 = np.linspace(min_, max_, num=21)

plt.xticks(t1)

# 2.2 添加网格

plt.grid()

# 3.显示

plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 51][]

In \[17\]:

\# Runtime (Minutes)分布

# 1.创建画布

plt.figure(figsize=(20, 8), dpi=100)

# 2.绘制图像

plt.hist(movie["Runtime (Minutes)"].values, bins=20)

# 2.1 添加刻度

max_ = movie["Runtime (Minutes)"].max()

min_ = movie["Runtime (Minutes)"].min()

t1 = np.linspace(min_, max_, num=21)

plt.xticks(t1)

# 2.2 添加网格

plt.grid()

# 3.显示

plt.show()

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 52][]

# 对于这一组电影数据，如果我们希望统计电影分类(genre)的情况，应该如何处理数据？ #

In \[22\]:

\# movie\["Genre"\]

temp_list = [i.split(",") for i in movie["Genre"]]

In \[23\]:

temp\_list

Out\[23\]:

[['Action', 'Adventure', 'Sci-Fi'],
     ['Adventure', 'Mystery', 'Sci-Fi'],
     ['Horror', 'Thriller'],
     ['Animation', 'Comedy', 'Family'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Comedy', 'Drama', 'Music'],
     ['Comedy'],
     ['Action', 'Adventure', 'Biography'],
     ['Adventure', 'Drama', 'Romance'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Biography', 'Drama', 'History'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Comedy', 'Drama'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Biography', 'Drama', 'History'],
     ['Action', 'Thriller'],
     ['Biography', 'Drama'],
     ['Drama', 'Mystery', 'Sci-Fi'],
     ['Adventure', 'Drama', 'Thriller'],
     ['Drama'],
     ['Crime', 'Drama', 'Horror'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Comedy'],
     ['Action', 'Adventure', 'Drama'],
     ['Horror', 'Thriller'],
     ['Comedy'],
     ['Action', 'Adventure', 'Drama'],
     ['Comedy'],
     ['Drama', 'Thriller'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Adventure', 'Comedy'],
     ['Action', 'Horror', 'Sci-Fi'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Adventure', 'Drama', 'Sci-Fi'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Adventure', 'Western'],
     ['Comedy', 'Drama'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Drama'],
     ['Horror'],
     ['Biography', 'Drama', 'History'],
     ['Drama'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Drama', 'Thriller'],
     ['Adventure', 'Drama', 'Fantasy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Drama'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Comedy', 'Drama'],
     ['Action', 'Crime', 'Thriller'],
     ['Action', 'Crime', 'Drama'],
     ['Adventure', 'Drama', 'History'],
     ['Crime', 'Horror', 'Thriller'],
     ['Drama', 'Romance'],
     ['Comedy', 'Drama', 'Romance'],
     ['Biography', 'Drama'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Horror', 'Mystery', 'Thriller'],
     ['Crime', 'Drama', 'Mystery'],
     ['Drama', 'Romance', 'Thriller'],
     ['Drama', 'Mystery', 'Sci-Fi'],
     ['Action', 'Adventure', 'Comedy'],
     ['Drama', 'History', 'Thriller'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Drama'],
     ['Action', 'Drama', 'Thriller'],
     ['Drama', 'History'],
     ['Action', 'Drama', 'Romance'],
     ['Drama', 'Fantasy'],
     ['Drama', 'Romance'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Sci-Fi'],
     ['Adventure', 'Drama', 'War'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Comedy', 'Fantasy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Comedy', 'Drama'],
     ['Biography', 'Comedy', 'Crime'],
     ['Crime', 'Drama', 'Mystery'],
     ['Action', 'Crime', 'Thriller'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Crime', 'Drama'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Crime', 'Drama', 'Mystery'],
     ['Action', 'Crime', 'Drama'],
     ['Crime', 'Drama', 'Mystery'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Drama'],
     ['Comedy', 'Crime', 'Drama'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Comedy', 'Crime'],
     ['Animation', 'Drama', 'Fantasy'],
     ['Horror', 'Mystery', 'Sci-Fi'],
     ['Drama', 'Mystery', 'Thriller'],
     ['Crime', 'Drama', 'Thriller'],
     ['Biography', 'Crime', 'Drama'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Adventure', 'Drama', 'Sci-Fi'],
     ['Crime', 'Mystery', 'Thriller'],
     ['Action', 'Adventure', 'Comedy'],
     ['Crime', 'Drama', 'Thriller'],
     ['Comedy'],
     ['Action', 'Adventure', 'Drama'],
     ['Drama'],
     ['Drama', 'Mystery', 'Sci-Fi'],
     ['Action', 'Horror', 'Thriller'],
     ['Biography', 'Drama', 'History'],
     ['Romance', 'Sci-Fi'],
     ['Action', 'Fantasy', 'War'],
     ['Adventure', 'Drama', 'Fantasy'],
     ['Comedy'],
     ['Horror', 'Thriller'],
     ['Action', 'Biography', 'Drama'],
     ['Drama', 'Horror', 'Mystery'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Adventure', 'Drama', 'Family'],
     ['Adventure', 'Mystery', 'Sci-Fi'],
     ['Adventure', 'Comedy', 'Romance'],
     ['Action'],
     ['Action', 'Thriller'],
     ['Adventure', 'Drama', 'Family'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Adventure', 'Crime', 'Mystery'],
     ['Comedy', 'Family', 'Musical'],
     ['Adventure', 'Drama', 'Thriller'],
     ['Drama'],
     ['Adventure', 'Comedy', 'Drama'],
     ['Drama', 'Horror', 'Thriller'],
     ['Drama', 'Music'],
     ['Action', 'Crime', 'Thriller'],
     ['Crime', 'Drama', 'Thriller'],
     ['Crime', 'Drama', 'Thriller'],
     ['Drama', 'Romance'],
     ['Mystery', 'Thriller'],
     ['Mystery', 'Thriller', 'Western'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Comedy', 'Family'],
     ['Biography', 'Comedy', 'Drama'],
     ['Drama'],
     ['Drama', 'Western'],
     ['Drama', 'Mystery', 'Romance'],
     ['Comedy', 'Drama'],
     ['Action', 'Drama', 'Mystery'],
     ['Comedy'],
     ['Action', 'Adventure', 'Crime'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Adventure', 'Sci-Fi', 'Thriller'],
     ['Drama'],
     ['Action', 'Crime', 'Drama'],
     ['Drama', 'Horror', 'Mystery'],
     ['Action', 'Horror', 'Sci-Fi'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Comedy', 'Drama', 'Romance'],
     ['Action', 'Comedy', 'Fantasy'],
     ['Action', 'Comedy', 'Mystery'],
     ['Thriller', 'War'],
     ['Action', 'Comedy', 'Crime'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Adventure', 'Crime'],
     ['Action', 'Adventure', 'Thriller'],
     ['Drama', 'Fantasy', 'Romance'],
     ['Action', 'Adventure', 'Comedy'],
     ['Biography', 'Drama', 'History'],
     ['Action', 'Drama', 'History'],
     ['Action', 'Adventure', 'Thriller'],
     ['Crime', 'Drama', 'Thriller'],
     ['Animation', 'Adventure', 'Family'],
     ['Adventure', 'Horror'],
     ['Drama', 'Romance', 'Sci-Fi'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Adventure', 'Family'],
     ['Action', 'Adventure', 'Drama'],
     ['Action', 'Comedy'],
     ['Horror', 'Mystery', 'Thriller'],
     ['Action', 'Adventure', 'Comedy'],
     ['Comedy', 'Romance'],
     ['Horror', 'Mystery'],
     ['Drama', 'Family', 'Fantasy'],
     ['Sci-Fi'],
     ['Drama', 'Thriller'],
     ['Drama', 'Romance'],
     ['Drama', 'War'],
     ['Drama', 'Fantasy', 'Horror'],
     ['Crime', 'Drama'],
     ['Comedy', 'Drama', 'Romance'],
     ['Drama', 'Romance'],
     ['Drama'],
     ['Crime', 'Drama', 'History'],
     ['Horror', 'Sci-Fi', 'Thriller'],
     ['Action', 'Drama', 'Sport'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Crime', 'Drama', 'Thriller'],
     ['Adventure', 'Biography', 'Drama'],
     ['Biography', 'Drama', 'Thriller'],
     ['Action', 'Comedy', 'Crime'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Drama', 'Fantasy', 'Horror'],
     ['Biography', 'Drama', 'Thriller'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Adventure', 'Mystery'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Drama', 'Horror'],
     ['Comedy', 'Drama', 'Romance'],
     ['Comedy', 'Romance'],
     ['Drama', 'Horror', 'Thriller'],
     ['Action', 'Adventure', 'Drama'],
     ['Drama'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Drama', 'Mystery'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Adventure', 'Comedy'],
     ['Drama', 'Horror'],
     ['Action', 'Comedy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Horror', 'Mystery'],
     ['Crime', 'Drama', 'Mystery'],
     ['Comedy', 'Crime'],
     ['Drama'],
     ['Comedy', 'Drama', 'Romance'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Adventure', 'Family'],
     ['Horror', 'Sci-Fi', 'Thriller'],
     ['Drama', 'Fantasy', 'War'],
     ['Crime', 'Drama', 'Thriller'],
     ['Action', 'Adventure', 'Drama'],
     ['Action', 'Adventure', 'Thriller'],
     ['Action', 'Adventure', 'Drama'],
     ['Drama', 'Romance'],
     ['Biography', 'Drama', 'History'],
     ['Drama', 'Horror', 'Thriller'],
     ['Adventure', 'Comedy', 'Drama'],
     ['Action', 'Adventure', 'Romance'],
     ['Action', 'Drama', 'War'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Drama', 'Musical', 'Romance'],
     ['Drama', 'Sci-Fi', 'Thriller'],
     ['Comedy', 'Drama'],
     ['Action', 'Comedy', 'Crime'],
     ['Biography', 'Comedy', 'Drama'],
     ['Comedy', 'Drama', 'Romance'],
     ['Drama', 'Thriller'],
     ['Biography', 'Drama', 'History'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Horror', 'Mystery', 'Thriller'],
     ['Comedy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Drama', 'Sci-Fi'],
     ['Horror'],
     ['Drama', 'Thriller'],
     ['Comedy', 'Drama', 'Romance'],
     ['Drama', 'Thriller'],
     ['Comedy', 'Drama'],
     ['Drama'],
     ['Action', 'Adventure', 'Comedy'],
     ['Drama', 'Horror', 'Thriller'],
     ['Comedy'],
     ['Drama', 'Sci-Fi'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Horror'],
     ['Action', 'Adventure', 'Thriller'],
     ['Adventure', 'Fantasy'],
     ['Action', 'Comedy', 'Crime'],
     ['Comedy', 'Drama', 'Music'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Adventure', 'Mystery'],
     ['Action', 'Comedy', 'Crime'],
     ['Crime', 'Drama', 'History'],
     ['Comedy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Crime', 'Mystery', 'Thriller'],
     ['Action', 'Adventure', 'Crime'],
     ['Thriller'],
     ['Biography', 'Drama', 'Romance'],
     ['Action', 'Adventure'],
     ['Action', 'Fantasy'],
     ['Action', 'Comedy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Comedy', 'Crime'],
     ['Thriller'],
     ['Action', 'Drama', 'Horror'],
     ['Comedy', 'Music', 'Romance'],
     ['Comedy'],
     ['Drama'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Drama', 'Romance'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Comedy', 'Drama'],
     ['Biography', 'Crime', 'Drama'],
     ['Drama', 'History'],
     ['Action', 'Crime', 'Thriller'],
     ['Action', 'Biography', 'Drama'],
     ['Horror'],
     ['Comedy', 'Romance'],
     ['Comedy', 'Romance'],
     ['Comedy', 'Crime', 'Drama'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Crime', 'Drama', 'Thriller'],
     ['Action', 'Crime', 'Thriller'],
     ['Comedy', 'Romance'],
     ['Biography', 'Drama', 'Sport'],
     ['Drama', 'Romance'],
     ['Drama', 'Horror'],
     ['Adventure', 'Fantasy'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Action', 'Drama', 'Sci-Fi'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Horror'],
     ['Comedy', 'Horror', 'Thriller'],
     ['Action', 'Crime', 'Thriller'],
     ['Crime', 'Drama', 'Music'],
     ['Drama'],
     ['Action', 'Crime', 'Thriller'],
     ['Action', 'Sci-Fi', 'Thriller'],
     ['Biography', 'Drama'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Drama', 'Horror', 'Sci-Fi'],
     ['Biography', 'Comedy', 'Drama'],
     ['Crime', 'Horror', 'Thriller'],
     ['Crime', 'Drama', 'Mystery'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Biography', 'Drama'],
     ['Biography', 'Drama'],
     ['Biography', 'Drama', 'History'],
     ['Action', 'Biography', 'Drama'],
     ['Drama', 'Fantasy', 'Horror'],
     ['Comedy', 'Drama', 'Romance'],
     ['Drama', 'Sport'],
     ['Drama', 'Romance'],
     ['Comedy', 'Romance'],
     ['Action', 'Crime', 'Thriller'],
     ['Action', 'Crime', 'Drama'],
     ['Action', 'Drama', 'Thriller'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Action', 'Adventure'],
     ['Action', 'Adventure', 'Romance'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Crime', 'Drama'],
     ['Comedy', 'Horror'],
     ['Comedy', 'Fantasy', 'Romance'],
     ['Drama'],
     ['Drama'],
     ['Comedy', 'Drama'],
     ['Comedy', 'Drama', 'Romance'],
     ['Adventure', 'Sci-Fi', 'Thriller'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Comedy', 'Drama'],
     ['Biography', 'Drama', 'Romance'],
     ['Comedy', 'Fantasy'],
     ['Comedy', 'Drama', 'Fantasy'],
     ['Comedy'],
     ['Horror', 'Thriller'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Adventure', 'Comedy', 'Horror'],
     ['Comedy', 'Mystery'],
     ['Drama'],
     ['Adventure', 'Drama', 'Fantasy'],
     ['Drama', 'Sport'],
     ['Action', 'Adventure'],
     ['Action', 'Adventure', 'Drama'],
     ['Action', 'Drama', 'Sci-Fi'],
     ['Action', 'Mystery', 'Sci-Fi'],
     ['Action', 'Crime', 'Drama'],
     ['Action', 'Crime', 'Fantasy'],
     ['Biography', 'Comedy', 'Drama'],
     ['Action', 'Crime', 'Thriller'],
     ['Biography', 'Crime', 'Drama'],
     ['Drama', 'Sport'],
     ['Adventure', 'Comedy', 'Drama'],
     ['Action', 'Adventure', 'Thriller'],
     ['Comedy', 'Fantasy', 'Horror'],
     ['Drama', 'Sport'],
     ['Horror', 'Thriller'],
     ['Drama', 'History', 'Thriller'],
     ['Animation', 'Action', 'Adventure'],
     ['Action', 'Adventure', 'Drama'],
     ['Action', 'Comedy', 'Family'],
     ['Action', 'Adventure', 'Drama'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Comedy'],
     ['Action', 'Crime', 'Drama'],
     ['Biography', 'Drama'],
     ['Comedy', 'Romance'],
     ['Comedy'],
     ['Drama', 'Fantasy', 'Romance'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Comedy'],
     ['Comedy', 'Sci-Fi'],
     ['Comedy', 'Drama'],
     ['Animation', 'Action', 'Adventure'],
     ['Horror'],
     ['Action', 'Biography', 'Crime'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Drama', 'Romance'],
     ['Drama', 'Mystery', 'Thriller'],
     ['Drama', 'History', 'Thriller'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Adventure', 'Comedy'],
     ['Action', 'Thriller'],
     ['Comedy', 'Music'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Crime', 'Drama', 'Thriller'],
     ['Action', 'Adventure', 'Crime'],
     ['Comedy', 'Drama', 'Horror'],
     ['Drama'],
     ['Drama', 'Mystery', 'Romance'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Drama'],
     ['Action', 'Drama', 'Thriller'],
     ['Drama'],
     ['Action', 'Horror', 'Romance'],
     ['Action', 'Drama', 'Fantasy'],
     ['Action', 'Crime', 'Drama'],
     ['Drama', 'Fantasy', 'Romance'],
     ['Action', 'Crime', 'Thriller'],
     ['Action', 'Mystery', 'Thriller'],
     ['Horror', 'Mystery', 'Thriller'],
     ['Action', 'Horror', 'Sci-Fi'],
     ['Comedy', 'Drama'],
     ['Comedy'],
     ['Action', 'Adventure', 'Horror'],
     ['Action', 'Adventure', 'Thriller'],
     ['Action', 'Crime', 'Drama'],
     ['Comedy', 'Crime', 'Drama'],
     ['Drama', 'Romance'],
     ['Drama', 'Thriller'],
     ['Action', 'Comedy', 'Crime'],
     ['Comedy'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Drama', 'Romance'],
     ['Animation', 'Family', 'Fantasy'],
     ['Drama', 'Romance'],
     ['Thriller'],
     ['Adventure', 'Horror', 'Mystery'],
     ['Action', 'Sci-Fi'],
     ['Adventure', 'Comedy', 'Drama'],
     ['Animation', 'Action', 'Adventure'],
     ['Drama', 'Horror'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Comedy', 'Drama'],
     ['Action', 'Horror', 'Mystery'],
     ['Action', 'Thriller'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Drama'],
     ['Comedy', 'Drama', 'Romance'],
     ['Comedy', 'Crime'],
     ['Comedy', 'Romance'],
     ['Drama', 'Romance'],
     ['Crime', 'Drama', 'Thriller'],
     ['Horror', 'Mystery', 'Thriller'],
     ['Biography', 'Drama'],
     ['Drama', 'Mystery', 'Sci-Fi'],
     ['Adventure', 'Comedy', 'Family'],
     ['Action', 'Adventure', 'Crime'],
     ['Action', 'Crime', 'Mystery'],
     ['Mystery', 'Thriller'],
     ['Action', 'Sci-Fi', 'Thriller'],
     ['Action', 'Comedy', 'Crime'],
     ['Biography', 'Crime', 'Drama'],
     ['Biography', 'Drama', 'History'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Biography', 'Drama', 'History'],
     ['Biography', 'Comedy', 'Drama'],
     ['Drama', 'Thriller'],
     ['Horror', 'Thriller'],
     ['Drama'],
     ['Drama', 'War'],
     ['Comedy', 'Drama', 'Romance'],
     ['Drama', 'Romance', 'Sci-Fi'],
     ['Action', 'Crime', 'Drama'],
     ['Comedy', 'Drama'],
     ['Animation', 'Action', 'Adventure'],
     ['Adventure', 'Comedy', 'Drama'],
     ['Comedy', 'Drama', 'Family'],
     ['Drama', 'Romance', 'Thriller'],
     ['Comedy', 'Crime', 'Drama'],
     ['Animation', 'Comedy', 'Family'],
     ['Drama', 'Horror', 'Sci-Fi'],
     ['Action', 'Adventure', 'Drama'],
     ['Action', 'Horror', 'Sci-Fi'],
     ['Action', 'Crime', 'Sport'],
     ['Drama', 'Horror', 'Sci-Fi'],
     ['Drama', 'Horror', 'Sci-Fi'],
     ['Action', 'Adventure', 'Comedy'],
     ['Mystery', 'Sci-Fi', 'Thriller'],
     ['Crime', 'Drama', 'Thriller'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Sci-Fi', 'Thriller'],
     ['Drama', 'Romance'],
     ['Crime', 'Drama', 'Thriller'],
     ['Comedy', 'Drama', 'Music'],
     ['Drama', 'Fantasy', 'Romance'],
     ['Crime', 'Drama', 'Thriller'],
     ['Crime', 'Drama', 'Thriller'],
     ['Comedy', 'Drama', 'Romance'],
     ['Comedy', 'Romance'],
     ['Drama', 'Sci-Fi', 'Thriller'],
     ['Drama', 'War'],
     ['Action', 'Crime', 'Drama'],
     ['Sci-Fi', 'Thriller'],
     ['Adventure', 'Drama', 'Horror'],
     ['Comedy', 'Drama', 'Music'],
     ['Comedy', 'Drama', 'Romance'],
     ['Action', 'Adventure', 'Drama'],
     ['Action', 'Crime', 'Drama'],
     ['Adventure', 'Fantasy'],
     ['Drama', 'Romance'],
     ['Biography', 'History', 'Thriller'],
     ['Crime', 'Drama', 'Thriller'],
     ['Action', 'Drama', 'History'],
     ['Biography', 'Comedy', 'Drama'],
     ['Crime', 'Drama', 'Thriller'],
     ['Action', 'Biography', 'Drama'],
     ['Action', 'Drama', 'Sci-Fi'],
     ['Adventure', 'Horror'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Adventure', 'Mystery'],
     ['Comedy', 'Drama', 'Romance'],
     ['Horror', 'Thriller'],
     ['Action', 'Sci-Fi', 'Thriller'],
     ['Action', 'Sci-Fi', 'Thriller'],
     ['Biography', 'Drama'],
     ['Action', 'Crime', 'Drama'],
     ['Action', 'Crime', 'Mystery'],
     ['Action', 'Adventure', 'Comedy'],
     ['Crime', 'Drama', 'Thriller'],
     ['Crime', 'Drama'],
     ['Mystery', 'Thriller'],
     ['Mystery', 'Sci-Fi', 'Thriller'],
     ['Action', 'Mystery', 'Sci-Fi'],
     ['Drama', 'Romance'],
     ['Drama', 'Thriller'],
     ['Drama', 'Mystery', 'Sci-Fi'],
     ['Comedy', 'Drama'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Biography', 'Drama', 'Sport'],
     ['Drama'],
     ['Comedy', 'Drama', 'Romance'],
     ['Biography', 'Drama', 'Romance'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Drama', 'Sci-Fi', 'Thriller'],
     ['Drama', 'Romance', 'Thriller'],
     ['Mystery', 'Thriller'],
     ['Mystery', 'Thriller'],
     ['Action', 'Drama', 'Fantasy'],
     ['Action', 'Adventure', 'Biography'],
     ['Adventure', 'Comedy', 'Sci-Fi'],
     ['Action', 'Adventure', 'Thriller'],
     ['Fantasy', 'Horror'],
     ['Horror', 'Mystery'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Adventure', 'Drama'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Comedy', 'Drama'],
     ['Comedy', 'Drama'],
     ['Crime', 'Drama', 'Thriller'],
     ['Comedy', 'Romance'],
     ['Animation', 'Comedy', 'Family'],
     ['Comedy', 'Drama'],
     ['Comedy', 'Drama'],
     ['Biography', 'Drama', 'Sport'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Drama', 'History'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Adventure', 'Mystery'],
     ['Crime', 'Drama', 'Mystery'],
     ['Action'],
     ['Action', 'Adventure', 'Family'],
     ['Comedy', 'Romance'],
     ['Comedy', 'Drama', 'Romance'],
     ['Biography', 'Drama', 'Sport'],
     ['Action', 'Fantasy', 'Thriller'],
     ['Biography', 'Drama', 'Sport'],
     ['Action', 'Drama', 'Fantasy'],
     ['Adventure', 'Sci-Fi', 'Thriller'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Drama', 'Mystery', 'Thriller'],
     ['Drama', 'Romance'],
     ['Crime', 'Drama', 'Mystery'],
     ['Comedy', 'Romance', 'Sport'],
     ['Comedy', 'Family'],
     ['Drama', 'Horror', 'Mystery'],
     ['Action', 'Drama', 'Sport'],
     ['Action', 'Adventure', 'Comedy'],
     ['Drama', 'Mystery', 'Sci-Fi'],
     ['Animation', 'Action', 'Comedy'],
     ['Action', 'Crime', 'Drama'],
     ['Action', 'Crime', 'Drama'],
     ['Comedy', 'Drama', 'Romance'],
     ['Animation', 'Action', 'Adventure'],
     ['Crime', 'Drama'],
     ['Drama'],
     ['Drama'],
     ['Comedy', 'Crime'],
     ['Drama'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Drama', 'Fantasy', 'Romance'],
     ['Comedy', 'Drama'],
     ['Drama', 'Fantasy', 'Thriller'],
     ['Biography', 'Crime', 'Drama'],
     ['Comedy', 'Drama', 'Romance'],
     ['Action', 'Crime', 'Drama'],
     ['Sci-Fi'],
     ['Action', 'Biography', 'Drama'],
     ['Action', 'Comedy', 'Romance'],
     ['Adventure', 'Comedy', 'Drama'],
     ['Comedy', 'Crime', 'Drama'],
     ['Action', 'Fantasy', 'Horror'],
     ['Drama', 'Horror'],
     ['Horror'],
     ['Action', 'Thriller'],
     ['Action', 'Adventure', 'Mystery'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Comedy', 'Drama', 'Romance'],
     ['Crime', 'Drama', 'Mystery'],
     ['Adventure', 'Comedy', 'Family'],
     ['Comedy', 'Drama', 'Romance'],
     ['Comedy'],
     ['Comedy', 'Drama', 'Horror'],
     ['Drama', 'Horror', 'Thriller'],
     ['Animation', 'Adventure', 'Family'],
     ['Comedy', 'Romance'],
     ['Mystery', 'Romance', 'Sci-Fi'],
     ['Crime', 'Drama'],
     ['Drama', 'Horror', 'Mystery'],
     ['Comedy'],
     ['Biography', 'Drama'],
     ['Comedy', 'Drama', 'Thriller'],
     ['Comedy', 'Western'],
     ['Drama', 'History', 'War'],
     ['Drama', 'Horror', 'Sci-Fi'],
     ['Drama'],
     ['Comedy', 'Drama'],
     ['Fantasy', 'Horror', 'Thriller'],
     ['Drama', 'Romance'],
     ['Action', 'Comedy', 'Fantasy'],
     ['Drama', 'Horror', 'Musical'],
     ['Crime', 'Drama', 'Mystery'],
     ['Horror', 'Mystery', 'Thriller'],
     ['Comedy', 'Music'],
     ['Drama'],
     ['Biography', 'Crime', 'Drama'],
     ['Drama'],
     ['Action', 'Adventure', 'Comedy'],
     ['Crime', 'Drama', 'Mystery'],
     ['Drama'],
     ['Action', 'Comedy', 'Crime'],
     ['Comedy', 'Drama', 'Romance'],
     ['Crime', 'Drama', 'Mystery'],
     ['Action', 'Comedy', 'Crime'],
     ['Drama'],
     ['Drama', 'Romance'],
     ['Crime', 'Drama', 'Mystery'],
     ['Adventure', 'Comedy', 'Romance'],
     ['Comedy', 'Crime', 'Drama'],
     ['Adventure', 'Drama', 'Thriller'],
     ['Biography', 'Crime', 'Drama'],
     ['Crime', 'Drama', 'Thriller'],
     ['Drama', 'History', 'Thriller'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Comedy'],
     ['Horror'],
     ['Action', 'Crime', 'Mystery'],
     ['Comedy', 'Romance'],
     ['Comedy'],
     ['Action', 'Drama', 'Thriller'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Drama', 'Mystery', 'Thriller'],
     ['Comedy', 'Drama', 'Romance'],
     ['Action', 'Fantasy', 'Horror'],
     ['Drama', 'Romance'],
     ['Biography', 'Drama'],
     ['Biography', 'Drama'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Drama', 'Mystery', 'Thriller'],
     ['Action', 'Horror', 'Sci-Fi'],
     ['Drama', 'Romance'],
     ['Biography', 'Drama'],
     ['Action', 'Adventure', 'Drama'],
     ['Adventure', 'Drama', 'Fantasy'],
     ['Drama', 'Family'],
     ['Comedy', 'Drama', 'Romance'],
     ['Drama', 'Romance', 'Sci-Fi'],
     ['Action', 'Adventure', 'Thriller'],
     ['Comedy', 'Romance'],
     ['Crime', 'Drama', 'Horror'],
     ['Comedy', 'Fantasy'],
     ['Action', 'Comedy', 'Crime'],
     ['Adventure', 'Drama', 'Romance'],
     ['Action', 'Crime', 'Drama'],
     ['Crime', 'Horror', 'Thriller'],
     ['Romance', 'Sci-Fi', 'Thriller'],
     ['Comedy', 'Drama', 'Romance'],
     ['Crime', 'Drama'],
     ['Crime', 'Drama', 'Mystery'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Animation', 'Fantasy'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Drama', 'Mystery', 'War'],
     ['Comedy', 'Romance'],
     ['Animation', 'Comedy', 'Family'],
     ['Comedy'],
     ['Horror', 'Mystery', 'Thriller'],
     ['Action', 'Adventure', 'Drama'],
     ['Comedy'],
     ['Drama'],
     ['Adventure', 'Biography', 'Drama'],
     ['Comedy'],
     ['Horror', 'Thriller'],
     ['Action', 'Drama', 'Family'],
     ['Comedy', 'Fantasy', 'Horror'],
     ['Comedy', 'Romance'],
     ['Drama', 'Mystery', 'Romance'],
     ['Action', 'Adventure', 'Comedy'],
     ['Thriller'],
     ['Comedy'],
     ['Adventure', 'Comedy', 'Sci-Fi'],
     ['Comedy', 'Drama', 'Fantasy'],
     ['Mystery', 'Thriller'],
     ['Comedy', 'Drama'],
     ['Adventure', 'Drama', 'Family'],
     ['Horror', 'Thriller'],
     ['Action', 'Drama', 'Romance'],
     ['Drama', 'Romance'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Comedy'],
     ['Action', 'Biography', 'Drama'],
     ['Drama', 'Mystery', 'Romance'],
     ['Adventure', 'Drama', 'Western'],
     ['Drama', 'Music', 'Romance'],
     ['Comedy', 'Romance', 'Western'],
     ['Thriller'],
     ['Comedy', 'Drama', 'Romance'],
     ['Horror', 'Thriller'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Crime', 'Drama', 'Mystery'],
     ['Horror', 'Mystery'],
     ['Comedy', 'Crime', 'Drama'],
     ['Action', 'Comedy', 'Romance'],
     ['Biography', 'Drama', 'History'],
     ['Adventure', 'Drama'],
     ['Drama', 'Thriller'],
     ['Drama'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Biography', 'Drama'],
     ['Drama', 'Music'],
     ['Comedy', 'Drama'],
     ['Drama', 'Thriller', 'War'],
     ['Action', 'Mystery', 'Thriller'],
     ['Horror', 'Sci-Fi', 'Thriller'],
     ['Comedy', 'Drama', 'Romance'],
     ['Action', 'Sci-Fi'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Drama', 'Mystery', 'Romance'],
     ['Drama'],
     ['Action', 'Adventure', 'Thriller'],
     ['Action', 'Crime', 'Thriller'],
     ['Animation', 'Action', 'Adventure'],
     ['Drama', 'Fantasy', 'Mystery'],
     ['Drama', 'Sci-Fi'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Horror', 'Thriller'],
     ['Action', 'Thriller'],
     ['Comedy'],
     ['Biography', 'Drama'],
     ['Action', 'Mystery', 'Thriller'],
     ['Action', 'Mystery', 'Sci-Fi'],
     ['Crime', 'Drama', 'Thriller'],
     ['Comedy', 'Romance'],
     ['Comedy', 'Drama', 'Romance'],
     ['Biography', 'Drama', 'Thriller'],
     ['Drama'],
     ['Action', 'Adventure', 'Family'],
     ['Animation', 'Comedy', 'Family'],
     ['Action', 'Crime', 'Drama'],
     ['Comedy'],
     ['Comedy', 'Crime', 'Thriller'],
     ['Comedy', 'Romance'],
     ['Animation', 'Comedy', 'Drama'],
     ['Action', 'Crime', 'Thriller'],
     ['Comedy', 'Romance'],
     ['Adventure', 'Biography', 'Drama'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Crime', 'Drama', 'Mystery'],
     ['Action', 'Comedy', 'Sci-Fi'],
     ['Comedy', 'Fantasy', 'Horror'],
     ['Comedy', 'Crime'],
     ['Animation', 'Action', 'Adventure'],
     ['Action', 'Drama', 'Thriller'],
     ['Fantasy', 'Horror'],
     ['Crime', 'Drama', 'Thriller'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Comedy', 'Drama', 'Romance'],
     ['Biography', 'Drama', 'Romance'],
     ['Action', 'Drama', 'History'],
     ['Action', 'Adventure', 'Comedy'],
     ['Horror', 'Thriller'],
     ['Horror', 'Mystery', 'Thriller'],
     ['Comedy', 'Romance'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Crime', 'Drama', 'Mystery'],
     ['Crime', 'Drama', 'Mystery'],
     ['Adventure', 'Biography', 'Drama'],
     ['Horror', 'Mystery', 'Thriller'],
     ['Horror', 'Thriller'],
     ['Drama', 'Romance', 'War'],
     ['Adventure', 'Fantasy', 'Mystery'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Biography', 'Drama'],
     ['Drama', 'Thriller'],
     ['Horror', 'Thriller'],
     ['Drama', 'Horror', 'Thriller'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Horror', 'Thriller'],
     ['Comedy'],
     ['Drama', 'Sport'],
     ['Comedy', 'Family'],
     ['Drama', 'Romance'],
     ['Action', 'Adventure', 'Comedy'],
     ['Comedy'],
     ['Mystery', 'Romance', 'Thriller'],
     ['Crime', 'Drama'],
     ['Action', 'Comedy'],
     ['Crime', 'Drama', 'Mystery'],
     ['Biography', 'Drama', 'Romance'],
     ['Comedy', 'Crime'],
     ['Drama', 'Thriller'],
     ['Drama'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Action', 'Thriller'],
     ['Drama', 'Thriller'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Crime', 'Drama', 'Mystery'],
     ['Thriller'],
     ['Biography', 'Drama', 'Sport'],
     ['Crime', 'Drama', 'Thriller'],
     ['Drama', 'Music'],
     ['Crime', 'Drama', 'Thriller'],
     ['Drama', 'Romance'],
     ['Animation', 'Action', 'Adventure'],
     ['Comedy', 'Drama'],
     ['Action', 'Adventure', 'Drama'],
     ['Biography', 'Crime', 'Drama'],
     ['Horror'],
     ['Biography', 'Drama', 'Mystery'],
     ['Drama', 'Romance'],
     ['Animation', 'Drama', 'Romance'],
     ['Comedy', 'Family'],
     ['Drama'],
     ['Mystery', 'Thriller'],
     ['Drama', 'Fantasy', 'Horror'],
     ['Drama', 'Romance'],
     ['Biography', 'Drama', 'History'],
     ['Comedy', 'Family'],
     ['Action', 'Adventure', 'Thriller'],
     ['Comedy', 'Drama'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Thriller'],
     ['Drama', 'Romance'],
     ['Comedy', 'Drama', 'Romance'],
     ['Drama', 'Horror', 'Sci-Fi'],
     ['Comedy', 'Horror', 'Romance'],
     ['Drama'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Action', 'Adventure', 'Drama'],
     ['Biography', 'Comedy', 'Drama'],
     ['Drama', 'Mystery', 'Romance'],
     ['Animation', 'Adventure', 'Comedy'],
     ['Drama', 'Romance', 'Sci-Fi'],
     ['Drama'],
     ['Drama', 'Fantasy'],
     ['Drama', 'Romance'],
     ['Comedy', 'Horror', 'Thriller'],
     ['Comedy', 'Drama', 'Romance'],
     ['Crime', 'Drama'],
     ['Comedy', 'Romance'],
     ['Action', 'Drama', 'Family'],
     ['Comedy', 'Drama', 'Romance'],
     ['Action', 'Thriller', 'War'],
     ['Action', 'Comedy', 'Horror'],
     ['Biography', 'Drama', 'Sport'],
     ['Adventure', 'Comedy', 'Drama'],
     ['Comedy', 'Romance'],
     ['Comedy', 'Romance'],
     ['Comedy', 'Drama', 'Romance'],
     ['Action', 'Adventure', 'Crime'],
     ['Comedy', 'Romance'],
     ['Animation', 'Action', 'Adventure'],
     ['Action', 'Crime', 'Sci-Fi'],
     ['Drama'],
     ['Comedy', 'Drama', 'Romance'],
     ['Crime', 'Thriller'],
     ['Comedy', 'Horror', 'Sci-Fi'],
     ['Drama', 'Thriller'],
     ['Drama', 'Fantasy', 'Horror'],
     ['Thriller'],
     ['Adventure', 'Drama', 'Family'],
     ['Mystery', 'Sci-Fi', 'Thriller'],
     ['Biography', 'Crime', 'Drama'],
     ['Drama', 'Fantasy', 'Horror'],
     ['Action', 'Adventure', 'Thriller'],
     ['Crime', 'Drama', 'Horror'],
     ['Crime', 'Drama', 'Fantasy'],
     ['Adventure', 'Family', 'Fantasy'],
     ['Action', 'Adventure', 'Drama'],
     ['Action', 'Comedy', 'Horror'],
     ['Comedy', 'Drama', 'Family'],
     ['Action', 'Thriller'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Adventure', 'Drama', 'Fantasy'],
     ['Drama'],
     ['Drama'],
     ['Comedy'],
     ['Drama'],
     ['Comedy', 'Drama', 'Music'],
     ['Drama', 'Fantasy', 'Music'],
     ['Drama'],
     ['Thriller'],
     ['Comedy', 'Horror'],
     ['Action', 'Comedy', 'Sport'],
     ['Horror'],
     ['Comedy', 'Drama'],
     ['Action', 'Drama', 'Thriller'],
     ['Drama', 'Romance'],
     ['Horror', 'Mystery'],
     ['Adventure', 'Drama', 'Fantasy'],
     ['Thriller'],
     ['Comedy', 'Romance'],
     ['Action', 'Sci-Fi', 'Thriller'],
     ['Fantasy', 'Mystery', 'Thriller'],
     ['Biography', 'Drama'],
     ['Crime', 'Drama'],
     ['Action', 'Adventure', 'Sci-Fi'],
     ['Adventure'],
     ['Comedy', 'Drama'],
     ['Comedy', 'Drama'],
     ['Comedy', 'Drama', 'Romance'],
     ['Adventure', 'Comedy', 'Drama'],
     ['Action', 'Sci-Fi', 'Thriller'],
     ['Comedy', 'Romance'],
     ['Action', 'Fantasy', 'Horror'],
     ['Crime', 'Drama', 'Thriller'],
     ['Action', 'Drama', 'Thriller'],
     ['Crime', 'Drama', 'Mystery'],
     ['Crime', 'Drama', 'Mystery'],
     ['Drama', 'Sci-Fi', 'Thriller'],
     ['Biography', 'Drama', 'History'],
     ['Crime', 'Horror', 'Thriller'],
     ['Drama'],
     ['Drama', 'Mystery', 'Thriller'],
     ['Adventure', 'Biography'],
     ['Adventure', 'Biography', 'Crime'],
     ['Action', 'Horror', 'Thriller'],
     ['Action', 'Adventure', 'Western'],
     ['Horror', 'Thriller'],
     ['Drama', 'Mystery', 'Thriller'],
     ['Comedy', 'Drama', 'Musical'],
     ['Horror', 'Mystery'],
     ['Biography', 'Drama', 'Sport'],
     ['Comedy', 'Family', 'Romance'],
     ['Drama', 'Mystery', 'Thriller'],
     ['Comedy'],
     ['Drama'],
     ['Drama', 'Thriller'],
     ['Biography', 'Drama', 'Family'],
     ['Comedy', 'Drama', 'Family'],
     ['Drama', 'Fantasy', 'Musical'],
     ['Comedy'],
     ['Adventure', 'Family'],
     ['Adventure', 'Comedy', 'Fantasy'],
     ['Horror', 'Thriller'],
     ['Drama', 'Romance'],
     ['Horror'],
     ['Biography', 'Drama', 'History'],
     ['Action', 'Adventure', 'Fantasy'],
     ['Drama', 'Family', 'Music'],
     ['Comedy', 'Drama', 'Romance'],
     ['Action', 'Adventure', 'Horror'],
     ['Comedy'],
     ['Crime', 'Drama', 'Mystery'],
     ['Horror'],
     ['Drama', 'Music', 'Romance'],
     ['Adventure', 'Comedy'],
     ['Comedy', 'Family', 'Fantasy']]

In \[42\]:

genre\_list = np.unique(\[i for j in temp\_list for i in j\])

genre_list

Out\[42\]:

array(['Action', 'Adventure', 'Animation', 'Biography', 'Comedy', 'Crime',
           'Drama', 'Family', 'Fantasy', 'History', 'Horror', 'Music',
           'Musical', 'Mystery', 'Romance', 'Sci-Fi', 'Sport', 'Thriller',
           'War', 'Western'], dtype='<U9')

In \[29\]:

zeros = np.zeros(\[movie.shape\[0\], genre\_list.shape\[0\]\])

In \[30\]:

temp\_movie = pd.DataFrame(zeros, columns=genre\_list)

In \[32\]:

temp\_movie.head()

Out\[32\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>Action</th> 
   <th>Adventure</th> 
   <th>Animation</th> 
   <th>Biography</th> 
   <th>Comedy</th> 
   <th>Crime</th> 
   <th>Drama</th> 
   <th>Family</th> 
   <th>Fantasy</th> 
   <th>History</th> 
   <th>Horror</th> 
   <th>Music</th> 
   <th>Musical</th> 
   <th>Mystery</th> 
   <th>Romance</th> 
   <th>Sci-Fi</th> 
   <th>Sport</th> 
   <th>Thriller</th> 
   <th>War</th> 
   <th>Western</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
  </tr> 
 </tbody> 
</table>

In \[33\]:

for i in range(1000):

temp_movie.ix[i, temp_list[i]] = 1

In \[35\]:

temp\_movie.head()

Out\[35\]:

<table> 
 <thead> 
  <tr> 
   <th></th> 
   <th>Action</th> 
   <th>Adventure</th> 
   <th>Animation</th> 
   <th>Biography</th> 
   <th>Comedy</th> 
   <th>Crime</th> 
   <th>Drama</th> 
   <th>Family</th> 
   <th>Fantasy</th> 
   <th>History</th> 
   <th>Horror</th> 
   <th>Music</th> 
   <th>Musical</th> 
   <th>Mystery</th> 
   <th>Romance</th> 
   <th>Sci-Fi</th> 
   <th>Sport</th> 
   <th>Thriller</th> 
   <th>War</th> 
   <th>Western</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <th>0</th> 
   <td>1.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
  </tr> 
  <tr> 
   <th>1</th> 
   <td>0.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
  </tr> 
  <tr> 
   <th>2</th> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
  </tr> 
  <tr> 
   <th>3</th> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
  </tr> 
  <tr> 
   <th>4</th> 
   <td>1.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>1.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
   <td>0.0</td> 
  </tr> 
 </tbody> 
</table>

In \[38\]:

genre = temp\_movie.sum().sort\_values(ascending=False)

genre

Out\[38\]:

Drama        513.0
    Action       303.0
    Comedy       279.0
    Adventure    259.0
    Thriller     195.0
    Crime        150.0
    Romance      141.0
    Sci-Fi       120.0
    Horror       119.0
    Mystery      106.0
    Fantasy      101.0
    Biography     81.0
    Family        51.0
    Animation     49.0
    History       29.0
    Sport         18.0
    Music         16.0
    War           13.0
    Western        7.0
    Musical        5.0
    dtype: float64

In \[41\]:

genre.plot(kind="bar", colormap="cool", figsize=(20, 8), fontsize=16)

Out\[41\]:

<matplotlib.axes._subplots.AxesSubplot at 0x128bdea58>

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 53][]` `

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

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 54][]

[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
[20200216213926720.png]: https://img-blog.csdnimg.cn/20200216213926720.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200216213951583.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 1]: https://img-blog.csdnimg.cn/20200216213958220.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/20200216214031986.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/20200216214059620.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[20200216214110785.png]: https://img-blog.csdnimg.cn/20200216214110785.png
[2020021621412229.png]: https://img-blog.csdnimg.cn/2020021621412229.png
[20200216214131404.png]: https://img-blog.csdnimg.cn/20200216214131404.png
[20200216214144910.png]: https://img-blog.csdnimg.cn/20200216214144910.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 4]: https://img-blog.csdnimg.cn/20200216214154923.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/20200216214204334.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/20200216214214877.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/20200216214352332.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/20200216214518253.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/20200216214530488.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/20200216214536842.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[20200216214708539.png]: https://img-blog.csdnimg.cn/20200216214708539.png
[20200216214718460.png]: https://img-blog.csdnimg.cn/20200216214718460.png
[20200216214735561.png]: https://img-blog.csdnimg.cn/20200216214735561.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 11]: https://img-blog.csdnimg.cn/20200216214749733.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/20200216214819144.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/20200216214831363.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[http_pandas.pydata.org_pandas-docs_stable_reference_api_pandas.DataFrame.plot.barh.html]: http://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.plot.barh.html
[https_pandas.pydata.org_pandas-docs_stable_generated_pandas.DataFrame.plot.html_highlight_plot_pandas.DataFrame.plot]: https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.plot.html?highlight=plot#pandas.DataFrame.plot
[https_pandas.pydata.org_pandas-docs_stable_generated_pandas.Series.plot.html_highlight_plot_pandas.Series.plot]: https://pandas.pydata.org/pandas-docs/stable/generated/pandas.Series.plot.html?highlight=plot#pandas.Series.plot
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 14]: https://img-blog.csdnimg.cn/20200216214915580.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/20200216214931649.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[2020021621494246.png]: https://img-blog.csdnimg.cn/2020021621494246.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 16]: https://img-blog.csdnimg.cn/20200216214958207.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 17]: https://img-blog.csdnimg.cn/20200216215032393.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/20200216215046265.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/20200216215104214.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/20200217101608600.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/20200216215140525.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/20200216215158318.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/20200216215212757.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/20200216215222105.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 25]: https://img-blog.csdnimg.cn/20200216215249117.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 26]: https://img-blog.csdnimg.cn/20200216215308292.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 27]: https://img-blog.csdnimg.cn/2020021621531749.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 28]: https://img-blog.csdnimg.cn/20200216215325348.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 29]: https://img-blog.csdnimg.cn/20200216215333729.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 30]: https://img-blog.csdnimg.cn/20200216215404611.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 31]: https://img-blog.csdnimg.cn/20200217112754201.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 32]: https://img-blog.csdnimg.cn/202002162155062.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 33]: https://img-blog.csdnimg.cn/20200216215516159.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[https_www.kaggle.com_starbucks_store-locations_data]: https://www.kaggle.com/starbucks/store-locations/data
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 34]: https://img-blog.csdnimg.cn/20200216215539419.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 35]: https://img-blog.csdnimg.cn/20200216215550455.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 36]: https://img-blog.csdnimg.cn/20200216215601789.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[https_www.kaggle.com_damianpanek_sunday-eda_data]: https://www.kaggle.com/damianpanek/sunday-eda/data
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 37]: https://img-blog.csdnimg.cn/20200216215629761.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 38]: https://img-blog.csdnimg.cn/20200216215640813.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 39]: https://img-blog.csdnimg.cn/20200216215650494.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 40]: https://img-blog.csdnimg.cn/20200216215701533.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[20200217210309220.png]: https://img-blog.csdnimg.cn/20200217210309220.png
[20200217210407216.png]: https://img-blog.csdnimg.cn/20200217210407216.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 41]: https://img-blog.csdnimg.cn/20200217210434397.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 42]: https://img-blog.csdnimg.cn/20200217210452371.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 43]: https://img-blog.csdnimg.cn/20200217210500470.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 44]: https://img-blog.csdnimg.cn/20200217210514940.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 45]: https://img-blog.csdnimg.cn/2020021721054040.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 46]: https://img-blog.csdnimg.cn/2020021721060627.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70
[20200217210621373.png]: https://img-blog.csdnimg.cn/20200217210621373.png
[20200217210631687.png]: https://img-blog.csdnimg.cn/20200217210631687.png
[20200217210646103.png]: https://img-blog.csdnimg.cn/20200217210646103.png
[20200217210701467.png]: https://img-blog.csdnimg.cn/20200217210701467.png
[20200217210739197.png]: https://img-blog.csdnimg.cn/20200217210739197.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg_size_16_color_FFFFFF_t_70 47]: https://img-blog.csdnimg.cn/2020021721114911.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 48]: https://img-blog.csdnimg.cn/20200217211600546.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 49]: https://img-blog.csdnimg.cn/20200217211617587.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 50]: https://img-blog.csdnimg.cn/20200217211740351.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 51]: https://img-blog.csdnimg.cn/20200217211757314.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 52]: https://img-blog.csdnimg.cn/20200217211816659.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 53]: https://img-blog.csdnimg.cn/20200217211901872.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 54]: https://img-blog.csdnimg.cn/20200219111457710.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3ppbWlhbzU1MjE0NzU3Mg==,size_16,color_FFFFFF,t_70