Python数据科学常用库——Pandas

向右看齐 2022-03-22 06:24 347阅读 0赞

# Python数据科学常用库——Pandas #

## 一、数据格式Series ##

### 0x1 创建Series ###

import numpy as np
    import pandas as pd
     s1 = pd.Series([1,2,3,4])      # 通过Python list创建
     s2 = pd.Series(np.arange(10))  # 通过numpy array创建
     s3 = pd.Series({'1':1,'2':2})  # 通过字典创建
     s4 = Series([1,2,3,4], index=['A','B','C','D'])  # 指定索引

### 0x2 Series操作 ###

s4['A'] = 1  # 通过索引访问
    s4[s4>2]     # 取值范围
    s4.to_dict() # 转换为字典

## 二、数据格式Dataframe ##

### 0x1 创建Dataframe ###

import numpy as np
    import pandas as pd
    from pandas import Series, DataFrame
    df = pd.read_clipboard()  # 从剪切板解析创建
    df.columns                # 返回表头元素
    df.Ratings                # 返回Ratings列的所有元素

### 0x2 Dataframe操作 ###

df_new = DataFrame(df,cloumns=['A','B'])  # 生成一个新的DataFrame，从df中选择某些列元素
    df_new['2018'] = range(0,10)  # 给某一列赋值
    df_new['2018'] = np.arange(0,10)
    df_new['2018'] = pd.Series(np.arange(0,10)) 
    df_new['2018'] = pd.Series([100,200],index=[1,2])  # 给某一列指定索引赋值

## 三、深入理解Series和Dataframe ##

`data = { 'Country': ['China', 'India', 'Brazil'], 'Capital': ['Beijing', 'New Delhi', 'Brasilia'], 'Population': ['1432732201', '1303171635', '207847528'] }`

s1 = Series(data['Country'],index=['A','B','C'])   # 转换数据为Series
    df = DataFrame(data) # 转换数据为Dataframe

**通过Series创建DataFrame**

s1 = Series(data['Country'])
    s2 = Series(data['Capital'])
    s3 = Series(data['Population'])
    df_new = DataFrame([s1,s2,s3])

df\_new:  
![20190126130240.png][]

df_new = DataFrame([s1,s2,s3], index=['Country','Capital', 'Population'])

![20190126130328.png][]

转置df\_new.T  
![20190126130429.png][]

**Series和DataFrame的关系**

![20190126130503.png][]

## 三、Dataframe的IO操作 ##

**通过`df1 = pd.read_clipboard()`和d`f1.to_clipboard()`方法，可以将列表存入到Excel文件中。**

### 0x1 CSV文件操作 ###

df1.to_csv('df1.csv', index=False)  # 写入文件
    df2 = pd.read_csv('df1.csv')        # 读取CSV

### 0x2 JSON文件操作 ###

df1.to_json()    # 转换为json
    pd.read_json(df1.to_json())  # 读取json

### 0x3 HTML文件操作 ###

df1.to_html('df1.html')
    df1.read_html('df1.html')

### 0x4 转换为EXCEL ###

df1.to_excel('df1.xlsx')

## 四、Dataframe的高阶操作 ##

imdb = pd.read_csv('a.csv')
    imdb.shape        # 返回数据大小
    imdb.head()       # 返回数据开头5行
    imdb.tail()       # 返回数据结尾5行

**切片操作**

imdb.iloc[10:20,0:2]  # 切片操作，通过索引
    imdb.iloc[2:4,:]      # 切片操作，取2-3行数据
    imdb.loc[15:17,:]     # 通过label标签切片
    imdb.loc[15:17,:'lable']

**Reindex**

s1 = Series([1,2,3,4], index=['A','B','C','D'])
    s1.reindex(index=['A','B','C','D','E'])  # 更改索引
    s1.reindex(index=['A','B','C','D','E'], fill_value=10) # 将索引没有值的填充为10
    s2 = Series(['A','B','C'], index=[1,5,10])
    s2.reindex(index=range(15),method='ffill')  # 将NaN的填充为前面的值

`df1 = DataFrame(np.random.rand(25).reshape([5,5]), index=['A','B','D','E','F'], columns=['c1','c2','c3','c4','c5'])`

![20190126143531.png][]

`df1.reindex(index=['A','B','C','D','E','F'],columns=['c1','c2','c3','c4','c5','c6'])`

![20190126143753.png][]

s1.reindex(index=['A','B'])  # 截取A、B
    df1.reindex(index=['A','B']) # 截取A、B两行

**删除操作**

s1.drop('A')  # 删除索引为A的series
    df1.drop('c1', axis=1)  # 删除label为c1的列
    df1.drop('A', axis=0)   # 删除label为A的行

## 五、Mapping和Replace ##

# create a dataframe
    df1 = DataFrame({"城市":["北京","上海","广州"], "人口":[1000,2000,1500]}, index=['A','B','C'])

![20190126151531.png][]

df1['GDP'] = Series([1000,2000,1500], index=['A','B','C'])  # Series默认索引是123，必须要加index参数
    
    //推荐用map的方式添加，不用考虑索引
    gdp_map = {"北京":1000,"上海":2000,"广州":1500}
    df1['GDP'] = df1['城市'].map(gdp_map)

![20190126151603.png][]

s1 = Series(np.arange(10))
    s1.replace([1,2,3], [10,20,30])   # 将索引为1 2 3的值改为10 20 20

[20190126130240.png]: /images/20220322/6a80c5c6cc1f4f34a3cc659cb9f42445.png
[20190126130328.png]: /images/20220322/31905b92bdfa43b1985e8415ab947675.png
[20190126130429.png]: /images/20220322/e935d4276b9148f2b25a28598bab9964.png
[20190126130503.png]: /images/20220322/8dc51242ea4743658fbdf3125b3bcb30.png
[20190126143531.png]: /images/20220322/53d3ac0fa9eb4733a8d2e1a1cb18ee4a.png
[20190126143753.png]: /images/20220322/e2eae450145c4c0d9d3816b4dec4603e.png
[20190126151531.png]: /images/20220322/e22d2d6b5c094cceb3e715aa7460fab7.png
[20190126151603.png]: /images/20220322/7e66d24736044a9d9e671ccbaf9e82f7.png