代码

import pandas as pd

import numpy as np

dates = pd.date_range('20130101', periods=6)

df=pd.DataFrame(np.arange(24).reshape((6,4)),index=dates, columns=['A','B','C','D'])

# 行数，列数，赋值

df.iloc[0,1] = np.nan

df.iloc[1,2] = np.nan

# 以行丢掉

print('-1-')

print(df.dropna(axis=0))

# 有nan就丢 这是默认情况

print('-2-')

print(df.dropna(axis=0, how='any'))

# 全是nan再丢

print('-3-')

print(df.dropna(axis=0, how='all'))

# 填上

print('-4-')

print(df.fillna(value=0))

# 判断每个的结果

print('-5-')

print(df.isnull())

# 整体内是不是有null

print('-6-')

print(np.any(df.isnull()) == True)

# 读取保存数据 read_csv to_csv

df1 = pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'])

df2 = pd.DataFrame(np.ones((3,4))*1,columns=['a','b','c','d'])

df3 = pd.DataFrame(np.ones((3,4))*2,columns=['a','b','c','d'])

print('-7-')

print(df1)

print(df2)

print(df3)

# axis=0 竖向合并

res = pd.concat([df1,df2,df3], axis=0)

print('-8-')

print(res)

res = pd.concat([df1,df2,df3], axis=0, ignore_index=True)

print('-9-')

print(res)

df1 = pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'],index=[1,2,3])

df2 = pd.DataFrame(np.ones((3,4))*1,columns=['b','c','d','e'],index=[2,3,4])

print('-10-')

print(df1)

print(df2)

# 组合模式

res = pd.concat([df1,df2])

print('-11-')

print(res)

# defalut 并集

res = pd.concat([df1,df2], join='outer')

print('-12-')

print(res)

# 交集

res = pd.concat([df1,df2], join='inner')

print('-13-')

print(res)

res = pd.concat([df1,df2], join='inner', ignore_index=True)

print('-14-')

print(res)

# axis=1 左右合并 只考虑df1的index

res = pd.concat([df1,df2], axis=1,join_axes=[df1.index])

print('-15-')

print(res)

# axis=1 左右合并

res = pd.concat([df1,df2], axis=1)

print('-16-')

print(res)

df1 = pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'])

df2 = pd.DataFrame(np.ones((3,4))*1,columns=['a','b','c','d'])

df3 = pd.DataFrame(np.ones((3,4))*2,columns=['b','c','d','e'],index=[2,3,4])

res = df1.append(df2, ignore_index=True)

print('-17-')

print(res)

res = df1.append([df2, df3], ignore_index=True)

print('-18-')

print(res)

s1 = pd.Series([1,2,3,4], index=['a','b','c','d'])

res = df1.append(s1,ignore_index=True)

print('-19-')

print(res)

　　

输出

-1-

             A     B     C   D

2013-01-03   8   9.0  10.0  11

2013-01-04  12  13.0  14.0  15

2013-01-05  16  17.0  18.0  19

2013-01-06  20  21.0  22.0  23

-2-

             A     B     C   D

2013-01-03   8   9.0  10.0  11

2013-01-04  12  13.0  14.0  15

2013-01-05  16  17.0  18.0  19

2013-01-06  20  21.0  22.0  23

-3-

             A     B     C   D

2013-01-01   0   NaN   2.0   3

2013-01-02   4   5.0   NaN   7

2013-01-03   8   9.0  10.0  11

2013-01-04  12  13.0  14.0  15

2013-01-05  16  17.0  18.0  19

2013-01-06  20  21.0  22.0  23

-4-

             A     B     C   D

2013-01-01   0   0.0   2.0   3

2013-01-02   4   5.0   0.0   7

2013-01-03   8   9.0  10.0  11

2013-01-04  12  13.0  14.0  15

2013-01-05  16  17.0  18.0  19

2013-01-06  20  21.0  22.0  23

-5-

                A      B      C      D

2013-01-01  False   True  False  False

2013-01-02  False  False   True  False

2013-01-03  False  False  False  False

2013-01-04  False  False  False  False

2013-01-05  False  False  False  False

2013-01-06  False  False  False  False

-6-

True

-7-

     a    b    c    d

0  0.0  0.0  0.0  0.0

1  0.0  0.0  0.0  0.0

2  0.0  0.0  0.0  0.0

     a    b    c    d

0  1.0  1.0  1.0  1.0

1  1.0  1.0  1.0  1.0

2  1.0  1.0  1.0  1.0

     a    b    c    d

0  2.0  2.0  2.0  2.0

1  2.0  2.0  2.0  2.0

2  2.0  2.0  2.0  2.0

-8-

     a    b    c    d

0  0.0  0.0  0.0  0.0

1  0.0  0.0  0.0  0.0

2  0.0  0.0  0.0  0.0

0  1.0  1.0  1.0  1.0

1  1.0  1.0  1.0  1.0

2  1.0  1.0  1.0  1.0

0  2.0  2.0  2.0  2.0

1  2.0  2.0  2.0  2.0

2  2.0  2.0  2.0  2.0

-9-

     a    b    c    d

0  0.0  0.0  0.0  0.0

1  0.0  0.0  0.0  0.0

2  0.0  0.0  0.0  0.0

3  1.0  1.0  1.0  1.0

4  1.0  1.0  1.0  1.0

5  1.0  1.0  1.0  1.0

6  2.0  2.0  2.0  2.0

7  2.0  2.0  2.0  2.0

8  2.0  2.0  2.0  2.0

-10-

     a    b    c    d

1  0.0  0.0  0.0  0.0

2  0.0  0.0  0.0  0.0

3  0.0  0.0  0.0  0.0

     b    c    d    e

2  1.0  1.0  1.0  1.0

3  1.0  1.0  1.0  1.0

4  1.0  1.0  1.0  1.0

d:\Alex\WorkLog\34-deeplearning\myWorks\TransferLearningExample\mofangTransferLearning\1.py:62: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version

of pandas will change to not sort by default.

To accept the future behavior, pass 'sort=True'.

To retain the current behavior and silence the warning, pass sort=False

  res = pd.concat([df1,df2])

-11-

     a    b    c    d    e

1  0.0  0.0  0.0  0.0  NaN

2  0.0  0.0  0.0  0.0  NaN

3  0.0  0.0  0.0  0.0  NaN

2  NaN  1.0  1.0  1.0  1.0

3  NaN  1.0  1.0  1.0  1.0

4  NaN  1.0  1.0  1.0  1.0

d:\Alex\WorkLog\34-deeplearning\myWorks\TransferLearningExample\mofangTransferLearning\1.py:66: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version

of pandas will change to not sort by default.

To accept the future behavior, pass 'sort=True'.

To retain the current behavior and silence the warning, pass sort=False

  res = pd.concat([df1,df2], join='outer')

-12-

     a    b    c    d    e

1  0.0  0.0  0.0  0.0  NaN

2  0.0  0.0  0.0  0.0  NaN

3  0.0  0.0  0.0  0.0  NaN

2  NaN  1.0  1.0  1.0  1.0

3  NaN  1.0  1.0  1.0  1.0

4  NaN  1.0  1.0  1.0  1.0

-13-

     b    c    d

1  0.0  0.0  0.0

2  0.0  0.0  0.0

3  0.0  0.0  0.0

2  1.0  1.0  1.0

3  1.0  1.0  1.0

4  1.0  1.0  1.0

-14-

     b    c    d

0  0.0  0.0  0.0

1  0.0  0.0  0.0

2  0.0  0.0  0.0

3  1.0  1.0  1.0

4  1.0  1.0  1.0

5  1.0  1.0  1.0

-15-

     a    b    c    d    b    c    d    e

1  0.0  0.0  0.0  0.0  NaN  NaN  NaN  NaN

2  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0

3  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0

-16-

     a    b    c    d    b    c    d    e

1  0.0  0.0  0.0  0.0  NaN  NaN  NaN  NaN

2  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0

3  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0

4  NaN  NaN  NaN  NaN  1.0  1.0  1.0  1.0

-17-

     a    b    c    d

0  0.0  0.0  0.0  0.0

1  0.0  0.0  0.0  0.0

2  0.0  0.0  0.0  0.0

3  1.0  1.0  1.0  1.0

4  1.0  1.0  1.0  1.0

5  1.0  1.0  1.0  1.0

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py:6201: FutureWarning: Sorting because non-concatenation axis

is not aligned. A future version

of pandas will change to not sort by default.

To accept the future behavior, pass 'sort=True'.

To retain the current behavior and silence the warning, pass sort=False

  sort=sort)

-18-

     a    b    c    d    e

0  0.0  0.0  0.0  0.0  NaN

1  0.0  0.0  0.0  0.0  NaN

2  0.0  0.0  0.0  0.0  NaN

3  1.0  1.0  1.0  1.0  NaN

4  1.0  1.0  1.0  1.0  NaN

5  1.0  1.0  1.0  1.0  NaN

6  NaN  2.0  2.0  2.0  2.0

7  NaN  2.0  2.0  2.0  2.0

8  NaN  2.0  2.0  2.0  2.0

-19-

     a    b    c    d

0  0.0  0.0  0.0  0.0

1  0.0  0.0  0.0  0.0

2  0.0  0.0  0.0  0.0

3  1.0  2.0  3.0  4.0

　　

16-numpy笔记-莫烦pandas-4的更多相关文章

  1. 15-numpy笔记-莫烦pandas-3

    代码 import pandas as pd import numpy as np dates = pd.date_range('20130101', periods=6) df=pd.DataFra ...

  2. 14-numpy笔记-莫烦pandas-2

    代码 import pandas as pd import numpy as np dates = pd.date_range('20130101', periods=6) df=pd.DataFra ...

  3. 18-numpy笔记-莫烦pandas-6-plot显示

    代码 import pandas as pd import numpy as np import matplotlib.pyplot as plt data = pd.Series(np.random ...

  4. 17-numpy笔记-莫烦pandas-5

    代码 import pandas as pd import numpy as np left=pd.DataFrame({'key':['K0','K1','K2','K3'], 'A':['A0', ...

  5. 13-numpy笔记-莫烦pandas-1

    代码 import pandas as pd import numpy as np s = pd.Series([1,3,6,np.nan, 44,1]) print('-1-') print(s) ...

  6. 11-numpy笔记-莫烦基础操作1

    代码 import numpy as np array = np.array([[1,2,5],[3,4,6]]) print('-1-') print('数组维度', array.ndim) pri ...

  7. 12-numpy笔记-莫烦基本操作2

    代码 import numpy as np A = np.arange(3,15) print('-1-') print(A) print('-2-') print(A[3]) A = np.aran ...

  8. tensorflow学习笔记-bili莫烦

    bilibili莫烦tensorflow视频教程学习笔记 1.初次使用Tensorflow实现一元线性回归 # 屏蔽警告 import os os.environ[' import numpy as ...

  9. Python pandas & numpy 笔记

    记性不好,多记录些常用的东西,真·持续更新中::先列出一些常用的网址: 参考了的 莫烦python pandas DOC numpy DOC matplotlib 常用 习惯上我们如此导入: impo ...

随机推荐

  1. Python socket & socket server

    socket 网络上的两个程序通过一个双向的通信连接实现数据的交换,这个连接的一端称为一个socket(套接字). 建立网络通信连接至少要一对socket.socket是对TCP/IP的封装 使用方法 ...

  2. numpy-数据清洗

    一.对G列数据进行清洗,根据['无','2000-3999','4000-5999','6000-7999','8000-9999','>10000']进行划分 去处重复值 # 删除重复值 # ...

  3. Java连载37-面向对象的封装性

    一.IDE上继续新建工程 1.在src目录下新建软件包:package机制后面再讲,目前先用着 2.给package命名一个名称:com.bjpowernode.java_learning 3.软件包 ...

  4. restful api的10个最佳实践

    Web API在过去的几年里非常盛行,因为它有着语法简单.规范化和轻量级的优点,因为得到广泛的推崇,很多过往的技术手段都慢慢转换为使用Web API来开发.而Web API通常使用的设计方式是REST ...

  5. webstorm关闭烦人的eslint语法检查

    使用了eslint语法检查之后发现JS代码里面处处是红线,通过右键菜单中的fix eslint problems选项又会发现页面代码的格式被eslint换行得不分青红皂白,索性关闭exlint语法检查 ...

  6. kubernetes 之一些报错

    1.kubelet与docker的Cgroup Driver不一致导致的报错 7月 :: kubeadm-master kubelet[]: W0701 :: watcher.go:] Error w ...

  7. MySQL问题记录——定义timestamp类型的数据

    MySQL问题记录——定义timestamp类型的数据 摘要:本文主要记录了在使用MySQL的过程中定义timestamp类型数据时遇到的问题以及解决方案. 问题重现 在Windows环境下安装MyS ...

  8. Python学习笔记之unittest测试类

    11-3 雇员:编写一个名为Employee 的类,其方法__init__()接受名.姓和年薪,并将它们都存储在属性中.编写一个名为give_raise()的方法,它默认将年薪增加5000美元,但也能 ...

  9. 2019 北森java面试笔试题 （含面试题解析）

      本人5年开发经验.18年年底开始跑路找工作,在互联网寒冬下成功拿到阿里巴巴.今日头条.北森等公司offer,岗位是Java后端开发,因为发展原因最终选择去了北森,入职一年时间了,也成为了面试官,之 ...

  10. Lucene搜索/索引过程笔记

    lucene索引文档过程: > 初始化IndexWriter > 构建Document > 调用IndexWriter.addDocument执行写入 > 初始化Documen ...