Pandas 10分钟入门(官方说明+个人小测试)_pandas in 10minutes-程序员宅基地
In [19]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
In [20]:
s= pd.Series([1,2,3,np.nan,5,6,]) #series 类型数组。
s
Out[20]:
In [21]:
dates= pd.date_range("20170112",periods=6) #Creating a DataFrame by passing a numpy array, with a datetime index and labeled column
dates
Out[21]:
In [22]:
list(dates)
dates.date
Out[22]:
In [23]:
list(dates.date)
Out[23]:
In [24]:
dates.year
Out[24]:
In [25]:
list(dates.year)
Out[25]:
In [26]:
list(dates.day)
Out[26]:
In [27]:
str(dates.date)
Out[27]:
In [28]:
df=pd.DataFrame(np.random.randn(6,4),index=dates,columns=list("ABCD"))
df
Out[28]:
In [29]:
df2 = pd.DataFrame({
'A' : 1.,
'B' : pd.Timestamp('20130102'),
'C' : pd.Series(1,index=list(range(4)),dtype='float32'),
'D' : np.array([3] * 4,dtype='int32'),
'E' : pd.Categorical(["test","train","test","train"]),
'F' : 'foo' }) #Creating a DataFrame by passing a dict of objects that can be converted to series-like.
df2
Out[29]:
In [30]:
df2.dtypes
Out[30]:
In [31]:
df.dtypes
Out[31]:
In [32]:
df2.<TAB> #使用jupyter时按tab键，可以看到代码提示。
In [36]:
df.head()
Out[36]:
In [37]:
df.index
Out[37]:
In [38]:
df.columns
Out[38]:
In [39]:
df.values
Out[39]:
In [40]:
df.describe()
Out[40]:
In [41]:
df
Out[41]:
In [42]:
df.T
Out[42]:
In [43]:
df.sort_index(axis=1,ascending=False) #Sorting by an axis 排序。
Out[43]:
In [44]:
df.sort_values(by="B") #Sorting by values
Out[44]:
In [45]:
df
Out[45]:
In [46]:
df["A"]# Selecting a single column, which yields a Series, equivalent to df.A
Out[46]:
In [47]:
df.A
Out[47]:
In [48]:
df[0:3] #Selecting via [], which slices the rows.
Out[48]:
In [49]:
df["2017-01-13":"2017-01-17"]
Out[49]:
In [50]:
dates
Out[50]:
In [51]:
df.loc[dates[0]] #For getting a cross section using a label
Out[51]:
In [52]:
df.loc[:,["A","B"]]
Out[52]:
In [53]:
df.loc['20170112':'20170116',['A','B']] #Showing label slicing, both endpoints are included
Out[53]:
In [54]:
df.loc["20170115",["A","B"]]
Out[54]:
In [55]:
df.loc[dates[3],"D"] #For getting a scalar value
Out[55]:
In [56]:
df.at[dates[3],"D"] #For getting fast access to a scalar (equiv to the prior method)
Out[56]:
In [57]:
df.iloc[3] #Select via the position of the passed integers
Out[57]:
In [58]:
df.iloc[2:5,0:2] # By integer slices, acting similar to numpy/python
Out[58]:
In [59]:
df.iloc[[1,3,4],[0,2]] #By lists of integer position locations, similar to the numpy/python style
Out[59]:
In [60]:
df.iloc[1:3,:]
Out[60]:
In [61]:
df.iloc[:,1:3]
Out[61]:
In [62]:
df.iloc[1,1] #For getting a value explicitly
Out[62]:
In [63]:
df.iat[1,1] #For getting fast access to a scalar (equiv to the prior method)
Out[63]:
In [64]:
df[df.A>0] #Using a single column’s values to select data
Out[64]:
In [65]:
df[df>0] #Selecting values from a DataFrame where a boolean condition is met
Out[65]:
In [66]:
df2
Out[66]:
In [67]:
df
Out[67]:
In [68]:
df2=df.copy()
df2
Out[68]:
In [69]:
df.equals(df2)
Out[69]:
In [70]:
df==df2
Out[70]:
In [71]:
df is df2
Out[71]:
In [72]:
df2["E"]=["one","one","two","three","four","three"]
df2
Out[72]:
In [73]:
df2[df2.E.isin(["two","four"])]
Out[73]:
In [74]:
df2[df2["E"].isin(["two","four"])]
Out[74]:
In [75]:
s1= pd.Series([1,2,3,4,5,6],index=pd.date_range("20171016",periods=6)) #Setting a new column automatically aligns the data by the indexes
s1
Out[75]:
In [76]:
df.at[dates[0],"A"]=0 #Setting values by label
In [77]:
df
Out[77]:
In [78]:
df.iat[0,1]=0
df
Out[78]:
In [79]:
df.loc[:,"D"]=np.array([5]*len(df)) #Setting by assigning with a numpy array
df
Out[79]:
In [80]:
df2=df.copy()
df2
Out[80]:
In [81]:
df2[df2>0]=-df2
df2
Out[81]:
In [83]:
df
Out[83]:
In [84]:
df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])
df1.loc[dates[0]:dates[1],'E'] = 1
df1
Out[84]:
In [85]:
df1.dropna(how="any") #To drop any rows that have missing data
Out[85]:
In [86]:
df1.fillna(value=5) # Filling missing data
Out[86]:
In [87]:
df1
Out[87]:
In [88]:
pd.isnull(df1)
Out[88]:
In [89]:
df1.isnull()
Out[89]:
In [90]:
df1.isna() #没有这个方法~~
In [91]:
df
Out[91]:
In [92]:
df.mean()
Out[92]:
In [93]:
df.mean(1) #Same operation on the other axis
Out[93]:
In [94]:
s= pd.Series([1,2,3,np.nan,4,5],index=dates).shift(2)
# Operating with objects that have different dimensionality and need alignment. In addition, pandas automatically broadcasts along the specified dimension.
s
Out[94]:
In [95]:
df
Out[95]:
In [96]:
df.sub(s,axis="index") #dataFrame与series的减法
Out[96]:
In [97]:
df
Out[97]:
In [98]:
df.apply(np.cumsum) #行叠加。
Out[98]:
In [99]:
df.apply(lambda x: x.max()-x.min())
Out[99]:
In [100]:
s= pd.Series(np.random.randint(0,7,size=10))
s
Out[100]:
In [101]:
s.value_counts()
Out[101]:
In [102]:
s= pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])
s.str.lower()
Out[102]:
In [103]:
s
Out[103]:
In [104]:
df
Out[104]:
In [105]:
df=pd.DataFrame(np.random.randn(10,4))
df
Out[105]:
In [106]:
# break it into pieces
pieces=[df[:3],df[3:7],df[7:]]
pd.concat(pieces)
Out[106]:
In [107]:
pieces
Out[107]:
In [108]:
left=pd.DataFrame({
"key":["foo","foo"],"lval":[1,2]})
right = pd.DataFrame({
'key': ['foo', 'foo'], 'rval': [4, 5]})
In [109]:
left
Out[109]:
In [110]:
right
Out[110]:
In [111]:
pd.merge(left,right,on="key")
Out[111]:
In [112]:
left = pd.DataFrame({
'key': ['foo', 'bar'], 'lval': [1, 2]})
right = pd.DataFrame({
'key': ['foo', 'bar'], 'rval': [4, 5]})
In [113]:
left
Out[113]:
In [114]:
right
Out[114]:
In [115]:
pd.merge(left,right,on="key")
Out[115]:
In [116]:
df = pd.DataFrame(np.random.randn(8, 4), columns=['A','B','C','D'])
df
Out[116]:
In [117]:
s=df.iloc[3]
s
Out[117]:
In [118]:
df.append(s,ignore_index=True)
Out[118]:
In [119]:
df = pd.DataFrame({
'A' : ['foo', 'bar', 'foo', 'bar',
'foo', 'bar', 'foo', 'foo'],
'B' : ['one', 'one', 'two', 'three',
'two', 'two', 'one', 'three'],
'C' : np.random.randn(8),
'D' : np.random.randn(8)})
df
Out[119]:
In [120]:
df.groupby("A").sum()
Out[120]:
In [121]:
df.groupby(["A","B"]).sum() #Grouping by multiple columns forms a hierarchical index, which we then apply the function.
Out[121]:
In [122]:
tuples = list(zip([['bar', 'bar', 'baz', 'baz',
'foo', 'foo', 'qux', 'qux'],
['one', 'two', 'one', 'two',
'one', 'two', 'one', 'two']]))
tuples
Out[122]:
In [123]:
tuples = list(zip(*[['bar', 'bar', 'baz', 'baz',
'foo', 'foo', 'qux', 'qux'],
['one', 'two', 'one', 'two',
'one', 'two', 'one', 'two']]))
tuples
Out[123]:
In [124]:
index=pd.MultiIndex.from_tuples(tuples,names=["first","second"])
index
Out[124]:
In [125]:
df=pd.DataFrame(np.random.randn(8,2),index=index,columns=['A', 'B'])
df
Out[125]:
In [126]:
df2=df[:4]
df2
Out[126]:
In [127]:
stacked= df2.stack()
stacked
Out[127]:
In [128]:
stacked.unstack()
Out[128]:
In [129]:
stacked.unstack(1)
Out[129]:
In [130]:
stacked.unstack(0)
Out[130]:
In [131]:
df = pd.DataFrame({
'A' : ['one', 'one', 'two', 'three'] * 3,
'B' : ['A', 'B', 'C'] * 4,
'C' : ['foo', 'foo', 'foo', 'bar', 'bar', 'bar'] * 2,
'D' : np.random.randn(12),
'E' : np.random.randn(12)})
df
Out[131]:
In [4]:
pd.pivot_table(df,values="D",index=["A","B"],columns=["C"])
Out[4]:
In [132]:
rng=pd.date_range("1/2/2017",periods=100,freq="S")
rng
Out[132]:
In [133]:
ts =pd.Series(np.random.randint(0,500,len(rng)),index=rng)
ts
Out[133]:
In [7]:
ts.resample("5Min").sum()
Out[7]:
In [9]:
ts.resample("1Min").sum()
Out[9]:
In [10]:
rng= pd.date_range("2/1/2017 00:00",periods=5,freq="D")
rng
Out[10]:
In [12]:
ts=pd.Series(np.random.randn(len(rng)),index=rng)
ts
Out[12]:
In [13]:
tsUtc=ts.tz_localize("UTC")
tsUtc
Out[13]:
In [14]:
tsUtc.tz_convert("US/Eastern")
Out[14]:
In [15]:
tsUtc
Out[15]:
In [16]:
rng=pd.date_range("1/8/2017",periods=5,freq="M")
rng
Out[16]:
In [18]:
ts=pd.Series(np.random.randn(len(rng)),rng)
ts
Out[18]:
In [20]:
ps=ts.to_period()
ps
Out[20]:
In [21]:
ps.to_timestamp()
Out[21]:
In [22]:
ps
Out[22]:
In [23]:
prng=pd.period_range("1990Q1","2017Q4",freq="Q-NOV")
prng
Out[23]:
In [25]:
ts= pd.Series(np.random.randn(len(prng)),prng)
ts.head()
Out[25]:
In [26]:
ts.index=(prng.asfreq("M","e")+1).asfreq("H","s")+9
ts.head()
Out[26]:
In [34]:
df = pd.DataFrame({
"id":[1,2,3,4,5,6],"raw_grade":["a","a","c","b","b","f"]})
df
Out[34]:
In [35]:
df["grade"]=df.raw_grade.astype("category")
df
Out[35]:
In [36]:
df.grade #Convert the raw grades to a categorical data type
Out[36]:
In [37]:
# Rename the categories to more meaningful names (assigning to Series.cat.categories is inplace!)
df.grade.cat.categories=["very good","good","nomal","bad"]
df
Out[37]:
In [38]:
# Reorder the categories and simultaneously add the missing categories (methods under Series .cat return a new Series per default).
df.grade=df.grade.cat.set_categories(["very bad", "bad", "medium","good", "very good"])
df.grade
Out[38]:
In [39]:
df
Out[39]:
In [40]:
df.sort_values(by="grade")
Out[40]:
In [41]:
df.groupby("grade").size()
Out[41]:
In [43]:
ts=pd.Series(np.random.randn(1000),index=pd.date_range("1/1/2017",periods=1000))
ts.head()
Out[43]:
In [45]:
ts=ts.cumsum()
ts.head()
Out[45]:
In [48]:
ts.plot()
Out[48]:
In [50]:
df=pd.DataFrame(np.random.randn(1000,4),index=ts.index,columns=["A","B","C","D"])
df.head()
Out[50]:
In [51]:
df=df.cumsum()
In [53]:
plt.figure()
df.plot()
plt.legend(loc="best")
plt.show()
In [ ]:
df.to_csv("foo.csv")
In [ ]:
pd.read_csv("foo.csv")
In [ ]:
df.to_hdf("foo.h5","df")
In [ ]:
pd.read_hdf("foo.h5","df")
In [ ]:
df.to_excel('foo.xlsx', sheet_name='Sheet1')
In [ ]:
pd.read_excel('foo.xlsx', 'Sheet1', index_col=None, na_values=['NA'])
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
智能推荐
generator逆向工程_java 逆向工程 generatorconfiguration-程序员宅基地
文章浏览阅读157次。pom.xml:<?xml version="1.0" encoding="UTF-8"?><project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.or_java 逆向工程 generatorconfiguration
快速使用 Javassist_ctmethod-程序员宅基地
文章浏览阅读523次。目录前置知识JVM指令码指令码编辑Javassist使用场景基本使用常见插入方法添加异常代码块总结方法拷贝特殊语法特殊语法表$0, $1, $2$args$$$cflow$r$w$_$sig$class创建类实例访问类实例变量参考链接：https://www.cnblogs.com/sunfie/p/5154246.html前置知识JVM指令码Java源代码不能直接运行，需要编译成class文件，然后被JVM加载后运行。Class文件是由JVM指令码所组成的，JVM加载Class文件，就是在加载Cl_ctmethod
Java语法进阶及常用技术（三）--Maven项目管理-程序员宅基地
文章浏览阅读559次。Maven介绍Maven是项目管理工具，对软件项目提供构建与依赖管理。Maven是Apache下的Java开源项目。Maven为Java项目提供了统一的管理方式，已成为业界标准。Maven核心特性项目设置遵循统一的规则，保证不同开发环境的兼容性。强大的依赖管理，项目依赖组件自动下载、自动更新。可扩展的插件机制，使用简单，功能丰富。Maven的安装与配置安装Maven之前需要安装jdk1.8。从官网下载MavenMaven官网：https://maven.apache.org/bin
C#排序 访问指定下标_c# 获取list 下表-程序员宅基地
文章浏览阅读1.9k次。一、C #中Sort()函数的使用与C++中类似，C#中也有自己的Sort()函数，其使用方式：（列表List的排序使用方式）第一步：声明一个myComparer类，它继承自IComparer：class myComparer : IComparer<MyPoint>/*实现 IComparer<T> 接口中的 Compare 方法， ..._c# 获取list 下表
Python不可变序列类型--字符串-程序员宅基地
文章浏览阅读1.7w次，点赞16次，收藏17次。Python从入门到精通零基础入门篇
java中预处理PrepareStatement起到防止SQL注入的作用_java sql prepare的作用-程序员宅基地
文章浏览阅读1.1k次。大家都知道，java中JDBC中，有个预处理功能，这个功能一大优势就是能提高执行速度尤其是多次操作数据库的情况，再一个优势就是预防SQL注入，严格的说，应该是预防绝大多数的SQL注入。 用法就是如下边所示：[java] view plain copyString sql="update cz_zj_directpayment dp_java sql prepare的作用
随便推点
Failed to start usr-lib-systemd-system-xxx.service.mount: Unit not found的一种可能情况_failed to start usr-lib-systemd-system-mode_export-程序员宅基地
文章浏览阅读290次。systemctl enable\start /usr/lib/systemd/system/xxx.service`则会报标题所示的错误。去掉路径，直接systemctl enable\start xxx.service则不会报错。xxx.service放入到/usr/lib/systemd/system下之后，如果以。_failed to start usr-lib-systemd-system-mode_exporter.service.mount: unit not
无人直播系统源码开发：功能、优势与开发方法探析-程序员宅基地
文章浏览阅读617次，点赞8次，收藏8次。本文介绍了无人直播系统的功能和优势，以及如何进行开发。无人直播系统能够实时采集、编码和传输视频流，支持弹幕互动，并具备实时性、互动性、灵活性和可扩展性等优势。开发无人直播系统的方法包括确定需求、设计系统架构、实现功能、部署上线和维护优化。通过定制开发无人直播系统，可以满足不同业务场景下的实时视频传输和互动需求，提供高质量的直播体验。_无人直播系统源码
windows10环境VS2017 编译Opencv和TensorFlow程序（cmake）-程序员宅基地
文章浏览阅读539次。嘿嘿，我刚上研一，体育方面的研究生，想做计算机视觉方面的课题，这几天都在配置opencv和tensorflow的环境，走了不少歪路，总结了一下。一、关于opencv源码的查看和编译：http://blog.csdn.net/poem_qianmo/article/details/21974023 这个网址介绍的很全。其中要注意的是：如果安装的是vs2017，那么current generato...
Android 设��默认浏览器后安装另外浏览器后默认浏览器功能修复-程序员宅基地
文章浏览阅读84次。在“设置”应用中，找到“应用程序”或“应用管理器”选项，然后找到默认浏览器应用。点击该应用，然后找到“存储”或“存储空间”选项，点击进入。在存储页面中，找到“清除数据”或“清除缓存”选项，并点击确认。在Android设备上，打开“设置”应用，并找到“应用程序”或“应用管理器”选项。点击该应用，然后找到“清除默认值”或“清除默认设置”的选项，并点击确认。在“设置”应用中，找到“应用程序”或“应用管理器”选项，然后找到另外一个浏览器应用。点击该应用，然后找到“清除数据”或“清除缓存”选项，并点击确认。
Ant Design vue自定义文件上传_ant design vue 上传-程序员宅基地
文章浏览阅读4.4k次。实际项目中，上传文件时实际可能需要传输一个token。方法一：1、查看vue antdesign文档https://vue.ant.design/components/upload-cn/2、使用customRequestcustomRequest 通过覆盖默认的上传行为，可以自定义自己的上传实现 Function3、定义customRequest，之前定义action行为会被覆盖，可以注释掉4、customRequest代码如下customRequest ._ant design vue 上传
C++ 学习路线：快速入门到进阶_c++学习路线-程序员宅基地
文章浏览阅读4.9k次，点赞12次，收藏92次。C/C++ 是一门底层、细粒度、功能强大、学习曲线陡峭的语言，掌握这门语言的程序员通常有着更长的生命周期以及更深的护城河。但入门门槛高也是不争的事实，这篇文章把C++学习划分为入门、进阶、深入三个阶段，每步提供相应的学习方法和资源，帮助大家更好地掌握这门语言。_c++学习路线