习惯上,我们做以下导入
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [1]: import pandas as pdIn [2]: import numpy as npIn [3]: import matplotlib.pyplot as plt# End www.jb51.cc使用传递的值列表序列创建序列,让pandas创建默认整数索引
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [4]: s = pd.SerIEs([1,3,5,np.nan,6,8])In [5]: sOut[5]: 0 11 32 53 NaN4 65 8dtype: float64# End www.jb51.cc使用传递的numpy数组创建数据帧,并使用日期索引和标记列.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [6]: dates = pd.date_range('20130101',periods=6)In [7]: datesOut[7]: [2013-01-01,...,2013-01-06]Length: 6,Freq: D,Timezone: None In [8]: df = pd.DataFrame(np.random.randn(6,4),index=dates,columns=List('ABCD'))In [9]: dfOut[9]: A B C D2013-01-01 0.469112 -0.282863 -1.509059 -1.1356322013-01-02 1.212112 -0.173215 0.119209 -1.0442362013-01-03 -0.861849 -2.104569 -0.494929 1.0718042013-01-04 0.721555 -0.706771 -1.039575 0.2718602013-01-05 -0.424972 0.567020 0.276232 -1.0874012013-01-06 -0.673690 0.113648 -1.478427 0.524988# End www.jb51.cc使用传递的可转换序列的字典对象创建数据帧.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [10]: 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' }) ....: In [11]: df2Out[11]: A B C D E F0 1 2013-01-02 1 3 test foo1 1 2013-01-02 1 3 train foo2 1 2013-01-02 1 3 test foo3 1 2013-01-02 1 3 train foo# End www.jb51.cc所有明确类型
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [12]: df2.dtypesOut[12]: A float64B datetime64[ns]C float32D int32E categoryF objectdtype: object# End www.jb51.cc如果你这个正在使用IPython，标签补全列名（以及公共属性）将自动启用。这里是将要完成的属性的子集：
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [13]: df2.df2.A df2.Boxplotdf2.abs df2.Cdf2.add df2.clipdf2.add_prefix df2.clip_lowerdf2.add_suffix df2.clip_upperdf2.align df2.columnsdf2.all df2.combinedf2.any df2.combineAdddf2.append df2.combine_firstdf2.apply df2.combineMultdf2.applymap df2.compounddf2.as_blocks df2.consolIDatedf2.asfreq df2.convert_objectsdf2.as_matrix df2.copydf2.astype df2.corrdf2.at df2.corrwithdf2.at_time df2.countdf2.axes df2.covdf2.B df2.cummaxdf2.between_time df2.cummindf2.bfill df2.cumproddf2.blocks df2.cumsumdf2.bool df2.D# End www.jb51.cc如你所见,列 A,B,C,和 D 也是自动完成标签. E 也是可用的; 为了简便起见,后面的属性显示被截断.
查看数据参阅基础部分
查看帧顶部和底部行
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [14]: df.head()Out[14]: A B C D2013-01-01 0.469112 -0.282863 -1.509059 -1.1356322013-01-02 1.212112 -0.173215 0.119209 -1.0442362013-01-03 -0.861849 -2.104569 -0.494929 1.0718042013-01-04 0.721555 -0.706771 -1.039575 0.2718602013-01-05 -0.424972 0.567020 0.276232 -1.087401 In [15]: df.tail(3)Out[15]: A B C D2013-01-04 0.721555 -0.706771 -1.039575 0.2718602013-01-05 -0.424972 0.567020 0.276232 -1.0874012013-01-06 -0.673690 0.113648 -1.478427 0.524988# End www.jb51.cc显示索引,列,和底层numpy数据
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [16]: df.indexOut[16]: [2013-01-01,Timezone: None In [17]: df.columnsOut[17]: Index([u'A',u'B',u'C',u'D'],dtype='object') In [18]: df.valuesOut[18]: array([[ 0.4691,-0.2829,-1.5091,-1.1356],[ 1.2121,-0.1732,0.1192,-1.0442],[-0.8618,-2.1046,-0.4949,1.0718],[ 0.7216,-0.7068,-1.0396,0.2719],[-0.425,0.567,0.2762,-1.0874],[-0.6737,0.1136,-1.4784,0.525 ]])# End www.jb51.cc描述显示数据快速统计摘要
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [19]: df.describe()Out[19]: A B C Dcount 6.000000 6.000000 6.000000 6.000000mean 0.073711 -0.431125 -0.687758 -0.233103std 0.843157 0.922818 0.779887 0.973118min -0.861849 -2.104569 -1.509059 -1.13563225% -0.611510 -0.600794 -1.368714 -1.07661050% 0.022070 -0.228039 -0.767252 -0.38618875% 0.658444 0.041933 -0.034326 0.461706max 1.212112 0.567020 0.276232 1.071804# End www.jb51.cc# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [20]: df.TOut[20]: 2013-01-01 2013-01-02 2013-01-03 2013-01-04 2013-01-05 2013-01-06A 0.469112 1.212112 -0.861849 0.721555 -0.424972 -0.673690B -0.282863 -0.173215 -2.104569 -0.706771 0.567020 0.113648C -1.509059 0.119209 -0.494929 -1.039575 0.276232 -1.478427D -1.135632 -1.044236 1.071804 0.271860 -1.087401 0.524988# End www.jb51.cc按轴排序
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [21]: df.sort_index(axis=1,ascending=False)Out[21]: D C B A2013-01-01 -1.135632 -1.509059 -0.282863 0.4691122013-01-02 -1.044236 0.119209 -0.173215 1.2121122013-01-03 1.071804 -0.494929 -2.104569 -0.8618492013-01-04 0.271860 -1.039575 -0.706771 0.7215552013-01-05 -1.087401 0.276232 0.567020 -0.4249722013-01-06 0.524988 -1.478427 0.113648 -0.673690# End www.jb51.cc按值排序
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [22]: df.sort(columns='B')Out[22]: A B C D2013-01-03 -0.861849 -2.104569 -0.494929 1.0718042013-01-04 0.721555 -0.706771 -1.039575 0.2718602013-01-01 0.469112 -0.282863 -1.509059 -1.1356322013-01-02 1.212112 -0.173215 0.119209 -1.0442362013-01-06 -0.673690 0.113648 -1.478427 0.5249882013-01-05 -0.424972 0.567020 0.276232 -1.087401# End www.jb51.cc选择器
注释: 标准Python / Numpy表达式可以完成这些互动工作,但在生产代码中,我们推荐使用优化的pandas数据访问方法,.at,.iat,.loc,.iloc 和 .ix.
参阅索引文档 索引和选择数据 and 多索引/高级索引
读取
选择单列,这会产生一个序列,等价df.A
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [23]: df['A']Out[23]: 2013-01-01 0.4691122013-01-02 1.2121122013-01-03 -0.8618492013-01-04 0.7215552013-01-05 -0.4249722013-01-06 -0.673690Freq: D,name: A,dtype: float64# End www.jb51.cc
使用[]选择行片断
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [24]: df[0:3]Out[24]: A B C D2013-01-01 0.469112 -0.282863 -1.509059 -1.1356322013-01-02 1.212112 -0.173215 0.119209 -1.0442362013-01-03 -0.861849 -2.104569 -0.494929 1.071804 In [25]: df['20130102':'20130104']Out[25]: A B C D2013-01-02 1.212112 -0.173215 0.119209 -1.0442362013-01-03 -0.861849 -2.104569 -0.494929 1.0718042013-01-04 0.721555 -0.706771 -1.039575 0.271860# End www.jb51.cc使用标签选择
更多信息请参阅按标签选择
使用标签获取横截面
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [26]: df.loc[dates[0]]Out[26]: A 0.469112B -0.282863C -1.509059D -1.135632name: 2013-01-01 00:00:00,dtype: float64# End www.jb51.cc使用标签选择多轴
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [27]: df.loc[:,['A','B']]Out[27]: A B2013-01-01 0.469112 -0.2828632013-01-02 1.212112 -0.1732152013-01-03 -0.861849 -2.1045692013-01-04 0.721555 -0.7067712013-01-05 -0.424972 0.5670202013-01-06 -0.673690 0.113648# End www.jb51.cc
显示标签切片,包含两个端点
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [28]: df.loc['20130102':'20130104','B']]Out[28]: A B2013-01-02 1.212112 -0.1732152013-01-03 -0.861849 -2.1045692013-01-04 0.721555 -0.706771# End www.jb51.cc降低返回对象维度
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [29]: df.loc['20130102','B']]Out[29]: A 1.212112B -0.173215name: 2013-01-02 00:00:00,dtype: float64# End www.jb51.cc获取标量值
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [30]: df.loc[dates[0],'A']Out[30]: 0.46911229990718628# End www.jb51.cc快速访问并获取标量数据 (等价上面的方法)
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [31]: df.at[dates[0],'A']Out[31]: 0.46911229990718628# End www.jb51.cc按位置选择
更多信息请参阅按位置参阅
传递整数选择位置
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [32]: df.iloc[3]Out[32]: A 0.721555B -0.706771C -1.039575D 0.271860name: 2013-01-04 00:00:00,dtype: float64# End www.jb51.cc使用整数片断,效果类似numpy/python
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [33]: df.iloc[3:5,0:2]Out[33]: A B2013-01-04 0.721555 -0.7067712013-01-05 -0.424972 0.567020# End www.jb51.cc使用整数偏移定位列表,效果类似 numpy/python 样式
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [34]: df.iloc[[1,2,4],[0,2]]Out[34]: A C2013-01-02 1.212112 0.1192092013-01-03 -0.861849 -0.4949292013-01-05 -0.424972 0.276232# End www.jb51.cc显式行切片
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [35]: df.iloc[1:3,:]Out[35]: A B C D2013-01-02 1.212112 -0.173215 0.119209 -1.0442362013-01-03 -0.861849 -2.104569 -0.494929 1.071804# End www.jb51.cc显式列切片
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [36]: df.iloc[:,1:3]Out[36]: B C2013-01-01 -0.282863 -1.5090592013-01-02 -0.173215 0.1192092013-01-03 -2.104569 -0.4949292013-01-04 -0.706771 -1.0395752013-01-05 0.567020 0.2762322013-01-06 0.113648 -1.478427# End www.jb51.cc显式获取一个值
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [37]: df.iloc[1,1]Out[37]: -0.17321464905330861# End www.jb51.cc
快速访问一个标量（等同上个方法）
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [38]: df.iat[1,1]Out[38]: -0.17321464905330861# End www.jb51.cc使用单个列的值选择数据.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [39]: df[df.A > 0]Out[39]: A B C D2013-01-01 0.469112 -0.282863 -1.509059 -1.1356322013-01-02 1.212112 -0.173215 0.119209 -1.0442362013-01-04 0.721555 -0.706771 -1.039575 0.271860# End www.jb51.ccwhere *** 作.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [40]: df[df > 0]Out[40]: A B C D2013-01-01 0.469112 NaN NaN NaN2013-01-02 1.212112 NaN 0.119209 NaN2013-01-03 NaN NaN NaN 1.0718042013-01-04 0.721555 NaN NaN 0.2718602013-01-05 NaN 0.567020 0.276232 NaN2013-01-06 NaN 0.113648 NaN 0.524988# End www.jb51.cc
使用 isin() 筛选：
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [41]: df2 = df.copy()In [42]: df2['E']=['one','one','two','three','four','three'] In [43]: df2Out[43]: A B C D E2013-01-01 0.469112 -0.282863 -1.509059 -1.135632 one2013-01-02 1.212112 -0.173215 0.119209 -1.044236 one2013-01-03 -0.861849 -2.104569 -0.494929 1.071804 two2013-01-04 0.721555 -0.706771 -1.039575 0.271860 three2013-01-05 -0.424972 0.567020 0.276232 -1.087401 four2013-01-06 -0.673690 0.113648 -1.478427 0.524988 three In [44]: df2[df2['E'].isin(['two','four'])]Out[44]: A B C D E2013-01-03 -0.861849 -2.104569 -0.494929 1.071804 two2013-01-05 -0.424972 0.567020 0.276232 -1.087401 four# End www.jb51.cc赋值一个新列，通过索引自动对齐数据
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [45]: s1 = pd.SerIEs([1,4,6],index=pd.date_range('20130102',periods=6))In [46]: s1Out[46]: 2013-01-02 12013-01-03 22013-01-04 32013-01-05 42013-01-06 52013-01-07 6Freq: D,dtype: int64 In [47]: df['F'] = s1# End www.jb51.cc按标签赋值
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [48]: df.at[dates[0],'A'] = 0# End www.jb51.cc按位置赋值
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [49]: df.iat[0,1] = 0# End www.jb51.cc通过numpy数组分配赋值
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [50]: df.loc[:,'D'] = np.array([5] * len(df))# End www.jb51.cc之前的 *** 作结果
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [51]: dfOut[51]: A B C D F2013-01-01 0.000000 0.000000 -1.509059 5 NaN2013-01-02 1.212112 -0.173215 0.119209 5 12013-01-03 -0.861849 -2.104569 -0.494929 5 22013-01-04 0.721555 -0.706771 -1.039575 5 32013-01-05 -0.424972 0.567020 0.276232 5 42013-01-06 -0.673690 0.113648 -1.478427 5 5# End www.jb51.ccwhere *** 作赋值.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [52]: df2 = df.copy()In [53]: df2[df2 > 0] = -df2In [54]: df2Out[54]: A B C D F2013-01-01 0.000000 0.000000 -1.509059 -5 NaN2013-01-02 -1.212112 -0.173215 -0.119209 -5 -12013-01-03 -0.861849 -2.104569 -0.494929 -5 -22013-01-04 -0.721555 -0.706771 -1.039575 -5 -32013-01-05 -0.424972 -0.567020 -0.276232 -5 -42013-01-06 -0.673690 -0.113648 -1.478427 -5 -5# End www.jb51.cc
丢失的数据
pandas主要使用np.nan替换丢失的数据. 默认情况下它并不包含在计算中. 请参阅 Missing Data section
重建索引允许更改/添加/删除指定轴索引,并返回数据副本.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [55]: df1 = df.reindex(index=dates[0:4],columns=List(df.columns) + ['E'])In [56]: df1.loc[dates[0]:dates[1],'E'] = 1In [57]: df1Out[57]: A B C D F E2013-01-01 0.000000 0.000000 -1.509059 5 NaN 12013-01-02 1.212112 -0.173215 0.119209 5 1 12013-01-03 -0.861849 -2.104569 -0.494929 5 2 NaN2013-01-04 0.721555 -0.706771 -1.039575 5 3 NaN# End www.jb51.cc删除任何有丢失数据的行.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [58]: df1.dropna(how='any')Out[58]: A B C D F E2013-01-02 1.212112 -0.173215 0.119209 5 1 1# End www.jb51.cc填充丢失数据
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [59]: df1.fillna(value=5)Out[59]: A B C D F E2013-01-01 0.000000 0.000000 -1.509059 5 5 12013-01-02 1.212112 -0.173215 0.119209 5 1 12013-01-03 -0.861849 -2.104569 -0.494929 5 2 52013-01-04 0.721555 -0.706771 -1.039575 5 3 5# End www.jb51.cc获取值是否nan的布尔标记
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [60]: pd.isnull(df1)Out[60]: A B C D F E2013-01-01 False False False False True False2013-01-02 False False False False False False2013-01-03 False False False False False True2013-01-04 False False False False False True# End www.jb51.cc参阅二元运算基础
统计计算时一般不包括丢失的数据
执行描述性统计
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [61]: df.mean()Out[61]: A -0.004474B -0.383981C -0.687758D 5.000000F 3.000000dtype: float64# End www.jb51.cc在其他轴做相同的运算
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [62]: df.mean(1)Out[62]: 2013-01-01 0.8727352013-01-02 1.4316212013-01-03 0.7077312013-01-04 1.3950422013-01-05 1.8836562013-01-06 1.592306Freq: D,dtype: float64# End www.jb51.cc用于运算的对象有不同的维度并需要对齐.除此之外，pandas会自动沿着指定维度计算.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [63]: s = pd.SerIEs([1,8],index=dates).shift(2)In [64]: sOut[64]: 2013-01-01 NaN2013-01-02 NaN2013-01-03 12013-01-04 32013-01-05 52013-01-06 NaNFreq: D,dtype: float64 In [65]: df.sub(s,axis='index')Out[65]: A B C D F2013-01-01 NaN NaN NaN NaN NaN2013-01-02 NaN NaN NaN NaN NaN2013-01-03 -1.861849 -3.104569 -1.494929 4 12013-01-04 -2.278445 -3.706771 -4.039575 2 02013-01-05 -5.424972 -4.432980 -4.723768 0 -12013-01-06 NaN NaN NaN NaN NaNApply# End www.jb51.cc在数据上使用函数
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [66]: df.apply(np.cumsum)Out[66]: A B C D F2013-01-01 0.000000 0.000000 -1.509059 5 NaN2013-01-02 1.212112 -0.173215 -1.389850 10 12013-01-03 0.350263 -2.277784 -1.884779 15 32013-01-04 1.071818 -2.984555 -2.924354 20 62013-01-05 0.646846 -2.417535 -2.648122 25 102013-01-06 -0.026844 -2.303886 -4.126549 30 15 In [67]: df.apply(lambda x: x.max() - x.min())Out[67]: A 2.073961B 2.671590C 1.785291D 0.000000F 4.000000dtype: float64# End www.jb51.cc请参阅 直方图和离散化
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [68]: s = pd.SerIEs(np.random.randint(0,7,size=10))In [69]: sOut[69]: 0 41 22 13 24 65 46 47 68 49 4dtype: int32 In [70]: s.value_counts()Out[70]: 4 56 22 21 1dtype: int64# End www.jb51.cc序列可以使用一些字符串处理方法很轻易 *** 作数据组中的每个元素,比如以下代码片断。 注意字符匹配方法默认情况下通常使用正则表达式（并且大多数时候都如此）. 更多信息请参阅字符串向量方法.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [71]: s = pd.SerIEs(['A','B','C','Aaba','Baca','CABA','dog','cat'])In [72]: s.str.lower()Out[72]: 0 a1 b2 c3 aaba4 baca5 NaN6 caba7 dog8 catdtype: object# End www.jb51.cc合并
连接
pandas提供各种工具以简便合并序列,数据桢,和组合对象,在连接/合并类型 *** 作中使用多种类型索引和相关数学函数.
请参阅合并部分
把pandas对象连接到一起
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [73]: df = pd.DataFrame(np.random.randn(10,4))In [74]: dfOut[74]: 0 1 2 30 -0.548702 1.467327 -1.015962 -0.4830751 1.637550 -1.217659 -0.291519 -1.7455052 -0.263952 0.991460 -0.919069 0.2660463 -0.709661 1.669052 1.037882 -1.7057754 -0.919854 -0.042379 1.247642 -0.0099205 0.290213 0.495767 0.362949 1.5481066 -1.131345 -0.089329 0.337863 -0.9458677 -0.932132 1.956030 0.017587 -0.0166928 -0.575247 0.254161 -1.143704 0.2158979 1.193555 -0.077118 -0.408530 -0.862495 # break it into pIEcesIn [75]: pIEces = [df[:3],df[3:7],df[7:]]In [76]: pd.concat(pIEces)Out[76]: 0 1 2 30 -0.548702 1.467327 -1.015962 -0.4830751 1.637550 -1.217659 -0.291519 -1.7455052 -0.263952 0.991460 -0.919069 0.2660463 -0.709661 1.669052 1.037882 -1.7057754 -0.919854 -0.042379 1.247642 -0.0099205 0.290213 0.495767 0.362949 1.5481066 -1.131345 -0.089329 0.337863 -0.9458677 -0.932132 1.956030 0.017587 -0.0166928 -0.575247 0.254161 -1.143704 0.2158979 1.193555 -0.077118 -0.408530 -0.862495# End www.jb51.cc连接
sql样式合并. 请参阅 数据库style联接
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [77]: left = pd.DataFrame({'key': ['foo','foo'],'lval': [1,2]})In [78]: right = pd.DataFrame({'key': ['foo','rval': [4,5]})In [79]: leftOut[79]: key lval0 foo 11 foo 2 In [80]: rightOut[80]: key rval0 foo 41 foo 5 In [81]: pd.merge(left,right,on='key')Out[81]: key lval rval0 foo 1 41 foo 1 52 foo 2 43 foo 2 5# End www.jb51.cc添加
添加行到数据增. 参阅 添加
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [82]: df = pd.DataFrame(np.random.randn(8,columns=['A','D'])In [83]: dfOut[83]: A B C D0 1.346061 1.511763 1.627081 -0.9905821 -0.441652 1.211526 0.268520 0.0245802 -1.577585 0.396823 -0.105381 -0.5325323 1.453749 1.208843 -0.080952 -0.2646104 -0.727965 -0.589346 0.339969 -0.6932055 -0.339355 0.593616 0.884345 1.5914316 0.141809 0.220390 0.435589 0.1924517 -0.096701 0.803351 1.715071 -0.708758 In [84]: s = df.iloc[3]In [85]: df.append(s,ignore_index=True)Out[85]: A B C D0 1.346061 1.511763 1.627081 -0.9905821 -0.441652 1.211526 0.268520 0.0245802 -1.577585 0.396823 -0.105381 -0.5325323 1.453749 1.208843 -0.080952 -0.2646104 -0.727965 -0.589346 0.339969 -0.6932055 -0.339355 0.593616 0.884345 1.5914316 0.141809 0.220390 0.435589 0.1924517 -0.096701 0.803351 1.715071 -0.7087588 1.453749 1.208843 -0.080952 -0.264610# End www.jb51.cc分组
对于“group by”指的是以下一个或多个处理
将数据按某些标准分割为不同的组
在每个独立组上应用函数
组合结果为一个数据结构
请参阅 分组部分
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [86]: df = pd.DataFrame({'A' : ['foo','bar','foo',....: 'foo',....: 'B' : ['one',....: 'two','three'],....: 'C' : np.random.randn(8),....: 'D' : np.random.randn(8)}) ....: In [87]: dfOut[87]: A B C D0 foo one -1.202872 -0.0552241 bar one -1.814470 2.3959852 foo two 1.018601 1.5528253 bar three -0.595447 0.1665994 foo two 1.395433 0.0476095 bar two -0.392670 -0.1364736 foo one 0.007207 -0.5617577 foo three 1.928123 -1.623033# End www.jb51.cc分组然后应用函数统计总和存放到结果组
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [88]: df.groupby('A').sum()Out[88]: C DA bar -2.802588 2.42611foo 3.146492 -0.63958# End www.jb51.cc按多列分组为层次索引,然后应用函数
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [89]: df.groupby(['A','B']).sum()Out[89]: C DA B bar one -1.814470 2.395985 three -0.595447 0.166599 two -0.392670 -0.136473foo one -1.195665 -0.616981 three 1.928123 -1.623033 two 2.414034 1.600434# End www.jb51.cc请参阅章节 分层索引 和 重塑.
堆叠
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [90]: tuples = List(zip(*[['bar','baz',....: 'foo','qux','qux'],....: ['one',....: 'one','two']])) ....: In [91]: index = pd.MultiIndex.from_tuples(tuples,names=['first','second'])In [92]: df = pd.DataFrame(np.random.randn(8,2),index=index,'B'])In [93]: df2 = df[:4]In [94]: df2Out[94]: A Bfirst second bar one 0.029399 -0.542108 two 0.282696 -0.087302baz one -1.575170 1.771208 two 0.816482 1.100230# End www.jb51.cc堆叠 函数 “压缩” 数据桢的列一个级别.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [95]: stacked = df2.stack()In [96]: stackedOut[96]: first second bar one A 0.029399 B -0.542108 two A 0.282696 B -0.087302baz one A -1.575170 B 1.771208 two A 0.816482 B 1.100230dtype: float64# End www.jb51.cc被“堆叠”数据桢或序列(有多个索引作为索引),其堆叠的反向 *** 作是未堆栈,上面的数据默认反堆叠到上一级别:
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [97]: stacked.unstack()Out[97]: A Bfirst second bar one 0.029399 -0.542108 two 0.282696 -0.087302baz one -1.575170 1.771208 two 0.816482 1.100230 In [98]: stacked.unstack(1)Out[98]: second one twofirst bar A 0.029399 0.282696 B -0.542108 -0.087302baz A -1.575170 0.816482 B 1.771208 1.100230 In [99]: stacked.unstack(0)Out[99]: first bar bazsecond one A 0.029399 -1.575170 B -0.542108 1.771208two A 0.282696 0.816482 B -0.087302 1.100230# End www.jb51.cc
数据透视表
查看数据透视表.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [100]: df = pd.DataFrame({'A' : ['one','three'] * 3,.....: 'B' : ['A','C'] * 4,.....: 'C' : ['foo','bar'] * 2,.....: 'D' : np.random.randn(12),.....: 'E' : np.random.randn(12)}) .....: In [101]: dfOut[101]: A B C D E0 one A foo 1.418757 -0.1796661 one B foo -1.879024 1.2918362 two C foo 0.536826 -0.0096143 three A bar 1.006160 0.3921494 one B bar -0.029716 0.2645995 one C bar -1.146178 -0.0574096 two A foo 0.100900 -1.4256387 three B foo -1.035018 1.0240988 one C foo 0.314665 -0.1060629 one A bar -0.773723 1.82437510 two B bar -1.170653 0.59597411 three C bar 0.648740 1.167115# End www.jb51.cc我们可以从此数据非常容易的产生数据透视表:
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [102]: pd.pivot_table(df,values='D',index=['A','B'],columns=['C'])Out[102]: C bar fooA B one A -0.773723 1.418757 B -0.029716 -1.879024 C -1.146178 0.314665three A 1.006160 NaN B NaN -1.035018 C 0.648740 NaNtwo A NaN 0.100900 B -1.170653 NaN C NaN 0.536826# End www.jb51.ccpandas有易用,强大且高效的函数用于高频数据重采样转换 *** 作(例如,转换秒数据到5分钟数据),这是很普遍的情况，但并不局限于金融应用,请参阅时间序列章节
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [103]: rng = pd.date_range('1/1/2012',periods=100,freq='S')In [104]: ts = pd.SerIEs(np.random.randint(0,500,len(rng)),index=rng)In [105]: ts.resample('5Min',how='sum')Out[105]: 2012-01-01 25083Freq: 5T,dtype: int32# End www.jb51.cc时区表示
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [106]: rng = pd.date_range('3/6/2012 00:00',periods=5,freq='D')In [107]: ts = pd.SerIEs(np.random.randn(len(rng)),rng)In [108]: tsOut[108]: 2012-03-06 0.4640002012-03-07 0.2273712012-03-08 -0.4969222012-03-09 0.3063892012-03-10 -2.290613Freq: D,dtype: float64 In [109]: ts_utc = ts.tz_localize('UTC')In [110]: ts_utcOut[110]: 2012-03-06 00:00:00+00:00 0.4640002012-03-07 00:00:00+00:00 0.2273712012-03-08 00:00:00+00:00 -0.4969222012-03-09 00:00:00+00:00 0.3063892012-03-10 00:00:00+00:00 -2.290613Freq: D,dtype: float64# End www.jb51.cc转换到其它时区
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [111]: ts_utc.tz_convert('US/Eastern')Out[111]: 2012-03-05 19:00:00-05:00 0.4640002012-03-06 19:00:00-05:00 0.2273712012-03-07 19:00:00-05:00 -0.4969222012-03-08 19:00:00-05:00 0.3063892012-03-09 19:00:00-05:00 -2.290613Freq: D,dtype: float64# End www.jb51.cc
转换不同的时间跨度
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [112]: rng = pd.date_range('1/1/2012',freq='M')In [113]: ts = pd.SerIEs(np.random.randn(len(rng)),index=rng)In [114]: tsOut[114]: 2012-01-31 -1.1346232012-02-29 -1.5618192012-03-31 -0.2608382012-04-30 0.2819572012-05-31 1.523962Freq: M,dtype: float64 In [115]: ps = ts.to_period()In [116]: psOut[116]: 2012-01 -1.1346232012-02 -1.5618192012-03 -0.2608382012-04 0.2819572012-05 1.523962Freq: M,dtype: float64 In [117]: ps.to_timestamp()Out[117]: 2012-01-01 -1.1346232012-02-01 -1.5618192012-03-01 -0.2608382012-04-01 0.2819572012-05-01 1.523962Freq: MS,dtype: float64# End www.jb51.cc
转换时段并且使用一些运算函数,下例中,我们转换年报11月到季度结束每日上午9点数据
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [118]: prng = pd.period_range('1990Q1','2000Q4',freq='Q-NOV')In [119]: ts = pd.SerIEs(np.random.randn(len(prng)),prng)In [120]: ts.index = (prng.asfreq('M','e') + 1).asfreq('H','s') + 9In [121]: ts.head()Out[121]: 1990-03-01 09:00 -0.9029371990-06-01 09:00 0.0681591990-09-01 09:00 -0.0578731990-12-01 09:00 -0.3682041991-03-01 09:00 -1.144073Freq: H,dtype: float64# End www.jb51.cc自版本0.15起,pandas可以在数据桢中包含分类. 完整的文档,请查看分类介绍 and the api文档.
In [122]: df = pd.DataFrame({"ID":[1,"raw_grade":['a','b','a','e']})
转换原始类别为分类数据类型.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [123]: df["grade"] = df["raw_grade"].astype("category")In [124]: df["grade"]Out[124]: 0 a1 b2 b3 a4 a5 ename: grade,dtype: categoryCategorIEs (3,object): [a,b,e]# End www.jb51.cc重命令分类为更有意义的名称 (分配到SerIEs.cat.categorIEs对应位置!)
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [125]: df["grade"].cat.categorIEs = ["very good","good","very bad"]# End www.jb51.cc重排顺分类,同时添加缺少的分类(序列 .cat方法下返回新默认序列)
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [126]: df["grade"] = df["grade"].cat.set_categorIEs(["very bad","bad","medium","very good"])In [127]: df["grade"]Out[127]: 0 very good1 good2 good3 very good4 very good5 very badname: grade,dtype: categoryCategorIEs (5,object): [very bad,bad,medium,good,very good]# End www.jb51.cc排列分类中的顺序,不是按词汇排列.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [128]: df.sort("grade")Out[128]: ID raw_grade grade5 6 e very bad1 2 b good2 3 b good0 1 a very good3 4 a very good4 5 a very good# End www.jb51.cc类别列分组,并且也显示空类别.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [129]: df.groupby("grade").size()Out[129]: gradevery bad 1bad NaNmedium NaNgood 2very good 3dtype: float64# End www.jb51.cc绘图文档.
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [130]: ts = pd.SerIEs(np.random.randn(1000),index=pd.date_range('1/1/2000',periods=1000))In [131]: ts = ts.cumsum()In [132]: ts.plot()Out[132]:# End www.jb51.cc在数据桢中,可以很方便的绘制带标签列:
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [133]: df = pd.DataFrame(np.random.randn(1000,index=ts.index,.....: columns=['A','D']) .....: In [134]: df = df.cumsum()In [135]: plt.figure(); df.plot(); plt.legend(loc='best')Out[135]:# End www.jb51.ccCSV
写入csv文件
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [136]: df.to_csv('foo.csv')# End www.jb51.cc读取csv文件
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [137]: pd.read_csv('foo.csv')Out[137]: Unnamed: 0 A B C D0 2000-01-01 0.266457 -0.399641 -0.219582 1.1868601 2000-01-02 -1.170732 -0.345873 1.653061 -0.2829532 2000-01-03 -1.734933 0.530468 2.060811 -0.5155363 2000-01-04 -1.555121 1.452620 0.239859 -1.1568964 2000-01-05 0.578117 0.511371 0.103552 -2.4282025 2000-01-06 0.478344 0.449933 -0.741620 -1.9624096 2000-01-07 1.235339 -0.091757 -1.543861 -1.084753.. ... ... ... ... ...993 2002-09-20 -10.628548 -9.153563 -7.883146 28.313940994 2002-09-21 -10.390377 -8.727491 -6.399645 30.914107995 2002-09-22 -8.985362 -8.485624 -4.669462 31.367740996 2002-09-23 -9.558560 -8.781216 -4.499815 30.518439997 2002-09-24 -9.902058 -9.340490 -4.386639 30.105593998 2002-09-25 -10.216020 -9.480682 -3.933802 29.758560999 2002-09-26 -11.856774 -10.671012 -3.216025 29.369368 [1000 rows x 5 columns]# End www.jb51.ccHDF5
读写HDF存储
写入HDF5存储
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [138]: df.to_hdf('foo.h5','df')# End www.jb51.cc读取HDF5存储
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [139]: pd.read_hdf('foo.h5','df')Out[139]: A B C D2000-01-01 0.266457 -0.399641 -0.219582 1.1868602000-01-02 -1.170732 -0.345873 1.653061 -0.2829532000-01-03 -1.734933 0.530468 2.060811 -0.5155362000-01-04 -1.555121 1.452620 0.239859 -1.1568962000-01-05 0.578117 0.511371 0.103552 -2.4282022000-01-06 0.478344 0.449933 -0.741620 -1.9624092000-01-07 1.235339 -0.091757 -1.543861 -1.084753... ... ... ... ...2002-09-20 -10.628548 -9.153563 -7.883146 28.3139402002-09-21 -10.390377 -8.727491 -6.399645 30.9141072002-09-22 -8.985362 -8.485624 -4.669462 31.3677402002-09-23 -9.558560 -8.781216 -4.499815 30.5184392002-09-24 -9.902058 -9.340490 -4.386639 30.1055932002-09-25 -10.216020 -9.480682 -3.933802 29.7585602002-09-26 -11.856774 -10.671012 -3.216025 29.369368 [1000 rows x 4 columns]# End www.jb51.ccExcel
读写MS Excel
写入excel文件
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [140]: df.to_excel('foo.xlsx',sheet_name='Sheet1')# End www.jb51.cc读取excel文件
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc In [141]: pd.read_excel('foo.xlsx','Sheet1',index_col=None,na_values=['NA'])Out[141]: A B C D2000-01-01 0.266457 -0.399641 -0.219582 1.1868602000-01-02 -1.170732 -0.345873 1.653061 -0.2829532000-01-03 -1.734933 0.530468 2.060811 -0.5155362000-01-04 -1.555121 1.452620 0.239859 -1.1568962000-01-05 0.578117 0.511371 0.103552 -2.4282022000-01-06 0.478344 0.449933 -0.741620 -1.9624092000-01-07 1.235339 -0.091757 -1.543861 -1.084753... ... ... ... ...2002-09-20 -10.628548 -9.153563 -7.883146 28.3139402002-09-21 -10.390377 -8.727491 -6.399645 30.9141072002-09-22 -8.985362 -8.485624 -4.669462 31.3677402002-09-23 -9.558560 -8.781216 -4.499815 30.5184392002-09-24 -9.902058 -9.340490 -4.386639 30.1055932002-09-25 -10.216020 -9.480682 -3.933802 29.7585602002-09-26 -11.856774 -10.671012 -3.216025 29.369368 [1000 rows x 4 columns]# End www.jb51.cc陷阱
如果尝试这样 *** 作可能会看到像这样的异常:
# @param 十分钟搞定pandas# @author 内存溢出 jb51.cc|www.www.jb51.cc >>> if pd.SerIEs([False,True,False]): print("I was true")Traceback ...ValueError: The truth value of an array is ambiguous. Use a.empty,a.any() or a.all().# End www.jb51.cc以上是内存溢出为你收集整理的Python搞定pandas入门实例全部内容，希望文章能够帮你解决Python搞定pandas入门实例所遇到的程序开发问题。
如果觉得内存溢出网站内容还不错，欢迎将内存溢出网站推荐给程序员好友。
欢迎分享，转载请注明来源：内存溢出
微信扫一扫
支付宝扫一扫
评论列表（0条）