第一次接触pandas时,我产生了黑人问号,大熊猫???,什么鬼,但是我熟悉pandas这个库之后我感觉这个库真的很神奇
下面是我对python中pandas的方法介绍
#!/usr/bin/python
# -*- coding:utf-8 -*-
import numpy as np
import pandas as pd
import random
s_data = pd.Series([1, 3, 5, 7, np.NaN, 9, 11]) # pandas中生产序列的函数,类似于我们平时说的数组
print s_data
print "------------------------------------------------"
#以20170220为基点向后生产时间点
dates = pd.date_range('20170220',periods=10)
#DataFrame生成函数,行索引为时间点,列索引为ABCD
data = pd.DataFrame(np.random.randn(10,6),index=dates,columns=list('ABCDEF'))#columns=list('ABCDEF')行数据 index=dates 列数据 np.random.randn(10,6)数据源
print data
print data.shape #获取几行几列
print data.values #获取数据源
print "-----------------------------------------------"
# 设计一个字典
d_data = {'A':[random.randint(0,100) for _ in range(5)],'B':pd.Timestamp('20170220'),'C':[random.randint(0,100) for _ in range(5)],'D':np.arange(5)}
print d_data #生成的原数据
#使用字典生成一个DataFrame
df_data = pd.DataFrame(d_data)
print df_data
# #DataFrame中每一列的类型
print df_data.dtypes
# #打印A列
print df_data.A
# #打印B列
print df_data.B
# #B列的类型
print type(df_data.B)
#输出DataFrame头部数据,默认为前5行
print data.head()
#输出输出DataFrame第一行数据
print data.head(1)
#输出DataFrame尾部数据,默认为后5行
print data.tail()
#输出输出DataFrame最后一行数据
print data.tail(1)
#输出行索引
print data.index
#输出列索引
print data.columns
#输出DataFrame数据值
print data.values
#输出DataFrame详细信息
print data.describe()
#转置 行和列索引调换
print data.T
#输出维度信息
print data.shape
#将列索引排序
print data.sort_index(axis = 1)
#将列索引排序,降序排列
print data.sort_index(axis = 1,ascending=False)
#将行索引排序,降序排列
print data.sort_index(axis = 0,ascending=False)
#按照A列的值进行升序排列
print data.sort_values(by='A')
#按照A列的值进行降低排列
print data.sort_values(by='A',ascending=False)
#输出A列
print data.A
#输出A列
print data['A']
#输出3,4行
print data[2:4]
#输出3,4行
print data['20170222':'20170223']
#输出3,4行
print data.loc['20170222':'20170223']
#输出3,4行
print data.iloc[2:4]
#输出B,C两列
print data.loc[:,['B','C']]
#输出A列中大于0的行
print data[data.A > 0]
#输出大于0的数据,小于等于0的用NaN补位
print data[data > 0]
#拷贝data
data2 = data.copy()
print data2
tag = ['a'] * 2 + ['b'] * 2 + ['c'] * 2+['d']*2+['f']*2
#在data2中增加TAG列用tag赋值
print tag
data2['TAG'] = tag
print data2
#打印TAG列中为a,c的行
print data2[data2.TAG.isin(['a','c'])]
dates = pd.date_range('20170220',periods = 6)
df = pd.DataFrame(np.random.randn(6,4) , index = dates , columns = list('ABCD'))
#重定义索引,并添加E列
dfl = df.reindex(index = dates[0:4],columns = list(df.columns)+['E'])
print dfl
#将E列中的2,3行赋值为2
dfl.loc[dates[1:3],'E'] = 2
print dfl
#去掉存在NaN元素的行
print dfl.dropna()
#将NaN元素赋值为5
print dfl.fillna(5)
#判断每个元素是否为NaN
print pd.isnull(dfl)
#求列平均值
print dfl.mean()
#对每列进行累加
print dfl.cumsum()
# #针对行求平均值
print dfl.mean(axis=1)
#生成序列并向右平移两位
s = pd.Series([1,3,5,np.nan,6,8],index = dates).shift(2)
print s
#df与s做减法运算
print df.sub(s,axis = 'index')
#每列进行累加运算
print df.apply(np.cumsum)
#每列的最大值减去最小值
print df.apply(lambda x: x.max() - x.min())
#统计序列中每个元素出现的次数
print s.value_counts()
#返回出现次数最多的元素
print s.mode()
df = pd.DataFrame(np.random.randn(10,4) , columns = list('ABCD'))
print df
#合并函数
dfl = pd.concat([df.iloc[:3],df.iloc[3:7],df.iloc[7:]])
print dfl
#判断两个DataFrame中元素是否相等
print df == dfl
#根据A列的索引求和
print df.groupby('A').sum()
print
#先根据A列的索引,在根据B列的索引求和
print df.groupby(['A','B']).sum()
print
#先根据B列的索引,在根据A列的索引求和
print df.groupby(['B','A']).sum()
控制台输出
0 1.0
1 3.0
2 5.0
3 7.0
4 NaN
5 9.0
6 11.0
dtype: float64
------------------------------------------------
A B C D E F
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704
2017-02-21 -1.018478 -1.706017 -1.158823 -1.564300 1.201966 -0.405304
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
2017-02-24 2.241062 -1.671190 0.529457 -0.397618 0.266720 -0.610356
2017-02-25 -1.375601 0.511432 -0.387201 -0.516504 -0.843040 1.971008
2017-02-26 -0.870253 -0.532562 -2.070748 0.556197 -1.590036 0.652505
2017-02-27 0.671369 0.111791 -0.994774 -0.345075 -0.043722 0.639117
2017-02-28 -1.279547 0.054616 -1.310744 -0.574317 0.254414 -0.844659
2017-03-01 -0.906736 -0.832826 -1.260035 0.207416 1.911902 1.351750
(10, 6)
[[ 0.4807726 -0.36825697 0.28071075 0.42824289 2.48190258 -0.69670352]
[-1.018478 -1.70601653 -1.15882275 -1.5642997 1.20196563 -0.40530392]
[-0.18233418 -0.51848992 -0.0159502 0.58248787 0.30715672 -1.52461268]
[ 0.58256491 -0.51866879 -0.42445884 -0.54920306 0.84198925 1.79636911]
[ 2.24106161 -1.6711903 0.52945692 -0.39761815 0.26672011 -0.61035606]
[-1.37560112 0.51143187 -0.38720069 -0.51650385 -0.84303976 1.9710077 ]
[-0.87025344 -0.53256244 -2.07074771 0.55619692 -1.59003606 0.65250461]
[ 0.67136909 0.11179128 -0.99477434 -0.34507527 -0.04372248 0.63911702]
[-1.27954652 0.05461646 -1.31074379 -0.57431657 0.25441413 -0.84465887]
[-0.90673633 -0.83282624 -1.26003525 0.207416 1.91190216 1.35175013]]
-----------------------------------------------
设计一个字典
{'A': [78, 4, 75, 96, 22], 'C': [60, 50, 31, 78, 0], 'B': Timestamp('2017-02-20 00:00:00'), 'D': array([0, 1, 2, 3, 4])}
使用字典生成一个DataFrame
A B C D
0 78 2017-02-20 60 0
1 4 2017-02-20 50 1
2 75 2017-02-20 31 2
3 96 2017-02-20 78 3
4 22 2017-02-20 0 4
DataFrame中每一列的类型
A int64
B datetime64[ns]
C int64
D int32
dtype: object
打印A列
0 78
1 4
2 75
3 96
4 22
Name: A, dtype: int64
打印B列
0 2017-02-20
1 2017-02-20
2 2017-02-20
3 2017-02-20
4 2017-02-20
Name: B, dtype: datetime64[ns]
B列的类型
<class 'pandas.core.series.Series'>
输出DataFrame头部数据,默认为前5行
A B C D E F
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704
2017-02-21 -1.018478 -1.706017 -1.158823 -1.564300 1.201966 -0.405304
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
2017-02-24 2.241062 -1.671190 0.529457 -0.397618 0.266720 -0.610356
输出输出DataFrame第一行数据
A B C D E F
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704
输出DataFrame尾部数据,默认为后5行
A B C D E F
2017-02-25 -1.375601 0.511432 -0.387201 -0.516504 -0.843040 1.971008
2017-02-26 -0.870253 -0.532562 -2.070748 0.556197 -1.590036 0.652505
2017-02-27 0.671369 0.111791 -0.994774 -0.345075 -0.043722 0.639117
2017-02-28 -1.279547 0.054616 -1.310744 -0.574317 0.254414 -0.844659
2017-03-01 -0.906736 -0.832826 -1.260035 0.207416 1.911902 1.351750
输出输出DataFrame最后一行数据
A B C D E F
2017-03-01 -0.906736 -0.832826 -1.260035 0.207416 1.911902 1.35175
#输出行索引
DatetimeIndex(['2017-02-20', '2017-02-21', '2017-02-22', '2017-02-23',
'2017-02-24', '2017-02-25', '2017-02-26', '2017-02-27',
'2017-02-28', '2017-03-01'],
dtype='datetime64[ns]', freq='D')
#输出列索引
Index([u'A', u'B', u'C', u'D', u'E', u'F'], dtype='object')
#输出DataFrame数据值
[[ 0.4807726 -0.36825697 0.28071075 0.42824289 2.48190258 -0.69670352]
[-1.018478 -1.70601653 -1.15882275 -1.5642997 1.20196563 -0.40530392]
[-0.18233418 -0.51848992 -0.0159502 0.58248787 0.30715672 -1.52461268]
[ 0.58256491 -0.51866879 -0.42445884 -0.54920306 0.84198925 1.79636911]
[ 2.24106161 -1.6711903 0.52945692 -0.39761815 0.26672011 -0.61035606]
[-1.37560112 0.51143187 -0.38720069 -0.51650385 -0.84303976 1.9710077 ]
[-0.87025344 -0.53256244 -2.07074771 0.55619692 -1.59003606 0.65250461]
[ 0.67136909 0.11179128 -0.99477434 -0.34507527 -0.04372248 0.63911702]
[-1.27954652 0.05461646 -1.31074379 -0.57431657 0.25441413 -0.84465887]
[-0.90673633 -0.83282624 -1.26003525 0.207416 1.91190216 1.35175013]]
输出DataFrame详细信息
A B C D E F
count 10.000000 10.000000 10.000000 10.000000 10.000000 10.000000
mean -0.165718 -0.547017 -0.681257 -0.217267 0.478925 0.232911
std 1.152223 0.717931 0.814763 0.668785 1.208591 1.215223
min -1.375601 -1.706017 -2.070748 -1.564300 -1.590036 -1.524613
25% -0.990543 -0.757760 -1.234732 -0.541028 0.030812 -0.675117
50% -0.526294 -0.518579 -0.709617 -0.371347 0.286938 0.116907
75% 0.557117 -0.051102 -0.108763 0.373036 1.111972 1.176939
max 2.241062 0.511432 0.529457 0.582488 2.481903 1.971008
转置 行和列索引调换
2017-02-20 2017-02-21 2017-02-22 2017-02-23 2017-02-24 2017-02-25 \
A 0.480773 -1.018478 -0.182334 0.582565 2.241062 -1.375601
B -0.368257 -1.706017 -0.518490 -0.518669 -1.671190 0.511432
C 0.280711 -1.158823 -0.015950 -0.424459 0.529457 -0.387201
D 0.428243 -1.564300 0.582488 -0.549203 -0.397618 -0.516504
E 2.481903 1.201966 0.307157 0.841989 0.266720 -0.843040
F -0.696704 -0.405304 -1.524613 1.796369 -0.610356 1.971008
2017-02-26 2017-02-27 2017-02-28 2017-03-01
A -0.870253 0.671369 -1.279547 -0.906736
B -0.532562 0.111791 0.054616 -0.832826
C -2.070748 -0.994774 -1.310744 -1.260035
D 0.556197 -0.345075 -0.574317 0.207416
E -1.590036 -0.043722 0.254414 1.911902
F 0.652505 0.639117 -0.844659 1.351750
#输出维度信息
(10, 6)
将列索引排序
A B C D E F
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704
2017-02-21 -1.018478 -1.706017 -1.158823 -1.564300 1.201966 -0.405304
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
2017-02-24 2.241062 -1.671190 0.529457 -0.397618 0.266720 -0.610356
2017-02-25 -1.375601 0.511432 -0.387201 -0.516504 -0.843040 1.971008
2017-02-26 -0.870253 -0.532562 -2.070748 0.556197 -1.590036 0.652505
2017-02-27 0.671369 0.111791 -0.994774 -0.345075 -0.043722 0.639117
2017-02-28 -1.279547 0.054616 -1.310744 -0.574317 0.254414 -0.844659
2017-03-01 -0.906736 -0.832826 -1.260035 0.207416 1.911902 1.351750
将列索引排序,降序排列
F E D C B A
2017-02-20 -0.696704 2.481903 0.428243 0.280711 -0.368257 0.480773
2017-02-21 -0.405304 1.201966 -1.564300 -1.158823 -1.706017 -1.018478
2017-02-22 -1.524613 0.307157 0.582488 -0.015950 -0.518490 -0.182334
2017-02-23 1.796369 0.841989 -0.549203 -0.424459 -0.518669 0.582565
2017-02-24 -0.610356 0.266720 -0.397618 0.529457 -1.671190 2.241062
2017-02-25 1.971008 -0.843040 -0.516504 -0.387201 0.511432 -1.375601
2017-02-26 0.652505 -1.590036 0.556197 -2.070748 -0.532562 -0.870253
2017-02-27 0.639117 -0.043722 -0.345075 -0.994774 0.111791 0.671369
2017-02-28 -0.844659 0.254414 -0.574317 -1.310744 0.054616 -1.279547
2017-03-01 1.351750 1.911902 0.207416 -1.260035 -0.832826 -0.906736
#将行索引排序,降序排列
A B C D E F
2017-03-01 -0.906736 -0.832826 -1.260035 0.207416 1.911902 1.351750
2017-02-28 -1.279547 0.054616 -1.310744 -0.574317 0.254414 -0.844659
2017-02-27 0.671369 0.111791 -0.994774 -0.345075 -0.043722 0.639117
2017-02-26 -0.870253 -0.532562 -2.070748 0.556197 -1.590036 0.652505
2017-02-25 -1.375601 0.511432 -0.387201 -0.516504 -0.843040 1.971008
2017-02-24 2.241062 -1.671190 0.529457 -0.397618 0.266720 -0.610356
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-21 -1.018478 -1.706017 -1.158823 -1.564300 1.201966 -0.405304
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704
按照A列的值进行升序排列
A B C D E F
2017-02-25 -1.375601 0.511432 -0.387201 -0.516504 -0.843040 1.971008
2017-02-28 -1.279547 0.054616 -1.310744 -0.574317 0.254414 -0.844659
2017-02-21 -1.018478 -1.706017 -1.158823 -1.564300 1.201966 -0.405304
2017-03-01 -0.906736 -0.832826 -1.260035 0.207416 1.911902 1.351750
2017-02-26 -0.870253 -0.532562 -2.070748 0.556197 -1.590036 0.652505
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
2017-02-27 0.671369 0.111791 -0.994774 -0.345075 -0.043722 0.639117
2017-02-24 2.241062 -1.671190 0.529457 -0.397618 0.266720 -0.610356
按照A列的值进行降低排列
A B C D E F
2017-02-24 2.241062 -1.671190 0.529457 -0.397618 0.266720 -0.610356
2017-02-27 0.671369 0.111791 -0.994774 -0.345075 -0.043722 0.639117
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-26 -0.870253 -0.532562 -2.070748 0.556197 -1.590036 0.652505
2017-03-01 -0.906736 -0.832826 -1.260035 0.207416 1.911902 1.351750
2017-02-21 -1.018478 -1.706017 -1.158823 -1.564300 1.201966 -0.405304
2017-02-28 -1.279547 0.054616 -1.310744 -0.574317 0.254414 -0.844659
2017-02-25 -1.375601 0.511432 -0.387201 -0.516504 -0.843040 1.971008
输出A列
2017-02-20 0.480773
2017-02-21 -1.018478
2017-02-22 -0.182334
2017-02-23 0.582565
2017-02-24 2.241062
2017-02-25 -1.375601
2017-02-26 -0.870253
2017-02-27 0.671369
2017-02-28 -1.279547
2017-03-01 -0.906736
Freq: D, Name: A, dtype: float64
输出A列
2017-02-20 0.480773
2017-02-21 -1.018478
2017-02-22 -0.182334
2017-02-23 0.582565
2017-02-24 2.241062
2017-02-25 -1.375601
2017-02-26 -0.870253
2017-02-27 0.671369
2017-02-28 -1.279547
2017-03-01 -0.906736
Freq: D, Name: A, dtype: float64
输出3,4行
A B C D E F
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
输出3,4行
A B C D E F
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
输出3,4行
A B C D E F
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
输出3,4行
A B C D E F
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
输出B,C两列
B C
2017-02-20 -0.368257 0.280711
2017-02-21 -1.706017 -1.158823
2017-02-22 -0.518490 -0.015950
2017-02-23 -0.518669 -0.424459
2017-02-24 -1.671190 0.529457
2017-02-25 0.511432 -0.387201
2017-02-26 -0.532562 -2.070748
2017-02-27 0.111791 -0.994774
2017-02-28 0.054616 -1.310744
2017-03-01 -0.832826 -1.260035
A B C D E F
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
2017-02-24 2.241062 -1.671190 0.529457 -0.397618 0.266720 -0.610356
2017-02-27 0.671369 0.111791 -0.994774 -0.345075 -0.043722 0.639117
输出大于0的数据,小于等于0的用NaN补位
A B C D E F
2017-02-20 0.480773 NaN 0.280711 0.428243 2.481903 NaN
2017-02-21 NaN NaN NaN NaN 1.201966 NaN
2017-02-22 NaN NaN NaN 0.582488 0.307157 NaN
2017-02-23 0.582565 NaN NaN NaN 0.841989 1.796369
2017-02-24 2.241062 NaN 0.529457 NaN 0.266720 NaN
2017-02-25 NaN 0.511432 NaN NaN NaN 1.971008
2017-02-26 NaN NaN NaN 0.556197 NaN 0.652505
2017-02-27 0.671369 0.111791 NaN NaN NaN 0.639117
2017-02-28 NaN 0.054616 NaN NaN 0.254414 NaN
2017-03-01 NaN NaN NaN 0.207416 1.911902 1.351750
拷贝data
A B C D E F
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704
2017-02-21 -1.018478 -1.706017 -1.158823 -1.564300 1.201966 -0.405304
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369
2017-02-24 2.241062 -1.671190 0.529457 -0.397618 0.266720 -0.610356
2017-02-25 -1.375601 0.511432 -0.387201 -0.516504 -0.843040 1.971008
2017-02-26 -0.870253 -0.532562 -2.070748 0.556197 -1.590036 0.652505
2017-02-27 0.671369 0.111791 -0.994774 -0.345075 -0.043722 0.639117
2017-02-28 -1.279547 0.054616 -1.310744 -0.574317 0.254414 -0.844659
2017-03-01 -0.906736 -0.832826 -1.260035 0.207416 1.911902 1.351750
在data2中增加TAG列用tag赋值
['a', 'a', 'b', 'b', 'c', 'c', 'd', 'd', 'f', 'f']
A B C D E F TAG
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704 a
2017-02-21 -1.018478 -1.706017 -1.158823 -1.564300 1.201966 -0.405304 a
2017-02-22 -0.182334 -0.518490 -0.015950 0.582488 0.307157 -1.524613 b
2017-02-23 0.582565 -0.518669 -0.424459 -0.549203 0.841989 1.796369 b
2017-02-24 2.241062 -1.671190 0.529457 -0.397618 0.266720 -0.610356 c
2017-02-25 -1.375601 0.511432 -0.387201 -0.516504 -0.843040 1.971008 c
2017-02-26 -0.870253 -0.532562 -2.070748 0.556197 -1.590036 0.652505 d
2017-02-27 0.671369 0.111791 -0.994774 -0.345075 -0.043722 0.639117 d
2017-02-28 -1.279547 0.054616 -1.310744 -0.574317 0.254414 -0.844659 f
2017-03-01 -0.906736 -0.832826 -1.260035 0.207416 1.911902 1.351750 f
打印TAG列中为a,c的行
A B C D E F TAG
2017-02-20 0.480773 -0.368257 0.280711 0.428243 2.481903 -0.696704 a
2017-02-21 -1.018478 -1.706017 -1.158823 -1.564300 1.201966 -0.405304 a
2017-02-24 2.241062 -1.671190 0.529457 -0.397618 0.266720 -0.610356 c
2017-02-25 -1.375601 0.511432 -0.387201 -0.516504 -0.843040 1.971008 c
重定义索引,并添加E列
A B C D E
2017-02-20 -1.030769 -1.421282 -0.779802 -0.151251 NaN
2017-02-21 0.035379 -0.903024 0.034918 1.493916 NaN
2017-02-22 -0.864893 0.127179 -0.973820 0.568832 NaN
2017-02-23 0.138600 0.351400 -0.226842 -0.475378 NaN
将E列中的2,3行赋值为2
A B C D E
2017-02-20 -1.030769 -1.421282 -0.779802 -0.151251 NaN
2017-02-21 0.035379 -0.903024 0.034918 1.493916 2.0
2017-02-22 -0.864893 0.127179 -0.973820 0.568832 2.0
2017-02-23 0.138600 0.351400 -0.226842 -0.475378 NaN
去掉存在NaN元素的行
A B C D E
2017-02-21 0.035379 -0.903024 0.034918 1.493916 2.0
2017-02-22 -0.864893 0.127179 -0.973820 0.568832 2.0
将NaN元素赋值为5
A B C D E
2017-02-20 -1.030769 -1.421282 -0.779802 -0.151251 5.0
2017-02-21 0.035379 -0.903024 0.034918 1.493916 2.0
2017-02-22 -0.864893 0.127179 -0.973820 0.568832 2.0
2017-02-23 0.138600 0.351400 -0.226842 -0.475378 5.0
判断每个元素是否为NaN
A B C D E
2017-02-20 False False False False True
2017-02-21 False False False False False
2017-02-22 False False False False False
2017-02-23 False False False False True
求列平均值
A -0.430421
B -0.461432
C -0.486386
D 0.359030
E 2.000000
dtype: float64
对每列进行累加
A B C D E
2017-02-20 -1.030769 -1.421282 -0.779802 -0.151251 NaN
2017-02-21 -0.995390 -2.324306 -0.744884 1.342664 2.0
2017-02-22 -1.860283 -2.197127 -1.718704 1.911496 4.0
2017-02-23 -1.721683 -1.845728 -1.945546 1.436119 NaN
针对行求平均值
2017-02-20 -0.845776
2017-02-21 0.532238
2017-02-22 0.171460
2017-02-23 -0.053055
Freq: D, dtype: float64
生成序列并向右平移两位
2017-02-20 NaN
2017-02-21 NaN
2017-02-22 1.0
2017-02-23 3.0
2017-02-24 5.0
2017-02-25 NaN
Freq: D, dtype: float64
df与s做减法运算
A B C D
2017-02-20 NaN NaN NaN NaN
2017-02-21 NaN NaN NaN NaN
2017-02-22 -1.864893 -0.872821 -1.973820 -0.431168
2017-02-23 -2.861400 -2.648600 -3.226842 -3.475378
2017-02-24 -5.022111 -5.453181 -3.750840 -5.087552
2017-02-25 NaN NaN NaN NaN
每列进行累加运算
A B C D
2017-02-20 -1.030769 -1.421282 -0.779802 -0.151251
2017-02-21 -0.995390 -2.324306 -0.744884 1.342664
2017-02-22 -1.860283 -2.197127 -1.718704 1.911496
2017-02-23 -1.721683 -1.845728 -1.945546 1.436119
2017-02-24 -1.743795 -2.298908 -0.696386 1.348566
2017-02-25 -2.164268 -2.782710 0.759248 3.387107
每列的最大值减去最小值
A 1.169370
B 1.772682
C 2.429454
D 2.513918
dtype: float64
统计序列中每个元素出现的次数
5.0 1
3.0 1
1.0 1
dtype: int64
返回出现次数最多的元素
0 1.0
1 3.0
2 5.0
dtype: float64
另外一个数据
A B C D
0 -0.725411 -0.923996 -1.862981 -1.630783
1 1.786859 0.213020 1.502242 -3.067034
2 -0.292734 -0.488127 -0.335808 -0.433709
3 -1.036601 0.637052 1.579392 -0.353550
4 -1.684811 -0.167147 -0.738355 -0.439455
5 -0.327458 -0.914152 0.018687 0.119501
6 0.880983 -0.390159 0.573263 -1.375928
7 0.711085 -1.234493 -0.624240 -0.177664
8 -0.386100 -0.029279 0.180789 -1.052394
9 1.629899 -0.953551 0.097774 0.869596
合并函数
A B C D
0 -0.725411 -0.923996 -1.862981 -1.630783
1 1.786859 0.213020 1.502242 -3.067034
2 -0.292734 -0.488127 -0.335808 -0.433709
3 -1.036601 0.637052 1.579392 -0.353550
4 -1.684811 -0.167147 -0.738355 -0.439455
5 -0.327458 -0.914152 0.018687 0.119501
6 0.880983 -0.390159 0.573263 -1.375928
7 0.711085 -1.234493 -0.624240 -0.177664
8 -0.386100 -0.029279 0.180789 -1.052394
9 1.629899 -0.953551 0.097774 0.869596
判断两个DataFrame中元素是否相等
A B C D
0 True True True True
1 True True True True
2 True True True True
3 True True True True
4 True True True True
5 True True True True
6 True True True True
7 True True True True
8 True True True True
9 True True True True
根据A列的索引求和
B C D
A
-1.684811 -0.167147 -0.738355 -0.439455
-1.036601 0.637052 1.579392 -0.353550
-0.725411 -0.923996 -1.862981 -1.630783
-0.386100 -0.029279 0.180789 -1.052394
-0.327458 -0.914152 0.018687 0.119501
-0.292734 -0.488127 -0.335808 -0.433709
0.711085 -1.234493 -0.624240 -0.177664
0.880983 -0.390159 0.573263 -1.375928
1.629899 -0.953551 0.097774 0.869596
1.786859 0.213020 1.502242 -3.067034
先根据A列的索引,在根据B列的索引求和
C D
A B
-1.684811 -0.167147 -0.738355 -0.439455
-1.036601 0.637052 1.579392 -0.353550
-0.725411 -0.923996 -1.862981 -1.630783
-0.386100 -0.029279 0.180789 -1.052394
-0.327458 -0.914152 0.018687 0.119501
-0.292734 -0.488127 -0.335808 -0.433709
0.711085 -1.234493 -0.624240 -0.177664
0.880983 -0.390159 0.573263 -1.375928
1.629899 -0.953551 0.097774 0.869596
1.786859 0.213020 1.502242 -3.067034
先根据B列的索引,在根据A列的索引求和
C D
B A
-1.234493 0.711085 -0.624240 -0.177664
-0.953551 1.629899 0.097774 0.869596
-0.923996 -0.725411 -1.862981 -1.630783
-0.914152 -0.327458 0.018687 0.119501
-0.488127 -0.292734 -0.335808 -0.433709
-0.390159 0.880983 0.573263 -1.375928
-0.167147 -1.684811 -0.738355 -0.439455
-0.029279 -0.386100 0.180789 -1.052394
0.213020 1.786859 1.502242 -3.067034
0.637052 -1.036601 1.579392 -0.353550