pandas <十分钟掌握pandas常用操作>

来源：互联网发布：淘宝网机械水压开关编辑：程序博客网时间：2024/06/06 02:59

panda version:’0.19.2’

1.创建数据集

In [58]: names=['Bob','Jessica','Mary','John','Mel']In [59]: births = [968, 155, 77, 578, 973]In [60]: BabyDataSet = list(zip(names,births))    ...: BabyDataSetOut[60]: [('Bob', 968), ('Jessica', 155), ('Mary', 77), ('John', 578), ('Mel', 973)]In [61]: df = pd.DataFrame(data = BabyDataSet, columns=['Names', 'Births    ...: '])    ...: dfOut[61]:     Names  Births0      Bob     9681  Jessica     1552     Mary      773     John     5784      Mel     973

2.查看数据类型

In [64]: df.dtypesOut[64]:Names     objectBirths     int64dtype: objectIn [65]: df.Names.dtypesOut[65]: dtype('O')In [66]: df.Births.dtypesOut[66]: dtype('int64')

3.按照指定的一列排序

In [68]: df.sort_values(['Births'])Out[68]:     Names  Births2     Mary      771  Jessica     1553     John     5780      Bob     9684      Mel     973In [69]: df.sort_values(['Births'],ascending=False)Out[69]:     Names  Births4      Mel     9730      Bob     9683     John     5781  Jessica     1552     Mary      77

4.选取前几行或者末尾几行

In [72]: df.head(3)Out[72]:     Names  Births0      Bob     9681  Jessica     1552     Mary      77In [73]: df.tail(2)Out[73]:  Names  Births3  John     5784   Mel     973In [74]: dfOut[74]:     Names  Births0      Bob     9681  Jessica     1552     Mary      773     John     5784      Mel     973

5.选取一列的最大值

In [75]: df['Births']Out[75]:0    9681    1552     773    5784    973Name: Births, dtype: int64In [76]: df['Births'].max()Out[76]: 973In [77]: df['Names'][df['Births'] == df['Births'].max()]Out[77]:4    MelName: Names, dtype: object

# encoding=utf-8import pandas as pdimport numpy as npimport matplotlib.pyplot as plt# Creating a Series by passing a list of values, letting pandas create a default integer indexs = pd.Series([1, 3, 5, np.nan, 6, 8])print(s)# Creating a DataFrame by passing a numpy array, with a datetime index and labeled columns:

0    1.01    3.02    5.03    NaN4    6.05    8.0dtype: float64

dates = pd.date_range('20130101', periods=6)print(dates)# Creating a DataFrame by passing a numpy array, with a datetime index and labeled columns:df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))print(df)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'})print(df2)

DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',               '2013-01-05', '2013-01-06'],              dtype='datetime64[ns]', freq='D')                   A         B         C         D2013-01-01 -1.324399 -0.917851 -0.710650  0.9770882013-01-02  0.034877 -0.417994  1.412711 -0.6261972013-01-03 -0.559784 -0.085540  1.067182  0.6496212013-01-04  0.849592 -1.251283  1.956991  1.1897812013-01-05 -1.742392  0.193744 -0.570087 -0.2771562013-01-06 -0.129934 -0.890113 -1.324529 -1.298726     A          B    C  D      E    F0  1.0 2013-01-02  1.0  3   test  foo1  1.0 2013-01-02  1.0  3  train  foo2  1.0 2013-01-02  1.0  3   test  foo3  1.0 2013-01-02  1.0  3  train  foo

# 查看数据的头部和尾部# See the top & bottom rows of the frameprint "--------*---------------"print(df2.head(1))print(df2.tail(1))print(df2.values)# 排序# Sorting by an axis（轴）print "--------*---------------"# 可以看到按照列名排序了print dfprint df.sort_index(axis=1, ascending=False)# Sorting by values# 按照B列排序print  df.sort_values(by='B')

     A          B    C  D     E    F0  1.0 2013-01-02  1.0  3  test  foo     A          B    C  D      E    F3  1.0 2013-01-02  1.0  3  train  foo[[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo'] [1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo'] [1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo'] [1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']]--------*---------------                   A         B         C         D2013-01-01 -1.324399 -0.917851 -0.710650  0.9770882013-01-02  0.034877 -0.417994  1.412711 -0.6261972013-01-03 -0.559784 -0.085540  1.067182  0.6496212013-01-04  0.849592 -1.251283  1.956991  1.1897812013-01-05 -1.742392  0.193744 -0.570087 -0.2771562013-01-06 -0.129934 -0.890113 -1.324529 -1.298726                   D         C         B         A2013-01-01  0.977088 -0.710650 -0.917851 -1.3243992013-01-02 -0.626197  1.412711 -0.417994  0.0348772013-01-03  0.649621  1.067182 -0.085540 -0.5597842013-01-04  1.189781  1.956991 -1.251283  0.8495922013-01-05 -0.277156 -0.570087  0.193744 -1.7423922013-01-06 -1.298726 -1.324529 -0.890113 -0.129934                   A         B         C         D2013-01-04  0.849592 -1.251283  1.956991  1.1897812013-01-01 -1.324399 -0.917851 -0.710650  0.9770882013-01-06 -0.129934 -0.890113 -1.324529 -1.2987262013-01-02  0.034877 -0.417994  1.412711 -0.6261972013-01-03 -0.559784 -0.085540  1.067182  0.6496212013-01-05 -1.742392  0.193744 -0.570087 -0.277156

# Selecting a single column, which yields a Series, equivalent to df.Aprint df.Aprint df['A']# Selecting via [], which slices the rows.print df[0:3]

2013-01-01   -1.3243992013-01-02    0.0348772013-01-03   -0.5597842013-01-04    0.8495922013-01-05   -1.7423922013-01-06   -0.129934Freq: D, Name: A, dtype: float642013-01-01   -1.3243992013-01-02    0.0348772013-01-03   -0.5597842013-01-04    0.8495922013-01-05   -1.7423922013-01-06   -0.129934Freq: D, Name: A, dtype: float64                   A         B         C         D2013-01-01 -1.324399 -0.917851 -0.710650  0.9770882013-01-02  0.034877 -0.417994  1.412711 -0.6261972013-01-03 -0.559784 -0.085540  1.067182  0.649621

#选取第一行print df.loc[dates[0]]

A   -1.324399B   -0.917851C   -0.710650D    0.977088Name: 2013-01-01 00:00:00, dtype: float64

#选取所有行中的A、B列df.loc[:,['A','B']]

A B 2013-01-01 -1.324399 -0.917851 2013-01-02 0.034877 -0.417994 2013-01-03 -0.559784 -0.085540 2013-01-04 0.849592 -1.251283 2013-01-05 -1.742392 0.193744 2013-01-06 -0.129934 -0.890113

df.loc['20130102':'20130104',['A','B']]#获取一个值df.loc[dates[0],'A']

-1.3243992801327025

#Using the isin() method for filtering:df2 = df.copy()df2['E'] = ['one', 'one','two','three','four','three']df2

A B C D E 2013-01-01 -1.324399 -0.917851 -0.710650 0.977088 one 2013-01-02 0.034877 -0.417994 1.412711 -0.626197 one 2013-01-03 -0.559784 -0.085540 1.067182 0.649621 two 2013-01-04 0.849592 -1.251283 1.956991 1.189781 three 2013-01-05 -1.742392 0.193744 -0.570087 -0.277156 four 2013-01-06 -0.129934 -0.890113 -1.324529 -1.298726 three

#Using the isin() method for filtering:df2[df2['E'].isin(['two','four'])]

A B C D E 2013-01-03 -0.559784 -0.085540 1.067182 0.649621 two 2013-01-05 -1.742392 0.193744 -0.570087 -0.277156 four

s1 = pd.Series([1,2,3,4,5,6], index=pd.date_range('20130102', periods=6))s1

2013-01-02 1 2013-01-03 2 2013-01-04 3 2013-01-05 4 2013-01-06 5 2013-01-07 6 Freq: D, dtype: int64

#在原有的数据集上添加新的数据df['F'] = s1df

A B C D F 2013-01-01 -1.324399 -0.917851 -0.710650 0.977088 NaN 2013-01-02 0.034877 -0.417994 1.412711 -0.626197 1.0 2013-01-03 -0.559784 -0.085540 1.067182 0.649621 2.0 2013-01-04 0.849592 -1.251283 1.956991 1.189781 3.0 2013-01-05 -1.742392 0.193744 -0.570087 -0.277156 4.0 2013-01-06 -0.129934 -0.890113 -1.324529 -1.298726 5.0

# 每列的平均数df.mean()

A -0.478673 B -0.561506 C 0.305270 D 0.102402 F 3.000000 dtype: float64

# 使用lamda表达式作用于每一列df.apply(lambda x: x.max() - x.min())

A 2.591984 B 1.445027 C 3.281519 D 2.488508 F 4.000000 dtype: float64

# 字符串大小写转换s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])s.str.lower()

0 a 1 b 2 c 3 aaba 4 baca 5 NaN 6 caba 7 dog 8 cat dtype: object

# merge操作left = pd.DataFrame({'key': ['foo', 'foo'], 'lval': [1, 2]})right = pd.DataFrame({'key': ['foo', 'foo'], 'rval': [4, 5]})leftrightpd.merge(left, right, on='key')

key lval rval 0 foo 1 4 1 foo 1 5 2 foo 2 4 3 foo 2 5

left = pd.DataFrame({'key': ['foo', 'bar'], 'lval': [1, 2]})right = pd.DataFrame({'key': ['foo', 'bar'], 'rval': [4, 5]})leftrightpd.merge(left, right, on='key')

key lval rval 0 foo 1 4 1 bar 2 5

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

A B C D 0 foo one 0.850151 -0.095071 1 bar one 0.252074 0.504999 2 foo two -0.139441 -1.190568 3 bar three -0.971856 0.340176 4 foo two 1.546175 -0.402114 5 bar two 0.026199 1.313452 6 foo one -0.267510 -0.981974 7 foo three 1.018972 1.100904

df.groupby('A').sum()

C D A bar -0.693583 2.158627 foo 3.008348 -1.568822

df.groupby(['A','B']).sum()

C D A B bar one 0.252074 0.504999 three -0.971856 0.340176 two 0.026199 1.313452 foo one 0.582641 -1.077045 three 1.018972 1.100904 two 1.406734 -1.592681

<matplotlib.axes._subplots.AxesSubplot at 0x9b27b00>

阅读全文

0 0