导入必要的包
In [1]: import pandas as pd
In [2]: import numpy as np
In [3]: import matplotlib.pyplot as plt创建
In [4]: s = pd.Series([1,3,5,np.nan,6,8])
In [5]: s
Out[5]:
0 1.0
1 3.0
2 5.0
3 NaN
4 6.0
5 8.0
dtype: float64
In [6]: dates = pd.date_range('20130101', periods=6)
In [7]: dates
Out[7]:
DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
'2013-01-05', '2013-01-06'],
dtype='datetime64[ns]', freq='D')
In [8]: df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=list('ABCD'))
In [9]: df
Out[9]:
A B C D
2013-01-01 0.469112 -0.282863 -1.509059 -1.135632
2013-01-02 1.212112 -0.173215 0.119209 -1.044236
2013-01-03 -0.861849 -2.104569 -0.494929 1.071804
2013-01-04 0.721555 -0.706771 -1.039575 0.271860
2013-01-05 -0.424972 0.567020 0.276232 -1.087401
2013-01-06 -0.673690 0.113648 -1.478427 0.524988
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]: df2
Out[11]:
A B C D E F
0 1.0 2013-01-02 1.0 3 test foo
1 1.0 2013-01-02 1.0 3 train foo
2 1.0 2013-01-02 1.0 3 test foo
3 1.0 2013-01-02 1.0 3 train foo
In [12]: df2.dtypes
Out[12]:
A float64
B datetime64[ns]
C float32
D int32
E category
F object
dtype: object观察
In [14]: df.head()
Out[14]:
A B C D
2013-01-01 0.469112 -0.282863 -1.509059 -1.135632
2013-01-02 1.212112 -0.173215 0.119209 -1.044236
2013-01-03 -0.861849 -2.104569 -0.494929 1.071804
2013-01-04 0.721555 -0.706771 -1.039575 0.271860
2013-01-05 -0.424972 0.567020 0.276232 -1.087401
In [15]: df.tail(3)
Out[15]:
A B C D
2013-01-04 0.721555 -0.706771 -1.039575 0.271860
2013-01-05 -0.424972 0.567020 0.276232 -1.087401
2013-01-06 -0.673690 0.113648 -1.478427 0.524988
In [16]: df.index
Out[16]:
DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
'2013-01-05', '2013-01-06'],
dtype='datetime64[ns]', freq='D')
In [17]: df.columns
Out[17]: Index(['A', 'B', 'C', 'D'], dtype='object')
In [18]: df.values
Out[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 ]])
In [19]: df.describe()
Out[19]:
A B C D
count 6.000000 6.000000 6.000000 6.000000
mean 0.073711 -0.431125 -0.687758 -0.233103
std 0.843157 0.922818 0.779887 0.973118
min -0.861849 -2.104569 -1.509059 -1.135632
25% -0.611510 -0.600794 -1.368714 -1.076610
50% 0.022070 -0.228039 -0.767252 -0.386188
75% 0.658444 0.041933 -0.034326 0.461706
max 1.212112 0.567020 0.276232 1.071804
In [20]: df.T
Out[20]:
2013-01-01 2013-01-02 2013-01-03 2013-01-04 2013-01-05 2013-01-06
A 0.469112 1.212112 -0.861849 0.721555 -0.424972 -0.673690
B -0.282863 -0.173215 -2.104569 -0.706771 0.567020 0.113648
C -1.509059 0.119209 -0.494929 -1.039575 0.276232 -1.478427
D -1.135632 -1.044236 1.071804 0.271860 -1.087401 0.524988
In [21]: df.sort_index(axis=1, ascending=False)
Out[21]:
D C B A
2013-01-01 -1.135632 -1.509059 -0.282863 0.469112
2013-01-02 -1.044236 0.119209 -0.173215 1.212112
2013-01-03 1.071804 -0.494929 -2.104569 -0.861849
2013-01-04 0.271860 -1.039575 -0.706771 0.721555
2013-01-05 -1.087401 0.276232 0.567020 -0.424972
2013-01-06 0.524988 -1.478427 0.113648 -0.673690
In [22]: df.sort_values(by='B')
Out[22]:
A B C D
2013-01-03 -0.861849 -2.104569 -0.494929 1.071804
2013-01-04 0.721555 -0.706771 -1.039575 0.271860
2013-01-01 0.469112 -0.282863 -1.509059 -1.135632
2013-01-02 1.212112 -0.173215 0.119209 -1.044236
2013-01-06 -0.673690 0.113648 -1.478427 0.524988
2013-01-05 -0.424972 0.567020 0.276232 -1.087401选取
取列
In [23]: df['A'] ----------------等价于df.A
Out[23]:
2013-01-01 0.469112
2013-01-02 1.212112
2013-01-03 -0.861849
2013-01-04 0.721555
2013-01-05 -0.424972
2013-01-06 -0.673690
Freq: D, Name: A, dtype: float64取行
In [24]: df[0:3]
Out[24]:
A B C D
2013-01-01 0.469112 -0.282863 -1.509059 -1.135632
2013-01-02 1.212112 -0.173215 0.119209 -1.044236
2013-01-03 -0.861849 -2.104569 -0.494929 1.071804
In [25]: df['20130102':'20130104']
Out[25]:
A B C D
2013-01-02 1.212112 -0.173215 0.119209 -1.044236
2013-01-03 -0.861849 -2.104569 -0.494929 1.071804
2013-01-04 0.721555 -0.706771 -1.039575 0.271860按位置取
loc传的是行列索引名，iloc传位置即可
In [26]: df.loc[dates[0]]-----------等价于df.iloc[0]
Out[26]:
A 0.469112
B -0.282863
C -1.509059
D -1.135632
Name: 2013-01-01 00:00:00, dtype: float64
In [27]: df.loc[:,['A','B']]----------等价于df.iloc[:,0:2]
Out[27]:
A B
2013-01-01 0.469112 -0.282863
2013-01-02 1.212112 -0.173215
2013-01-03 -0.861849 -2.104569
2013-01-04 0.721555 -0.706771
2013-01-05 -0.424972 0.567020
2013-01-06 -0.673690 0.113648
In [28]: df.loc['20130102':'20130104',['A','B']]-------等价于df.iloc[1:4,0:2]
Out[28]:
A B
2013-01-02 1.212112 -0.173215
2013-01-03 -0.861849 -2.104569
2013-01-04 0.721555 -0.706771
In [29]: df.loc['20130102',['A','B']]
Out[29]:
A 1.212112
B -0.173215
Name: 2013-01-02 00:00:00, dtype: float64
In [30]: df.loc[dates[0],'A']---------等价于df.at[dates[0],'A']
Out[30]: 0.46911229990718628
----------
In [34]: df.iloc[[1,2,4],[0,2]]
Out[34]:
A C
2013-01-02 1.212112 0.119209
2013-01-03 -0.861849 -0.494929
2013-01-05 -0.424972 0.276232
In [37]: df.iloc[1,1]-----------等价于df.iat[1,1]
Out[37]: -0.17321464905330858按条件取
In [39]: df[df.A > 0]
Out[39]:
A B C D
2013-01-01 0.469112 -0.282863 -1.509059 -1.135632
2013-01-02 1.212112 -0.173215 0.119209 -1.044236
2013-01-04 0.721555 -0.706771 -1.039575 0.271860
In [40]: df[df > 0]
Out[40]:
A B C D
2013-01-01 0.469112 NaN NaN NaN
2013-01-02 1.212112 NaN 0.119209 NaN
2013-01-03 NaN NaN NaN 1.071804
2013-01-04 0.721555 NaN NaN 0.271860
2013-01-05 NaN 0.567020 0.276232 NaN
2013-01-06 NaN 0.113648 NaN 0.524988
#示范isin()函数
In [41]: df2 = df.copy()
In [42]: df2['E'] = ['one', 'one','two','three','four','three']
In [43]: df2
Out[43]:
A B C D E
2013-01-01 0.469112 -0.282863 -1.509059 -1.135632 one
2013-01-02 1.212112 -0.173215 0.119209 -1.044236 one
2013-01-03 -0.861849 -2.104569 -0.494929 1.071804 two
2013-01-04 0.721555 -0.706771 -1.039575 0.271860 three
2013-01-05 -0.424972 0.567020 0.276232 -1.087401 four
2013-01-06 -0.673690 0.113648 -1.478427 0.524988 three
In [44]: df2[df2['E'].isin(['two','four'])]
Out[44]:
A B C D E
2013-01-03 -0.861849 -2.104569 -0.494929 1.071804 two
2013-01-05 -0.424972 0.567020 0.276232 -1.087401 four赋值
#新增列
In [45]: s1 = pd.Series([1,2,3,4,5,6], index=pd.date_range('20130102', periods=6))
In [46]: s1
Out[46]:
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
In [47]: df['F'] = s1
#Setting values by label
In [48]: df.at[dates[0],'A'] = 0
#Setting values by position
In [49]: df.iat[0,1] = 0
#Setting by assigning with a numpy array
In [50]: df.loc[:,'D'] = np.array([5] * len(df))
In [51]: df
Out[51]:
A B C D F
2013-01-01 0.000000 0.000000 -1.509059 5 NaN
2013-01-02 1.212112 -0.173215 0.119209 5 1.0
2013-01-03 -0.861849 -2.104569 -0.494929 5 2.0
2013-01-04 0.721555 -0.706771 -1.039575 5 3.0
2013-01-05 -0.424972 0.567020 0.276232 5 4.0
2013-01-06 -0.673690 0.113648 -1.478427 5 5.0
In [52]: df2 = df.copy()
In [53]: df2[df2 > 0] = -df2
In [54]: df2
Out[54]:
A B C D F
2013-01-01 0.000000 0.000000 -1.509059 -5 NaN
2013-01-02 -1.212112 -0.173215 -0.119209 -5 -1.0
2013-01-03 -0.861849 -2.104569 -0.494929 -5 -2.0
2013-01-04 -0.721555 -0.706771 -1.039575 -5 -3.0
2013-01-05 -0.424972 -0.567020 -0.276232 -5 -4.0
2013-01-06 -0.673690 -0.113648 -1.478427 -5 -5.0缺失值
In [55]: df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])
In [56]: df1.loc[dates[0]:dates[1],'E'] = 1
In [57]: df1
Out[57]:
A B C D F E
2013-01-01 0.000000 0.000000 -1.509059 5 NaN 1.0
2013-01-02 1.212112 -0.173215 0.119209 5 1.0 1.0
2013-01-03 -0.861849 -2.104569 -0.494929 5 2.0 NaN
2013-01-04 0.721555 -0.706771 -1.039575 5 3.0 NaN
# 只要有NaN,都drop
In [58]: df1.dropna(how='any')
Out[58]:
A B C D F E
2013-01-02 1.212112 -0.173215 0.119209 5 1.0 1.0
# 填充
In [59]: df1.fillna(value=5)
Out[59]:
A B C D F E
2013-01-01 0.000000 0.000000 -1.509059 5 5.0 1.0
2013-01-02 1.212112 -0.173215 0.119209 5 1.0 1.0
2013-01-03 -0.861849 -2.104569 -0.494929 5 2.0 5.0
2013-01-04 0.721555 -0.706771 -1.039575 5 3.0 5.0
In [60]: pd.isna(df1)
Out[60]:
A B C D F E
2013-01-01 False False False False True False
2013-01-02 False False False False False False
2013-01-03 False False False False False True
2013-01-04 False False False False False True操作
stats
在总体数据上操作（缺失值除外）
In [61]: df.mean()
Out[61]:
A -0.004474
B -0.383981
C -0.687758
D 5.000000
F 3.000000
dtype: float64
# 不同维
In [62]: df.mean(1)
Out[62]:
2013-01-01 0.872735
2013-01-02 1.431621
2013-01-03 0.707731
2013-01-04 1.395042
2013-01-05 1.883656
2013-01-06 1.592306
Freq: D, dtype: float64
In [63]: s = pd.Series([1,3,5,np.nan,6,8], index=dates).shift(2)------------往下挪了两步开始赋值
In [64]: s
Out[64]:
2013-01-01 NaN
2013-01-02 NaN
2013-01-03 1.0
2013-01-04 3.0
2013-01-05 5.0
2013-01-06 NaN
Freq: D, dtype: float64
In [65]: df.sub(s, axis='index')------df中每一列都减去s中对应index的值，对于有NaN的都标志为NaN
Out[65]:
A B C D F
2013-01-01 NaN NaN NaN NaN NaN
2013-01-02 NaN NaN NaN NaN NaN
2013-01-03 -1.861849 -3.104569 -1.494929 4.0 1.0
2013-01-04 -2.278445 -3.706771 -4.039575 2.0 0.0
2013-01-05 -5.424972 -4.432980 -4.723768 0.0 -1.0
2013-01-06 NaN NaN NaN NaN NaNapply
In [66]: df.apply(np.cumsum)--------cumsum:计算轴向元素累加和，返回由中间结果组成的数组
Out[66]:
A B C D F
2013-01-01 0.000000 0.000000 -1.509059 5 NaN
2013-01-02 1.212112 -0.173215 -1.389850 10 1.0
2013-01-03 0.350263 -2.277784 -1.884779 15 3.0
2013-01-04 1.071818 -2.984555 -2.924354 20 6.0
2013-01-05 0.646846 -2.417535 -2.648122 25 10.0
2013-01-06 -0.026844 -2.303886 -4.126549 30 15.0
In [67]: df.apply(lambda x: x.max() - x.min())
Out[67]:
A 2.073961
B 2.671590
C 1.785291
D 0.000000
F 4.000000
dtype: float64histogramming
In [68]: s = pd.Series(np.random.randint(0, 7, size=10))
In [69]: s
Out[69]:
0 4
1 2
2 1
3 2
4 6
5 4
6 4
7 6
8 4
9 4
dtype: int64
In [70]: s.value_counts()------------统计数值个数
Out[70]:
4 5
6 2
2 2
1 1
dtype: int64string methods
In [71]: s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])
In [72]: s.str.lower()
Out[72]:
0 a
1 b
2 c
3 aaba
4 baca
5 NaN
6 caba
7 dog
8 cat
dtype: object合并
concat
In [73]: df = pd.DataFrame(np.random.randn(10, 4))
In [74]: df
Out[74]:
0 1 2 3
0 -0.548702 1.467327 -1.015962 -0.483075
1 1.637550 -1.217659 -0.291519 -1.745505
2 -0.263952 0.991460 -0.919069 0.266046
3 -0.709661 1.669052 1.037882 -1.705775
4 -0.919854 -0.042379 1.247642 -0.009920
5 0.290213 0.495767 0.362949 1.548106
6 -1.131345 -0.089329 0.337863 -0.945867
7 -0.932132 1.956030 0.017587 -0.016692
8 -0.575247 0.254161 -1.143704 0.215897
9 1.193555 -0.077118 -0.408530 -0.862495
# break it into pieces
In [75]: pieces = [df[:3], df[3:7], df[7:]]
In [76]: pd.concat(pieces)
Out[76]:
0 1 2 3
0 -0.548702 1.467327 -1.015962 -0.483075
1 1.637550 -1.217659 -0.291519 -1.745505
2 -0.263952 0.991460 -0.919069 0.266046
3 -0.709661 1.669052 1.037882 -1.705775
4 -0.919854 -0.042379 1.247642 -0.009920
5 0.290213 0.495767 0.362949 1.548106
6 -1.131345 -0.089329 0.337863 -0.945867
7 -0.932132 1.956030 0.017587 -0.016692
8 -0.575247 0.254161 -1.143704 0.215897
9 1.193555 -0.077118 -0.408530 -0.862495join
In [77]: left = pd.DataFrame({'key': ['foo', 'foo'], 'lval': [1, 2]})
In [78]: right = pd.DataFrame({'key': ['foo', 'foo'], 'rval': [4, 5]})
In [79]: left
Out[79]:
key lval
0 foo 1
1 foo 2
In [80]: right
Out[80]:
key rval
0 foo 4
1 foo 5
In [81]: pd.merge(left, right, on='key')
Out[81]:
key lval rval
0 foo 1 4
1 foo 1 5
2 foo 2 4
3 foo 2 5append
In [87]: df = pd.DataFrame(np.random.randn(8, 4), columns=['A','B','C','D'])
In [88]: df
Out[88]:
A B C D
0 1.346061 1.511763 1.627081 -0.990582
1 -0.441652 1.211526 0.268520 0.024580
2 -1.577585 0.396823 -0.105381 -0.532532
3 1.453749 1.208843 -0.080952 -0.264610
4 -0.727965 -0.589346 0.339969 -0.693205
5 -0.339355 0.593616 0.884345 1.591431
6 0.141809 0.220390 0.435589 0.192451
7 -0.096701 0.803351 1.715071 -0.708758
In [89]: s = df.iloc[3]
In [90]: df.append(s, ignore_index=True)
Out[90]:
A B C D
0 1.346061 1.511763 1.627081 -0.990582
1 -0.441652 1.211526 0.268520 0.024580
2 -1.577585 0.396823 -0.105381 -0.532532
3 1.453749 1.208843 -0.080952 -0.264610
4 -0.727965 -0.589346 0.339969 -0.693205
5 -0.339355 0.593616 0.884345 1.591431
6 0.141809 0.220390 0.435589 0.192451
7 -0.096701 0.803351 1.715071 -0.708758
8 1.453749 1.208843 -0.080952 -0.264610分组
By “group by” we are referring to a process involving one or more of the following steps
Splitting the data into groups based on some criteria
Applying a function to each group independently
Combining the results into a data structure
In [91]: 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)})
....:
In [92]: df
Out[92]:
A B C D
0 foo one -1.202872 -0.055224
1 bar one -1.814470 2.395985
2 foo two 1.018601 1.552825
3 bar three -0.595447 0.166599
4 foo two 1.395433 0.047609
5 bar two -0.392670 -0.136473
6 foo one 0.007207 -0.561757
7 foo three 1.928123 -1.623033
In [93]: df.groupby('A').sum()
Out[93]:
C D
A
bar -2.802588 2.42611
foo 3.146492 -0.63958
In [94]: df.groupby(['A','B']).sum()
Out[94]:
C D
A B
bar one -1.814470 2.395985
three -0.595447 0.166599
two -0.392670 -0.136473
foo one -1.195665 -0.616981
three 1.928123 -1.623033
two 2.414034 1.600434重塑
stack
In [95]: tuples = list(zip(*[['bar', 'bar', 'baz', 'baz',
....: 'foo', 'foo', 'qux', 'qux'],
....: ['one', 'two', 'one', 'two',
....: 'one', 'two', 'one', 'two']]))
....:
In [2]: tuples
Out[2]:
[('bar', 'one'),
('bar', 'two'),
('baz', 'one'),
('baz', 'two'),
('foo', 'one'),
('foo', 'two'),
('qux', 'one'),
('qux', 'two')]
In [96]: index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])
In [97]: df = pd.DataFrame(np.random.randn(8, 2), index=index, columns=['A', 'B'])
In [98]: df2 = df[:4]
In [99]: df2
Out[99]:
A B
first second
bar one 0.029399 -0.542108
two 0.282696 -0.087302
baz one -1.575170 1.771208
two 0.816482 1.100230
# 重塑stack
In [100]: stacked = df2.stack()
In [101]: stacked
Out[101]:
first second
bar one A 0.029399
B -0.542108
two A 0.282696
B -0.087302
baz one A -1.575170
B 1.771208
two A 0.816482
B 1.100230
dtype: float64With a “stacked” DataFrame or Series (having a MultiIndex as the index), the inverse operation of stack() is unstack(), which by default unstacks the last level:
In [102]: stacked.unstack()
Out[102]:
A B
first second
bar one 0.029399 -0.542108
two 0.282696 -0.087302
baz one -1.575170 1.771208
two 0.816482 1.100230
In [103]: stacked.unstack(1)
Out[103]:
second one two
first
bar A 0.029399 0.282696
B -0.542108 -0.087302
baz A -1.575170 0.816482
B 1.771208 1.100230
In [104]: stacked.unstack(0)
Out[104]:
first bar baz
second
one A 0.029399 -1.575170
B -0.542108 1.771208
two A 0.282696 0.816482
B -0.087302 1.100230pivot
In [105]: 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)})
.....:
In [106]: df
Out[106]:
A B C D E
0 one A foo 1.418757 -0.179666
1 one B foo -1.879024 1.291836
2 two C foo 0.536826 -0.009614
3 three A bar 1.006160 0.392149
4 one B bar -0.029716 0.264599
5 one C bar -1.146178 -0.057409
6 two A foo 0.100900 -1.425638
7 three B foo -1.035018 1.024098
8 one C foo 0.314665 -0.106062
9 one A bar -0.773723 1.824375
10 two B bar -1.170653 0.595974
11 three C bar 0.648740 1.167115
In [107]: pd.pivot_table(df, values='D', index=['A', 'B'], columns=['C'])
Out[107]:
C bar foo
A B
one A -0.773723 1.418757
B -0.029716 -1.879024
C -1.146178 0.314665
three A 1.006160 NaN
B NaN -1.035018
C 0.648740 NaN
two A NaN 0.100900
B -1.170653 NaN
C NaN 0.536826时间序列
In [108]: rng = pd.date_range('1/1/2012', periods=100, freq='S')
In [7]: rng[0:2]
Out[7]: DatetimeIndex(['2012-01-01 00:00:00', '2012-01-01 00:00:01'], dtype='datetime64[ns]', freq='S')
In [109]: ts = pd.Series(np.random.randint(0, 500, len(rng)), index=rng)
In [110]: ts.resample('5Min').sum()
Out[110]:
2012-01-01 25083
Freq: 5T, dtype: int64
----------
In [111]: rng = pd.date_range('3/6/2012 00:00', periods=5, freq='D')
In [112]: ts = pd.Series(np.random.randn(len(rng)), rng)
In [113]: ts
Out[113]:
2012-03-06 0.464000
2012-03-07 0.227371
2012-03-08 -0.496922
2012-03-09 0.306389
2012-03-10 -2.290613
Freq: D, dtype: float64
In [114]: ts_utc = ts.tz_localize('UTC')
In [115]: ts_utc
Out[115]:
2012-03-06 00:00:00+00:00 0.464000
2012-03-07 00:00:00+00:00 0.227371
2012-03-08 00:00:00+00:00 -0.496922
2012-03-09 00:00:00+00:00 0.306389
2012-03-10 00:00:00+00:00 -2.290613
Freq: D, dtype: float64
----------
# 转时区
In [116]: ts_utc.tz_convert('US/Eastern')
Out[116]:
2012-03-05 19:00:00-05:00 0.464000
2012-03-06 19:00:00-05:00 0.227371
2012-03-07 19:00:00-05:00 -0.496922
2012-03-08 19:00:00-05:00 0.306389
2012-03-09 19:00:00-05:00 -2.290613
Freq: D, dtype: float64
----------
In [117]: rng = pd.date_range('1/1/2012', periods=5, freq='M')
In [118]: ts = pd.Series(np.random.randn(len(rng)), index=rng)
In [119]: ts
Out[119]:
2012-01-31 -1.134623
2012-02-29 -1.561819
2012-03-31 -0.260838
2012-04-30 0.281957
2012-05-31 1.523962
Freq: M, dtype: float64
In [120]: ps = ts.to_period()
In [121]: ps
Out[121]:
2012-01 -1.134623
2012-02 -1.561819
2012-03 -0.260838
2012-04 0.281957
2012-05 1.523962
Freq: M, dtype: float64
In [122]: ps.to_timestamp()
Out[122]:
2012-01-01 -1.134623
2012-02-01 -1.561819
2012-03-01 -0.260838
2012-04-01 0.281957
2012-05-01 1.523962
Freq: MS, dtype: float64
#以季度为单位转换
In [123]: prng = pd.period_range('1990Q1', '2000Q4', freq='Q-NOV')
In [124]: ts = pd.Series(np.random.randn(len(prng)), prng)
In [125]: ts.index = (prng.asfreq('M', 'e') + 1).asfreq('H', 's') + 9
In [126]: ts.head()
Out[126]:
1990-03-01 09:00 -0.902937
1990-06-01 09:00 0.068159
1990-09-01 09:00 -0.057873
1990-12-01 09:00 -0.368204
1991-03-01 09:00 -1.144073
Freq: H, dtype: float64离散数据（Categoricals）
In [127]: df = pd.DataFrame({"id":[1,2,3,4,5,6], "raw_grade":['a', 'b', 'b', 'a', 'a', 'e']})
In [128]: df["grade"] = df["raw_grade"].astype("category")
In [129]: df["grade"]
Out[129]:
0 a
1 b
2 b
3 a
4 a
5 e
Name: grade, dtype: category
Categories (3, object): [a, b, e]
# 对离散变量进行重命名
In [130]: df["grade"].cat.categories = ["very good", "good", "very bad"]
In [22]: df
Out[22]:
id raw_grade grade
0 1 a very good
1 2 b good
2 3 b good
3 4 a very good
4 5 a very good
5 6 e very bad
# 设置离散值有哪几种
In [131]: df["grade"] = df["grade"].cat.set_categories(["very bad", "bad", "medium", "good", "very good"])
In [132]: df["grade"]
Out[132]:
0 very good
1 good
2 good
3 very good
4 very good
5 very bad
Name: grade, dtype: category
Categories (5, object): [very bad, bad, medium, good, very good]
# 排序
In [133]: df.sort_values(by="grade")
Out[133]:
id raw_grade grade
5 6 e very bad
1 2 b good
2 3 b good
0 1 a very good
3 4 a very good
4 5 a very good
In [134]: df.groupby("grade").size()
Out[134]:
grade
very bad 1
bad 0
medium 0
good 2
very good 3
dtype: int64展示
In [135]: ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))
In [35]: ts.iloc[0:3]
Out[35]:
2000-01-01 -0.510591
2000-01-02 0.315922
2000-01-03 0.659409
Freq: D, dtype: float64
In [136]: ts = ts.cumsum()
In [37]: ts.iloc[0:3]
Out[37]:
2000-01-01 -0.510591
2000-01-02 -0.194669
2000-01-03 0.464740
Freq: D, dtype: float64
In [137]: ts.plot()
In [138]: df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index,
.....: columns=['A', 'B', 'C', 'D'])
.....:
In [139]: df = df.cumsum()
In [140]: plt.figure(); df.plot(); plt.legend(loc='best')
Out[140]: <matplotlib.legend.Legend at 0x109a28860>
I/O
# CSV
df.to_csv('foo.csv')
pd.read_csv('foo.csv')
# HDF5
df.to_hdf('foo.h5','df')
pd.read_hdf('foo.h5','df')
# Excel
df.to_excel('foo.xlsx', sheet_name='Sheet1')
pd.read_excel('foo.xlsx', 'Sheet1', index_col=None, na_values=['NA'])
扫一扫
171
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
