Python基本数据统计（一）便捷数据获取数据准备和整理数据显示

In [7]: from matplotlib.finance import quotes_historical_yahoo_ochlIn [8]: from datetime import dateIn [9]: from datetime import datetimeIn [10]: import pandas as pdIn [11]: today &＃61; date.today()In [12]: start &＃61; (today.year-1, today.month, today.day)In [14]: quotes &＃61; quotes_historical_yahoo_ochl(&＃39;AXP&＃39;, start, today) # 获取数据In [15]: fields &＃61; [&＃39;date&＃39;, &＃39;open&＃39;, &＃39;close&＃39;, &＃39;high&＃39;, &＃39;low&＃39;, &＃39;volume&＃39;]In [16]: list1 &＃61; []In [18]: for i in range(0,len(quotes)):...: x &＃61; date.fromordinal(int(quotes[i][0])) # 取每一行的第一列&＃xff0c;通过date.fromordinal设置为日期数据类型...: y &＃61; datetime.strftime(x,&＃39;%Y-%m-%d&＃39;) # 通过datetime.strftime把日期设置为指定格式...: list1.append(y) # 将日期放入列表中...: In [19]: quotesdf &＃61; pd.DataFrame(quotes,index&＃61;list1,columns&＃61;fields) # index设置为日期&＃xff0c;columns设置为字段In [20]: quotesdf &＃61; quotesdf.drop([&＃39;date&＃39;],axis&＃61;1) # 删除date列In [21]: print quotesdfopen close high low volume
2016-01-20 60.374146 61.835916 62.336256 60.128882 9043800.0
2016-01-21 61.806486 61.453305 63.101479 61.325767 8992300.0
2016-01-22 57.283819 54.016907 57.774347 53.114334 43783400.0

In [1]: import nltkIn [2]: nltk.download()
NLTK Downloader
---------------------------------------------------------------------------d) Download l) List u) Update c) Config h) Help q) Quit
---------------------------------------------------------------------------
Downloader> dDownload which package (l&＃61;list; x&＃61;cancel)?Identifier> gutenbergDownloading package gutenberg to /root/nltk_data...Package gutenberg is already up-to-date!

In [3]: from nltk.corpus import gutenbergIn [4]: print gutenberg.fileids()
[u&＃39;austen-emma.txt&＃39;, u&＃39;austen-persuasion.txt&＃39;, u&＃39;austen-sense.txt&＃39;, u&＃39;bible-kjv.txt&＃39;, u&＃39;blake-poems.txt&＃39;, u&＃39;bryant-stories.txt&＃39;, u&＃39;burgess-busterbrown.txt&＃39;, u&＃39;carroll-alice.txt&＃39;, u&＃39;chesterton-ball.txt&＃39;, u&＃39;chesterton-brown.txt&＃39;, u&＃39;chesterton-thursday.txt&＃39;, u&＃39;edgeworth-parents.txt&＃39;, u&＃39;melville-moby_dick.txt&＃39;, u&＃39;milton-paradise.txt&＃39;, u&＃39;shakespeare-caesar.txt&＃39;, u&＃39;shakespeare-hamlet.txt&＃39;, u&＃39;shakespeare-macbeth.txt&＃39;, u&＃39;whitman-leaves.txt&＃39;]In [5]: texts &＃61; gutenberg.words(&＃39;shakespeare-hamlet.txt&＃39;)In [6]: texts
Out[6]: [u&＃39;[&＃39;, u&＃39;The&＃39;, u&＃39;Tragedie&＃39;, u&＃39;of&＃39;, u&＃39;Hamlet&＃39;, u&＃39;by&＃39;, ...]

In [79]: quotesdf &＃61; pd.DataFrame(quotes)In [80]: quotesdf
Out[80]: 0 1 2 3 4 5
0 735983.0 60.374146 61.835916 62.336256 60.128882 9043800.0
1 735984.0 61.806486 61.453305 63.101479 61.325767 8992300.0
2 735985.0 57.283819 54.016907 57.774347 53.114334 43783400.0
3 735988.0 53.428272 53.977664 54.713455 53.114334 18498300.0[253 rows x 6 columns]In [81]: fields &＃61; [&＃39;date&＃39;,&＃39;open&＃39;,&＃39;close&＃39;,&＃39;high&＃39;,&＃39;low&＃39;,&＃39;volume&＃39;]In [82]: quotesdf &＃61; pd.DataFrame(quotes,columns&＃61;fields) # 设置列属性名称In [83]: quotesdf
Out[83]: date open close high low volume
0 735983.0 60.374146 61.835916 62.336256 60.128882 9043800.0
1 735984.0 61.806486 61.453305 63.101479 61.325767 8992300.0
2 735985.0 57.283819 54.016907 57.774347 53.114334 43783400.0
3 735988.0 53.428272 53.977664 54.713455 53.114334 18498300.0

In [84]: quotesdf
Out[84]: date open close high low volume
0 735983.0 60.374146 61.835916 62.336256 60.128882 9043800.0
1 735984.0 61.806486 61.453305 63.101479 61.325767 8992300.0
2 735985.0 57.283819 54.016907 57.774347 53.114334 43783400.0[253 rows x 6 columns]In [85]: quotesdf &＃61; pd.DataFrame(quotes, index&＃61;range(1,len(quotes)&＃43;1),columns&＃61;fields) # 把index属性从0,1,2...改为1,2,3...In [86]: quotesdf
Out[86]: date open close high low volume
1 735983.0 60.374146 61.835916 62.336256 60.128882 9043800.0
2 735984.0 61.806486 61.453305 63.101479 61.325767 8992300.0
3 735985.0 57.283819 54.016907 57.774347 53.114334 43783400.0

In [88]: from datetime import dateIn [89]: firstday &＃61; date.fromordinal(735190)In [93]: firstday
Out[93]: datetime.date(2013, 11, 18)In [95]: firstday &＃61; datetime.strftime(firstday,&＃39;%Y-%m-%d&＃39;)In [96]: firstday
Out[96]: &＃39;2013-11-18&＃39;

In [120]: import pandas as pdIn [121]: dates &＃61; pd.date_range(&＃39;20170101&＃39;, periods&＃61;7) # 根据起始日期和长度生成日期序列In [122]: dates
Out[122]:
DatetimeIndex([&＃39;2017-01-01&＃39;, &＃39;2017-01-02&＃39;, &＃39;2017-01-03&＃39;, &＃39;2017-01-04&＃39;,&＃39;2017-01-05&＃39;, &＃39;2017-01-06&＃39;, &＃39;2017-01-07&＃39;],dtype&＃61;&＃39;datetime64[ns]&＃39;, freq&＃61;&＃39;D&＃39;)In [123]: import numpy as npIn [124]: dates &＃61; pd.DataFrame(np.random.randn(7,3), index&＃61;dates, columns&＃61;list(&＃39;ABC&＃39;)) # 时间序列当作index&＃xff0c;ABC当作列的name属性&＃xff0c;表内容为七行三列随机数In [125]: dates
Out[125]: A B C
2017-01-01 0.705927 0.311453 1.455362
2017-01-02 -0.331531 -0.358449 0.175375
2017-01-03 -0.284583 -1.760700 -0.582880
2017-01-04 -0.759392 -2.080658 -2.015328
2017-01-05 -0.517370 0.906072 -0.106568
2017-01-06 -0.252802 -2.135604 -0.692153
2017-01-07 -0.275184 0.142973 -1.262126

In [101]: datetime.now() # 显示当前日期和时间
Out[101]: datetime.datetime(2017, 1, 20, 16, 11, 50, 43258)
&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;
In [108]: datetime.now().month # 显示当前月份
Out[108]: 1&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;&＃61;
In [126]: import pandas as pdIn [127]: dates &＃61; pd.date_range(&＃39;2015-02-01&＃39;,periods&＃61;10)In [128]: dates
Out[128]:
DatetimeIndex([&＃39;2015-02-01&＃39;, &＃39;2015-02-02&＃39;, &＃39;2015-02-03&＃39;, &＃39;2015-02-04&＃39;,&＃39;2015-02-05&＃39;, &＃39;2015-02-06&＃39;, &＃39;2015-02-07&＃39;, &＃39;2015-02-08&＃39;,&＃39;2015-02-09&＃39;, &＃39;2015-02-10&＃39;],dtype&＃61;&＃39;datetime64[ns]&＃39;, freq&＃61;&＃39;D&＃39;)In [133]: res &＃61; pd.DataFrame(range(1,11),index&＃61;dates,columns&＃61;[&＃39;value&＃39;])In [134]: res
Out[134]: value
2015-02-01 1
2015-02-02 2
2015-02-03 3
2015-02-04 4
2015-02-05 5
2015-02-06 6
2015-02-07 7
2015-02-08 8
2015-02-09 9
2015-02-10 10

In [180]: quotesdf2.index # 显示索引
Out[180]:
Index([u&＃39;2016-01-20&＃39;, u&＃39;2016-01-21&＃39;, u&＃39;2016-01-22&＃39;, u&＃39;2016-01-25&＃39;,...u&＃39;2017-01-11&＃39;, u&＃39;2017-01-12&＃39;, u&＃39;2017-01-13&＃39;, u&＃39;2017-01-17&＃39;,u&＃39;2017-01-18&＃39;, u&＃39;2017-01-19&＃39;],dtype&＃61;&＃39;object&＃39;, length&＃61;253)In [181]: quotesdf2.columns # 显示列名
Out[181]: Index([u&＃39;open&＃39;, u&＃39;close&＃39;, u&＃39;high&＃39;, u&＃39;low&＃39;, u&＃39;volume&＃39;], dtype&＃61;&＃39;object&＃39;)In [182]: quotesdf2.values # 显示数据的值
Out[182]:
array([[ 6.03741455e&＃43;01, 6.18359160e&＃43;01, 6.23362562e&＃43;01,6.01288817e&＃43;01, 9.04380000e&＃43;06],..., [ 7.76100010e&＃43;01, 7.66900020e&＃43;01, 7.77799990e&＃43;01,7.66100010e&＃43;01, 7.79110000e&＃43;06]])In [183]: quotesdf2.describe # 显示数据描述
Out[183]:
<bound method DataFrame.describe of open close high low volume
2016-01-20 60.374146 61.835916 62.336256 60.128882 9043800.0
2016-01-21 61.806486 61.453305 63.101479 61.325767 8992300.0
2016-01-22 57.283819 54.016907 57.774347 53.114334 43783400.0

In [193]: quotesdf.head(2) # 专用方式显示头两行
Out[193]: date open close high low volume
1 735983.0 60.374146 61.835916 62.336256 60.128882 9043800.0
2 735984.0 61.806486 61.453305 63.101479 61.325767 8992300.0In [194]: quotesdf.tail(2) # 专用方式显示尾两行
Out[194]: date open close high low volume
252 736347.0 77.110001 77.489998 77.610001 76.510002 5988400.0
253 736348.0 77.610001 76.690002 77.779999 76.610001 7791100.0In [195]: quotesdf[:2] # 切片方式显示头两行
Out[195]: date open close high low volume
1 735983.0 60.374146 61.835916 62.336256 60.128882 9043800.0
2 735984.0 61.806486 61.453305 63.101479 61.325767 8992300.0In [197]: quotesdf[251:] # 切片方式显示尾两行
Out[197]: date open close high low volume
252 736347.0 77.110001 77.489998 77.610001 76.510002 5988400.0
253 736348.0 77.610001 76.690002 77.779999 76.610001 7791100.0