pandas基础-Python3

 

未完

 

for examples:

 

example 1:

 1 # Code based on Python 3.x
 2 # _*_ coding: utf-8 _*_
 3 # __Author: "LEMON"
 4 
 5 import pandas as pd
 6 
 7 d = pd.date_range('20170101', periods=7)
 8 aList = list(range(1,8))
 9 
10 df = pd.DataFrame(aList, index=d, columns=[' '])
11 df.index.name = 'value'
12 
13 print('----------df.index---------')
14 print(df.index)
15 
16 print('---------df.columns---------')
17 print(df.columns)
18 
19 print('----------df.values---------')
20 print(df.values)
21 
22 print('----------df.describe--------')
23 print(df.describe)
24 
25 print('----------information details--------')
26 print(df.head(2)) #获取开始的n条记录
27 print(df.tail(3)) #后去最后的n条记录
28 print(df[3:5])  # df[a:b]，获取第a+1至第b-1的记录

运行结果如下：

 1 ----------df.index---------
 2 DatetimeIndex(['2017-01-01', '2017-01-02', '2017-01-03', '2017-01-04',
 3                '2017-01-05', '2017-01-06', '2017-01-07'],
 4               dtype='datetime64[ns]', name='value', freq='D')
 5 ---------df.columns---------
 6 Index([' '], dtype='object')
 7 ----------df.values---------
 8 [[1]
 9  [2]
10  [3]
11  [4]
12  [5]
13  [6]
14  [7]]
15 ----------df.describe--------
16 <bound method NDFrame.describe of              
17 value        
18 2017-01-01  1
19 2017-01-02  2
20 2017-01-03  3
21 2017-01-04  4
22 2017-01-05  5
23 2017-01-06  6
24 2017-01-07  7>
25 ----------information details--------
26              
27 value        
28 2017-01-01  1
29 2017-01-02  2
30              
31 value        
32 2017-01-05  5
33 2017-01-06  6
34 2017-01-07  7
35              
36 value        
37 2017-01-04  4
38 2017-01-05  5

 

example 2:

 1 # Code based on Python 3.x
 2 # _*_ coding: utf-8 _*_
 3 # __Author: "LEMON"
 4 
 5 from pandas import Series, DataFrame
 6 import pandas as pd
 7 
 8 data = {'state': ['Ohino', 'Ohino', 'Ohino', 'Nevada', 'Nevada'],
 9         'year': [2000, 2001, 2002, 2001, 2002],
10         'pop': [1.5, 1.7, 3.6, 2.4, 2.9]}
11 
12 df = DataFrame(data, index=list(range(1, 6)),
13                columns=['year', 'state', 'pop', 'name'])
14 print(df)
15 
16 print('\n', '---------------')
17 print(list(df.ix[3]))
18 
19 print('\n', '---------------')
20 print(list(df['year']))
21 
22 aList = ['1', '2', '3', '4']
23 bList = ['aa', 'bb', 'cb', 'dd']
24 cList = ['lemon', 'apple', 'orange', 'banana']
25 
26 d = {'num': aList, 'char': bList, 'fruit': cList}
27 
28 
29 df1 = DataFrame(d, index=['a', 'b', 'c', 'd'])
30 # df2 = DataFrame(bList)
31 print('\n', '---------------')
32 print(df1)
33 #print(df1.num)
34 
35 print('\n', '---------------')
36 print(df1.ix['b'])  # 获取索引号为 'b' 的行的数据
37 
38 
39 print('\n', '---------------')
40 print(df1.ix[:2, 1:3]) # 以切片形式获取部分数据

运行结果如下：

 1  year   state  pop name
 2 1  2000   Ohino  1.5  NaN
 3 2  2001   Ohino  1.7  NaN
 4 3  2002   Ohino  3.6  NaN
 5 4  2001  Nevada  2.4  NaN
 6 5  2002  Nevada  2.9  NaN
 7 
 8  ---------------
 9 [2002, 'Ohino', 3.6000000000000001, nan]
10 
11  ---------------
12 [2000, 2001, 2002, 2001, 2002]
13 
14  ---------------
15   char   fruit num
16 a   aa   lemon   1
17 b   bb   apple   2
18 c   cb  orange   3
19 d   dd  banana   4
20 
21  ---------------
22 char        bb
23 fruit    apple
24 num          2
25 Name: b, dtype: object
26 
27  ---------------
28    fruit num
29 a  lemon   1
30 b  apple   2

 

example 3 (数据选择-DateFrame.loc()和DateFrame.iloc()) :

 1 # Code based on Python 3.x
 2 # _*_ coding: utf-8 _*_
 3 # __Author: "LEMON"
 4 
 5 from matplotlib.finance import quotes_historical_yahoo_ochl
 6 from datetime import date
 7 import pandas as pd
 8 
 9 today = date.today()
10 
11 start =(today.year-4, today.month+11, today.day-1)
12 end = (today.year-4, today.month+11, today.day+3)
13 quotes = quotes_historical_yahoo_ochl('AMX', start, end)
14 # each items in quotes is type of "tuple"
15 
16 fields = ['date', 'open', 'close', 'high', 'low', 'volume']
17 
18 quotes1 = []
19 for t in quotes:
20     t1 = list(t)
21     quotes1.append(t1)
22 # each items in quotes1 is type of "list"
23 
24 for i in range(0, len(quotes1)):
25     quotes1[i][0] = date.fromordinal(int(quotes1[i][0]))
26     # date format is changed
27 
28 df = pd.DataFrame(quotes1, index=range(1, len(quotes1)+1), columns=fields)
29 # df = pd.DataFrame(quotes1, index=['a','b','c','d','e'], columns=fields)
30 # df = df.drop(['date'], axis=1)
31 
32 print(df)
33 
34 print(df['close'].mean())  #计算某列的mean值
35 # print(dict(df.mean())['close'])  #计算某列的mean值
36 
37 print(df.sort_values(['open'],ascending = True)) #进行排序，默认(True)是升序
38 print(df[df.open>=21].date)
39 
40 
41 
42 # index是整数
43 print(df.loc[2:5, 'date':'close'])
44 print(df.loc[[2,5],['open','close']])  
45 # loc方法在行和列的选择上是标签形式，可以是连续的选择，或者单个行或列的选择
46 print(df.iloc[1:6,0:4])  #iloc方法以切片形式选取数据
47 
48       
49 # index是标签形式
50 # print(df.loc['a':'d', 'date':'close'])
51 # print(df.loc[['b','e'],['open','close']])  
52 # loc方法在行和列的选择上是标签形式，可以是连续的选择，或者单个行或列的选择
53 
54 # 根据判断条件来选择数据
55 print(df[(df.index>=4) & (df.open>=21)])
56 
57 
58 # DateFrame 的均值
59 print(df.mean())  # 默认计算每列的均值
60 print(df.mean(axis=1))  # axis=1是计算每行的均值
61 
62 
63 '''
64 # 获取多只股票的信息
65 d1 = (today.year-1, today.month+11, today.day)
66 
67 aList = ['BABA', 'KO', 'AMX'] # List of the stock code of companys
68 
69 
70 for i in aList:
71     q1 = quotes_historical_yahoo_ochl(i, d1, today)
72     df1 = pd.DataFrame(q1)
73     print(df1)
74 '''

运行结果如下：

 1          date       open      close       high        low     volume
 2 1  2013-12-03  20.999551  21.156955  21.184731  20.795851  5152600.0
 3 2  2013-12-04  20.971773  20.934738  21.064364  20.703261  5174400.0
 4 3  2013-12-05  20.518079  20.545857  21.231027  20.379193  7225600.0
 5 4  2013-12-06  21.166215  20.601411  21.295841  20.536598  9989500.0
 6 20.80974025
 7 20.80974025
 8          date       open      close       high        low     volume
 9 3  2013-12-05  20.518079  20.545857  21.231027  20.379193  7225600.0
10 2  2013-12-04  20.971773  20.934738  21.064364  20.703261  5174400.0
11 1  2013-12-03  20.999551  21.156955  21.184731  20.795851  5152600.0
12 4  2013-12-06  21.166215  20.601411  21.295841  20.536598  9989500.0
13 4    2013-12-06
14 Name: date, dtype: object
15 
16 runfile('E:/Python/Anaco/test_yahoo.py', wdir='E:/Python/Anaco')
17          date       open      close       high        low     volume
18 1  2013-12-03  20.999551  21.156955  21.184731  20.795851  5152600.0
19 2  2013-12-04  20.971773  20.934738  21.064364  20.703261  5174400.0
20 3  2013-12-05  20.518079  20.545857  21.231027  20.379193  7225600.0
21 4  2013-12-06  21.166215  20.601411  21.295841  20.536598  9989500.0
22 20.80974025
23          date       open      close       high        low     volume
24 3  2013-12-05  20.518079  20.545857  21.231027  20.379193  7225600.0
25 2  2013-12-04  20.971773  20.934738  21.064364  20.703261  5174400.0
26 1  2013-12-03  20.999551  21.156955  21.184731  20.795851  5152600.0
27 4  2013-12-06  21.166215  20.601411  21.295841  20.536598  9989500.0
28 4    2013-12-06
29 Name: date, dtype: object
30          date       open      close
31 2  2013-12-04  20.971773  20.934738
32 3  2013-12-05  20.518079  20.545857
33 4  2013-12-06  21.166215  20.601411
34         open      close
35 2  20.971773  20.934738
36 5        NaN        NaN
37          date       open      close       high
38 2  2013-12-04  20.971773  20.934738  21.064364
39 3  2013-12-05  20.518079  20.545857  21.231027
40 4  2013-12-06  21.166215  20.601411  21.295841
41          date       open      close       high        low     volume
42 4  2013-12-06  21.166215  20.601411  21.295841  20.536598  9989500.0
43 open      2.091390e+01
44 close     2.080974e+01
45 high      2.119399e+01
46 low       2.060373e+01
47 volume    6.885525e+06
48 dtype: float64
49 1    1.030537e+06
50 2    1.034897e+06
51 3    1.445137e+06
52 4    1.997917e+06
53 dtype: float64
View Code

 

examples 4: 求微软公司（MSFT）2015年每月股票收盘价的平均值。

  1 # Code based on Python 3.x
  2 # _*_ coding: utf-8 _*_
  3 # __Author: "LEMON"
  4 
  5 # 求微软公司（MSFT）2015年每月股票收盘价的平均值。
  6 
  7 
  8 #Method 1 (update)
  9 
 10 from matplotlib.finance import quotes_historical_yahoo_ochl
 11 from datetime import date
 12 import pandas as pd
 13 from datetime import datetime
 14 
 15 today = date.today()
 16 fields = ['date', 'open', 'close', 'high', 'low', 'volume']
 17 
 18 start = (today.year - 3, today.month, today.day)
 19 end = today
 20 quotes = quotes_historical_yahoo_ochl('MSFT', start, end)
 21 # each items in quotes is type of "tuple"
 22 
 23 df = pd.DataFrame(quotes, index=range(1, len(quotes) + 1), columns=fields)
 24 
 25 list = df.date.tolist()
 26 list1 = []
 27 for x in list:
 28     x = date.fromordinal(int(x))
 29     y = date.strftime(x, '%Y/%m')
 30     list1.append(y)
 31 
 32 # print(list1)
 33 df1 = df.set_index([list1]).drop('date',axis=1)
 34 # 把日期设置成索引，并删除“date”列
 35 
 36 df2 = df1['2015/01':'2015/12']  #选取2015年的数据
 37 print(df2.groupby(df2.index).close.mean())
 38 # 将数据按index进行聚类分析，并计算收盘价“close”的均值
 39 
 40 
 41 # -----------------------------------------------------
 42 # #Method 1 (old)
 43 #
 44 # from matplotlib.finance import quotes_historical_yahoo_ochl
 45 # from datetime import date
 46 # import pandas as pd
 47 # from datetime import datetime
 48 #
 49 #
 50 # today = date.today()
 51 # fields = ['date', 'open', 'close', 'high', 'low', 'volume']
 52 #
 53 # start2 = (today.year - 3, today.month, today.day)
 54 # end2 = today
 55 # quotes2 = quotes_historical_yahoo_ochl('MSFT', start2, end2)
 56 # # each items in quotes is type of "tuple"
 57 #
 58 # quotes3 = []
 59 # for t in quotes2:
 60 #     t1 = list(t)
 61 #     quotes3.append(t1)
 62 # # each items in quotes1 is type of "list"
 63 #
 64 # for i in range(0, len(quotes3)):
 65 #     quotes3[i][0] = date.fromordinal(int(quotes3[i][0]))
 66 #     # date format is changed
 67 #
 68 # df2 = pd.DataFrame(quotes3, index=range(1, len(quotes3) + 1), columns=fields)
 69 #
 70 # df2['date'] = pd.to_datetime(df2['date'], format='%Y-%m-%d')  # 转化成pandas的日期格式
 71 # # print(df2)
 72 #
 73 # start2015 = datetime(2015,1,1)
 74 # end2015 = datetime(2015,12,31)
 75 # # start2015 = datetime.strptime('2015-1-1', '%Y-%m-%d')
 76 # # # 将'2015-1-1'字符串设置为时间格式
 77 # # end2015 = datetime.strptime('2015-12-31', '%Y-%m-%d')
 78 # # # 将'2015-12-31'字符串设置为时间格式
 79 #
 80 # df1 = df2[(start2015 <= df2.date) & (df2.date <= end2015)]
 81 # # 通过时间条件来选择2015年的记录
 82 #
 83 # permonth1 = df1.date.dt.to_period('M')  #data per month
 84 # g_month1 = df1.groupby(permonth1)
 85 # g_closequotes = g_month1['close']
 86 #
 87 # s_month = g_closequotes.mean()  # s_month is Series class
 88 # s_month.index.name = 'date_index'
 89 #
 90 # print(s_month)
 91 # -----------------------------------------------------
 92 
 93 # =================================================================
 94 # Method 2
 95 
 96 # from matplotlib.finance import quotes_historical_yahoo_ochl
 97 # from datetime import date
 98 #
 99 # import pandas as pd
100 # today = date.today()
101 # start = (today.year-3, today.month, today.day)
102 # quotesMS = quotes_historical_yahoo_ochl('MSFT', start, today)
103 # attributes=['date','open','close','high','low','volume']
104 # quotesdfMS = pd.DataFrame(quotesMS, columns= attributes)
105 #
106 #
107 #
108 # list = []
109 # for i in range(0, len(quotesMS)):
110 #     x = date.fromordinal(int(quotesMS[i][0]))
111 #     y = date.strftime(x, '%y/%m/%d')
112 #     list.append(y)
113 # quotesdfMS.index = list
114 # quotesdfMS = quotesdfMS.drop(['date'], axis = 1)
115 # list = []
116 # quotesdfMS15 = quotesdfMS['15/01/01':'15/12/31']
117 #
118 # print(quotesdfMS15)
119 #
120 # for i in range(0, len(quotesdfMS15)):
121 #     list.append(int(quotesdfMS15.index[i][3:5])) #get month just like '02'
122 # quotesdfMS15['month'] = list
123 # print(quotesdfMS15.groupby('month').mean().close)
124 # =================================================================

输出结果如下：

 

 1 2015/01    43.124433
 2 2015/02    40.956772
 3 2015/03    40.203918
 4 2015/04    41.477685
 5 2015/05    45.472291
 6 2015/06    44.145879
 7 2015/07    43.807541
 8 2015/08    43.838895
 9 2015/09    42.114155
10 2015/10    47.082882
11 2015/11    52.252878
12 2015/12    53.916431
13 Name: close, dtype: float64

 

posted @ 2017-01-02 23:14  lemonbit  阅读(1937)  评论(0)  编辑  收藏  举报