python数据分析实战-第5章-pandas数据读写

Posted learnfromnow

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了python数据分析实战-第5章-pandas数据读写相关的知识，希望对你有一定的参考价值。

第5章　pandas：数据读写　　91

5.1　I/O API 工具　　91

5.2　CSV和文本文件　　92

5.3　读取CSV或文本文件中的数据　　92

1
 
from pandas import *

myCSV_01.csv
white,red,blue,green,animal
1,5,2,3,cat
2,7,8,5,dog
3,3,6,7,horse
2,2,8,3,duck
4,4,2,1,mouse

1
2
 
csvframe = read_csv(‘myCSV_01.csv‘)
print(csvframe)
 
   white  red  blue  green animal
0      1    5     2      3    cat
1      2    7     8      5    dog
2      3    3     6      7  horse
3      2    2     8      3   duck
4      4    4     2      1  mouse

white,red,blue,green,animal
1,5,2,3,cat
2,7,8,5,dog
3,3,6,7,horse
2,2,8,3,duck
4,4,2,1,mouse

1
2
 
temp = read_table(‘ch05_01.csv‘,sep=‘,‘)
print(temp)
 
   white  red  blue  green animal
0      1    5     2      3    cat
1      2    7     8      5    dog
2      3    3     6      7  horse
3      2    2     8      3   duck
4      4    4     2      1  mouse

1,5,2,3,cat
2,7,8,5,dog
3,3,6,7,horse
2,2,8,3,duck
4,4,2,1,mouse

1
2
 
temp = read_csv(‘ch05_02.csv‘)
print(temp)
 
   1  5  2  3    cat
0  2  7  8  5    dog
1  3  3  6  7  horse
2  2  2  8  3   duck
3  4  4  2  1  mouse

1
2
 
temp = read_csv(‘ch05_02.csv‘, header=None)
print(temp)
 
   0  1  2  3      4
0  1  5  2  3    cat
1  2  7  8  5    dog
2  3  3  6  7  horse
3  2  2  8  3   duck
4  4  4  2  1  mouse

1
2
 
temp = read_csv(‘ch05_02.csv‘, names=[‘white‘,‘red‘,‘blue‘,‘green‘,‘animal‘])
print(temp)
 
   white  red  blue  green animal
0      1    5     2      3    cat
1      2    7     8      5    dog
2      3    3     6      7  horse
3      2    2     8      3   duck
4      4    4     2      1  mouse

color,status,item1,item2,item3
black,up,3,4,6
black,down,2,6,7
white,up,5,5,5
white,down,3,3,2
white,left,1,2,1
red,up,2,2,2
red,down,1,1,4

1
2
 
temp = read_csv(‘ch05_03.csv‘, index_col=[‘color‘,‘status‘])
print(temp)
 
              item1  item2  item3
color status                     
black up          3      4      6
      down        2      6      7
white up          5      5      5
      down        3      3      2
      left        1      2      1
red   up          2      2      2
      down        1      1      4

5.3.1　用RegExp解析TXT文件　　94

white red blue green
1 5 2 3
2 7 8 5
3 3 6 7

1
2
 
temp = read_table(‘ch05_04.txt‘,sep=‘s+‘)
print(temp)
 
   white  red  blue  green
0      1    5     2      3
1      2    7     8      5
2      3    3     6      7

ch05_05.txt
000END123AAA122
001END124BBB321
002END125CCC333

1
2
 
temp = read_table(‘ch05_05.txt‘,sep=‘D+‘,header=None)
print(temp)
 
   0    1    2
0  0  123  122
1  1  124  321
2  2  125  333


D:ProgramDataAnaconda3_32libsite-packagesipykernel_launcher.py:1: ParserWarning: Falling back to the ‘python‘ engine because the ‘c‘ engine does not support regex separators (separators > 1 char and different from ‘s+‘ are interpreted as regex); you can avoid this warning by specifying engine=‘python‘.
  """Entry point for launching an IPython kernel.

Table 5-1. Metacharacters
. single character, except newline
d digit
D non-digit character
s whitespace character
S non-whitespace character
new line character
tab character
uxxxx unicode character specified by the hexadecimal number xxxxch05_06.txt

##### LOG FILE

This file has been generated by automatic system
white,red,blue,green,animal
12-Feb-2015: Counting of animals inside the house
1,5,2,3,cat
2,7,8,5,dog
13-Feb-2015: Counting of animals outside the house
3,3,6,7,horse
2,2,8,3,duck
4,4,2,1,mouse

1
2
 
temp = read_table(‘ch05_06.txt‘,sep=‘,‘,skiprows=[0,1,3,6])
print(temp)
 
   white  red  blue  green animal
0      1    5     2      3    cat
1      2    7     8      5    dog
2      3    3     6      7  horse
3      2    2     8      3   duck
4      4    4     2      1  mouse

5.3.2　从TXT文件读取部分数据　　96

1,5,2,3,cat
2,7,8,5,dog
3,3,6,7,horse
2,2,8,3,duck
4,4,2,1,mouse

1
2
 
temp = read_csv(‘ch05_02.csv‘,skiprows=[2],nrows=3,header=None)
print(temp)
 
   0  1  2  3     4
0  1  5  2  3   cat
1  2  7  8  5   dog
2  2  2  8  3  duck

white,red,blue,green,animal
1,5,2,3,cat
2,7,8,5,dog
3,3,6,7,horse
2,2,8,3,duck
4,4,2,1,mouse

1
2
3
4
5
6
7
8
 
out = Series()
i = 0
pieces = read_csv(‘ch05_01.csv‘,chunksize=3)
for piece in pieces:
    print(piece)
    out.set_value(i,piece[‘white‘].sum())
    i = i + 1
print(out)
 
   white  red  blue  green animal
0      1    5     2      3    cat
1      2    7     8      5    dog
2      3    3     6      7  horse
   white  red  blue  green animal
3      2    2     8      3   duck
4      4    4     2      1  mouse
0    6
1    6
dtype: int64

5.3.3　往CSV文件写入数据　　97

1
2
3
 
import numpy as np
frame2 = DataFrame(np.arange(16).reshape((4,4)), columns = [‘ball‘,‘pen‘,‘pencil‘,‘paper‘])
print(frame2)
 
   ball  pen  pencil  paper
0     0    1       2      3
1     4    5       6      7
2     8    9      10     11
3    12   13      14     15

1
 
frame2.to_csv(‘ch05_07.csv‘)
 
1
 
frame2.to_csv(‘ch05_07b.csv‘, index=False, header=False)
 
1
2
 
frame3 = read_csv(‘ch05_08.csv‘)
print(frame3)
 
  Unnamed: 0  ball  mug  paper   pen  pencil
0       blue   6.0  NaN    NaN   6.0     NaN
1      green   NaN  NaN    NaN   NaN     NaN
2        red   NaN  NaN    NaN   NaN     NaN
3      white  20.0  NaN    NaN  20.0     NaN
4     yellow  19.0  NaN    NaN  19.0     NaN

1
 
frame3.to_csv(‘ch05_08.csv‘)
 
1
 
frame3.to_csv(‘ch05_09.csv‘, na_rep =‘NaN‘)

ch05_08.csv
,ball,mug,paper,pen,pencil
blue,6.0,,,6.0,
green,,,,,
red,,,,,
white,20.0,,,20.0,
yellow,19.0,,,19.0,ch05_09.csv
,ball,mug,paper,pen,pencil
blue,6.0,NaN,NaN,6.0,NaN
green,NaN,NaN,NaN,NaN,NaN
red,NaN,NaN,NaN,NaN,NaN
white,20.0,NaN,NaN,20.0,NaN
yellow,19.0,NaN,NaN,19.0,NaN

5.4　读写HTML文件　　98

5.4.1　写入数据到HTML文件　　99

1
2
 
import pandas as pd
frame = pd.DataFrame(np.arange(4).reshape(2,2))
 
1
 
print(frame.to_html())
 
<table border="1" class="dataframe">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>0</th>
      <th>1</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <th>0</th>
      <td>0</td>
      <td>1</td>
    </tr>
    <tr>
      <th>1</th>
      <td>2</td>
      <td>3</td>
    </tr>
  </tbody>
</table>

1
2
3
4
 
frame = pd.DataFrame( np.random.random((4,4)),
    index = [‘white‘,‘black‘,‘red‘,‘blue‘],
    columns = [‘up‘,‘down‘,‘right‘,‘left‘])
print(frame)
 
             up      down     right      left
white  0.821537  0.070376  0.131624  0.718632
black  0.723164  0.409424  0.554343  0.361086
red    0.671485  0.993762  0.316291  0.999724
blue   0.834104  0.565786  0.922212  0.166467

1
2
3
4
5
6
7
8
9
10
 
s = [‘<HTML>‘]
s.append(‘<HEAD><TITLE>My DataFrame</TITLE></HEAD>‘)
s.append(‘<BODY>‘)
s.append(frame.to_html())
s.append(‘</BODY></HTML>‘)
html = ‘‘.join(s)

html_file = open(‘myFrame.html‘,‘w‘)
html_file.write(html)
html_file.close()

打开html
技术分享图片

5.4.2　从HTML文件读取数据　　100

1
2
 
web_frames = pd.read_html(‘myFrame.html‘)
print(web_frames[0])
 
  Unnamed: 0        up      down     right      left
0      white  0.821537  0.070376  0.131624  0.718632
1      black  0.723164  0.409424  0.554343  0.361086
2        red  0.671485  0.993762  0.316291  0.999724
3       blue  0.834104  0.565786  0.922212  0.166467

1
2
 
ranking = pd.read_html(‘http://www.meccanismocomplesso.org/en/meccanismo-complesso-sito-2/classifica-punteggio/‘)
print(ranking[0])
 
       #                        Nome    Exp  Livelli
0      1                 Fabio Nelli  17521      NaN
1      2                       admin   9029      NaN
2      3                 BrunoOrsini   2124      NaN
3      4                   Berserker    700      NaN
4      5                    Dnocioni    543      NaN
5      6             albertosallusti    409      NaN
6      7                         Jon    231      NaN
7      8                        Mr.Y    180      NaN
8      9             michele sisinni    157      NaN
9     10                      Selina    136      NaN
10    11                     Massimo    127      NaN
11    12             Beniamino Feula    122      NaN
12    13              stefano gustin    121      NaN
13    14           Maurizio Andreoli    111      NaN
14    15                Pietro Baima    108      NaN
15    16  Cecilia Lalatta Costerbosa    108      NaN
16    17              Leonardo Zampi    108      NaN
17    18               Davide Aloisi    106      NaN
18    19               gildalombardi    105      NaN
19    20               Telerobotlabs    104      NaN
20    21            Marco Contigiani    101      NaN
21    22                    berillio     58      NaN
22    23                         ron     55      NaN
23    24                  Titanic4wd     43      NaN
24    25                         deg     40      NaN
25    26                        al45     40      NaN
26    27                      il_mix     38      NaN
27    28                     AndreaC     35      NaN
28    29                  Sergio fly     32      NaN
29    30                     bigazzi     32      NaN
..   ...                         ...    ...      ...
220  221                        pozi      3      NaN
221  222                      mattia      3      NaN
222  223             mauro.menegazzi      3      NaN
223  224                      cico89      3      NaN
224  225                       eta38      3      NaN
225  226                Chinje Chang      3      NaN
226  227                 fraschettin      2      NaN
227  228                       Rocco      2      NaN
228  229                     Dimitri      2      NaN
229  230                      Arturo      2      NaN
230  231           Paolo Indennidate      2      NaN
231  232                fabioroberto      2      NaN
232  233                     ycomyca      2      NaN
233  234                         bdb      2      NaN
234  235             paolotirispetta      2      NaN
235  236                   Roberto72      2      NaN
236  237                 Christian76      2      NaN
237  238                    paolos46      2      NaN
238  239                    Giolat90      2      NaN
239  240                giampyypmaig      1      NaN
240  241              Marco Corbetta      1      NaN
241  242                     softeng      1      NaN
242  243                    strechum      1      NaN
243  244                      an6991      1      NaN
244  245                       plato      1      NaN
245  246              CarloAlberto98      1      NaN
246  247                        cris      1      NaN
247  248                  emilibassi      1      NaN
248  249                    mehrbano      1      NaN
249  250              NIKITA PANCHAL      1      NaN

[250 rows x 4 columns]

5.5　从XML读取数据　　101

books.xml
<?xml version=”1.0”?>

272103_1_EnRoss, Mark Computer 23.56 2014-22-01 272103_1_EnBracket, Barbara Computer 35.95 2014-12-16

1
 
from lxml import objectify
 
1
2
 
xml = objectify.parse(‘books.xml‘)
xml
 
<lxml.etree._ElementTree at 0xc5d74b8>

1
2
3
 
root = xml.getroot()
print(root.Book.Author)
print(root.Book.PublishDate)
 
272103_1_EnRoss, Mark
2014-22-01

1
 
root.getchildren()
 
[<Element Book at 0xc761378>, <Element Book at 0xc761d78>]

1
 
[child.tag for child in root.Book.getchildren()]
 
[‘Author‘, ‘Title‘, ‘Genre‘, ‘Price‘, ‘PublishDate‘]

1
 
[child.text for child in root.Book.getchildren()]
 
[‘272103_1_EnRoss, Mark‘, ‘XML Cookbook‘, ‘Computer‘, ‘23.56‘, ‘2014-22-01‘]

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
 
def etree2df(root):
    column_names = []
    for i in range(0,len(root.getchildren()[0].getchildren())):
        column_names.append(root.getchildren()[0].getchildren()[i].tag)
        
    xml_frame = pd.DataFrame(columns=column_names)
    for j in range(0, len(root.getchildren())):
        obj = root.getchildren()[j].getchildren()
        texts = []
        for k in range(0, len(column_names)):
            texts.append(obj[k].text)
        row = dict(zip(column_names, texts))
        
        row_s = pd.Series(row)
        row_s.name = j
        xml_frame = xml_frame.append(row_s)
    return xml_frame
 
1
2
 
temp = etree2df(root)
print(temp)
 
                        Author            Title     Genre  Price PublishDate
0        272103_1_EnRoss, Mark     XML Cookbook  Computer  23.56  2014-22-01
1  272103_1_EnBracket, Barbara  XML for Dummies  Computer  35.95  2014-12-16

5.6　读写Microsoft Excel文件　　103

1
2
 
temp = pd.read_excel(‘data.xls‘)
print(temp)
 
   white  red  green  black
a     12   23     17     18
b     22   16     19     18
c     14   23     22     21

1
2
 
temp = pd.read_excel(‘data.xls‘,‘Sheet2‘)
print(temp)
 
   yellow  purple  blue  orange
A      11      16    44      22
B      20      22    23      44
C      30      31    37      32

1
2
 
temp = pd.read_excel(‘data.xls‘,1)
print(temp)
 
   yellow  purple  blue  orange
A      11      16    44      22
B      20      22    23      44
C      30      31    37      32

1
2
3
4
 
frame = pd.DataFrame(np.random.random((4,4)),
    index = [‘exp1‘,‘exp2‘,‘exp3‘,‘exp4‘],
    columns = [‘Jan2015‘,‘Fab2015‘,‘Mar2015‘,‘Apr2005‘])
print(frame)
 
       Jan2015   Fab2015   Mar2015   Apr2005
exp1  0.610508  0.434578  0.019900  0.099366
exp2  0.306480  0.961355  0.073820  0.742758
exp3  0.232366  0.197025  0.312307  0.697120
exp4  0.374647  0.123761  0.521675  0.641097

1
 
frame.to_excel(‘data2.xlsx‘)

技术分享图片

5.7　JSON数据　　105

1
2
3
4
5
 
frame = pd.DataFrame(np.arange(16).reshape(4,4),
    index=[‘white‘,‘black‘,‘red‘,‘blue‘],
    columns=[‘up‘,‘down‘,‘right‘,‘left‘])
print(frame)
frame.to_json(‘frame.json‘)
 
       up  down  right  left
white   0     1      2     3
black   4     5      6     7
red     8     9     10    11
blue   12    13     14    15

{“up”:{“white”:0,”black”:4,”red”:8,”blue”:12},”down”:{“white”:1,”black”:5,”red”:9,”blue”:13},”right”:{“white”:2,”black”:6,”red”:10,”blue”:14},”left”:{“white”:3,”black”:7,”red”:11,”blue”:15}}

1
2
 
temp = pd.read_json(‘frame.json‘)
print(temp)
 
       down  left  right  up
black     5     7      6   4
blue     13    15     14  12
red       9    11     10   8
white     1     3      2   0

1
2
3
4
5
6
7
8
9
 
from pandas.io.json import json_normalize
file = open(‘books.json‘,‘r‘)
text = file.read()
text = json.loads(text)
temp = json_normalize(text,‘books‘)
print(temp)
print()
temp = json_normalize(text,‘books‘,[‘writer‘,‘nationality‘])
print(temp)
 
   price                title
0  23.56         XML Cookbook
1  50.70  Python Fundamentals
2  12.30    The NumPy library
3  28.60      Java Enterprise
4  31.35                HTML5
5  28.00   Python for Dummies

   price                title           writer nationality
0  23.56         XML Cookbook        Mark Ross         USA
1  50.70  Python Fundamentals        Mark Ross         USA
2  12.30    The NumPy library        Mark Ross         USA
3  28.60      Java Enterprise  Barbara Bracket          UK
4  31.35                HTML5  Barbara Bracket          UK
5  28.00   Python for Dummies  Barbara Bracket          UK


D:ProgramDataAnaconda3_32libsite-packagesipykernel_launcher.py:4: FutureWarning: pandas.json is deprecated and will be removed in a future version.
You can access loads as pandas.io.json.loads
  after removing the cwd from sys.path.

5.8　HDF5格式　　107

1
2
3
4
5
6
7
 
from pandas.io.pytables import HDFStore
frame = pd.DataFrame(np.arange(16).reshape(4,4),
    index=[‘white‘,‘black‘,‘red‘,‘blue‘],
    columns=[‘up‘,‘down‘,‘right‘,‘left‘])
store = HDFStore(‘mydata.h5‘)
store[‘obj1‘] = frame
store
 
<class ‘pandas.io.pytables.HDFStore‘>
File path: mydata.h5
/obj1            frame        (shape->[4,4])

1
2
 
temp = store[‘obj1‘]
print(temp)
 
       up  down  right  left
white   0     1      2     3
black   4     5      6     7
red     8     9     10    11
blue   12    13     14    15

5.9　pickle——Python对象序列化　　108

5.9.1　用pickle实现Python对象序列化　　109

1
2
3
4
 
import pickle as pickle
data = { ‘color‘: [‘white‘,‘red‘], ‘value‘: [5, 7]}
pickled_data = pickle.dumps(data)
print(pickled_data)
 
b‘x80x03}qx00(Xx05x00x00x00colorqx01]qx02(Xx05x00x00x00whiteqx03Xx03x00x00x00redqx04eXx05x00x00x00valueqx05]qx06(Kx05Kx07eu.‘

1
2
 
nframe = pickle.loads(pickled_data)
nframe
 
{‘color‘: [‘white‘, ‘red‘], ‘value‘: [5, 7]}

5.9.2　用pandas实现对象序列化　　109

1
2
3
4
5
 
frame = pd.DataFrame(np.arange(16).reshape(4,4), index = [‘up‘,‘down‘,‘left‘,‘right‘])
frame.to_pickle(‘frame.pkl‘)

temp = pd.read_pickle(‘frame.pkl‘)
print(temp)
 
        0   1   2   3
up      0   1   2   3
down    4   5   6   7
left    8   9  10  11
right  12  13  14  15

5.10　对接数据库　　110

1
2
3
4
5
6
7
8
9
10
11
 
from sqlalchemy import create_engine
#For PostgreSQL
engine = create_engine(‘postgresql://scott:[email protected]:5432/mydatabase‘)
#For MySQL
engine = create_engine(‘mysql+mysqldb://scott:[email protected]/foo‘)
#For Oracle
engine = create_engine(‘oracle://scott:[email protected]:1521/sidname‘)
#For MSSQL
engine = create_engine(‘mssql+pyodbc://mydsn‘)
#For SQLite
engine = create_engine(‘sqlite:///foo.db‘)

上面代码运行可能会出现错误，根据运行结果，缺少什么使用pip安装什么就可以了。

5.10.1　SQLite3数据读写　　111

1
2
3
 
frame = pd.DataFrame( np.arange(20).reshape(4,5),
    columns=[‘white‘,‘red‘,‘blue‘,‘black‘,‘green‘])
print(frame)
 
   white  red  blue  black  green
0      0    1     2      3      4
1      5    6     7      8      9
2     10   11    12     13     14
3     15   16    17     18     19

1
2
3
4
5
 
engine = create_engine(‘sqlite:///foo.db‘)
frame.to_sql(‘colors‘,engine)

temp = pd.read_sql(‘colors‘,engine)
print(temp)
 
   index  white  red  blue  black  green
0      0      0    1     2      3      4
1      1      5    6     7      8      9
2      2     10   11    12     13     14
3      3     15   16    17     18     19

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
 
import sqlite3
query = """
CREATE TABLE test
(a VARCHAR(20), b VARCHAR(20),
c REAL, d INTEGER
);"""
con = sqlite3.connect(‘:memory:‘)
con.execute(query)
con.commit()

data = [(‘white‘,‘up‘,1,3),
        (‘black‘,‘down‘,2,8),
        (‘green‘,‘up‘,4,4),
        (‘red‘,‘down‘,5,5)]
stmt = "INSERT INTO test VALUES(?,?,?,?)"
con.executemany(stmt, data)
con.commit()
 
1
2
3
4
 
cursor = con.execute(‘select * from test‘)
print(cursor)
rows = cursor.fetchall()
rows
 
<sqlite3.Cursor object at 0x0D591820>





[(‘white‘, ‘up‘, 1.0, 3),
 (‘black‘, ‘down‘, 2.0, 8),
 (‘green‘, ‘up‘, 4.0, 4),
 (‘red‘, ‘down‘, 5.0, 5)]

1
 
cursor.description
 
((‘a‘, None, None, None, None, None, None),
 (‘b‘, None, None, None, None, None, None),
 (‘c‘, None, None, None, None, None, None),
 (‘d‘, None, None, None, None, None, None))

1
2
 
temp = pd.DataFrame(rows, columns=[‘a‘,‘b‘,‘c‘,‘d‘])
print(temp)
 
       a     b    c  d
0  white    up  1.0  3
1  black  down  2.0  8
2  green    up  4.0  4
3    red  down  5.0  5

5.10.2　PostgreSQL数据读写　　112

1
 
engine = create_engine(‘postgresql://scott:[email protected]:5432/mydatabase‘)
 
1
2
3
4
5
6
 
import pandas as pd
import numpy as np
frame = pd.DataFrame(np.random.random((4,4)),
    index=[‘exp1‘,‘exp2‘,‘exp3‘,‘exp4‘],
    columns=[‘feb‘,‘mar‘,‘apr‘,‘may‘]);
frame.to_sql(‘dataframe‘,engine)

postgres=# SELECT * FROM DATAFRAME;

技术分享图片

1
2
 
temp = pd.read_sql_table(‘dataframe‘,engine)
print(temp)
 
  index       feb       mar       apr       may
0  exp1  0.406820  0.964683  0.181662  0.660217
1  exp2  0.573869  0.940819  0.426104  0.484574
2  exp3  0.649881  0.059990  0.616504  0.681356
3  exp4  0.061554  0.733131  0.998748  0.127283

1
2
 
temp = pd.read_sql_query(‘SELECT index,apr,may FROM DATAFRAME WHERE apr > 0.5‘,engine)
print(temp)
 
  index       apr       may
0  exp3  0.616504  0.681356
1  exp4  0.998748  0.127283

5.11　NoSQL数据库MongoDB数据读写　　114

1
2
3
4
 
import pymongo
client = pymongo.MongoClient(‘localhost‘,27017)
db = client.mydatabase
db
 
Database(MongoClient(host=[‘localhost:27017‘], document_class=dict, tz_aware=False, connect=True), ‘mydatabase‘)

1
 
client[‘mydatabase‘]
 
Database(MongoClient(host=[‘localhost:27017‘], document_class=dict, tz_aware=False, connect=True), ‘mydatabase‘)

1
2
 
collection = db.mycollection
db[‘mycollection‘]
 
Collection(Database(MongoClient(host=[‘localhost:27017‘], document_class=dict, tz_aware=False, connect=True), ‘mydatabase‘), ‘mycollection‘)

1
 
collection
 
Collection(Database(MongoClient(host=[‘localhost:27017‘], document_class=dict, tz_aware=False, connect=True), ‘mydatabase‘), ‘mycollection‘)

1
2
3
 
frame = pd.DataFrame( np.arange(20).reshape(4,5),
    columns=[‘white‘,‘red‘,‘blue‘,‘black‘,‘green‘])
print(frame)
 
   white  red  blue  black  green
0      0    1     2      3      4
1      5    6     7      8      9
2     10   11    12     13     14
3     15   16    17     18     19

1
2
3
 
import json
record = json.loads(frame.T.to_json()).values()
record
 
dict_values([{‘white‘: 0, ‘red‘: 1, ‘blue‘: 2, ‘black‘: 3, ‘green‘: 4}, {‘white‘: 5, ‘red‘: 6, ‘blue‘: 7, ‘black‘: 8, ‘green‘: 9}, {‘white‘: 10, ‘red‘: 11, ‘blue‘: 12, ‘black‘: 13, ‘green‘: 14}, {‘white‘: 15, ‘red‘: 16, ‘blue‘: 17, ‘black‘: 18, ‘green‘: 19}])

1
 
collection.mydocument.insert(record)
 
1
2
3
4
5
6
 
cursor = collection[‘mydocument‘].find()
print(type(cursor))
dataframe = (list(cursor))
data = pd.DataFrame(dataframe)
del data[‘_id‘]
print(data)
 
<class ‘pymongo.cursor.Cursor‘>
   black  blue  green  red  white
0      3     2      4    1      0
1      8     7      9    6      5
2     13    12     14   11     10
3     18    17     19   16     15

5.12　小结　　116



































































以上是关于python数据分析实战-第5章-pandas数据读写的主要内容，如果未能解决你的问题，请参考以下文章

python数据分析实战-第6章-深入pandas数据处理

python数据分析实战-第2章-ptyhon世界简介

python数据分析实战-第11章-识别手写数字

python数据分析实战-第9章-数据分析实例气象数据

Scala大数据深度好课Scala大数据操作实战

python数据分析实战-第3章-numpy库