原文地址：

https://github.com/AsuraDong/Blog/blob/master/Articles/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0/%E6%95%B0%E6%8D%AE%E5%8A%A0%E8%BD%BD%E5%AD%98%E5%82%A8%E5%92%8C%E6%96%87%E4%BB%B6%E6%A0%BC%E5%BC%8F.md

1.讀取文本格式數據

import pandas as pd
import numpy as np
import sys
import pymysql

# 圖片：pandas解析函數

df = pd.read_csv(‘ex1.csv‘)
print(df)
 

   a   b   c   d message
0  1   2   3   4   hello
1  5   6   7   8   world
2  9  10  11  12     foo

df = pd.read_table(‘ex1.csv‘,sep=‘,‘) #可以使用read_table，但必須指定分隔符
# sep還可以是正則表達式
print(df)

   a   b   c   d message
0  1   2   3   4   hello
1  5   6   7   8   world
2  9  10  11  12     foo

df = pd.read_csv(‘ex2.csv‘,header = None)#不是每一個csv都有header
print(df)
 

   0   1   2   3      4
0  1   2   3   4  hello
1  5   6   7   8  world
2  9  10  11  12    foo

df = pd.read_csv(‘ex2.csv‘,names=[‘a‘,‘b‘,‘c‘,‘d‘,‘names‘])#指定名字
print(df)

   a   b   c   d  names
0  1   2   3   4  hello
1  5   6   7   8  world
2  9  10  11  12    foo

names=[‘a‘,‘b‘,‘c‘,‘d‘,‘names‘]
df = pd.read_csv(‘ex2.csv‘,names=names,index_col=‘names‘) #將names做成索引
print(df)
#names對應三個，abcd分別有對應的
 

       a   b   c   d
names               
hello  1   2   3   4
world  5   6   7   8
foo    9  10  11  12

df = pd.read_csv(‘csv_mindex.csv‘)
print(‘原始樣子：‘,‘\n‘,df)
df = pd.read_csv(‘csv_mindex.csv‘,index_col=[‘keys‘,‘key2‘])
#層次化索引.
#請註意keys和key2的順序
print(df)

原始樣子： 
   keys key2  value1  value2
0  one    a       1       2
1  one    b       3       4
2  two    a       9      10
3  two    c      13      14
           value1  value2
keys key2                
one  a          1       2
     b          3       4
two  a          9      10
     c         13      14

df = pd.read_csv(‘ex4.csv‘)
print(‘原始樣子：‘,‘\n‘,df)
#跳過文件的第幾行
print()
df = pd.read_csv(‘ex4.csv‘,skiprows=[0,2])
print(df)

原始樣子： 
                                                           # hey!
a                                           b   c   d    message
# just wanted to make things more difficult NaN NaN NaN      NaN
1                                           2   NaN 4      hello

   a  b   c  d message
0  1  2 NaN  4   hello

pd.isnull(df)# 處理缺失值
df = pd.read_csv(‘ex4.csv‘,skiprows=[0,2],na_values=[‘hello‘])# 接收一組用於表示缺失值的字符串
print(df)
print(pd.isnull(df))

   a  b   c  d  message
0  1  2 NaN  4      NaN
       a      b     c      d  message
0  False  False  True  False     True

sentinels = {‘message‘:[‘foo‘,‘NA‘],‘d‘:[‘a‘,‘NaN‘]}# 用一個字典為各列指定不同的NA標記值
df = pd.read_csv(‘ex4.csv‘,skiprows=[0,2],na_values=sentinels)
print(df)

   a  b   c  d message
0  1  2 NaN  4   hello

# 圖片：read_table/csv參數

2.逐塊讀取文本文件

# nrows參數指定只讀取定行。算上第一行哦
pd.read_csv(‘ex1.csv‘,nrows=4)

.dataframe thead th {
    text-align: left;
}

.dataframe tbody tr th {
    vertical-align: top;
}

# chunksize 指定分塊讀取
chunks = pd.read_csv(‘ex1.csv‘,chunksize=2)
print(chunks)

<pandas.io.parsers.TextFileReader object at 0x0000007D7E4A39B0>

for chunk in chunks:
    print(chunk)
    print(‘=‘*10,)

   a  b  c  d message
0  1  2  3  4   hello
1  5  6  7  8   world
==========
   a   b   c   d message
2  9  10  11  12     foo
==========

3.將數據寫出到文本格式

data = pd.read_csv(‘ex1.csv‘,nrows=3)
data.to_csv(‘ex1_1.csv‘) #to_csv寫入
data.to_csv(‘ex1_2.csv‘,sep=‘|‘)# 別的分隔符
data.to_csv(‘ex1_1.csv‘,na_rep=‘NULL‘)# 缺失值會被替換為na_rep

data.to_csv(sys.stdout,index=False,header=False) 
# 行、列標簽被禁止
# 輸出到控制臺

1,2,3,4,hello
5,6,7,8,world
9,10,11,12,foo

data.to_csv(sys.stdout,index=False,columns=[‘a‘,‘b‘])

a,b
1,2
5,6
9,10

data.to_csv(sys.stdout)

,a,b,c,d,message
0,1,2,3,4,hello
1,5,6,7,8,world
2,9,10,11,12,foo

4.DataFrame

# 可以將json格式的數據傳給DataFreame
# 也可以數據將數據庫的rows傳給DataFrame

conn = pymysql.Connect(host=‘172.31.238.166‘,port=3306,user=‘luowang‘,passwd=‘root‘,                      charset=‘UTF8‘,db=‘dyx‘)
cursor=conn.cursor()
sql=‘select * from access_log‘;
cursor.execute(sql)
rows= cursor.fetchall()
print(cursor.description)

((‘aid‘, 3, None, 16, 16, 0, False), (‘site_id‘, 3, None, 16, 16, 0, False), (‘count‘, 3, None, 32, 32, 0, False))

# cursor.description第一個保存了列的信息
# pd.DataFrame(rows,columns=[i[0] for i in cursor.description])
pd.DataFrame(rows,columns=zip(*cursor.description)[0])

---------------------------------------------------------------------------

TypeError                                 Traceback (most recent call last)

<ipython-input-74-05969a36ac33> in <module>()
      1 # cursor.description第一個保存了列的信息
      2 # pd.DataFrame(rows,columns=[i[0] for i in cursor.description])
----> 3 pd.DataFrame(rows,columns=zip(*cursor.description)[0])


TypeError: ‘zip‘ object is not subscriptable

[i[0] for i in cursor.description]

[‘aid‘, ‘site_id‘, ‘count‘]

pd.DataFrame(list(rows),columns=[i[0] for i in cursor.description]) #rows必須是list類型

.dataframe thead th {
    text-align: left;
}

.dataframe tbody tr th {
    vertical-align: top;
}

數據加載存儲和文件格式