利用python实现数据分析

1:文件内容格式为json的数据如何解析

    import json,os,sys
    current_dir=os.path.abspath(".")

    filename=[file for file in os.listdir(current_dir) if ".txt" in file]#得到当前目录中，后缀为.txt的数据文件
    fn=filename[0] if len(filename)==1 else "" #从list中取出第一个文件名

    if fn: # means we got a valid filename
      fd=open(fn)
      content=[json.loads(line) for line in fd]

    else:
      print("no txt file in current directory")
      sys.exit(1)
    for linedict in content:
      for key,value in linedict.items():
        print(key,value)
      print("\n")

2：出现频率统计

    import random
    from collections import Counter
    fruits=[random.choice(["apple","cherry","orange","pear","watermelon","banana"]) for i in range(20)]
    print(fruits) #查看所有水果出现的次数

    cover_fruits=Counter(fruits)
    for fruit,times in cover_fruits.most_common(3):
      print(fruit,times)

    ########运行结果如下：apple在fruits里出了5次
    apple 5  
    banana 4
    pear 4

3:重新加载module的方法py3

    import importlib
    import.reload(modulename)

4:pylab中包含了哪些module

from pylab import *

等效于下面的导入语句：

      from pylab import *
      from numpy import *
      from scipy import *
      import matplotlib