Python【8】-分析json文件

for line in open('E:\Demo\python\json.txt'):
    print line

import json

s='{ "a": "GoogleMaps\/RochesterNY", "c": "US", "nk": 0, "tz": "America\/Denver", "gr": "UT", "g": "mwszkS", "h": "mwszkS", "l": "bitly", "hh": "1.usa.gov", "r": "http:\/\/www.AwareMap.com\/", "u": "http:\/\/www.monroecounty.gov\/etc\/911\/rss.php", "t": 1331926741, "hc": 1308262393, "cy": "Provo", "ll": [ 40.218102, -111.613297 ] }'
o=json.loads(s)
print o

{u'a': u'GoogleMaps/RochesterNY', u'c': u'US', u'nk': 0, u'tz': u'America/Denver', u'gr': u'UT', u'g': u'mwszkS', u'h': u'mwszkS', u'cy': u'Provo', u'l': u'bitly', u'hh': u'1.usa.gov', u'r': u'http://www.AwareMap.com/', u'u': u'http://www.monroecounty.gov/etc/911/rss.php', u't': 1331926741, u'hc': 1308262393, u'll': [40.218102, -111.613297]}

import json
#读取文件并解析为字典组成的列表
dicList=[json.loads(line) for line in open('E:\Demo\python\json.txt')]
#打印第一个字典元素
print dicList[0]
#打印第一个元素中的时区
print dicList[0]['tz']

#获取所有时区数据
timezones=[item['tz'] for item in dicList if 'tz' in item]
#测试打印前五条
print timezones[0:5]

#自定义函数，统计时区出现次数
def countZone(timezones):
    count_zone={}
    for tz in timezones:
        if(tz in count_zone):
            count_zone[tz]+=1
        else:
            count_zone[tz]=1
    return count_zone

#自定义函数，返回top N
def countTop(dicCount,n):
    valueKeyItems=[(value,key) for key,value in dicCount.items()]
    valueKeyItems.sort()
    return valueKeyItems[-n:]
    
#测试并打印出现次数最多的5个时区    
count=countZone(timezones)
print countTop(count,5)

from collections import defaultdict,Counter
def countZone(timezones):
    count_zone=defaultdict(int)
    for tz in timezones:
        count_zone[tz]+=1
    return count_zone

from collections import Counter

def countTop(dicCount,n):
    return Counter(dicCount).most_common(n)

# -*- coding: utf-8 -*-
import json
#1.读取文件并转换为字典列表
#读取文件并解析为字典组成的列表
dicList=[json.loads(line) for line in open('E:\Demo\python\json.txt')]

#2.统计时区
#获取所有时区数据
timezones=[item['tz'] for item in dicList if 'tz' in item]

#统计时区出现次数
from collections import defaultdict,Counter
def countZone(timezones):
    count_zone=defaultdict(int)
    for tz in timezones:
        count_zone[tz]+=1
    return count_zone

#返回top N
def countTop(dicCount,n):
    return Counter(dicCount).most_common(n)
    
#测试并打印出现次数最多的5个时区    
count=countZone(timezones)
print countTop(count,5)

# -*- coding: utf-8 -*-
import json
from pandas import DataFrame
dicList=[json.loads(line) for line in open('E:\Demo\python\json.txt')]
frame=DataFrame(dicList)
#测试打印时区列表中前5个元素
print frame['tz'][:5]

print frame['tz'].value_counts()[:5]

tzList=frame['tz'].fillna('Missing')
tzList[tzList =='']='Unknown'
print tzList.value_counts()[:5]

# -*- coding: utf-8 -*-
import json
from pandas import DataFrame
dicList=[json.loads(line) for line in open('E:\Demo\python\json.txt')]
frame=DataFrame(dicList)
#打印出现次数最多的5个时区
print frame['tz'].value_counts()[:5]

#补全时区不存在或者为空的情况
tzList=frame['tz'].fillna('Missing')
tzList[tzList =='']='Unknown'
print tzList.value_counts()[:5]

ipython

%pylab

%paste