数据可视化

前期准备：

以管理员身份运行cmd，输入net start MongoDB,回车
输入jupyter notebook,回车，等待网页跳出

基础设置：

import pymongo
import charts
client=pymongo.MongoClient('localhost',27017)
local=client['local']
sample=local['sample']

pipeline筛选查看数据：
pipeline = [
    {'$match':{'cates':'手机'}},
    {'$limit':100}
]

pipeline计数排列功能：

pipeline = [
    {'$match':{'$and':[{'pub_date':'2015.12.24'},{'time':3}]}},
    {'$group':{'_id':'$price','counts':{'$sum':1}}},
    {'$sort' :{'counts':-1}},
    {'$limit':10}
]

set函数看一共有几类：

look_list=[]
for i in sample.aggregate(pipeline):
    look_list.append(i['look'])
    look_index=list(set(look_list))
print(look_index)

计数：

the_cate_list=['二手物品', '家具', '办公用品/设备', '文体/户外/乐器', '笔记本', '台式机/配件', '服装/鞋帽/箱包', '图书/音像/软件', '美容/保健', '设备', '数码产品', '家电', '手机', '母婴/儿童用品', '平板电脑']
look_dic={}
for cate in the_cate_list:
    pipeline = [{'$match':{'cates':cate}}]
    detailed_list=[]
    for i in sample.aggregate(pipeline):
        look_list.append(i['look'])
        count=len(look_list)
        look_index=list(set(look_list))

    sample.insert_one({'cate':cate,'look':look_index})
    print({'cate':cate,'look':look_index})

pipeline-match，group（包含，切片，排除，平均值）：

# {'area':[1,2,3]}
pipeline1 = [
    {'$match':{'$and':[{'pub_date':{'$gte':'2015.12.25','$lte':'2015.12.27'}},{'area':{'$all':['朝阳']}}]}},  #列表包含朝阳的
    {'$group':{'_id':{'$slice':['$cates',2,1]},'counts':{'$sum':1}}},  #cate为列表，取从左数两个后的那一个，切片法
    {'$limit':3}
]

for i in item_info.aggregate(pipeline1):
    print(i)

pipeline2 = [
    {'$match':{'$and':[{'pub_date':{'$gte':'2015.12.25','$lte':'2015.12.27'}},
                       {'cates':{'$all':['北京二手手机']}},
                       {'look':{'$nin':['-']}}  #not in ,排除
                      ]}},
    {'$group':{'_id':'$look','avg_price':{'$avg':'$price'}}}, #avg求平均值
    {'$sort':{'avg_price':-1}} #以group的结果排序
]

取字典里的值：用索引

def data_gen(date1,date2,area,limit):
    pipeline1 = [
    {'$match':{'$and':[{'pub_date':{'$gte':date1,'$lte':date2}},{'area':{'$all':area}}]}},
    {'$group':{'_id':{'$slice':['$cates',2,1]},'counts':{'$sum':1}}},
    {'$limit':limit},
    {'$sort':{'counts':-1}}
]

    for i in item_info.aggregate(pipeline1):
        data = {
            'name': i['_id'][0], #此处用到了索引
            'data': [i['counts']], #同上，但data的固定格式就是一定外面有[]
            'type': 'column'
        }
        yield data