数据工程师推荐你用的几个工具

import MySQLdb
import pandas as pd
from sqlalchemy import create_engine

class con_analyze:
 """数据分析平台连接"""

 def __init__(self, database='myanalyze'):
 self.database = database
 self.conn = None

 def connect(self):
 self.conn = MySQLdb.connect(host='***', user='root', passwd='***', db=self.database, charset='utf8')

 def query(self, sql):
 try:
 self.connect()
            data = pd.read_sql(sql, self.conn)
 except (AttributeError, MySQLdb.OperationalError):
 self.connect()
            data = pd.read_sql(sql, self.conn) # 读取数据出现错误,再次连接
 return data

 def store(self, mydataframe, table_name, if_exists='replace'):
        conn2 = "mysql+mysqldb://root:***@***:3306/%s" % self.database
        local_engine = create_engine(conn2)
        mydataframe.to_sql(table_name, local_engine, if_exists=if_exists, index=False, chunksize=10000)

 '''还可以加一个函数用来执行单条sql语句,不仅仅是读取数据，还可以update，create等'''

from config import con_analyze


class AnalyzeData:
 def __init__(self):
 # 此处初始化，可以带一个参数：database,默认为myanalyze
 self.conn = con_analyze()
 # self.conn2 = con_analyze("myanalyze_2")

 def get_data(self, sql):
 # 执行sql查询结果保存到df中
        df = self.conn.query(sql=sql)

 def store_data(self, df):
 # 将dataframe类型的数据df，存入名为dd_name的数据表中
 self.conn.store(df, 'db_name')

import pymongo
import pandas as pd

class Conn_Mongo:
 """mongo 数据库连接"""

 def __init__(self):
 self.mongo_utoken = pymongo.MongoClient('mongodb://***:27000').utoken  # 用户表

 def get_user_data_mongo(self,list_id):
 """
        通过连接 mongo查找 
        """
        user_data = pd.DataFrame(list(self.mongo_fotor.userinfo.find({'FToken': {'$in': list(list_id)}})))
 return user_data

import pandas as pd
import json, requests
class Conn_Flurry:
 """flurry api data"""
    api_token = "******.****.****" 
    headers = {'Authorization': 'Bearer {}'.format(api_token)}
    url = "https://api-metrics.flurry.com/public/v1/data/appEvent/day/app?metrics=activeDevices,newDevices,averageTimePerDevice&dateTime=2017-05-23/2017-05-24"

 def get_results(self, url=url):
 '''
        这里使用的url是一个示例，也可以使用get_url函数创建需要的url传入此函数作为参数
        '''
        data = requests.get(url, headers=self.headers)
        cleaned = json.loads(data.text, 'utf-8')
        cleaned = pd.DataFrame(cleaned['rows'])
 return cleaned

 def get_url(self, table='appEvent', timegrain='day', dimensions='app/event', metrics='occurrences',
                dateTime='2017-09-23/2017-05-24', filters=""):
 '''
        若filters为空， 不影响结果
        标准的url：endpoint + '/table/timeGrain/dimension1/dimension2;show=all/dimension3{...}?metrics=[comma-separated-metrics]&dateTime=[..]&filters=[...]&topN=[..]&sort=[..]&having=[..]&format=[..]&timeZone=[..]'
        App Usage url： endpoint+ "/appUsage/day?metrics=sessions,activeDevices,newDevices&dateTime=2016-06-01/2016-08-01&filters=app|name-in[appname]"
        app event url: endpoint + "/appEvent/day/app/appVersion/event?metrics=occurrences&dateTime=2016-07-01/2016-07-03&filters=app|name-in[foo],event|name-in[login,register]"
        app event url2: endpoint + "/appEvent/day/app/country?metrics=activeDevices,newDevices&dateTime=2016-07-01/2016-07-03&filters=app|name-in[foo],event|name-in[login]&topN=5&sort=activeDevices|desc"
        event parameter: endpoint+ "/eventParams/day/app;show=all/event/paramName/paramValue?metrics=count&dateTime=2016-11-07/2016-11-08&filters=app|name-in[foo],event|name-in[level_complete]"
        注意，dimensions的变化，当要看某一事件的具体信息时：app;show=all/event/paramName/paramValue，加了个show=all
        注意filters里面filters的格式，可以选择app名称和事件名称
        注意timegrain和datetime的关系，常见的就是day和month，datetime的格式也要跟着变
        '''
        endpoint = 'https://api-metrics.flurry.com/public/v1/data'
        url = "{}/{}/{}/{}?metrics={}&dateTime={}&filters={}".format(endpoint, table, timegrain, dimensions, metrics,
                                                                     dateTime, filters)
 return url

url = self.conn_flurry.get_url('appUsage', 'month', 'app','averageTimePerSession,activeDevices,newDevices,sessions', self.time_range)
user_mobile = self.conn_flurry.get_results(url)

self.time_range = '2017-09/2017-10'