将数据导入MongoDB集群与MySQL
import sys
import json
import pymongo
import datetime
from pymongo import MongoClient
client = MongoClient('mongodb://192.168.1.31:20000,192.168.1.34:20000')
db = client.RHY
collection = db.ST_RIVER_R
f = open("D:/bigdata/st_river_r.CSV")
line = f.readline()
print(line)
fieldNames = line.split(',')
# STCD,TM,Z,Q,XSA,XSAVV,XSMXV,FLWCHRCD,WPTN,MSQMT,MSAMT,MSVMT
line = f.readline()
count = 0
records = []
insertCount = 0
while line:
#
count = count + 1
fieldValues = line.split(',')
if len(fieldValues) == 12 or fieldValues[0].strip() != '':
insertObj = {}
STCD = fieldValues[0]
insertObj['STCD'] = STCD
TM = fieldValues[1]
if TM.strip() != '':
TM = datetime.datetime.strptime(TM, '%Y-%m-%d %H:%M:%S')
insertObj['TM'] = TM
Z = fieldValues[2]
if Z.strip() != '':
Z = float(Z)
insertObj['Z'] = Z
Q = fieldValues[3]
if Q.strip() != '':
Q = float(Q)
insertObj['Q'] = Q
# XSA
XSA = fieldValues[4]
if XSA.strip() != '':
XSA = float(XSA)
insertObj['XSA'] = XSA
# XSAVV
XSAVV = fieldValues[5]
if XSAVV.strip() != '':
XSAVV = float(XSAVV)
insertObj['XSAVV'] = XSAVV
#
XSMXV = fieldValues[6]
if XSMXV.strip() != '':
XSMXV = float(XSMXV)
insertObj['XSMXV'] = XSMXV
#
FLWCHRCD = fieldValues[7]
if FLWCHRCD.strip() != '':
insertObj['FLWCHRCD'] = FLWCHRCD
#
WPTN = fieldValues[8]
if WPTN.strip() != '':
insertObj['WPTN'] = WPTN
#
MSQMT = fieldValues[9]
if MSQMT.strip() != '':
insertObj['MSQMT'] = MSQMT
#
MSAMT = fieldValues[10]
if MSAMT.strip() != '':
insertObj['MSAMT'] = MSAMT
#
MSVMT = fieldValues[11]
if MSVMT.strip() != '':
insertObj['MSVMT'] = MSVMT
#
# collection.insert_one(insertObj)
# collection.insert_many(new_posts)
records.append(insertObj)
if len(records) == 1000:
insertCount = insertCount + 1
if count > 1451000:
collection.insert_many(records)
print(str(count) + ' ' + str(insertCount))
print(count)
records = []
else:
print(line)
#
line = f.readline()
f.close()
client.close()
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
import sys
import json
import math
import copy
import pymongo
import datetime
from pymongo import MongoClient
import shapefile
import pymysql
sf = shapefile.Reader(r'E:/Ambari/ubuntu/mapdata/aircraftPositionLine50.shp')
fields = sf.fields
shapes = sf.shapes()
count = len(shapes)
print('count: ' + str(count))
fieldName = []
for index in range(len(fields)):
if index > 0:
field = fields[index]
# print(field)
fieldName.append(field[0])
#print(fieldName)
#
db = pymysql.connect("127.0.0.1","root","gis","acms" )
cursor = db.cursor()
sql = "INSERT INTO airline_r(id, code, name, time_index, x, y, z, angle) VALUES (%s, %s, %s, %s, %s, %s, %s, %s)"
for index in range(count):
preX = None
preY = None
preZ = None
angle = None
features = []
record = sf.record(index)
attribute = record[0:len(fields)]
attribute[0] = index
print(attribute)
shap = shapes[index]
points = shap.points
pointCount = len(points)
for i in range(pointCount):
coordinate = shap.points[i]
x = coordinate[0]
y = coordinate[1]
z = (0 if (len(coordinate) < 3) else coordinate[2])
if preX != None:
angle = math.atan2(y-preY, x - preX)
feature = copy.deepcopy(attribute)
feature.append(i-1)
feature.append(preX)
feature.append(preY)
feature.append(preZ)
feature.append(angle)
print(feature)
features.append(tuple(feature))
#cursor.execute(sql % tuple(feature))
#cursor.execute(sql, feature)
if i == pointCount -1:
feature = copy.deepcopy(attribute)
feature.append(i)
feature.append(x)
feature.append(y)
feature.append(z)
feature.append(angle)
print(feature)
features.append(tuple(feature))
#cursor.execute(sql % tuple(feature))
#cursor.execute(sql, feature)
preX = x
preY = y
preZ = z
#print(features)
cursor.executemany(sql, features)
db.commit()
'''
try:
# 执行sql语句
cursor.executemany(sql, features)
# 提交到数据库执行
db.commit()
except:
# 如果发生错误则回滚
print()
db.rollback()
'''
# 关闭数据库连接
db.close()
'''
client = MongoClient('mongodb://192.168.1.31:20000,192.168.1.34:20000')
db = client.RHY
collection = db.ST_RIVER_R
f = open("D:/bigdata/st_river_r.CSV")
line = f.readline()
print(line)
fieldNames = line.split(',')
# STCD,TM,Z,Q,XSA,XSAVV,XSMXV,FLWCHRCD,WPTN,MSQMT,MSAMT,MSVMT
line = f.readline()
count = 0
records = []
insertCount = 0
while line:
#
count = count + 1
fieldValues = line.split(',')
if len(fieldValues) == 12 or fieldValues[0].strip() != '':
insertObj = {}
STCD = fieldValues[0]
insertObj['STCD'] = STCD
TM = fieldValues[1]
if TM.strip() != '':
TM = datetime.datetime.strptime(TM, '%Y-%m-%d %H:%M:%S')
insertObj['TM'] = TM
Z = fieldValues[2]
if Z.strip() != '':
Z = float(Z)
insertObj['Z'] = Z
Q = fieldValues[3]
if Q.strip() != '':
Q = float(Q)
insertObj['Q'] = Q
# XSA
XSA = fieldValues[4]
if XSA.strip() != '':
XSA = float(XSA)
insertObj['XSA'] = XSA
# XSAVV
XSAVV = fieldValues[5]
if XSAVV.strip() != '':
XSAVV = float(XSAVV)
insertObj['XSAVV'] = XSAVV
#
XSMXV = fieldValues[6]
if XSMXV.strip() != '':
XSMXV = float(XSMXV)
insertObj['XSMXV'] = XSMXV
#
FLWCHRCD = fieldValues[7]
if FLWCHRCD.strip() != '':
insertObj['FLWCHRCD'] = FLWCHRCD
#
WPTN = fieldValues[8]
if WPTN.strip() != '':
insertObj['WPTN'] = WPTN
#
MSQMT = fieldValues[9]
if MSQMT.strip() != '':
insertObj['MSQMT'] = MSQMT
#
MSAMT = fieldValues[10]
if MSAMT.strip() != '':
insertObj['MSAMT'] = MSAMT
#
MSVMT = fieldValues[11]
if MSVMT.strip() != '':
insertObj['MSVMT'] = MSVMT
#
# collection.insert_one(insertObj)
# collection.insert_many(new_posts)
records.append(insertObj)
if len(records) == 1000:
insertCount = insertCount + 1
if count > 1451000:
collection.insert_many(records)
print(str(count) + ' ' + str(insertCount))
print(count)
records = []
else:
print(line)
#
line = f.readline()
f.close()
client.close()
'''
将数据导入MongoDB集群与MySQL的更多相关文章
- sqoop将oracle数据导入hdfs集群
使用sqoop将oracle数据导入hdfs集群 集群环境: hadoop1.0.0 hbase0.92.1 zookeeper3.4.3 hive0.8.1 sqoop-1.4.1-incubati ...
- 使用pandas把mysql的数据导入MongoDB。
使用pandas把mysql的数据导入MongoDB. 首先说下我的需求,我需要把mysql的70万条数据导入到mongodb并去重, 同时在第二列加入一个url字段,字段的值和第三列的值一样,代码如 ...
- rancher导入k8s集群后添加监控无数据
1.日志报错 rancher导入k8s集群后添加监控无数据,rancher日志报错: k8s.io/kube-state-metrics/pkg/collectors/builder.go:: Fai ...
- mongodb集群安装及到现在遇到的一些问题
集群搭建 只有3台服务器,开始搭建mongodb集群里主要参照的是http://www.lanceyan.com/tech/arch/mongodb_shard1.html,端口的设置也是mongos ...
- 搭建高可用mongodb集群(四)—— 分片(经典)
转自:http://www.lanceyan.com/tech/arch/mongodb_shard1.html 按照上一节中<搭建高可用mongodb集群(三)-- 深入副本集>搭建后还 ...
- [转]搭建高可用mongodb集群(四)—— 分片
按照上一节中<搭建高可用mongodb集群(三)—— 深入副本集>搭建后还有两个问题没有解决: 从节点每个上面的数据都是对数据库全量拷贝,从节点压力会不会过大? 数据压力大到机器支撑不了的 ...
- 搭建高可用mongodb集群(四)—— 分片
按照上一节中<搭建高可用mongodb集群(三)—— 深入副本集>搭建后还有两个问题没有解决: 从节点每个上面的数据都是对数据库全量拷贝,从节点压力会不会过大? 数据压力大到机器支撑不了的 ...
- 搭建高可用mongodb集群(三)—— 深入副本集内部机制
在上一篇文章<搭建高可用mongodb集群(二)—— 副本集> 介绍了副本集的配置,这篇文章深入研究一下副本集的内部机制.还是带着副本集的问题来看吧! 副本集故障转移,主节点是如何选举的? ...
- 搭建高可用mongodb集群(一)——配置mongodb
在大数据的时代,传统的关系型数据库要能更高的服务必须要解决高并发读写.海量数据高效存储.高可扩展性和高可用性这些难题.不过就是因为这些问题Nosql诞生了. NOSQL有这些优势: 大数据量,可以通过 ...
随机推荐
- [Leetcode]146.LRU缓存机制
Leetcode难题,题目为: 运用你所掌握的数据结构,设计和实现一个 LRU (最近最少使用) 缓存机制.它应该支持以下操作: 获取数据 get 和 写入数据 put . 获取数据 get(key ...
- vue教程2-05 v-for循环 重复数据无法添加问题 加track-by='索引'
vue教程2-05 v-for循环 重复数据无法添加问题 加track-by='索引' 解决问题的代码示例: <!DOCTYPE html> <html lang="en ...
- C# 自定义类型通过实现IFormattable接口,来输出指定的格式和语言文化的字符串(例:DateTime)
常规的调用ToString()方法,存在两个问题. (1).调用者无法控制字符串的格式 (2).调用者不能方便的选择一种特定的语言文化来格式化字符串. 在开发一些国际化的应用时,应用程序需要调用与当前 ...
- .net core2 mvc项目中,加入RazorPages页面
2017.08.22 试验结果: 1.手工添加/Pages文件夹 2.复制/Views/_ViewImports.cshtml到/Pages/_ViewImports.cshtml 2.1 修改@u ...
- 关于 OpenIdConnect 认证启用 HTTPS 回调 RedirectUri 不生效问题
在搭建 IdentityServer 服务端后,我们尝试使用了 OIDC(OpenID Connect) 的中间件来代替了原先的 Session 系统认证方式,起初采用的是 HTTP 协议,一切都没有 ...
- error C4996: 'scanf': This function or variable may be unsafe.
项目属性-配置属性-c/c++-预处理器- 在下面的编辑窗口中添加一句命令:_CRT_SECURE_NO_WARNINGS 添加完成后应用并退出 http://jingyan.baidu.com/al ...
- Android H5调起原生微信或支付宝支付
Android H5调起原生微信或支付宝支付 WebView调用原生微信或支付宝回调:其原理就是在shouldOverrideUrlLoading(final WebView view, String ...
- 删除Myeclipse中废弃的workspace记录
一个不用的workspace被我们删除后,但是在工作空间切换时File --> Switch Workspace,旧的 workspace 选项还会存在,看着很碍眼.删除遗留 workspace ...
- 08 - JavaSE之IO流
IO流 JAVA流式输入输出原理:可以想象成一根管道怼到文件上,另一端是我们程序,然后流的输入输出都是按照程序本身作为第一人称说明的.比如 input,对于我们程序来说就是有数据输入我们程序,outp ...
- tensorflow 根据节点名称获取节点
ckpt_file = os.path.join(self.args.bert_dir, 'model.ckpt-6123') # 获取图的reader reader = self.tf_instan ...