notes.txt

* export
mongoexport --db flow --collection pageviews --out flow-pageviews-030613-030913.json
mongoexport --db flow --collection pageflows --out flow-pageflows-030613-030913.json

* import
mongoimport --db flow --collection pageviews --file flow-pageviews-030613-030913.json
mongoimport --db flow --collection pageflows --file flow-pageflows-030613-030913.json

* db pageviews cleaning
db.pageviews.remove({domain:{$not:/^www.livechatinc.com$/}})
db.pageviews.remove({url: /\/\?/})
db.pageviews.remove({url: /(frame)|(click)|(wp-content)|(ghost)|(.png)|(.jpg)|(%)|(wix)/})

* db pageflows cleaning
db.pageflows.remove({domain: {$not: /^www.livechatinc.com$/}})
db.pageflows.remove({source_url: {$not: /^http:\/\/www.livechatinc.com/}})
db.pageflows.remove({source_url: /wix/})
db.pageflows.remove({dest_url:/\/\?/})
db.pageflows.remove({source_url:/\/\?/})

* useful db queries
db.pageviews.aggregate({$match: {url: /^http:\/\/www.livechatinc.com\/\?/}},{$group:{_id: "$domain",total: {$sum: "$count"}}})
db.pageviews.update({url: "http:\/\/www.livechatinc.com\/"}, {$inc: {count: x}})
db.pageviews.find({count: {$gt: 1}}).toArray().length