如何从MongoDB中删除重复项?但是MongoDB db.collection.find((看起来根本不起作用。
法典
start_date = "2020-05-00"
end_date = "2020-07-00"
collection.create_index([('text', 'text')])
df = pd.DataFrame(list(collection.find({"$text":
{"$search": "ACTIVE - ACT 06"},
"datetime": {
"$gte": start_date+"T00:00:00.000Z",
"$lt": end_date+"T00:00:00.000Z"
}},
{"_id":1, "datetime":1,"name":1})))
示例重复数据。我想确保每个日期的名称都是唯一的(忽略时间(。
{
"datetime": "2020-05-03 06:43:52",
"name": "ACTIVE - ACT 06"
},
{
"datetime": "2020-05-03 06:44:01",
"name": "ACTIVE - ACT 05"
},
{
"datetime": "2020-05-03 07:43:52",
"name": "ACTIVE - ACT 06"
},
{
"datetime": "2020-05-03 07:44:01",
"name": "ACTIVE - ACT 05"
},
{
"datetime": "2020-05-03 08:43:52",
"name": "ACTIVE - ACT 06"
},
{
"datetime": "2020-05-03 08:44:01",
"name": "ACTIVE - ACT 05"
}
移除后。仅保存较早的记录。
{
"datetime": "2020-05-03 06:43:52",
"name": "ACTIVE - ACT 06"
},
{
"datetime": "2020-05-03 06:44:01",
"name": "ACTIVE - ACT 05"
}
你可以像这样使用聚合框架:
- 首先列出重复数据。
- 然后,将其一一删除。
db.collection.aggregate([
{
$group: {
_id: "$name",
dups: {
$push: "$_id"
},
count: {
$sum: 1
}
}
},
{
$match: {
count: {
$gt: 1
}
}
}
]).forEach(function(doc){
db.collection.remove({
_id: {
$in: doc.dups
}
});
})