mongo cheats

mongocheats.js

// remove field from all samples
db.getCollection('samples').update({}, {'$unset': {'viterbi_haplotypes': 1}}, {multi: true})

// initialize fields in all samples
db.getCollection('samples').update({}, {'$set': {'viterbi_haplotypes': {}}}, {multi: true})

// how to slice without getting everything you don't care about
db.getCollection('samples').find(
    {'_id': ObjectId("55e9cf1a6606af0e6e5cb5a1")},
    {
        'chromosome_data.6.allele1_fwds': {'$slice': 10},
        'chromosome_data.6.allele2_fwds': {'$slice': 10},
        // see http://stackoverflow.com/questions/23804254/
        // this is a hack that can be used to avoid pulling down all of the other data that
        // we don't really care about (the default with slice is to pull down everything else)
        'chromosome_data.6.no_read_count': 1
    })

// find attributes that are not unique (based on http://blog.mlab.com/2014/03/finding-duplicate-keys-with-the-mongodb-aggregation-framework/)
db.getCollection('samples').aggregate([{
    $group: {
        _id: {organism_id: '$organism_id'},
        count: {$sum: 1}
    }
}, {
    $match: {
        count: {$gt: 1}
    }
}])