MapReduce

#ENCODING
import io
import sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-16')
#MONGO
from pymongo import MongoClient
client = MongoClient()
client.progzoo.authenticate('scott','tiger')
db = client['progzoo']
#PRETTY
import pprint
pp = pprint.PrettyPrinter(indent=4)

Top Tips

Find

Sort

Introducing the MapReduce function

The MapReduce function is an aggregate function that consists of two functions: Map and Reduce.

The map is always performed before the reduce.

The map function examines every document in the collection and emits (key,value) pairs.

The map function takes no input however the current document can be accessed as this

The reduce function has two inputs, for every distinct key emitted by map the reduce function is called with a list of the corresponding values.

How many countries in each continent

This example returns the number of countries in each continent.

db.world.mapReduce(
  function(){emit(this.continent, 1);}, 
  function(k, v){ return v.length; }
  out={"inline":1}
)

query can be used to filter the input documents to map.

Find the GDP for each continent, but only include data from countries that start with the letter A or B.

from bson.code import Code
temp = db.world.map_reduce(
        query={"name": {"$regex":"^(A|B)"}},
        map=Code("function(){emit(this.continent, this.gdp)}"), 
        reduce=Code("""function(key, values){
                           return Array.sum(values)
                      }
                   """),
        out={"inline":1},
)

pp.pprint(
   temp["results"]
)

from bson.code import Code;temp = db.world.map_reduce(query={"name": {"$regex":"^(A|B)"}},map=Code("function(){emit(this.continent, this.gdp)}"),reduce=Code("function(key, values){return Array.sum(values)}"),out={"inline":1});import operator;pp.pprint(temp["results"])

scope takes in a document:{} and lets you create global variables.

It's syntax is: scope={}.

Using scope, list all the countries with a higher population than Mexico.

mexico_data = db.world.find_one({"name":"Mexico"})
pp.pprint(mexico_data)

from bson.code import Code
temp = db.world.map_reduce(
        scope = {"MEXICO":mexico_data},
        map = Code("""function(){
                         if (this.population > MEXICO.population) emit(this.name, this.population)
                      }
                   """), 
        reduce=Code("function(key, values){return values}"),
        out={"inline":1},
)
pp.pprint(
   temp["results"]
)

mexico_data = db.world.find_one({"name":"Mexico"}); pp.pprint(mexico_data); from bson.code import Code; temp = db.world.map_reduce( scope={"MEXICO":mexico_data}, map=Code("function(){if (this.population > MEXICO.population) emit(this.name, this.population)}"), reduce=Code("function(key, values){return values}"), out={"inline":1});pp.pprint(temp['results'])

sort and limit

Sort allows us to sort the input documents that are passed to map
Limit is self explanatory and also applies to the input documents that are passed to map

Get the five countries with the highest GDPs

from bson.code import Code
temp = db.world.map_reduce(
        query={"gdp":{"$ne":None}},
        sort={"gdp":-1},
        limit=5,
        map=Code("function(){emit(this.name, this.gdp)}"), 
        reduce=Code("function(key, values){return values}"),
        out={"inline":1},
)

pp.pprint(
   temp["results"]
)

from bson.code import Code; temp = db.world.map_reduce( query={"gdp":{"$ne":None}}, sort={"gdp":-1}, limit=5, map=Code("function(){emit(this.name, this.gdp)}"), reduce=Code("function(key, values){return values}"), out={"inline":1}, );pp.pprint(temp["results"])

finalize is an optional additional step that allows you to modify the data produce by reduce

Show the top 15 countries by population, then show their population as a percentage of Mexico's population.

mexico_data = db.world.find_one({"name":"Mexico"})

from bson.code import Code
temp = db.world.map_reduce(
        scope = {"MEXICO":mexico_data},
        query={"population":{"$ne":None}},
        sort={"population":-1},
        limit=15,
        map=Code("function(){emit(this.name, this.population)}"), 
        reduce=Code("function(key, values){return values}"),
        out={"inline":1},
        finalize=Code("""function(key, values){
                             return 100*(values/MEXICO.population)+"%"
                         }
                      """)
)

pp.pprint(
   temp["results"]
)

mexico_data = db.world.find_one({"name":"Mexico"});from bson.code import Code; temp = db.world.map_reduce( scope = {"MEXICO":mexico_data}, query={"population":{"$ne":None}}, sort={"population":-1}, limit=15, map=Code("function(){emit(this.name, this.population)}"), reduce=Code("function(key, values){return values}"), out={"inline":1}, finalize=Code("""function(key, values){return 100*(values/MEXICO.population)+"%"} """) );pp.pprint(temp["results"] );

Rounding can also be performed by using JavaScript.

Show the top 15 countries by population, then show their population as a whole number percentage of Mexico's population.

mexico_data = db.world.find_one({"name":"Mexico"})

from bson.code import Code
temp = db.world.map_reduce(
        scope = {"MEXICO":mexico_data},
        query={"population":{"$ne":None}},
        sort={"population":-1},
        limit=15,
        map=Code("function(){emit(this.name, this.population)}"), 
        reduce=Code("function(key, values){return values}"),
        out={"inline":1},
        finalize=Code("""function(key, values){
                             return Math.round(100*(values/MEXICO.population))+"%"
                         }
                      """)
)

pp.pprint(
   temp["results"]
)

mexico_data = db.world.find_one({"name":"Mexico"});from bson.code import Code;temp=db.world.map_reduce(scope ={"MEXICO":mexico_data},query={"population":{"$ne":None}},sort={"population":-1},limit=15,map=Code("function(){emit(this.name,this.population)}"),reduce=Code("function(key, values){return values}"), out={"inline":1},finalize=Code("function(key,values){return Math.round(100*(values/MEXICO.population))+'%'}"));pp.pprint(temp["results"])