FIND from WORLD
#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)
Working with the world
collection of countries
This tutorial introduces NoSQL using MonogDB and PyMongo under Python3.4. We will be using the find()
command and comparison functions on the collection world which contains details of around 250 countries of the world:
FIND examples are available.
Observe the result of running a simple mongoDB command.
FIND name, continent, population FROM world
pp.pprint(list( db.world.find({},{ "name":1, "continent":1, "population":1, "_id":0 }) ))
pp.pprint(list(db.world.find({},{"name":1,"continent":1,"population":1,"_id":0})))
Show the name for the countries that have a population of at least 200 million. 200 million is 200000000, there are eight zeros.
pp.pprint(list( db.world.find( {"population":{"$gt":200000000}}, {"name":1, "_id":0} ) ))
pp.pprint(list(db.world.find({"population":{"$gt":200000000}},{"name":1, "_id":0})))
Give the name and the per capita GDP for those countries with a population of at least 200 million.
AGGREGATE examples are available.
pp.pprint(list( db.world.aggregate([ {"$match":{"population":{"$gt":200000000}}}, {"$project":{"name":1, "gdp/population":{"$divide":["$gdp","$population"]}, "_id":0}} ]) ))
pp.pprint(list(db.world.aggregate([{"$match":{"population":{"$gt":200000000}}},{"$project":{"name":1, "gdp/population":{"$divide":["$gdp","$population"]}, "_id":0}}])))
Show the name and population in millions for the countries of the continent 'South America'. Divide the population by 1000000 to get population in millions.
pp.pprint(list( db.world.aggregate([ {"$match":{"continent":{"$eq":"South America"}}}, {"$project":{"name":1, "population in millions":{"$divide":["$population",1000000]}, "_id":0}} ]) ))
pp.pprint(list(db.world.aggregate([{"$match":{"continent":{"$eq":"South America"}}},{"$project":{"name":1, "population in millions":{"$divide":["$population",1000000]}, "_id":0}}])))
Show the name and population for France, Germany, Italy
pp.pprint(list( db.world.aggregate([ {"$match":{"name":{"$in":["France", "Germany", "Italy"]}}}, {"$project":{"name":1, "population":1, "_id":0}} ]) ))
pp.pprint(list(db.world.aggregate([{"$match":{"name":{"$in":["France", "Germany", "Italy"]}}},{"$project":{"name":1, "population":1, "_id":0}}])))
Show the countries which have a name that includes the word 'United'
pp.pprint(list( db.world.find( {"name":{"$regex":"\s?United\s?"}}, {"name":1, "_id":0} ) ))
pp.pprint(list(db.world.find({"name":{"$regex":"\s?United\s?"}},{"name":1, "_id":0})))
Two ways to be big: A country is big if it has an area of more than 3 million sq km or it has a population of more than 250 million.
Show the countries that are big by area or big by population. Show name, population and area
pp.pprint(list( db.world.find( {"$or":[{"area":{"$gt":3000000}},{"population":{"$gt":250000000}}]}, {"name":1,"population":1,"area":1,"_id":0} ) ))
pp.pprint(list(db.world.find({"$or":[{"area":{"$gt":3000000}},{"population":{"$gt":250000000}}]},{"name":1,"population":1,"area":1,"_id":0})))
USA and China are big in population and big by area. Exclude these countries.
Show the countries that are big by area or big by population but not both. Show name, population and area.
pp.pprint(list( db.world.find( {"$or":[ {"area":{"$gt":3000000},"population":{"$lt":250000000}}, {"area":{"$lt":3000000},"population":{"$gt":250000000}} ]}, {"name":1,"population":1,"area":1,"_id":0} ) ))
pp.pprint(list(db.world.find({"$or":[{"area":{"$gt":3000000},"population":{"$lt":250000000}},{"area":{"$lt":3000000},"population":{"$gt":250000000}}]}, {"name":1,"population":1,"area":1,"_id":0})))
Show the name and population in millions and the GDP in billions for the countries of the continent 'South America'. Use the ROUND function to show the values to two decimal places.
Introducing MapReduce
For South America show population in millions and GDP in billions to 2 decimal places.
from bson.code import Code temp = db.world.map_reduce( query={"continent":"South America"}, map=Code("function(){emit(this.name,{'gdp':this.gdp,'pop':this.population});}"), reduce=Code("""function(key, values){ return values} """), finalize=Code("""function(k, v){ return { 'pop in millions':Math.round(v['pop']*1000000)/1000000, 'gdp in billions':Math.round(v['gdp']*1000000000)/1000000000 }; } """), out={"inline":1} ) pp.pprint(temp['results']);
from bson.code import Code temp = db.world.map_reduce(query={"continent":"South America"},map=Code("function(){emit(this.name, {'gdp':this.gdp,'pop':this.population});}"),reduce=Code("""function(key, values){ return values} """),finalize=Code("""function(k, v){return {'pop in millions':Math.round(v['pop']*1000000)/1000000,'gdp in billions':Math.round(v['gdp']*1000000000)/1000000000};}"""),out={"inline":1}) pp.pprint(temp['results']);
Show the per-capita GDP for those countries with a GDP of at least one trillion (1000000000000; that is 12 zeros). Round this value to the nearest 1000.
Show per-capita GDP for the trillion dollar countries to the nearest $1000.
from bson.code import Code temp = db.world.map_reduce( map=Code("function(){if(this.gdp > 1000000000000)emit(this.name,{'gdp':this.gdp,'pop':this.population});}"), reduce=Code("""function(key, values){ return values} """), finalize=Code("""function(k, v){ return {'per-capita GDP':Math.round((v['gdp']/v['pop'])/1000)*1000}; } """), out={"inline":1} ) pp.pprint(temp['results']);
from bson.code import Code temp = db.world.map_reduce(map=Code("function(){if(this.gdp > 1000000000000)emit(this.name,{'gdp':this.gdp,'pop':this.population});}"),reduce=Code("""function(key, values){ return values} """),finalize=Code("""function(k, v){ return {'per-capita GDP':Math.round((v['gdp']/v['pop'])/1000)*1000};}"""),out={"inline":1}) pp.pprint(temp['results']);