Difference between revisions of "MAPREDUCE basics"
From NoSQLZoo
| Line 44: | Line 44: | ||
<div class=q data-lang="py3"> | <div class=q data-lang="py3"> | ||
| − | <p class=strong> | + | <p class=strong>Use the previous answer to find the population of the world to the nearest million</p> |
| + | <div class=hint title="How to round to the nearest million">Use the JavaScript round function : Math.round(population/1000000)*1000000 </div> | ||
<pre class=def> | <pre class=def> | ||
| + | </pre> | ||
| + | <div class=ans> | ||
from bson.code import Code | from bson.code import Code | ||
temp = db.world.map_reduce( | temp = db.world.map_reduce( | ||
| − | map=Code("function(){emit(this. | + | map=Code("function(){emit('World Population in Millions', this.population)}"), |
reduce=Code("""function(key, values){ | reduce=Code("""function(key, values){ | ||
| − | return Array.sum(values); | + | return Math.round(Array.sum(values)/1000000)*1000000; |
}"""), | }"""), | ||
out={"inline":1}) | out={"inline":1}) | ||
pp.pprint(temp["results"]) | pp.pprint(temp["results"]) | ||
| + | </div> | ||
| + | </div> | ||
| + | |||
| + | <div class=q data-lang="py3"> | ||
| + | <p class=strong>Show the number of countries on each continent</p> | ||
| + | <pre class=def> | ||
</pre> | </pre> | ||
<div class=ans> | <div class=ans> | ||
| Line 68: | Line 77: | ||
<div class=q data-lang="py3"> | <div class=q data-lang="py3"> | ||
| − | <p class=strong>Show the smallest 3 countries (ignore areas of 0 or None)</p> | + | <p class=strong>Show the smallest 3 countries name and area (ignore areas of 0 or None)</p> |
<pre class=def> | <pre class=def> | ||
</pre> | </pre> | ||
| Line 110: | Line 119: | ||
<div class=q data-lang="py3"> | <div class=q data-lang="py3"> | ||
| − | <p class=strong> | + | <p class=strong>Without using query return the name and capital for any country or capital that starts with an 'L'</p> |
<pre class=def> | <pre class=def> | ||
</pre> | </pre> | ||
| Line 116: | Line 125: | ||
from bson.code import Code | from bson.code import Code | ||
temp = db.world.map_reduce( | temp = db.world.map_reduce( | ||
| − | map=Code("function(){ | + | map=Code("""function(){ if((this.name).startsWith('L')|(this.capital).startsWith('L'))emit(this.name, this.capital)}"""), |
reduce=Code("""function(key, values){ | reduce=Code("""function(key, values){ | ||
| − | + | return values; | |
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
}"""), | }"""), | ||
out={"inline":1}) | out={"inline":1}) | ||
Revision as of 12:24, 30 July 2015
#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)
MapReduce the basics
This tutorial introduces the MapReduce command.
MapReduce examples are available.
Find the total population of the each continent
from bson.code import Code
temp = db.world.map_reduce(
map=Code("function(){emit(this.continent, this.population)}"),
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(
map=Code("function(){emit(this.continent, this.population)}"),
reduce=Code("""function(key, values){
return Array.sum(values);
}"""),
out={"inline":1})
pp.pprint(temp["results"])
Use the previous answer to find the population of the world to the nearest million
Use the JavaScript round function : Math.round(population/1000000)*1000000
from bson.code import Code temp = db.world.map_reduce(
map=Code("function(){emit('World Population in Millions', this.population)}"),
reduce=Code("""function(key, values){
return Math.round(Array.sum(values)/1000000)*1000000;
}"""),
out={"inline":1})
pp.pprint(temp["results"])
Show the number of countries on each continent
from bson.code import Code temp = db.world.map_reduce(
map=Code("function(){emit(this.continent, 1)}"),
reduce=Code("""function(key, values){
return Array.sum(values);
}"""),
out={"inline":1})
pp.pprint(temp["results"])
Show the smallest 3 countries name and area (ignore areas of 0 or None)
from bson.code import Code temp = db.world.map_reduce(
query={"$and":[{"area":{"$ne":None}}, {"area":{"$ne":0}}]},
sort={"area":1},
limit=3,
map=Code("function(){emit(this.name, this.area)}"),
reduce=Code("function(key, values){}"),
out={"inline":1},
)
pp.pprint(
temp["results"]
)
Return the first and last country based on name order for each continent
from bson.code import Code temp = db.world.map_reduce(
map=Code("function(){emit(this.continent, {min:this.name,max:this.name})}"),
reduce=Code("""function(key, values){
var ret = {min:'ZZZ',max:'AAA'};
for(var i=0;i<values.length;i++){
if (ret.min>values[i].min) ret.min=values[i].min;
if (ret.max<values[i].max) ret.max=values[i].max;
}
return ret;
}"""),
out={"inline":1})
pp.pprint(temp["results"])
Without using query return the name and capital for any country or capital that starts with an 'L'
from bson.code import Code temp = db.world.map_reduce(
map=Code("""function(){ if((this.name).startsWith('L')|(this.capital).startsWith('L'))emit(this.name, this.capital)}"""),
reduce=Code("""function(key, values){
return values;
}"""),
out={"inline":1})
pp.pprint(temp["results"])