nodes = {
:node1 => {
:inherits => nil,
:variables => { :foo => 1, :bar => 2 }
},
:node2 => {
:inherits => :node1,
:variables => { :foo => 9, :baz => 4 }
}
}
I've been trying to understand how to return a new nodes hash where each node's :variables hash is merged with :variables from the node specified in :inheritance. In other words, node1 would be left as is while node2 to end up with :variabes => { :foo => 9, :bar => 2, :baz => 4 }
I've been swimming through docs involving Enumerable#inject, Hash#merge with a block, and more and figure it's time to ask for help.
UPDATE:
Figured I'd provide an update. This code is certainly not the solution but it might be heading in the right direction...
nodes = {
:node1 => { :inherits => nil, :variables => { :foo => 1, :bar => 2 } },
:node2 => { :inherits => :node1, :variables => { :foo => 9, :baz => 4 } }
}
new = nodes.inject({}) do |result, (k, v)|
result.merge k => v.merge({ :variables => { :a => 6, :b => 7 } })
end
returns
{:node2=>{:inherits=>:node1, :variables=>{:a=>6, :b=>7}}, :node1=>{:inherits=>nil, :variables=>{:a=>6, :b=>7}}}
So that v.merge is not working as intended...
You want Hash#merge:
merged_variables = nodes[:node1][:variables].merge(nodes[:node2][:variables])
nodes[:node2][:variables].replace(
nodes[:node1][:variables]
.merge(nodes[:node2][:variables])
)
merged_nodes = {}
nodes.each do |name, node|
merged_nodes[name] = node.dup
merged_nodes[name][:variables] = if node[:inherits]
nodes[node[:inherits]][:variables].merge node[:variables]
else
node[:variables].dup
end
end
will give you
{
:node1=>{:inherits=>nil, :variables=>{:foo=>1, :bar=>2}},
:node2=>{:inherits=>:node1, :variables=>{:foo=>9, :bar=>2, :baz=>4}}
}
but it won't handle deeper nesting i.e. if :node3 then inherits :node2... if you need anything as complicated as that, this hash-based approach is going to get pretty clunky.
A little bit shorter by merging in place:
nodes[:node2][:variables].merge!(nodes[:node1][:variables])
nodes #=> {:node1=>{:inherits=>nil, :variables=>{:foo=>1, :bar=>2}},
# :node2=>{:inherits=>:node1, :variables=>{:foo=>1, :baz=>4, :bar=>2}}}
new = {}
nodes.each do |e, v|
v.each do |attribute, value|
if attribute == :inherits
new[e] = value.nil? ? v : nodes[value][:variables].merge( v[:variables] )
end
end
end
p new #=> {:node1=>{:inherits=>nil, :variables=>{:foo=>1, :bar=>2}}, :node2=>{:foo=>9, :bar=>2, :baz=>4}}
Related
I have the following array of hashes:
[
{"BREAD" => {:price => 1.50, :discount => true }},
{"BREAD" => {:price => 1.50, :discount => true }},
{"MARMITE" => {:price => 1.60, :discount => false}}
]
And I would like to translate this array into a hash that includes the counts for each item:
Output:
{
"BREAD" => {:price => 1.50, :discount => true, :count => 2},
"MARMITE" => {:price => 1.60, :discount => false, :count => 1}
}
I have tried two approaches to translate the array into a hash.
new_cart = cart.inject(:merge)
hash = Hash[cart.collect { |item| [item, ""] } ]
Both work but then I am stumped at how to capture and pass the count value.
Expected output
{
"BREAD" => {:price => 1.50, :discount => true, :count => 2},
"MARMITE" => {:price => 1.60, :discount => false, :count => 1}
}
We are given the array:
arr = [
{"BREAD" => {:price => 1.50, :discount => true }},
{"BREAD" => {:price => 1.50, :discount => true }},
{"MARMITE" => {:price => 1.60, :discount => false}}
]
and make the assumption that each hash has a single key and if two hashes have the same (single) key, the value of that key is the same in both hashes.
The first step is create an empty hash to which will add key-value pairs:
h = {}
Now we loop through arr to build the hash h. I've added a puts statement to display intermediate values in the calculation.
arr.each do |g|
k, v = g.first
puts "k=#{k}, v=#{v}"
if h.key?(k)
h[k][:count] += 1
else
h[k] = v.merge({ :count => 1 })
end
end
displays:
k=BREAD, v={:price=>1.5, :discount=>true}
k=BREAD, v={:price=>1.5, :discount=>true}
k=MARMITE, v={:price=>1.6, :discount=>false}
and returns:
#=> [{"BREAD" =>{:price=>1.5, :discount=>true}},
# {"BREAD" =>{:price=>1.5, :discount=>true}},
# {"MARMITE"=>{:price=>1.6, :discount=>false}}]
each always returns its receiver (here arr), which is not what we want.
h #=> {"BREAD"=>{:price=>1.5, :discount=>true, :count=>2},
# "MARMITE"=>{:price=>1.6, :discount=>false, :count=>1}}
is the result we need. See Hash#key? (aka, has_key?), Hash#[], Hash#[]= and Hash#merge.
Now let's wrap this in a method.
def hashify(arr)
h = {}
arr.each do |g|
k, v = g.first
if h.key?(k)
h[k][:count] += 1
else
h[k] = v.merge({ :count=>1 })
end
end
h
end
hashify(arr)
#=> {"BREAD"=>{:price=>1.5, :discount=>true, :count=>2},
# "MARMITE"=>{:price=>1.6, :discount=>false, :count=>1}}
Rubyists would often use the method Enumerable#each_with_object to simplify.
def hashify(arr)
arr.each_with_object({}) do |g,h|
k, v = g.first
if h.key?(k)
h[k][:count] += 1
else
h[k] = v.merge({ :count => 1 })
end
end
end
Compare the two methods to identify their differences. See Enumerable#each_with_object.
When, as here, the keys are symbols, Ruby allows you to use the shorthand { count: 1 } for { :count=>1 }. Moreover, she permits you to write :count = 1 or count: 1 without the braces when the hash is an argument. For example,
{}.merge('cat'=>'meow', dog:'woof', :pig=>'oink')
#=> {"cat"=>"meow", :dog=>"woof", :pig=>"oink"}
It's probably more common to see the form count: 1 when keys are symbols and for the braces to be omitted when a hash is an argument.
Here's a further refinement you might see. First create
h = arr.group_by { |h| h.keys.first }
#=> {"BREAD" =>[{"BREAD"=>{:price=>1.5, :discount=>true}},
# {"BREAD"=>{:price=>1.5, :discount=>true}}],
# "MARMITE"=>[{"MARMITE"=>{:price=>1.6, :discount=>false}}]}
See Enumerable#group_by. Now convert the values (arrays) to their sizes:
counts = h.transform_values { |arr| arr.size }
#=> {"BREAD"=>2, "MARMITE"=>1}
which can be written in abbreviated form:
counts = h.transform_values(&:size)
#=> {"BREAD"=>2, "MARMITE"=>1}
See Hash#transform_values. We can now write:
uniq_arr = arr.uniq
#=> [{"BREAD"=>{:price=>1.5, :discount=>true}},
#= {"MARMITE"=>{:price=>1.6, :discount=>false}}]
uniq_arr.each_with_object({}) do |g,h|
puts "g=#{g}"
k,v = g.first
puts " k=#{k}, v=#{v}"
h[k] = v.merge(counts: counts[k])
puts " h=#{h}"
end
which displays:
g={"BREAD"=>{:price=>1.5, :discount=>true}}
k=BREAD, v={:price=>1.5, :discount=>true}
h={"BREAD"=>{:price=>1.5, :discount=>true, :counts=>2}}
g={"MARMITE"=>{:price=>1.6, :discount=>false}}
k=MARMITE, v={:price=>1.6, :discount=>false}
h={"BREAD"=>{:price=>1.5, :discount=>true, :counts=>2},
"MARMITE"=>{:price=>1.6, :discount=>false, :counts=>1}}
and returns:
#=> {"BREAD"=>{:price=>1.5, :discount=>true, :counts=>2},
# "MARMITE"=>{:price=>1.6, :discount=>false, :counts=>1}}
See Array#uniq.
This did the trick:
arr = [
{ bread: { price: 1.50, discount: true } },
{ bread: { price: 1.50, discount: true } },
{ marmite: { price: 1.60, discount: false } }
]
Get the count for each occurrence of hash, add as key value pair and store:
h = arr.uniq.each { |x| x[x.first.first][:count] = arr.count(x) }
Then convert hashes into arrays, flatten to a single array then construct a hash:
Hash[*h.collect(&:to_a).flatten]
#=> {:bread=>{:price=>1.50, :discount=>true, :count=>2}, :marmite=>{:price=>1.60, :discount=>false, :count=>1}}
Combined a couple of nice ideas from here:
https://raycodingdotnet.wordpress.com/2013/08/05/array-of-hashes-into-single-hash-in-ruby/
and here:
http://carol-nichols.com/2015/08/07/ruby-occurrence-couting/
I have two hashes with some data that I need to aggregate. The first one is a mapping of which ids (id_1, id_2, id_3, id_4) belong under what category (a, b, c):
hash_1 = {'a' => ['id_1','id_2'], 'b' => ['id_3'], 'c' => ['id_4']}
The second hash holds values of how many events happened per id for a given date (date_1, date_2, date_3):
hash_2 = {
'id_1' => {'date_1' => 5, 'date_2' => 6, 'date_3' => 8},
'id_2' => {'date_1' => 0, 'date_3' => 6},
'id_3' => {'date_1' => 0, 'date_2' => nil, 'date_3' => 1},
'id_4' => {'date_1' => 10, 'date_2' => 1}
}
What I want is to get the total event per category (a,b,c). For the above example, the result would look something like:
hash_3 = {'a' => (5+6+8+0+6), 'b' => (0+0+1), 'c' => (10+1)}
My problem is, that there are about 5000 categories, each pointing to typically 1 to 3 ids, and each ID having event counts for 30 dates or more. So this takes quite a bit of computation. What will be the most performant (time effective) way to do this grouping in Ruby?
update
This is what I tried so far (took like 6-8 seconds!, horribly slow):
def total_clicks_per_category
{}.tap do |res|
hash_1.each do |cat, ids|
res[cat] = total_event_per_ids(ids)
end
end
end
def total_event_per_ids(ids)
ids.reduce(0) do |memo, id|
events = hash_2.fetch(id, {})
memo + (events.values.reduce(:+) || 0)
end
end
P.S. I’m using Ruby 2.3.
I'm writing this on a phone so I cannot test right now, but it looks OK.
g = hash_2.each_with_object({}) { |(k,v),g| g[k] = v.values.compact.sum }
hash_3 = hash_1.each_with_object({}) { |(k,v),h| h[k] = g.values_at(*v).sum }
First, create an intermediate hash that holds the sum of hash_2:
hash_4 = hash_2.map{|k, v| [k, v.values.inject(:+)]}.to_h
# => {"id_1"=>19, "id_2"=>6, "id_3"=>1, "id_4"=>11}
Then do the final summation:
hash_3 = hash_1.map{|k, v| [k, v.map{|k| hash_4[k]}.inject(:+)]}.to_h
# => {"a"=>25, "b"=>1, "c"=>11}
Theory
5000*3*30 isn't that many. Ruby probably will need a second at most for this kind of job.
Hash lookup is fast by default, you won't be able to optimize much.
You could pre-calculate hash_2_sum, though :
hash_2_sum = {
'id_1' => 5+6+8,
'id_2' => 0+6,
'id_3' => 0+0+1,
'id_4' => 10+1
}
A loop on hash1 with hash_2_sum lookup, and you're done.
Code
Your example has been updated with some nil values. You need to remove them with compact, and make sure the sum is 0 when no element is found with inject(0, :+):
hash_1 = {'a' => ['id_1','id_2'], 'b' => ['id_3'], 'c' => ['id_4']}
hash_2 = {
'id_1' => { 'date_1' => 5, 'date_2' => 6, 'date_3' => 8 },
'id_2' => { 'date_1' => 0, 'date_3' => 6 },
'id_3' => { 'date_1' => 0, 'date_2' => nil, 'date_3' => 1 },
'id_4' => { 'date_1' => 10, 'date_2' => 1 }
}
hash_2_sum = hash_2.each_with_object({}) do |(key, dates), sum|
sum[key] = dates.values.compact.inject(0, :+)
end
hash_3 = hash_1.each_with_object({}) do |(key, ids), sum|
sum[key] = hash_2_sum.values_at(*ids).inject(0, :+)
end
# {"a"=>25, "b"=>1, "c"=>11}
Note
{}.tap do |res|
hash_1.each do |cat, ids|
res[cat] = total_event_per_ids(ids)
end
end
isn't very readable IMHO.
You can either use each_with_object or Array#to_h :
result = [1, 2, 3].each_with_object({}) do |i, hash|
hash[i] = i * i
end
#=> {1=>1, 2=>4, 3=>9}
result = [1, 2, 3].map { |i| [i, i * i] }.to_h
#=> {1=>1, 2=>4, 3=>9}
I'm pretty new in Ruby programming. In Ruby there are plenty ways to write elegant code. Is there any elegant way to link two arrays with objects of the same type by attribute value?
It's hard to explain. Let's look at the next example:
a = [ { :id => 1, :value => 1 }, { :id => 2, :value => 2 }, { :id => 3, :value => 3 } ]
b = [ { :id => 1, :value => 2 }, { :id => 3, :value => 4 } ]
c = link a, b
# Result structure after linkage.
c = {
"1" => {
:a => { :id => 1, :value => 1 },
:b => { :id => 1, :value => 1 }
},
"3" => {
:a => { :id => 3, :value => 3 },
:b => { :id => 3, :value => 4 }
}
}
So the basic idea is to get pairs of objects from different arrays by their common ID and construct a hash, which will give this pair by ID.
Thanks in advance.
If you want to take an adventure through Enumerable, you could say this:
(a.map { |h| [:a, h] } + b.map { |h| [:b, h] })
.group_by { |_, h| h[:id] }
.select { |_, a| a.length == 2 }
.inject({}) { |h, (n, v)| h.update(n => Hash[v]) }
And if you really want the keys to be strings, say n.to_s => Hash[v] instead of n => Hash[v].
The logic works like this:
We need to know where everything comes from we decorate the little hashes with :a and :b symbols to track their origins.
Then add the decorated arrays together into one list so that...
group_by can group things into almost-the-final-format.
Then find the groups of size two since those groups contain the entries that appeared in both a and b. Groups of size one only appeared in one of a or b so we throw those away.
Then a little injection to rearrange things into their final format. Note that the arrays we built in (1) just somehow happen to be in the format that Hash[] is looking for.
If you wanted to do this in a link method then you'd need to say things like:
link :a => a, :b => b
so that the method will know what to call a and b. This hypothetical link method also easily generalizes to more arrays:
def link(input)
input.map { |k, v| v.map { |h| [k, h] } }
.inject(:+)
.group_by { |_, h| h[:id] }
.select { |_, a| a.length == input.length }
.inject({}) { |h, (n, v)| h.update(n => Hash[v]) }
end
link :a => [...], :b => [...], :c => [...]
I assume that, for any two elements h1 and h2 of a (or of b), h1[:id] != h2[:id].
I would do this:
def convert(arr) Hash[arr.map {|h| [h[:id], h]}] end
ah, bh = convert(a), convert(b)
c = ah.keys.each_with_object({}) {|k,h|h[k]={a: ah[k], b: bh[k]} if bh.key?(k)}
# => {1=>{:a=>{:id=>1, :value=>1}, :b=>{:id=>1, :value=>2}},
# 3=>{:a=>{:id=>3, :value=>3}, :b=>{:id=>3, :value=>4}}}
Note that:
ah = convert(a)
# => {1=>{:id=>1, :value=>1}, 2=>{:id=>2, :value=>2}, 3=>{:id=>3, :value=>3}}
bh = convert(b)
# => {1=>{:id=>1, :value=>2}, 3=>{:id=>3, :value=>4}}
Here's a second approach. I don't like it as well, but it represents a different way of looking at the problem.
def sort_by_id(a) a.sort_by {|h| h[:id]} end
c = Hash[*sort_by_id(a.select {|ha| b.find {|hb| hb[:id] == ha[:id]}})
.zip(sort_by_id(b))
.map {|ha,hb| [ha[:id], {a: ha, b: hb}]}
.flatten]
Here's what's happening. The first step is to select only the elements ha of a for which there is an element hb of b for which ha[:id] = hb[id]. Then we sort both (what's left of) a and b on h[:id], zip them together and then make the hash c.
r1 = a.select {|ha| b.find {|hb| hb[:id] == ha[:id]}}
# => [{:id=>1, :value=>1}, {:id=>3, :value=>3}]
r2 = sort_by_id(r1)
# => [{:id=>1, :value=>1}, {:id=>3, :value=>3}]
r3 = sort_by_id(b)
# => [{:id=>1, :value=>2}, {:id=>3, :value=>4}]
r4 = r2.zip(r3)
# => [[{:id=>1, :value=>1}, {:id=>1, :value=>2}],
# [{:id=>3, :value=>3}, {:id=>3, :value=>4}]]
r5 = r4.map {|ha,hb| [ha[:id], {a: ha, b: hb}]}
# => [[1, {:a=>{:id=>1, :value=>1}, :b=>{:id=>1, :value=>2}}],
# [3, {:a=>{:id=>3, :value=>3}, :b=>{:id=>3, :value=>4}}]]
r6 = r5.flatten
# => [1, {:a=>{:id=>1, :value=>1}, :b=>{:id=>1, :value=>2}},
# 3, {:a=>{:id=>3, :value=>3}, :b=>{:id=>3, :value=>4}}]
c = Hash[*r6]
# => {1=>{:a=>{:id=>1, :value=>1}, :b=>{:id=>1, :value=>2}},
# 3=>{:a=>{:id=>3, :value=>3}, :b=>{:id=>3, :value=>4}}}
Ok, I've found the answer by myself. Here is a quite short line of code, which should do the trick:
Hash[a.product(b)
.select { |pair| pair[0][:id] == pair[1][:id] }
.map { |pair| [pair[0][:id], { :a => pair[0], :b => pair[1] }] }]
The product method gives us all possible pairs, then we filter them by equal IDs of pair elements. And then we map pairs to the special form, which will produce a Hash we are looking for.
So Hash[["key1", "value1"], ["key2", "value2"]] returns { "key1" => "value1", "key2" => "value2" }. And I use this to get the answer on my question.
Thanks.
P.S.: you can use pair.first instead of pair[0] and pair.last instead of pair[1] for better readability.
UPDATE
As Cary pointed out, it is better to replace |pair| with |ha, hb| to avoid these ugly indices:
Hash[a.product(b)
.select { |ha, hb| ha[:id] == hb[:id] }
.map { |ha, hb| [ha[:id], { :a => ha, :b => hb }] }]
I'm looking for a solution how to write the format function which will take a string or nested hash as an argument and return the flatten version of it with the path as a key.
arg = "foo"
format(arg) # => { "hash[keys]" => "foo" }
arg = {:a => "foo", :b => { :c => "bar", :d => "baz" }}
format(arg) # => { "hash[keys][a]" => "foo", "hash[keys][b][c]" => "bar", "hash[keys][b][d]" => "baz" }
def hash_flatten h
h.inject({}) do |a,(k,v)|
if v.is_a?(Hash)
hash_flatten(v).each do |sk, sv|
a[[k]+sk] = sv
end
else
k = k ? [k] : []
a[k] = v
end
a
end
end
def format h
if h.is_a?(Hash)
a = hash_flatten(h).map do |k,v|
key = k.map{|e| "[#{e}]"}.join
"\"event[actor]#{key}\" => \"#{v}\""
end.join(', ')
else
format({nil => h})
end
end
arg = "sth"
puts format(arg)
# => "event[actor]" => "sth"
arg = {:a => "sth", :b => { :c => "sth else", :d => "trololo" }}
puts format(arg)
# => "event[actor][a]" => "sth", "event[actor][b][c]" => "sth else", "event[actor][b][d]" => "trololo"
Let's say I have an arbitrarily deep nested Hash h:
h = {
:foo => { :bar => 1 },
:baz => 10,
:quux => { :swozz => {:muux => 1000}, :grimel => 200 }
# ...
}
And let's say I have a class C defined as:
class C
attr_accessor :dict
end
How do I replace all nested values in h so that they are now C instances with the dict attribute set to that value? For instance, in the above example, I'd expect to have something like:
h = {
:foo => <C #dict={:bar => 1}>,
:baz => 10,
:quux => <C #dict={:swozz => <C #dict={:muux => 1000}>, :grimel => 200}>
# ...
}
where <C #dict = ...> represents a C instance with #dict = .... (Note that as soon as you reach a value which isn't nested, you stop wrapping it in C instances.)
def convert_hash(h)
h.keys.each do |k|
if h[k].is_a? Hash
c = C.new
c.dict = convert_hash(h[k])
h[k] = c
end
end
h
end
If we override inspect in C to give a more friendly output like so:
def inspect
"<C #dict=#{dict.inspect}>"
end
and then run with your example h this gives:
puts convert_hash(h).inspect
{:baz=>10, :quux=><C #dict={:grimel=>200,
:swozz=><C #dict={:muux=>1000}>}>, :foo=><C #dict={:bar=>1}>}
Also, if you add an initialize method to C for setting dict:
def initialize(d=nil)
self.dict = d
end
then you can reduce the 3 lines in the middle of convert_hash to just h[k] = C.new(convert_hash_h[k])
class C
attr_accessor :dict
def initialize(dict)
self.dict = dict
end
end
class Object
def convert_to_dict
C.new(self)
end
end
class Hash
def convert_to_dict
Hash[map {|k, v| [k, v.convert_to_dict] }]
end
end
p h.convert_to_dict
# => {
# => :foo => {
# => :bar => #<C:0x13adc18 #dict=1>
# => },
# => :baz => #<C:0x13adba0 #dict=10>,
# => :quux => {
# => :swozz => {
# => :muux => #<C:0x13adac8 #dict=1000>
# => },
# => :grimel => #<C:0x13ada50 #dict=200>
# => }
# => }