Merge two hashes and return common data - ruby

I have two hashes:
h1 = { "a" => 100, "b" => 200 }
h2 = { "b" => 254, "c" => 300 }
I need to return hash such as:
h3 = {
"a" => { "h1" => 100, "h2" => nil},
"b" => { "h1" => 200, "h2" => 254},
"c" => { "h1" => nil, "h2" => 300}
}
I am trying to use:
h1.merge(h2) { |k, val, old| { 'h1' => val, 'h2' => old } }
but it return only:
{"a"=>100, "b"=>{"h1"=>200, "h2"=>254}, "c"=>300}
without nil.
Any ideas?

The block is only invoked for duplicate keys. You can either ensure that both hashes contain all keys:
h1 = { "a" => 100, "b" => 200, "c" => nil }
h2 = { "a" => nil, "b" => 254, "c" => 300 }
h1.merge(h2) { |k, val, old| { 'h1' => val, 'h2' => old } }
#=> {"a"=>{"h1"=>100, "h2"=>nil},
# "b"=>{"h1"=>200, "h2"=>254},
# "c"=>{"h1"=>nil, "h2"=>300}}
Or build a new hash yourself, e.g. using the keys from both hashes:
h1 = { "a" => 100, "b" => 200 }
h2 = { "b" => 254, "c" => 300 }
(h1.keys | h2.keys).map { |k| [k, { 'h1' => h1[k], 'h2' => h2[k] }] }.to_h
#=> {"a"=>{"h1"=>100, "h2"=>nil},
# "b"=>{"h1"=>200, "h2"=>254},
# "c"=>{"h1"=>nil, "h2"=>300}}

If you read the official document for merge (here) it say:
the value for each duplicate key is determined by calling the block
with the key, its value in hsh and its value in other_hash.
This means for keys "a" and "c" , the block is never called (as they are not duplicate keys), as a result you are missing nil in your result hash.
You can try this instead:
h3 = {}
(h1.keys + h2.keys).uniq.each{|a| h3[a] = {"h1" => h1[a], "h2" => h2[a]}}
h3
# => {"a"=>{"h1"=>100, "h2"=>nil}, "b"=>{"h1"=>200, "h2"=>254}, "c"=>{"h1"=>nil, "h2"=>300}}

Here is another way that is somewhat general in terms of the numbers of hashes and hash labels:
h1 = { "a" => 100, "b" => 200 }
h2 = { "b" => 254, "c" => 300 }
h3 = { "c" => 111, "b" => 222 }
a = [h1,h2,h3]
labels = {h1=>"h1", h2=>"h2", h3=>"h3"}
h.reduce([]) { |keys,h| keys | h.keys }
.each_with_object({}) { |k,h|
h[k] = a.each_with_object({}) { |f,g| g[labels[f]] = f[k] } }
#=> {"a"=>{"h1"=>100, "h2"=>nil, "h3"=>nil},
# "b"=>{"h1"=>200, "h2"=>254, "h3"=>222},
# "c"=>{"h1"=>nil, "h2"=>300, "h3"=>111}}
The steps:
keys = h.reduce([]) { |keys,h| keys | h.keys }
#=> ["a", "b", "c"]
enum = keys.each_with_object({})
#=> #<Enumerator: ["a", "b", "c"]:each_with_object({})>
k,h = enum.next
#=> ["a", {}]
h[k] = a.each_with_object({}) { |f,g| g[labels[f]] = f[k] }
#=> {"h1"=>100, "h2"=>nil, "h3"=>nil}
k,h = enum.next
#=> ["b", {"a"=>{"h1"=>100, "h2"=>nil, "h3"=>nil}}]
h[k] = a.each_with_object({}) { |f,g| g[labels[f]] = f[k] }
#=> {"h1"=>200, "h2"=>254, "h3"=>222}
k,h = enum.next
#=> ["c", {"a"=>{"h1"=>100, "h2"=>nil, "h3"=>nil},
# "b"=>{"h1"=>200, "h2"=>254, "h3"=>222}}]
h[k] = a.each_with_object({}) { |f,g| g[labels[f]] = f[k] }
#=> {"h1"=>nil, "h2"=>300, "h3"=>111}
h
#=> {"a"=>{"h1"=>100, "h2"=>nil, "h3"=>nil},
# "b"=>{"h1"=>200, "h2"=>254, "h3"=>222},
# "c"=>{"h1"=>nil, "h2"=>300, "h3"=>111}}

Related

How to find the largest value of a hash in an array of hashes

In my array, I'm trying to retrieve the key with the largest value of "value_2", so in this case, "B":
myArray = [
"A" => {
"value_1" => 30,
"value_2" => 240
},
"B" => {
"value_1" => 40,
"value_2" => 250
},
"C" => {
"value_1" => 18,
"value_2" => 60
}
]
myArray.each do |array_hash|
array_hash.each do |key, value|
if value["value_2"] == array_hash.values.max
puts key
end
end
end
I get the error:
"comparison of Hash with Hash failed (ArgumentError)".
What am I missing?
Though equivalent, the array given in the question is generally written:
arr = [{ "A" => { "value_1" => 30, "value_2" => 240 } },
{ "B" => { "value_1" => 40, "value_2" => 250 } },
{ "C" => { "value_1" => 18, "value_2" => 60 } }]
We can find the desired key as follows:
arr.max_by { |h| h.values.first["value_2"] }.keys.first
#=> "B"
See Enumerable#max_by. The steps are:
g = arr.max_by { |h| h.values.first["value_2"] }
#=> {"B"=>{"value_1"=>40, "value_2"=>250}}
a = g.keys
#=> ["B"]
a.first
#=> "B"
In calculating g, for
h = arr[0]
#=> {"A"=>{"value_1"=>30, "value_2"=>240}}
the block calculation is
a = h.values
#=> [{"value_1"=>30, "value_2"=>240}]
b = a.first
#=> {"value_1"=>30, "value_2"=>240}
b["value_2"]
#=> 240
Suppose now arr is as follows:
arr << { "D" => { "value_1" => 23, "value_2" => 250 } }
#=> [{"A"=>{"value_1"=>30, "value_2"=>240}},
# {"B"=>{"value_1"=>40, "value_2"=>250}},
# {"C"=>{"value_1"=>18, "value_2"=>60}},
# {"D"=>{"value_1"=>23, "value_2"=>250}}]
and we wish to return an array of all keys for which the value of "value_2" is maximum (["B", "D"]). We can obtain that as follows.
max_val = arr.map { |h| h.values.first["value_2"] }.max
#=> 250
arr.select { |h| h.values.first["value_2"] == max_val }.flat_map(&:keys)
#=> ["B", "D"]
flat_map(&:keys) is shorthand for:
flat_map { |h| h.keys }
which returns the same array as:
map { |h| h.keys.first }
See Enumerable#flat_map.
Code
p myArray.pop.max_by{|k,v|v["value_2"]}.first
Output
"B"
I'd use:
my_array = [
"A" => {
"value_1" => 30,
"value_2" => 240
},
"B" => {
"value_1" => 40,
"value_2" => 250
},
"C" => {
"value_1" => 18,
"value_2" => 60
}
]
h = Hash[*my_array]
# => {"A"=>{"value_1"=>30, "value_2"=>240},
# "B"=>{"value_1"=>40, "value_2"=>250},
# "C"=>{"value_1"=>18, "value_2"=>60}}
k = h.max_by { |k, v| v['value_2'] }.first # => "B"
Hash[*my_array] takes the array of hashes and turns it into a single hash. Then max_by will iterate each key/value pair, returning an array containing the key value "B" and the sub-hash, making it easy to grab the key using first:
k = h.max_by { |k, v| v['value_2'] } # => ["B", {"value_1"=>40, "value_2"=>250}]
I guess the idea of your solution is looping through each hash element and compare the found minimum value with hash["value_2"].
But you are getting an error at
if value["value_2"] == array_hash.values.max
Because the array_hash.values is still a hash
{"A"=>{"value_1"=>30, "value_2"=>240}}.values.max
#=> {"value_1"=>30, "value_2"=>240}
It should be like this:
max = nil
max_key = ""
myArray.each do |array_hash|
array_hash.each do |key, value|
if max.nil? || value.values.max > max
max = value.values.max
max_key = key
end
end
end
# max_key #=> "B"
Another solution:
myArray.map{ |h| h.transform_values{ |v| v["value_2"] } }.max_by{ |k| k.values }.keys.first
You asked "What am I missing?".
I think you are missing a proper understanding of the data structures that you are using. I suggest that you try printing the data structures and take a careful look at the results.
The simplest way is p myArray which gives:
[{"A"=>{"value_1"=>30, "value_2"=>240}, "B"=>{"value_1"=>40, "value_2"=>250}, "C"=>{"value_1"=>18, "value_2"=>60}}]
You can get prettier results using pp:
require 'pp'
pp myArray
yields:
[{"A"=>{"value_1"=>30, "value_2"=>240},
"B"=>{"value_1"=>40, "value_2"=>250},
"C"=>{"value_1"=>18, "value_2"=>60}}]
This helps you to see that myArray has only one element, a Hash.
You could also look at the expression array_hash.values.max inside the loop:
myArray.each do |array_hash|
p array_hash.values
end
gives:
[{"value_1"=>30, "value_2"=>240}, {"value_1"=>40, "value_2"=>250}, {"value_1"=>18, "value_2"=>60}]
Not what you expected? :-)
Given this, what would you expect to be returned by array_hash.values.max in the above loop?
Use p and/or pp liberally in your ruby code to help understand what's going on.

Convert array into hash and add a counter value to the new hash

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/

How to insert a hash inside a hash ruby

I was wondering how I could insert a hash into another hash. For example, in:
{"abcd"=>{}, "hgfe"=>34567}
I want to put "hgfe" => 34567 into the "abcd" key.
output:
{"abcd"=>{"hgfe" => 34567}}
im wanting to convert this hash
"##### RUBY HASH ####
(1)
INPUT
{
'abcd.hgfe' => 34567,
'abcd.efgh.hijk' => 12345,
'abcd.efgh.ijkl' => 56789,
'wxyz.abcd' => 9876,
'wxyz.uvwx.abcd' => 23456,
}
(1)
OUTPUT
{
'abcd' => {
'efgh' => {
'hijk' => 12345,
'ijkl' => 56789
},
'hgfe' => 34567,
},
'wxyz' => {
'abcd' => 9876,
'uvwx' => {'abcd' => 23456}
}
}
"
my currrent code:
def method1(hash)
result = {}
array2 = []
hash.each_pair do|k, v|
array1 = k.split('.')
count = array1.length
hash2 = {}
array1.each_with_index do |str, index|
if (index + 1) == count
hash2[str] = v
else
hash2[str] = {}
end
end
puts hash2.inspect
puts "--------------"
end
result
end
hash_result = method1(h2c)
Do as below
hash = {"abcd"=>{}, "hgfe"=>34567}
hash['abcd']['hgfe'] = hash.delete('hgfe')
hash # => {"abcd"=>{"hgfe"=>34567}}
You can write something like below :
def delete_key_and_add_to_another_key(hash, update_key, del_key)
hash[update_key][del_key] = hash.delete(del_key)
hash
end
hash = {"abcd"=>{}, "hgfe"=>34567}
delete_key_and_add_to_another_key(hash, 'abcd', 'hgfe')
h = {"abcd"=>{}, "hgfe"=>34567}
f, l = h.partition { |_,v| v =={} }.flatten(1)
{ f.first=> { l.first => l.last } }
#=> {"abcd"=>{"hgfe"=>34567}}

How to add elements to Hash in one line?

I have a hash with some data inside. I want to add more elements into it, in one line, for simplicity. This is what I'm trying to do:
hash = add_items_to_it(hash, { alpha: 1, beta: 2 })
Is it possible?
Use Hash#merge!
hash.merge! { alpha: 1, beta: 2 }
Read documentation :
arup#linux-wzza:~/Ruby> ri Hash#merge!
= Hash#merge!
(from ruby site)
------------------------------------------------------------------------------
hsh.merge!(other_hash) -> hsh
hsh.merge!(other_hash){|key, oldval, newval| block} -> hsh
------------------------------------------------------------------------------
Adds the contents of other_hash to hsh. If no block
is specified, entries with duplicate keys are overwritten with the values from
other_hash, otherwise the value of each duplicate key is
determined by calling the block with the key, its value in hsh and its
value in other_hash.
h1 = { "a" => 100, "b" => 200 }
h2 = { "b" => 254, "c" => 300 }
h1.merge!(h2) #=> {"a"=>100, "b"=>254, "c"=>300}
h1 = { "a" => 100, "b" => 200 }
h2 = { "b" => 254, "c" => 300 }
h1.merge!(h2) { |key, v1, v2| v1 }
#=> {"a"=>100, "b"=>200, "c"=>300}
lines 1-25/25 (END)
You are looking for Hash#merge:
hash = { one: 1, two: 2 }
#=> {:one=>1, :two=>2}
hash = hash.merge({ alpha: 1, beta: 2 })
#=> {:one=>1, :two=>2, :alpha=>1, :beta=>2}

Averaging values across multiple hashes

EDIT I am accepting #CarySwoveland's answer because he got the closest on the first try, accounting for the most scenarios, and outputting the data into a hash so that you don't need to rely on order. Many honerable mentions though! Be sure to check out #ArupRakshit's answer as well if you want your output in an array!
I have an array of hashes like:
#my_hashes = [{"key1" => "10", "key2" => "5"...},{"key1" => "", "key2" => "9"...},{"key1" => "6", "key2" => "4"...}]
and I want an average for each key across the array. ie. 8.0,6.0...
Note that the hashes all have the exact same keys, in order, even if the value for the key is blank. Right now this works:
<%= #my_hashes[0].keys.each do |key| %>
<% sum = 0 %>
<% count = 0 %>
<% #my_hashes.each do |hash| %>
<% sum += hash[key].to_f %>
<% count += if hash[key].blank? then 0 else 1 end %>
<% end %>
<%= (sum/count) %>
<% end %>
but I feel like there may be a better way... any thoughts?
Do as below
#my_hashes = [{"key1" => "10", "key2" => "5"},{"key1" => "", "key2" => "9"},{"key1" => "6", "key2" => "4"}]
ar = #my_hashes[0].keys.map do |k|
a = #my_hashes.map { |h| h[k].to_f unless h[k].blank? }.compact
a.inject(:+)/a.size unless a.empty? #Accounting for "key1" => nil or "key1" => ""
end
ar # => [8, 6]
Another way:
#my_hashes = [ {"key1"=>"10", "key2"=>"5"},
{"key1"=> "", "key2"=>"9"},
{"key1"=> "6", "key2"=>"4"} ]
def avg(arr) arr.any? ? arr.reduce(:+)/arr.size.to_f : 0.0 end
(#my_hashes.each_with_object ( Hash.new { |h,k| h[k]=[] } ) {
|mh,h| mh.keys.each { |k| h[k] << mh[k].to_f unless mh[k].empty? } })
.each_with_object({}) { |(k,v),h| h[k] = avg(v) }
# => {"key1"=>8.0, "key2"=>6.0}
The object created by the first each_with_object is a hash whose default value is an empty array. That hash is represented by the block variable h. This means that if h[k] << mh[k].to_f is to be executed when h.key?(k) => false, h[k] = [] is executed first.
One could alternatively drop the avg method and create a temporary variable before computing the averages:
h = #my_hashes.each_with_object ( Hash.new { |h,k| h[k]=[] } ) { |mh,h|
mh.keys.each { |k| h[k] << mh[k].to_f unless mh[k].empty? } }
h.each_with_object({}) { |(k,v),h|
h[k] = ( avg(v) arr.any? ? arr.reduce(:+)/arr.size.to_f : 0.0 }
I think I found a quite elegant solution.
Here is a sample array:
a = [
{:a => 2, :b => 10},
{:a => 4, :b => 20},
{:a => 2, :b => 10},
{:a => 8, :b => 40},
]
And the solution:
class Array
def average
self.reduce(&:+) / self.size
end
end
r = a[0].keys.map do |key|
[key, a.map { |hash| hash[key] }.average]
end
puts Hash[*r.flatten]
Try this
#my_hashes = [{"key1" => "10", "key2" => "5"},{"key1" => "", "key2" => "9"},{"key1" => "6", "key2" => "4"}]
average_values = #my_hashes.map(&:values).transpose.map { |arr|
arr.map(&:to_f).inject(:+) / arr.size
}
with_keys = Hash[#my_hashes.first.keys.zip(average_values)]
average_values # => [5.333333333333333, 6.0]
with_keys # => {"key1"=>5.333333333333333, "key2"=>6.0}
if you want to exclude empty values from the average, could change average_values to reject empty values
average_values = #my_hashes.map(&:values).transpose.map { |arr|
arr.reject!(&:empty?)
arr.map(&:to_f).inject(:+) / arr.size
}
average_values # => [8.0, 6.0]
No super clean solution, but I would write:
a = [
{:a => 2, :b => 10},
{:a => 4, :b => 20},
{:a => 2, :b => 10},
{:a => 8, :b => 40},
]
grouped = a.flat_map(&:to_a).group_by{|x,|x}
grouped.keys.each do |key|
len = grouped[key].size
grouped[key] = 1.0 * grouped[key].map(&:last).inject(:+) / len
end

Resources