We all know that Ruby can give us superpowers, but can we use it do something truly magical - write a brand new Harry Potter completely automatically? It turns out that Ruby and the dark arts of Natural Language Programming are a match made in heaven! Using some basic NLP techniques, a dash of probability, and a few lines of simple Ruby code, we can create a virtual author capable of generating a very convincing Potter pastiche. And if the life of an author’s not for you, don’t worry. In the last part of the talk, we'll explore how we can apply what we've learned to everyday coding problems.

1. Ruby-us Hagrid
Writing Harry Potter with Ruby
@alexpeattiealexpeattie.com/hp

2. Why should we do it?
What can we achieve?
How can we do it?
Writing Harry Potter with Ruby

3. Why should we do it?

4. Category A
The “Potheads”
Category B
The “Notters”
“Ouch, my heart” “Is that Yoda?”

5. What can we achieve?

6. (Spoiler!)

7. Neville, Seamus and Dean were muttering but did
not speak when Harry had told Fudge mere weeks
ago that Malfoy was crying, actually crying tears,
streaming down the sides of their heads. “They
revealed a spell to make your bludger” said Harry,
anger rising once more.

8. How can we do it?

9. “They revealed a spell to make your bludger” said
Harry, anger rising once more.
Key idea 1: Tell the story word by word
Key idea 2: Let’s take inspiration from our phones

11. After “birthday”, I’ve used the word:
- “party” 30 times
- “cake” 20 times
- “wishes” 10 times

12. After “golden”, J.K. used the word:
- “egg” 13 times
- “snitch” 11 times
- “plates” 10 times
The world “golden” appears in the Harry
Potter books 226 times.

13. After “golden”, J.K. used the word:
- “egg” 13 times
- “snitch” 11 times
- “plates” 10 times
The world “golden” appears in the Harry
Potter books 226 times.
Head
Continuations

14. Step 1
Learn
Step 2
Generate
Key idea 3

15. golden egg
snitch
plates
light
⋮
liquid
13
11
10
9
1
goldfish out
any
bowls
above
1
1
1
1
golf balls 2
⋮
21,814 words
⋮

16. {
:golden => {
:egg => 13,
:snitch => 11,
:plates => 10,
:light => 9,
:liquid => 1
},
:goldfish => {
:out => 1,
:any => 1,
:of => 1,
:bowls => 1
},
:golf => {
:balls => 2
}
}

17. alexpeattie.com/hp

18. def tokenize(text)
text.downcase.split(/[^a-z]+/).reject(&:empty?).map(&:to_sym)
end
"Mr. and Mrs. Dursley, of number four, Privet Drive,
were proud to say that they were perfectly normal"
[:mr, :and, :mrs, :dursley, :of, :number, :four, :privet, :drive,
:were, :proud, :to, :say, :that, :they, :were, :perfectly, :normal]

19. text = tokenize "The cat sat on the mat.
The cat was happy."
stats = {}
text.each_cons(2) do |head, continuation|
stats[head] ||= Hash.new(0)
stats[head][continuation] += 1
end

20. text = tokenize "The cat sat on the mat.
The cat was happy."
stats = {}
text.each_cons(2) do |head, continuation|
stats[head] ||= Hash.new(0)
stats[head][continuation] += 1
end
[:the, :cat]
head continuation
{
:the => {
:cat => 1
}
}

21. text = tokenize "The cat sat on the mat.
The cat was happy."
stats = {}
text.each_cons(2) do |head, continuation|
stats[head] ||= Hash.new(0)
stats[head][continuation] += 1
end
[:cat, :sat]
head continuation
{
:the => {
:cat => 1
},
:cat => {
:sat => 1
}
}

22. text = tokenize "The cat sat on the mat.
The cat was happy."
stats = {}
text.each_cons(2) do |head, continuation|
stats[head] ||= Hash.new(0)
stats[head][continuation] += 1
end
{
:the => {
:cat => 2,
:mat => 1
},
:cat => {
:sat => 1,
:was => 1
},
:sat => {
:on => 1
},
:on => {
:the => 1
},
:mat => {
:the => 1
},
:was => {
:happy => 1
}
}

23. Step 1
Learn ✅
Step 2
Generate

24. Greedy algorithm

25. Pick most
frequent
continuation

26. Pick most
frequent
continuation

27. def pick_next_word_greedily(head)
continuations = stats[head]
chosen_word, count = continuations.max_by { |word, count| count }
return chosen_word
end

28. story = [stats.keys.sample] # start with a random word from corpus
1.upto(50) do # 50 word story
story << pick_next_word_greedily(story.last)
end
puts story.join(" ")

29. Drumroll….

30. “Oh no” said Harry. A few seconds later they
were all the door and the door and the door
and the door and the door.

31. Take two….

32. Surreptitiously, several of the door and the
door and the door and the door and the door
and the door and the door.

34. several
of
the
door
and

35. conference enchantingly nasty little more
than ever since he was a few seconds later
they were all the door and…
conference

36. Greedy algorithm

37. Let’s get random
Uniform random algorithm

38. Pick randomly w/equal probability

39. Pick randomly w/equal probability
⅓
⅓ ⅓

40. Pick randomly w/equal probability
egg
snitch
plates
light
⋮
liquid
1/117
1/117
1/117
1/117
1/117
112 more

41. def pick_random_next_word(head)
continuations = stats[head]
return continuations.keys.sample
end

42. Debris from boys or accompany him bodily
from Ron, yell the waters. Harry laughing
together soon father would then bleated the
smelly cloud.

43. What’s the problem?

44. house elf
102 times
~1/200
chance
prices
1 time
~1/200
chance

45. Let’s get (a bit less) random
Weighted random algorithm

46. house elf
102 times
prices
1 time
~1/200
chance
~1/200
chance
734 times

47. house elf
102 times
prices
1 time
~1/7
chance
~1/700
chance
734 times

48. Pick randomly w/weighted probabilities
½
⅓ ⅙

49. def pick_next_word_weighted_randomly(head)
continuations = stats[head]
continuations.flat_map { |word, count| [word] * count }.sample
end

50. Springing forward as though they had a bite of the
hippogriff, he staggered blindly retorting Harry
some pumpkin tart.

51. One last big idea…

54. Key idea 4: Improve output by looking at more
than just 1 previous word

55. {
:golden => {
:egg => 12,
:snitch => 11,
:plates => 10,
:light => 9,
:liquid => 1
},
:goldfish => {
:out => 1,
:any => 1,
:of => 1,
:bowls => 1
},
:golf => {
:balls => 2
}
}
Two words
bi·gram
two word

56. {
[:golden, :egg] => {
:harry => 1,
:very => 1,
:and => 2,
:which => 1,
:upstairs => 1,
:does => 1,
:he => 2,
:said => 1,
:still => 1,
:fell => 1
},
[:golden, :snitch] => {
:and => 1,
:had => 1,
:said => 1,
:it => 1,
:a => 1,
:with => 1,
:was => 1,
:where => 1,
:worked => 1
}
}
321,727 entriestri·gram
three word
Three words

57. stats = {}
n = 3
corpus.each_cons(n) do |*head, continuation|
stats[head] ||= Hash.new(0)
stats[head][continuation] += 1
end
Added splat

58. [[:the, :cat], :sat]
head continuation
{
[:the, :cat] => {
:sat => 1
}
}
stats = {}
n = 3
corpus.each_cons(n) do |*head, continuation|
stats[head] ||= Hash.new(0)
stats[head][continuation] += 1
end

59. Normally when Dudley found his voice barely
louder than before. “Dementors” said Dumbledore
steadily, he however found all this mess is utterly
worthless. Harry looked at him, put Slughorn into
his bag more securely on to bigger and bigger until
their blackness swallowed Harry whole and started
emptying his drawers.
— trigram model

60. Neville, Seamus and Dean were muttering but did
not speak when Harry had told Fudge mere weeks
ago that Malfoy was crying, actually crying tears,
streaming down the sides of their heads. “They
revealed a spell to make your bludger” said Harry,
anger rising once more.
— 4-gram model

61. def tokenize(sentence)
sentence.downcase.split(/[^a-z]+/).reject(&:empty?).map(&:to_sym)
end
def pick_next_word_weighted_randomly(head, stats)
continuations = stats[head]
continuations.flat_map { |word, count | [word] * count }.sample
end
text = tokenize(IO.read('hp.txt'))
stats = {}
n = 3
text.each_cons(n) do |*head, continuation|
stats[head] ||= Hash.new(0)
stats[head][continuation] += 1
end
story = stats.keys.sample
1.upto(50) do
story << pick_next_word_weighted_randomly(story.last(n - 1), stats)
end
puts story.join(" ")
20 lines

62. Harry Potter

63. Harry Potter
Hard Problems

66. 1. Understand how to break down the
….problem
2. Pay attention to your failures
3. Find the right metaphor

67. 1. Understand how to break down the
….problem
2. Pay attention to your failures
3. Find the right metaphor

68. How do you eat an elephant? One
bite at a time.
— Proverb

70. Obvious
1 bite = 1 move

72. Less obvious
1 bite = 1 turn
⏎

74. Less obvious still
1 bite = 1 landmark

75. “What are the building blocks for solving
this problem?”

76. 1. Understand how to break down the
….problem
2. Pay attention to your failures
3. Find the right metaphor

78. several
of
the
door
and

79. “Why didn’t this work?”

80. 1. Understand how to break down the
….problem
2. Pay attention to your failures
3. Find the right metaphor

82. Keeps the essential parts of the problem.

83. Keeps the essential parts of the problem.
Can play around with the metaphor, and learn more
about the problem.

84. Harry Potions
Hermione Potions
Neville Potions
Hermione Arithmancy
Hermione Ancient Runes
Neville Herbology
Harry Herbology
Harry Divination

85. Harry Potions
Hermione Potions
Neville Potions
Hermione Arithmancy
Hermione Ancient Runes
Neville Herbology
Harry Herbology
Harry Divination
Whoops

86. Herbology
Divination
Potions
Ancient Runes
Arithmancy

87. Herbology
Divination
Potions
Ancient Runes
Arithmancy

88. Herbology
Divination
Potions
Ancient Runes
Arithmancy

89. “What’s a good metaphor for this problem?”

90. 1. Understand how to break down the
….problem
2. Pay attention to your failures
3. Find the right metaphor
Hard Problems

91. alexpeattie.com/hp
Thank you!
Slides and notes online at: