Des Boucles Aux Transducers - Meetup CraftingSw Paris 2016

Les boucles, tout le monde les utilise pour transformer de large collection.

Et si vous les abandonniez en gagnant par la même occasion en clarté ? Et si vous pouviez appliquer les mêmes transformations sur des ensembles infinis tout en améliorant drastiquement les performances ?

Par refactoring successif, nous passerons des boucles aux filtres et pipelines pour clôturer sur les transducers.

Une présentation qui mélange transformation de données et programmation fonctionnelle (tout en restant ouverte aux débutants).

Transcript

1. DES BOUCLES AUX TRANSDUCTEURS @LILOBASE - ARPINUM.FR
2. IL ÉTAIT UNE COLLECTION DE DONNÉE invoices = (
 dict(
 due_date=datetime(2016, 10, 22),
 amount_excl_vat=36,
 quantity=1,
 vat_rate=20,
 paid=False
 ),
 dict(
 due_date=datetime(2016, 9, 18),
 amount_excl_vat=28,
 quantity=1,
 vat_rate=10,
 paid=True
 ),
 dict(
 due_date=datetime(2016, 10, 23),
 amount_excl_vat=17,
 quantity=2,
 vat_rate=5,
 paid=False
 )
 )
3. EXEMPLE DE TRAITEMENT IMPÉRATIF def get_amount_for_month(invoices, month):
 total_amount = 0
 for invoice in invoices:
 if (invoice['due_date'].month != month):
 continue
 
 total_amount += invoice['amount_excl_vat']\
 + (invoice['amount_excl_vat']
 / 100.0
 * invoice['vat_rate']) \
 * invoice['quantity']
 
 return total_amount
4. PIPELINES MAP, FILTER, REDUCE…
5. def get_amount_for_month(invoices, month):
 total_amount = 0
 for invoice in invoices:
 if (invoice['due_date'].month != month):
 continue
 
 total_amount += invoice['amount_excl_vat']\
 + (invoice['amount_excl_vat']
 / 100.0
 * invoice['vat_rate']) \
 * invoice['quantity']
 
 return total_amount IDENTIFICATION DES ÉTAPES DU PIPELINE filter = tri 1 1 reduce = accumulateur 2 2 map = traitements sur chaque élément de la collection 3 3
6. REFACTORONS POUR UTILISER DES PIPELINES def get_amount_for_month(invoices, month):
 invoices_of_the_month = filter(
 lambda invoice: invoice['due_date'].month == month,
 invoices
 )
 
 incl_vat_amount = map(
 lambda invoice: invoice['amount_excl_vat']\
 + (invoice['amount_excl_vat']
 / 100.0
 * invoice['vat_rate']) \
 * invoice['quantity'],
 invoices_of_the_month
 )
 
 return reduce(
 lambda carry, x: carry + x,
 incl_vat_amount
 )
7. EXTRACTION DES FONCTIONS def invoice_is_due_for(month):
 return lambda invoice: \ invoice['due_date'].month == month def including_vat(invoice):
 return invoice[‘amount_excl_vat'] \
 + (invoice['amount_excl_vat']
 / 100.0
 * invoice['vat_rate']) \
 * invoice['quantity']
 
 
 def sum_invoice_amount(carry, x):
 return carry + x Closure = pré-contextualisation d’une fonction 1 1
8. VERSION REFACTORÉE def get_amount_for_month(invoices, month):
 invoice_of_the_month = \
 filter(invoice_is_due_for(month), invoices)
 
 including_vat_amount = \
 map(including_vat, invoice_of_the_month)
 
 return reduce(sum_invoice_amount, including_vat_amount)
9. COLLECTION PIPELINE Les comportements sont isolées et sans effet de bord Les comportements peuvent être réutilisés Le code est plus modulaire et résilient
10. MAIS… L’ensemble des éléments de la collection est parcouru à chaque étape de transformation Chaque étape de transformation crée une collection intermédiaire Chaque étape supplémentaire augmente le temps de calcul et la mémoire consommée
11. AVEC DES DESSINS C’EST PLUS FACILE COLLECTION COLLECTION COLLECTION COLLECTION Invoices of the month VAT included amount sum Invoices
12. PARLONS DE REDUCE REDUCE…
13. REDUCE PEUT ACCUMULER DU NON SCALAIRES def letter_count(sentence):
 
 def acc_letter(carry, word):
 if(not carry.has_key(word)):
 carry[word] = 1
 else:
 carry[word] += 1
 
 return carry
 
 return reduce(acc_letter, sentence, {})
14. MAP OU FILTER PEUVENT ÊTRE EXPRIMÉS VIA REDUCE def reduced_map(callable, collection):
 
 def map_reducer(carry, item):
 carry.append(callable(item))
 return carry
 
 return reduce(map_reducer, collection, [])
 
 def reduced_filter(callable, collection):
 
 def filter_reducer(carry, item):
 if callable(item):
 carry.append(item)
 return carry
 
 return reduce(filter_reducer, collection, [])
15. ON PEUT DONC RÉÉCRIRE NOTRE FONCTION PRÉCÉDENTE SOUS FORME D’UN REDUCER def get_amount_for_month_reduced(invoices, month):
 def reducer(carry, invoice):
 if invoice['due_date'].month == month:
 carry += invoice['amount_excl_vat'] \
 + (invoice['amount_excl_vat'] / 100
 * invoice['vat_rate']) \
 * invoice['quantity']
 return carry
 
 return reduce(reducer, invoices, 0)
16. AVEC DES DESSINS C’EST PLUS FACILE COLLECTION COLLECTION Sum Invoices
17. MAIS… C’est complètement illisible
18. TRANSDUCERS MAPPING, FILTERING, REDUCING…
19. SORTONS L’INSTRUCTION REDUCE def mapper(callable):
 
 def map_reducer(carry, item):
 carry.append(callable(item))
 return carry
 
 return map_reducer
 
 def filterer(callable):
 
 def filter_reducer(carry, item):
 if callable(item):
 carry.append(item)
 return carry
 
 return filter_reducer
21. UTILISATION def paid_invoice(invoice):
 return invoice['paid']
 
 
 
 reduce(filterer(paid_invoice), invoices, [])
22. DÉPLAÇONS APPEND def appender(carry, item):
 carry.append(item)
 return carry
23. ET NOS RÉDUCERS DEVIENNENT TRANSDUCERS def mapping(callable):
 def transducer(next_reducer):
 
 def map_reducer(carry, item):
 return next_reducer(carry, callable(item))
 
 return map_reducer
 
 return transducer
 
 
 def filtering(callable):
 def transducer(next_reducer):
 
 def filter_reducer(carry, item):
 if callable(item):
 return next_reducer(carry, item)
 else:
 return carry
 
 return filter_reducer
 
 return transducer
25. ET VOICI LES TRANSDUCTEURS À L’ACTION def adder(carry, item):
 return carry + item
 
 
 
 reduce(
 filtering(invoice_is_due_for(10))(
 mapping(including_vat)(
 adder
 )
 ), 
 invoices, 
 0
 )
26. TRANSDUCERS L’ensemble des traitements est composé 
 en une fonction Chaque élément de la collection parcourt l’ensemble des transformations en une fois Le nombre d’itération ne dépend plus du nombre de transformation
27. TRANSDUCERS Gains en consommation mémoire et temps de calcul Peut traiter des ensembles infinis Plus besoin de créer des représentations intermédiaires de la collection
28. AVEC DES DESSINS C’EST PLUS FACILE COLLECTION COLLECTION sum Invoices }
29. Les traitements se font successivement sur la collection L’ensemble des transformations est composé en une fonction pipelines « classiques » transducers
30. SUCRE SYNTAXIQUE COMPOSE, MAPITY, FILTERITY
31. COMPOSE def compose2(f, g):
 return lambda *a, **kw: f(g(*a, **kw))
 
 
 def compose(*fs):
 return reduce(compose2, fs)
 
 
 def get_amount_for_month(invoices, month):
 return reduce(
 compose(
 filtering(invoice_is_due_for(month)),
 mapping(including_vat),
 )(adder),
 invoices,
 0
 )
33. AMÉLIORONS L’API DES TRANSDUCERS def mapity(callable, collection = None):
 if collection is None:
 return mapping(callable)
 else:
 return map(callable, collection)
 
 
 def filterity(callable, collection = None):
 if collection is None:
 return filtering(callable)
 else:
 return filter(callable, collection)
34. AMÉLIORONS L’API DES TRANSDUCERS, SUITE… filterity(
 paid_invoice, 
 mapity(
 including_vat, 
 invoices
 )
 )
 
 compose(
 filterity(paid_invoice),
 mapity(including_vat)
 )(appender) Génération d’un transducer Utilisation avec les pipelines « classiques »
35. STATEFULLNESS PARTITION_BY, BATCH, FIRST
36. EN OOP, EN PHP ET AVEC UN ÉTAT ! class Batching implements Reducer
 {
 protected $next_reducer;
 protected $batch_size;
 protected $current_batch = [];
 
 public function __construct(Reducer $next_reducer, Integer $batch_size)
 {
 $this->batch_size = $batch_size;
 $this->next_reducer = $next_reducer;
 }
 
 public function init()
 {
 return $this->next_reducer->init();
 }
 
 public function step($result, $current)
 {
 $this->current_batch[] = $current;
 if (count($this->current_batch) >= $this->batch_size) {
 $batch = $this->current_batch;
 $this->current_batch = [];
 
 return $this->next_reducer->step($result, $batch);
 }
 
 return $result; 
 }
 
 public function complete($result)
 {
 if (count($this->current_batch) > 0) {
 $result = $this->next_reducer->step($result, $this->current_batch);
 }
 
 return $this->next_reducer->complete($result);
 }
 }
37. NE BLOQUEZ PAS LE PIPELINE ! class Partitioning extends Reducer {
 
 private $predicate;
 private $next_reducer;
 private $partions = [[], []];
 
 public function __construct(Reducer $next_reducer, Callable $predicate) {
 $this->next_reducer = $next_reducer;
 $this->predicate = $predicate;
 } public function init() {
 return $this->next_reducer->init();
 }
 
 public function step($result, $current) {
 if($this->predicate->__invoke($current))
 $this->partions[0] = $current;
 else
 $this->partions[1] = $current;
 }
 
 public function complete($result) {
 return $this->partions;
 }
 }
38. NE BLOQUEZ PAS LE PIPELINE class Partitioning extends Reducer {
 private $predicate;
 private $next_reducer;
 
 public function __construct(Reducer $next_reducer, Callable $predicate) {
 $this->next_reducer = $next_reducer;
 $this->predicate = $predicate;
 }
 
 public function init() {
 return [[], []];
 }
 
 public function step($result, $current) {
 if ($this->callback($current)) {
 $result[0][] = $current;
 } else {
 $result[1][] = $current;
 }
 
 return $result;
 }
 
 public function complete($result) {
 return $result;
 }
 }
39. EARLY TERMINATION namespace Fp\Reducer;
 
 class First implements Reducer
 {
 use Mixin\Stateless;
 use Mixin\ConstructWithCallback;
 
 public function step($result, $current)
 {
 if ($this->callback->__invoke($current)) {
 return new Reduced($this->next_reducer->step($result, $current));
 }
 
 return $result;
 }
 
 }

40. TRANSDUCE function transduce(callable $transducer, Reducer $reducer, Iterable $iterable, $init = null)
 {
 $internal_reducer = $transducer($reducer);
 
 $accumulator = (is_null($init)) ? $internal_reducer->init() : $init;
 foreach ($iterable as $current) {
 $accumulator = $internal_reducer->step($accumulator, $current);
 
 //early termination
 if ($accumulator instanceof Reduced) {
 $accumulator = $accumulator->value();
 break;
 }
 }
 
 return $internal_reducer->complete($accumulator);
 }
41. USAGE Fp\transduce(
 Fp\compose(
 Fp\mapping(square_makker()),
 Fp\batching(3)
 ),
 Fp\appending(), range(1, 6)); Fp\transduce(
 Fp\compose(
 Fp\mapping(square_makker()),
 Fp\first(function ($x) { return $x > 6; })
 ),
 Fp\single_result(), range(1, 6)); Fp\transduce(
 Fp\compose(
 Fp\mapping(square_makker()),
 Fp\filtering(is_even_makker()),
 Fp\enumerating()
 ),
 Fp\appending(), range(1, 6));
42. @LILOBASE MERCI !