ajout du cas discret
This commit is contained in:
François Pelletier
parent
ee8c7cbb2a
commit
54badfdff4
2 changed files with 89 additions and 44 deletions
|
|
@ -10,7 +10,8 @@ je vais avoir besoin de tester les méthodes train, predict et test de votre cod
|
|||
"""
|
||||
|
||||
import numpy as np
|
||||
|
||||
import metrics
|
||||
import time
|
||||
|
||||
# le nom de votre classe
|
||||
# NeuralNet pour le modèle Réseaux de Neurones
|
||||
|
|
@ -18,13 +19,14 @@ import numpy as np
|
|||
|
||||
class DecisionTree: #nom de la class à changer
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
def __init__(self, attribute_type, **kwargs):
|
||||
"""
|
||||
c'est un Initializer.
|
||||
Vous pouvez passer d'autre paramètres au besoin,
|
||||
c'est à vous d'utiliser vos propres notations
|
||||
"""
|
||||
self.tree=[]
|
||||
self.attribute_type=attribute_type
|
||||
|
||||
def plurality_value(self,train_labels):
|
||||
values,_,counts = np.unique(train_labels,return_index=True, return_counts=True)
|
||||
|
|
@ -36,33 +38,39 @@ class DecisionTree: #nom de la class à changer
|
|||
total_count = sum(counts)
|
||||
entropie_total = -sum(counts/total_count * np.log2(counts/total_count))
|
||||
#print("Entropie Total:"+str(entropie_total))
|
||||
#Trouver split
|
||||
attribute_sort_order = np.argsort(train[:,attribute])
|
||||
sorted_labels = train_labels[attribute_sort_order]
|
||||
lags = np.hstack((np.array([False]),sorted_labels[:-1] != sorted_labels[1:]))
|
||||
lags2 = np.hstack((np.array([False]),lags))[:-1]
|
||||
potential_splits = 0.5*train[attribute_sort_order,attribute][lags]+0.5*train[attribute_sort_order,attribute][lags2]
|
||||
if (len(potential_splits)==0):
|
||||
potential_splits = np.array([np.median(train[attribute_sort_order,attribute])])
|
||||
#print("Potential Split:"+str(potential_splits))
|
||||
split_gain = []
|
||||
for v in potential_splits:
|
||||
split_labels_1 = train_labels[train[:,attribute] <= v]
|
||||
split_labels_2 = train_labels[train[:,attribute] > v]
|
||||
_,_,counts1 = np.unique(split_labels_1,return_index=True, return_counts=True)
|
||||
|
||||
if (self.attribute_type=="continuous"):
|
||||
#Trouver split
|
||||
attribute_sort_order = np.argsort(train[:,attribute])
|
||||
sorted_labels = train_labels[attribute_sort_order]
|
||||
lags = np.hstack((np.array([False]),sorted_labels[:-1] != sorted_labels[1:]))
|
||||
lags2 = np.hstack((np.array([False]),lags))[:-1]
|
||||
potential_splits = 0.5*train[attribute_sort_order,attribute][lags]+0.5*train[attribute_sort_order,attribute][lags2]
|
||||
if (len(potential_splits)==0):
|
||||
potential_splits = np.array([np.median(train[attribute_sort_order,attribute])])
|
||||
#print("Potential Split:"+str(potential_splits))
|
||||
split_gain = []
|
||||
for v in potential_splits:
|
||||
split_labels_1 = train_labels[train[:,attribute] <= v]
|
||||
split_labels_2 = train_labels[train[:,attribute] > v]
|
||||
_,_,counts1 = np.unique(split_labels_1,return_index=True, return_counts=True)
|
||||
total_count1 = sum(counts1)
|
||||
entropie_total1 = -sum(counts1/total_count1 * np.log2(counts1/total_count1))
|
||||
_,_,counts2 = np.unique(split_labels_2,return_index=True, return_counts=True)
|
||||
total_count2 = sum(counts2)
|
||||
entropie_total2 = -sum(counts2/total_count2 * np.log2(counts2/total_count2))
|
||||
split_gain.append(entropie_total-(total_count1/total_count*entropie_total1+total_count2/total_count*entropie_total2))
|
||||
#Valeur unique attribut
|
||||
#print("Split Gain:"+str(split_gain))
|
||||
best_split = potential_splits[np.argmax(split_gain)]
|
||||
best_gain = max(split_gain)
|
||||
return best_gain,best_split
|
||||
if (self.attribute_type=="discrete"):
|
||||
_,counts1 = np.unique(train[:,attribute], return_counts=True)
|
||||
total_count1 = sum(counts1)
|
||||
entropie_total1 = -sum(counts1/total_count1 * np.log2(counts1/total_count1))
|
||||
_,_,counts2 = np.unique(split_labels_2,return_index=True, return_counts=True)
|
||||
total_count2 = sum(counts2)
|
||||
entropie_total2 = -sum(counts2/total_count2 * np.log2(counts2/total_count2))
|
||||
split_gain.append(entropie_total-(total_count1/total_count*entropie_total1+total_count2/total_count*entropie_total2))
|
||||
#Valeur unique attribut
|
||||
#print("Split Gain:"+str(split_gain))
|
||||
best_split = potential_splits[np.argmax(split_gain)]
|
||||
best_gain = max(split_gain)
|
||||
|
||||
return best_gain,best_split
|
||||
|
||||
gain = entropie_total - entropie_total1
|
||||
return gain,None
|
||||
|
||||
|
||||
def decision_tree_learning(self,train, train_labels, attributes, parent_examples):
|
||||
|
|
@ -92,22 +100,35 @@ class DecisionTree: #nom de la class à changer
|
|||
gain, split = self.importance(train, train_labels, a)
|
||||
a_gain.append(gain)
|
||||
a_split.append(split)
|
||||
|
||||
# Calcul du meilleur attribut
|
||||
|
||||
pos_gain_max = np.argmax(a_gain)
|
||||
a_max = attr[pos_gain_max]
|
||||
a_max_split = a_split[pos_gain_max]
|
||||
tree = []
|
||||
attributes[a_max]=0
|
||||
|
||||
# Nouvel arbre
|
||||
|
||||
tree = []
|
||||
|
||||
# pour chaque valeur de l'attribut, faire un sous-arbre
|
||||
for v in [True,False]:
|
||||
print("Nouvelle branche: l'attribut "+str(a_max)+"<="+str(a_max_split)+" est: "+str(v))
|
||||
train_pos = np.where((train[:,a_max] <= a_max_split) == v)
|
||||
subtree = self.decision_tree_learning(train[train_pos],train_labels[train_pos],attributes,train_labels)
|
||||
tree.append(("Branche",a_max,a_max_split,v,subtree))
|
||||
if (self.attribute_type=="continuous"):
|
||||
for v in [True,False]:
|
||||
print("Nouvelle branche: l'attribut "+str(a_max)+"<="+str(a_max_split)+" est: "+str(v))
|
||||
train_pos = np.where((train[:,a_max] <= a_max_split) == v)
|
||||
subtree = self.decision_tree_learning(train[train_pos],train_labels[train_pos],attributes,train_labels)
|
||||
tree.append(("Branche",a_max,a_max_split,v,subtree))
|
||||
if (self.attribute_type=="discrete"):
|
||||
for v in np.unique(train[:,a_max]):
|
||||
print("Nouvelle branche: l'attribut "+str(a_max)+" est: "+str(v))
|
||||
train_pos = np.where(train[:,a_max] == v)
|
||||
subtree = self.decision_tree_learning(train[train_pos],train_labels[train_pos],attributes,train_labels)
|
||||
tree.append(("Branche",a_max,v,subtree))
|
||||
return tree
|
||||
|
||||
|
||||
def train(self, train, train_labels): #vous pouvez rajouter d'autres attribus au besoin
|
||||
def train(self, train, train_labels,verbose=True): #vous pouvez rajouter d'autres attribus au besoin
|
||||
"""
|
||||
c'est la méthode qui va entrainer votre modèle,
|
||||
train est une matrice de taille nxm, avec
|
||||
|
|
@ -115,6 +136,7 @@ class DecisionTree: #nom de la class à changer
|
|||
m : le mobre d'attribus (le nombre de caractéristiques)
|
||||
|
||||
train_labels : est une matrice de taille nx1
|
||||
verbose: afficher les métriques calculées
|
||||
|
||||
vous pouvez rajouter d'autres arguments, il suffit juste de
|
||||
les expliquer en commentaire
|
||||
|
|
@ -131,6 +153,8 @@ class DecisionTree: #nom de la class à changer
|
|||
|
||||
self.tree = self.decision_tree_learning(train, train_labels, attributes, None)
|
||||
|
||||
return self.test(train, train_labels,verbose)
|
||||
|
||||
|
||||
def extract_tree(self,myTree,exemple):
|
||||
for b in myTree:
|
||||
|
|
@ -138,8 +162,12 @@ class DecisionTree: #nom de la class à changer
|
|||
if b[0] == 'Feuille':
|
||||
return b[1]
|
||||
# On est dans une branche, on teste le split
|
||||
if ((exemple[b[1]] <= b[2]) == b[3]):
|
||||
return self.extract_tree(b[4],exemple)
|
||||
if self.attribute_type=="continuous":
|
||||
if ((exemple[b[1]] <= b[2]) == b[3]):
|
||||
return self.extract_tree(b[4],exemple)
|
||||
if self.attribute_type=="discrete":
|
||||
if (exemple[b[1]] == b[2]):
|
||||
return self.extract_tree(b[3],exemple)
|
||||
return None
|
||||
|
||||
|
||||
|
|
@ -155,15 +183,13 @@ class DecisionTree: #nom de la class à changer
|
|||
|
||||
return self.extract_tree(self.tree,exemple)
|
||||
|
||||
|
||||
|
||||
|
||||
def test(self, test, test_labels):
|
||||
def test(self, test, test_labels, verbose=True):
|
||||
"""
|
||||
c'est la méthode qui va tester votre modèle sur les données de test
|
||||
l'argument test est une matrice de taille nxm, avec
|
||||
n : le nombre d'exemple de test dans le dataset
|
||||
m : le mobre d'attribus (le nombre de caractéristiques)
|
||||
verbose: afficher les métriques calculées
|
||||
|
||||
test_labels : est une matrice taille nx1
|
||||
|
||||
|
|
@ -177,6 +203,15 @@ class DecisionTree: #nom de la class à changer
|
|||
Bien entendu ces tests doivent etre faits sur les données de test seulement
|
||||
|
||||
"""
|
||||
start_time = time.time()
|
||||
prediction_test = [self.predict(exemple,label) for exemple,label in zip(test,test_labels)]
|
||||
cm = metrics.confusion_matrix(test_labels,prediction_test)
|
||||
accuracy, precision, recall = metrics.prediction_metrics(cm,test_labels,prediction_test)
|
||||
compute_time = time.time() - start_time
|
||||
if (verbose):
|
||||
metrics.print_prediction_metrics(cm,accuracy,precision,recall,compute_time)
|
||||
|
||||
return cm,accuracy,precision,recall,compute_time
|
||||
|
||||
|
||||
# Vous pouvez rajouter d'autres méthodes et fonctions,
|
||||
|
|
|
|||
18
Code/main.py
18
Code/main.py
|
|
@ -8,10 +8,20 @@ import DecisionTree # importer la classe de l'Arbre de Décision
|
|||
# importer d'autres fichiers et classes si vous en avez développés
|
||||
# importer d'autres bibliothèques au besoin, sauf celles qui font du machine learning
|
||||
|
||||
dt = DecisionTree.DecisionTree()
|
||||
train1, train_labels1, test1, test_labels1 = ld.load_iris_dataset(train_ratio = 0.7)
|
||||
train2, train_labels2, test2, test_labels2 = ld.load_monks_dataset(1)
|
||||
train3, train_labels3, test3, test_labels3 = ld.load_monks_dataset(2)
|
||||
train4, train_labels4, test4, test_labels4 = ld.load_monks_dataset(3)
|
||||
train5, train_labels5, test5, test_labels5 = ld.load_congressional_dataset(train_ratio = 0.7)
|
||||
|
||||
dt.train(train,train_labels)
|
||||
|
||||
dt.tree
|
||||
dt1 = DecisionTree.DecisionTree(attribute_type="continuous")
|
||||
dt1.train(train1, train_labels1)
|
||||
dt1.predict(test1[0],test_labels1[0])
|
||||
dt1.test(test1, test_labels1)
|
||||
|
||||
[(dt.predict(exemple,label),label) for exemple,label in zip(train,train_labels)]
|
||||
|
||||
dt5 = DecisionTree.DecisionTree(attribute_type="discrete")
|
||||
dt5.train(train5, train_labels5)
|
||||
dt5.predict(test5[0],test_labels5[0])
|
||||
dt5.test(test5, test_labels5)
|
||||
Loading…
Add table
Reference in a new issue