def main():
# Initializer vos paramètres
i = ld.load_iris_dataset(0.7)
c = ld.load_congressional_dataset(0.7)
m1 = ld.load_monks_dataset(1)
m2 = ld.load_monks_dataset(2)
m3 = ld.load_monks_dataset(3)
# Initializer/instanciez vos classifieurs avec leurs paramètres
euclide = lambda x, y: pow(
(x - y), 2
) # Pas besoin d'extraire la racine, car cela ne changera pas l'ordre de classement
diff_binaire = lambda x, y: 0 if x == y else 1
knn_i = Knn(train=i[0], train_labels=i[1], dist_equation=euclide)
knn_c = Knn(train=c[0], train_labels=c[1], dist_equation=euclide)
knn_m1 = Knn(train=m1[0], train_labels=m1[1], dist_equation=diff_binaire)
knn_m2 = Knn(train=m2[0], train_labels=m2[1], dist_equation=diff_binaire)
knn_m3 = Knn(train=m3[0], train_labels=m3[1], dist_equation=diff_binaire)
bn_i = BayesNaifClassifier([1])
bn_c = BayesNaifClassifier([0])
bn_m1 = BayesNaifClassifier([2])
bn_m2 = BayesNaifClassifier([2])
bn_m3 = BayesNaifClassifier([2])
# Entrainez votre classifieur
print("\n=============\nKNN train tests\n=============")
knn_i.train_test(i[0], i[1], "Dataset: Iris, Training")
knn_c.train_test(c[0], c[1], "Dataset: Congressional, Training")
knn_m1.train_test(m1[0], m1[1], "Dataset: MONKS-1, Training")
knn_m2.train_test(m2[0], m2[1], "Dataset: MONKS-2, Training")
knn_m3.train_test(m3[0], m3[1], "Dataset: MONKS-3, Training")
print("\n=============\nBayes Naif train tests\n=============")
bn_i.train(i[0], i[1], "Dataset: Iris, Test")
bn_c.train(c[0], c[1], "Dataset: Congressional, Test")
bn_m1.train(m1[0], m1[1], "Dataset: MONKS-1, Test")
bn_m2.train(m2[0], m2[1], "Dataset: MONKS-2, Test")
bn_m3.train(m3[0], m3[1], "Dataset: MONKS-3, Test")
print("\n=============\nKNN tests\n=============")
# Tester votre classifieur
knn_i.train_test(i[2], i[3], "Dataset: Iris, Test")
knn_c.train_test(c[2], c[3], "Dataset: Congressional, Test")
knn_m1.train_test(m1[2], m1[3], "Dataset: MONKS-1, Test")
knn_m2.train_test(m2[2], m2[3], "Dataset: MONKS-2, Test")
knn_m3.train_test(m3[2], m3[3], "Dataset: MONKS-3, Test")
print("\n=============\nBayes Naif tests\n=============")
bn_i.test(i[2], i[3], "Dataset: Iris, Test")
bn_c.test(c[2], c[3], "Dataset: Congressional, Test")
bn_m1.test(m1[2], m1[3], "Dataset: MONKS-1, Test")
bn_m2.test(m2[2], m2[3], "Dataset: MONKS-2, Test")
bn_m3.test(m3[2], m3[3], "Dataset: MONKS-3, Test")
decision_tree_monks2 = DecisionTree.DecisionTree() decision_tree_monks3 = DecisionTree.DecisionTree() rn_iris = NeuralNet.NeuralNet() rn_congress = NeuralNet.NeuralNet() rn_monks1 = NeuralNet.NeuralNet() rn_monks2 = NeuralNet.NeuralNet() rn_monks3 = NeuralNet.NeuralNet() # Charger/lire les datasets (train_iris, train_labels_iris, test_iris, test_labels_iris) = load_datasets.load_iris_dataset(0.7) (train_congress, train_labels_congress, test_congress, test_labels_congress) = load_datasets.load_congressional_dataset(0.7) (train_monks1, train_labels_monks1, test_monks1, test_labels_monks1) = load_datasets.load_monks_dataset(1) (train_monks2, train_labels_monks2, test_monks2, test_labels_monks2) = load_datasets.load_monks_dataset(2) (train_monks3, train_labels_monks3, test_monks3, test_labels_monks3) = load_datasets.load_monks_dataset(3) #Learning_curve # decision_tree_iris.learning_curve(train_iris, train_labels_iris, test_iris, test_labels_iris) # decision_tree_congress.learning_curve(train_congress, train_labels_congress, test_congress, test_labels_congress) # decision_tree_monks1.learning_curve(train_monks1, train_labels_monks1, test_monks1, test_labels_monks1) # decision_tree_monks2.learning_curve(train_monks2, train_labels_monks2, test_monks2, test_labels_monks2) # decision_tree_monks3.learning_curve(train_monks3, train_labels_monks3, test_monks3, test_labels_monks3) # # Entrainez votre classifieur decision_tree_iris.train(train_iris, train_labels_iris) decision_tree_congress.train(train_congress, train_labels_congress)
iris_knn.train(iris_train, iris_train_labels)
iris_knn.test(iris_test, iris_test_labels)
print(f"\n --- Elapse time: {time.time() - startTime:.2f} s --- \n")
print('-' * 175)
print(f"Congressional dataset classification: \n")
startTime = time.time()
cong_train, cong_train_labels, cong_test, cong_test_labels = load_datasets.load_congressional_dataset(train_ratio)
cong_knn = Nbc()
cong_knn.train(cong_train, cong_train_labels)
cong_knn.test(cong_test, cong_test_labels)
print(f"\n --- Elapse time: {time.time() - startTime:.2f} s --- \n")
print('-' * 175)
for i in range(3):
print(f"Monks({i + 1}) dataset classification: \n")
startTime = time.time()
monks_train, monks_train_labels, monks_test, monks_test_labels = load_datasets.load_monks_dataset(i + 1)
monks_knn = Nbc()
monks_knn.train(monks_train, monks_train_labels)
monks_knn.test(monks_test, monks_test_labels)
print(f"\n --- Elapse time: {time.time() - startTime:.2f} s --- \n")
print('-' * 175)
# On initialise les classifieurs BayesNaïf en leur indiquant le dataset
iris_bayes = BayesNaif.BayesNaif("iris dataset")
congressional_bayes = BayesNaif.BayesNaif("congres dataset")
monks_bayes = BayesNaif.BayesNaif("monks dataset")
# On initialise les classifieurs Knn en leur indiquant le dataset
iris_knn = Knn.Knn("iris dataset")
congressional_knn = Knn.Knn("congres dataset")
monks_knn = Knn.Knn("monks dataset")
# On charge les 4 dataset, et pour chacun on les sépare en 4 np_matrix
iris_train_dataset, iris_train_labels, iris_test_dataset, iris_test_labels =\
load_datasets.load_iris_dataset(0.60) # On utilise un ratio de 0.60 pour les instances qui vont servir à l'entrainement
congressional_train_dataset, congressional_train_labels, congressional_test_dataset, congressional_test_labels =\
load_datasets.load_congressional_dataset(0.60) # On utilise un ratio de 0.60 pour les instances qui vont servir à l'entrainement
monks_train_dataset, monks_train_labels, monks_test_dataset, monks_test_labels =\
load_datasets.load_monks_dataset(2) # Ici on utilise les sets numéro 2
# On entraine nos classifieurs et puis on fait les tests
iris_bayes.train(iris_train_dataset, iris_train_labels, "iris dataset")
iris_bayes.test(iris_test_dataset, iris_test_labels, "iris dataset")
iris_knn.train(iris_train_dataset, iris_train_labels, "iris dataset")
iris_knn.test(iris_test_dataset, iris_test_labels, "iris dataset")
congressional_bayes.train(congressional_train_dataset,
congressional_train_labels, "congressional dataset")
congressional_bayes.test(congressional_test_dataset, congressional_test_labels,
"congressional dataset")
congressional_knn.train(congressional_train_dataset,
congressional_train_labels, "congres dataset")
congressional_knn.test(congressional_test_dataset, congressional_test_labels,
"congressional dataset")
import numpy as np
import copy
import NeuralNet
import load_datasets
# X = (hours sleeping, hours studying), y = score on test
X = ([2, 9], [1, 5], [3, 6])
y = np.array(([92], [86], [89]), dtype=float)
X = [[0,0,1], [0,1,1], [1,0,1], [1,1,1]]
y = [0, 1, 1, 0]
n= 1;
train_iris, train_labels_iris, test_iris, test_labels_iris = load_datasets.load_iris_dataset(0.03)
train_votes, train_labels_votes, test_votes, test_labels_votes = load_datasets.load_congressional_dataset(0.02)
train_monks, train_labels_monks, test_monks, test_labels_monks = load_datasets.load_monks_dataset(n)
train = train_votes
labels = train_labels_votes
NN = NeuralNet.NeuralNet(1, 2, len(train[0]), 1)
for i in xrange(1000):
NN.train(train, labels)
print "Actual Output: \n" + str(labels)
print "Predicted Output: \n" + str(NN.forward(train).T[0])
# [0,1,0,1,1,1,0,0,0,0,0,0,1,1,2,1], 0))
class BestCase:
def __init__(self):
self.error = 1
self.nbNodes = 0
self.nbFolds = 0
self.nbLayers = 1
self.epoch = 0
datasetsNames = ["Iris", "Monks 1", "Monks 2", "Monks 3", "Congressional"]
datasets = [
load_datasets.load_iris_dataset(0.65),
load_datasets.load_monks_dataset(1),
load_datasets.load_monks_dataset(2),
load_datasets.load_monks_dataset(3),
load_datasets.load_congressional_dataset(0.5)
]
best_cases = [BestCase(), BestCase(), BestCase(), BestCase(), BestCase()]
folds = 6
for datasetNo in range(len(datasets)):
train, train_labels, test, test_labels = datasets[datasetNo]
best_case = best_cases[datasetNo]
train = train[:len(train) - len(train) % folds]
train_labels = train_labels[:len(train_labels) - len(train_labels) % folds]
knn_iris = Knn.Knn() knn_congress = Knn.Knn() knn_monks1 = Knn.Knn() knn_monks2 = Knn.Knn() knn_monks3 = Knn.Knn() bayesNaif_iris = BayesNaif.BayesNaif() bayesNaif_congress = BayesNaif.BayesNaif() bayesNaif_monks1 = BayesNaif.BayesNaif() bayesNaif_monks2 = BayesNaif.BayesNaif() bayesNaif_monks3 = BayesNaif.BayesNaif() # Charger/lire les datasets (train_iris, train_labels_iris, test_iris, test_labels_iris) = load_datasets.load_iris_dataset(0.5) (train_congress, train_labels_congress, test_congress, test_labels_congress) = load_datasets.load_congressional_dataset(0.5) (train_monks1, train_labels_monks1, test_monks1, test_labels_monks1) = load_datasets.load_monks_dataset(1) (train_monks2, train_labels_monks2, test_monks2, test_labels_monks2) = load_datasets.load_monks_dataset(2) (train_monks3, train_labels_monks3, test_monks3, test_labels_monks3) = load_datasets.load_monks_dataset(3) # # Entrainez votre classifieur knn_iris.train(train_iris, train_labels_iris) knn_congress.train(train_congress, train_labels_congress) knn_monks1.train(train_monks1, train_labels_monks1) knn_monks2.train(train_monks2, train_labels_monks2) knn_monks3.train(train_monks3, train_labels_monks3) bayesNaif_iris.train(train_iris, train_labels_iris) bayesNaif_congress.train(train_congress, train_labels_congress) bayesNaif_monks1.train(train_monks1, train_labels_monks1) bayesNaif_monks2.train(train_monks2, train_labels_monks2) bayesNaif_monks3.train(train_monks3, train_labels_monks3)
classifieur_Knn_monks_1 = Knn.Knn()
classifieur_Knn_monks_2 = Knn.Knn()
classifieur_Knn_monks_3 = Knn.Knn()
classifieur_bayes_naif_iris = BayesNaif.BayesNaif()
classifieur_bayes_naif_congressional = BayesNaif.BayesNaif()
classifieur_bayes_naif_monks_1 = BayesNaif.BayesNaif()
classifieur_bayes_naif_monks_2 = BayesNaif.BayesNaif()
classifieur_bayes_naif_monks_3 = BayesNaif.BayesNaif()
# Charger/lire les datasets
dataset_iris = load_datasets.load_iris_dataset(train_pourcentage_iris)
dataset_congressional = load_datasets.load_congressional_dataset(
train_pourcentage_congressional)
dataset_monks_1 = load_datasets.load_monks_dataset(1)
dataset_monks_2 = load_datasets.load_monks_dataset(2)
dataset_monks_3 = load_datasets.load_monks_dataset(3)
# Entrainez votre classifieur
print(
"Entrainement du classifieur KNN avec le dataset Iris et un pourcentage d'entrainement de "
+ str(train_pourcentage_iris))
algo_starting_time = time()
classifieur_Knn_iris.train(dataset_iris[0], dataset_iris[1], num_datset_iris)
algo_end_time = time()
print("\nTemps d'exécution de l'algorithme : " +
str(algo_end_time - algo_starting_time) + "\n")
print("---------------------------------------------------------\n")
print(
knn_monks_2 = Knn(k=k)
knn_monks_3 = Knn(k=k)
bayesNaif_iris = BayesNaif()
bayesNaif_vote = BayesNaif()
bayesNaif_monks = BayesNaif()
# Charger/lire les datasets
iris_train, iris_train_labels, iris_test, iris_test_labels = load_datasets.load_iris_dataset(
0.7)
congressional_train, congressional_train_labels, congressional_test, \
congressional_test_labels = load_datasets.load_congressional_dataset(0.7)
# Lecture des données pour monk = 1
monks_train_1, monks_train_labels_1, monks_test_1, monks_test_labels_1 = load_datasets.load_monks_dataset(
1)
# Lecture des données pour monk = 2
monks_train_2, monks_train_labels_2, monks_test_2, monks_test_labels_2 = load_datasets.load_monks_dataset(
2)
#Lecture des données pour monk = 3
monks_train_3, monks_train_labels_3, monks_test_3, monks_test_labels_3 = load_datasets.load_monks_dataset(
3)
print('----------------------------')
print('----------------------------')
print('CLASSIFIEUR DE KNN')
print('----------------------------')
print('----------------------------')
# Entrainez votre classifieur KNN
print('--------------------')
Knn_clf.train(train, train_labels, muted=False)
start = time.time()
Knn_clf.test(test, test_labels)
print('KNN test time: ', time.time() - start)
print('Naïve Bayes classifier:')
BN_clf = BayesNaif.BayesNaif()
BN_clf.train(train, train_labels, muted=False)
start = time.time()
BN_clf.test(test, test_labels)
print('Naïve Bayes test time: ', time.time() - start)
###MONK-1 DATASET###
# Initializer vos paramètres
print("MONK-1 DATASET:")
train, train_labels, test, test_labels = load_datasets.load_monks_dataset(1)
# Initializer/instanciez vos classifieurs avec leurs paramètres
kf = K_folds(n_splits=10)
train_kf, train_label_kf = kf.split(train, train_labels)
k_neighb = [1, 3, 5, 7, 9, 11]
metrics = ['minkowski', 'manhattan', 'euclidean']
best_k = 1
best_metric = 'minkowski'
best_score = 0
for k in k_neighb:
for metric in metrics:
knn_clf = Knn.Knn(n_neighbors=k, metric=metric)
# kf = K_folds(n_splits=10)
# train_kf, train_label_kf = kf.split(train, train_labels)
avg_score = 0