def cross_validation(path):
kf = KFold(n_splits=5)
z = np.zeros(100)
data, labels = load_dataset(join(DATA, path[0]))
data = np.array(data)
labels = np.array(labels)
for train, test in kf.split(data):
"""
train_data = []
train_labels = []
test_data = []
test_labels = []
for indice in train:
train_data.append(data[indice])
train_labels.append(labels[indice])
for indice in test:
test_data.append(data[indice])
test_labels.append(labels[indice])
print(train)
print(test)
train_data = np.array(train_data)
train_labels = np.array(train_labels)
test_data = np.array(test_data)
test_labels = np.array(test_labels)"""
#train_data = data[0:800]
#train_labels = labels[0:800]
#test_data = data[801:999]
#test_labels = labels[801:999]
train_data = data[train]
train_labels = labels[train]
test_data = data[test]
test_labels = labels[test]
print(len(train_data))
print(len(train_labels))
print(len(test_data))
print(len(test_labels))
#print(train_data)
#print(train_labels)
#print(test_data)
#print(test_labels)
# GAUSSIENNE
g = GaussianBayes()
g.fit(train_data, train_labels)
# - Score:
score_baye = g.score(test_data, test_labels)
# K-NN
n_neighbors = 10
clf = neighbors.KNeighborsClassifier(n_neighbors, weights='uniform')
clf.fit(train_data, train_labels)
# - Score:
score_voisin = clf.score(test_data, test_labels)
print(score_voisin)
break
def main():
train_data, train_labels = load_dataset("./data/train.csv")
test_data, test_labels = load_dataset("./data/test.csv")
#affichage
plot_scatter_hist(train_data, train_labels)
# Instanciation de la classe GaussianB
g = GaussianBayes(priors=[0.3, 0.3, 0.3], diag=True)
# Apprentissage
g.fit(train_data, train_labels)
# Score
score = g.score(test_data, test_labels)
print("precision : {:.2f}".format(score))
input("Press any key to exit...")
def baye_voisin(data, labels, ts):
train_data, test_data, train_labels, test_labels = train_test_split(data, labels, test_size = ts / 100, random_state = 42)
# GAUSSIENNE
g = GaussianBayes()
evaltime()
g.fit(train_data, train_labels)
somme_bayes.append(evaltime())
# - Score:
score_baye = g.score(test_data, test_labels)
Z = g.predict(test_data)
cfmat_bayes = confusion_matrix(test_labels, Z, labels=np.unique(test_labels))
# K-NN
n_neighbors = 10
clf = neighbors.KNeighborsClassifier(n_neighbors, weights='uniform')
evaltime()
clf.fit(train_data, train_labels)
somme_knn.append(evaltime())
# - Score:
score_voisin = clf.score(test_data, test_labels)
Z = clf.predict(test_data)
cfmat_knn = confusion_matrix(test_labels, Z, labels=np.unique(test_labels))
return score_baye, cfmat_bayes, score_voisin, cfmat_knn
def baye_voisin(data, labels, ts):
train_data, test_data, train_labels, test_labels = train_test_split(
data, labels, train_size=ts / 100, random_state=42)
print("test taille:", len(test_data), " train test:", len(train_data),
" test size: ", ts)
# GAUSSIENNE
g = GaussianBayes()
g.fit(train_data, train_labels)
# - Score:
score_baye = g.score(test_data, test_labels)
Z = g.predict(test_data)
cfmat_bayes = confusion_matrix(test_labels,
Z,
labels=np.unique(test_labels))
# K-NN
n_neighbors = 10
clf = neighbors.KNeighborsClassifier(n_neighbors, weights='uniform')
clf.fit(train_data, train_labels)
# - Score:
score_voisin = clf.score(test_data, test_labels)
Z = clf.predict(test_data)
cfmat_knn = confusion_matrix(test_labels, Z, labels=np.unique(test_labels))
return score_baye, cfmat_bayes, score_voisin, cfmat_knn
labelteststart = 100 * i + teststart
labeltestend = 100 * i + testend
labeltrainend = 100 * (i + 1)
labelstest = np.concatenate(
(labelstest, total_labels[labelteststart:labeltestend]))
valeurstest = np.concatenate(
(valeurstest, total_data[labelteststart:labeltestend]))
labelstrain = np.concatenate(
(np.concatenate(
(labelstrain, total_labels[labelstrainstart:labelteststart])),
total_labels[labeltestend:labeltrainend]))
valeurstrain = np.concatenate((np.concatenate(
(valeurstrain, total_data[labelstrainstart:labelteststart])),
total_data[labeltestend:labeltrainend]))
g = GaussianBayes(priors=None, diag=False)
# Apprentissage
g.fit(valeurstrain, labelstrain)
# Score
gaussianresult = gaussianresult + g.score(valeurstest, labelstest)
neigh = KNeighborsClassifier(n_neighbors=3,
weights='uniform',
algorithm='brute')
neigh.fit(valeurstrain, labelstrain)
KNNresult = KNNresult + np.sum(
labelstest == neigh.predict(valeurstest)) / len(labelstest)
gaussianresult = gaussianresult / K
KNNresult = KNNresult / K
print("gaussian average precision")
for i in range(1, round(len(total_labels) / 100)):
labelteststart = 100 * i
labeltestend = 100 * i + proportionseparation
labeltrainend = 100 * (i + 1)
print(i)
labelstest = np.concatenate(
(labelstest, total_labels[labelteststart:labeltestend]))
valeurstest = np.concatenate(
(valeurstest, total_data[labelteststart:labeltestend]))
labelstrain = np.concatenate(
(labelstrain, total_labels[labeltestend:labeltrainend]))
valeurstrain = np.concatenate(
(valeurstrain, total_data[labeltestend:labeltrainend]))
g = GaussianBayes(priors=None, diag=False)
# Apprentissage
g.fit(valeurstrain, labelstrain)
# Score
score = g.score(valeurstest, labelstest)
print("precision : {:.2f}".format(score))
neigh = KNeighborsClassifier(n_neighbors=3,
weights='uniform',
algorithm='brute')
neigh.fit(valeurstrain, labelstrain)
KNeighborsClassifier()
print(np.sum(labelstest == neigh.predict(valeurstest)) / len(labelstest))
#Confusion matrixes
def main():
folder = './data/'
files = os.listdir(folder)
for name in files:
print("\n\n-Filename=", name)
filename = folder + name
rates = [0.8, 0.5, 0.2]
for rate in rates:
learnCut = round(rate * 100)
testCut = round((1 - rate) * 100)
print("\n\n\n-Actual rate:", rate)
learn, test = utils.build_dataset(filename,
random=False,
learnCut=rate)
X_test, y_test, labels = format_dataset(test)
X_learn, y_learn, _ = format_dataset(learn)
data_dim = len(X_test[0])
#Gaussian Bayes
start = time.perf_counter()
b = GaussianBayes(diag=True)
b.fit(X_learn, y_learn)
pred = b.predict(X_test)
end = time.perf_counter()
print("\n-Gaussian Bayes:\nTime : ", (end - start))
print("Confusion Matrix :\n", confusion_matrix(y_test, pred),
"\nScore : ", score(pred, y_test))
plot_confusion_matrix(
confusion_matrix(y_test, pred),
labels,
title=
"Confusion matrix, Bayes, dim=%d, learn/test division : %d%%/%d%%"
% (data_dim, learnCut, testCut),
filename="cm_bayes_dim%d_div%d" % (data_dim, learnCut))
#K Neighbors Regressor
success = []
bestPredN = []
bestTime = 0
bestScore = 0
bestK = 0
#Test in different K
for i in range(1, 40):
start = time.perf_counter()
neigh = KNeighborsRegressor(n_neighbors=i, weights='uniform')
neigh.fit(X_learn, y_learn)
predN = neigh.predict(X_test).astype(int)
end = time.perf_counter()
success.append(score(predN, y_test))
if (bestScore < score(predN, y_test)):
bestPredN = predN
bestTime = end - start
bestScore = score(predN, y_test)
bestK = i
print("\n-The best: K=", bestK, " Neighbors Regressor:\nTime : ",
bestTime)
print("Confusion Matrix :\n", confusion_matrix(y_test, bestPredN),
"\nScore : ", bestScore)
plot_confusion_matrix(
confusion_matrix(y_test, bestPredN),
labels,
title=
'Confusion matrix, KNN, k=%d, dim=%d, learn/test division : %d%%/%d%%'
% (bestK, data_dim, learnCut, testCut),
filename="cm_knn_k%d_dim%d_div%d" %
(bestK, data_dim, learnCut))
#Affichage comparaison K Neighbors Regressor
plt.close()
#plt.figure(figsize=(12,6))
plt.plot([score(pred, y_test) for x in range(40)],
color='blue',
label="Bayes")
plt.plot(range(1, 40),
success,
color='green',
linestyle='dashed',
marker='o',
markerfacecolor='green',
markersize=5,
label="KNN")
plt.title(
'Success Rate (higher is better), dim=%d, learn/test division : %d%%/%d%%'
% (data_dim, learnCut, testCut))
plt.xlabel('K value')
plt.ylabel('Success Rate')
plt.legend()
plt.savefig("bayesVknn_dim%d_div%d" % (data_dim, learnCut))
#plot effect of learn/test division
bayesScores = []
knnScores = []
cutRange = range(5, 100, 5)
for i in cutRange:
rate = round(i / 100.0, 2)
#print(rate)
learn, test = utils.build_dataset(filename,
random=False,
learnCut=rate)
X_test, y_test, labels = format_dataset(test)
X_learn, y_learn, _ = format_dataset(learn)
data_dim = len(X_test[0])
b = GaussianBayes(diag=True)
b.fit(X_learn, y_learn)
pred = b.predict(X_test)
bayesScores.append(score(pred, y_test))
neigh = KNeighborsRegressor(n_neighbors=1, weights='uniform')
neigh.fit(X_learn, y_learn)
pred = neigh.predict(X_test).astype(int)
knnScores.append(score(pred, y_test))
plt.close()
#plt.ylim(bottom=0, top=1.1)
plt.xticks(ticks=range(len(cutRange)),
labels=[str(i) for i in cutRange])
plt.plot(bayesScores, color='blue', label="Bayes")
plt.plot(knnScores,
color='green',
linestyle='dashed',
marker='o',
markerfacecolor='green',
markersize=5,
label="KNN")
plt.title('Success Rate with different learn/test division, dim=%d' %
(data_dim))
plt.xlabel('Learn cut of the dataset (%)')
plt.ylabel('Success Rate')
plt.legend()
plt.savefig("learn-test-div_dim%d" % (data_dim), pad_inches=1)
ax.scatter(xd[20:30], yd[20:30], Z[20:30], c='red')
ax.set_xlabel('r')
ax.set_ylabel('v')
ax.set_zlabel('Vraisemblance')
plt.show()
color, labels = load_dataset("./couleurs_moyennes_better.csv")
#affichage nuage de point
#plot_training(color,labels)
# Instanciation de la classe GaussianB
g = GaussianBayes(priors=[0.33, 0.3, 0.326])
# Apprentissage
mu, sig = g.fit(color, labels)
#tab_proba = g.predict(color)
#affichage vraissemblance
#plot_vraissemblance(color,labels,tab_proba)
g.predict(color)
print(g.score(color, labels))
"""
for i in range(n_fleurs):
file_name = "ch"