def visualization(self):
feature_1 = self.x_pca[:, 0]
feature_2 = self.x_pca[:, 1]
labels = self.y
cdict = {0: 'red', 1: 'green'}
labl = {0: 'without bug', 1: 'bug'}
marker = {0: '*', 1: 'o'}
alpha = {0: .3, 1: .5}
fig, ax = plt.subplots(figsize=(7, 5))
fig.patch.set_facecolor('white')
for l in np.unique(labels):
ix = np.where(labels == l)
ax.scatter(feature_1[ix],
feature_2[ix],
c=cdict[l],
s=100,
label=labl[l],
marker=marker[l],
alpha=alpha[l])
# for loop ends
plt.xlabel("First Principal Component", fontsize=14)
plt.ylabel("Second Principal Component", fontsize=14)
plt.legend()
plt.savefig(
str(pathlib.Path().absolute()) + "/File/PCA_visualization.png")
def threshold_search(true, prob, criteria):
true = true.to_numpy()
prob_train, prob_test, true_train, true_test = train_test_split(prob, true, test_size=0.2, random_state=1234)
thresholds = np.linspace(0, 1, 101)
all_f1_train = np.zeros(len(thresholds))
for j in range(len(thresholds)):
predictions_train = np.ones(len(prob_train))
predictions_train[prob_train < thresholds[j]] = 0
macro_f1_train = macro_weighted_f1(true_train, predictions_train, [0, 1])
all_f1_train[j] = macro_f1_train
best_threshold = thresholds[np.where(max(all_f1_train) == all_f1_train)]
best_threshold = best_threshold[0]
predictions_test = np.ones(len(prob_test))
predictions_test[prob_test < best_threshold] = 0
print("The best threshold for this prediction is: %s" % best_threshold)
plt.plot(thresholds, all_f1_train, 'b')
plt.axvline(x=0.5, linestyle=':', color='r')
plt.axvline(x=best_threshold, linestyle='--', color='g')
plt.axhline(y=all_f1_train[np.where(thresholds == 0.5)], linestyle=':', color='r')
plt.axhline(y=max(all_f1_train), linestyle='--', color='g')
plt.xlabel("Threshold")
plt.ylabel("Macro F1")
plt.savefig('{0} threshold plot.png'.format(criteria), bbox_inches='tight')
plt.clf()
return best_threshold
def get_hist(data, col):
[columndates, orderdates] = column_and_order_dates(data, col)
[difference_dates, date_values] = days_difference(columndates, orderdates,
31)
plt.hist(x=difference_dates, bins=100)
plt.xlabel('Day')
plt.ylabel('Amount')
plt.show()
print(date_values)
def create_plot(logbook, name_file):
maxFitnessValues, meanFitnessValues, minFitnessValues, medianFitnessValues, stdFitnessValues = \
logbook.select("max", "avg", "min", "median", "std")
plt.plot(maxFitnessValues, color='red', label="Worst Fitness")
plt.plot(meanFitnessValues, color='green', label="Mean Fitness")
plt.plot(minFitnessValues, color='orange', label="Best Fitness")
plt.plot(medianFitnessValues, color='blue', label="Avg. Fitness")
plt.plot(stdFitnessValues, color='pink', label="Std. Fitness")
plt.xlabel('Generation')
plt.ylabel('Max / Average / Min / Median/ Std Fitness')
plt.title('Max, Average, Min, Median and Std Fitness over Generations')
plt.legend(loc='lower right')
plt.savefig(name_file)
plt.close()
def show_images(images, labels, preds):
plt.figure(figsize=(8, 4))
for i, image in enumerate(images):
plt.subplot(1, 6, i + 1, xticks=[], yticks=[])
image = image.numpy().transpose((1, 2, 0))
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
image = image * std + mean
image = np.clip(image, 0., 1.)
plt.imshow(image)
col = 'green'
if preds[i] != labels[i]:
col = 'red'
plt.xlabel(f'{class_names[int(labels[i].numpy())]}')
plt.ylabel(f'{class_names[int(preds[i].numpy())]}', color=col)
plt.tight_layout()
plt.show()
with open(file_graph) as f:
content = f.readlines()
# read each line
content = [x.strip() for x in content]
original_cc = []
supergraph_cc = []
for line in content:
value = line.split(" ")
if len(value):
supergraph_cc.append(float(value.pop()))
original_cc.append(float(value.pop()))
plt.clf()
plt.plot(k_array, original_cc, 'r--', k_array,
supergraph_cc, 'g-')
plt.ylabel("Clustering Coefficent")
plt.xlabel("k_degree")
plt.legend(('Original Graph', 'Supergraph'),
loc='lower center',
shadow=True)
plt.title(str(sys.argv[4]))
plt.savefig("metric_cc_web.png") #if choose dataset web
#plt.savefig("metric_cc_socfb.png")
plt.clf()
list_norm = []
for i in norm:
list_norm.append(float(i))
list_k_array = []
for i in k_array:
list_k_array.append(float(i))
plt.plot(list_k_array, list_norm, 'r--')
if size == 1:
for line in content:
k_array = line.split(" ")
file_graph = str(sys.argv[2])
if os.path.exists(file_graph):
# if file exist
with open(file_graph) as f:
content = f.readlines()
# read each line
content = [x.strip() for x in content]
ratio = NULL
size = len(content)
if size == 1:
for line in content:
ratio = line.split(" ")
list_ratio = []
for i in ratio:
list_ratio.append(float(i))
list_k_array = []
for i in k_array:
list_k_array.append(float(i))
plt.clf()
plt.figure(figsize=(16, 10))
plt.ylabel("Ratio")
plt.xlabel("k_degree")
plt.plot(list_k_array, list_ratio, 'r--')
plt.title("Graph friend 1000 10 100")
plt.savefig("ratio_fakedataset.png", dpi=120)
epochs = 5 #训练5次
model1.summary() #模型输出
model1.compile(
loss='sparse_categorical_crossentropy', #模型编译
optimizer='adam',
metrics=['accuracy'])
#从训练集中抽取0.2进行验证
history = model1.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
validation_split=0.2)
#-----------------------------------------------保存模型，可视化--------------------------
#保存模型
model1.save('model_CNN_text.h5')
#模型可视化
plot_model(model1, to_file='model_CNN_text.png', show_shape=True)
#加载模型
model = load_model('model_CNN_text.h5')
y_new = model.predict(x_train[0].reshape(1, 50))
#训练结果可视化
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('Model accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend(['Train', 'Valid'], loc='upper left')
plt.savefig('Valid_acc.png')
plt.show()
#-----------------------------------------------------查看解码效果--------------------------------------------
decoded_imgs = model.predict(x_test)
n = 10
plt.figure(figsize=(20, 6))
for i in range(n):
# 原图
ax = plt.subplot(3, n, i+1)
plt.imshow(x_test[i].reshape(28, 28))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
# 解码效果图
ax = plt.subplot(3, n, i+n+1)
plt.imshow(decoded_imgs[i].reshape(28, 28))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
plt.show()
#----------------------------------------------------训练过程可视化---------------------------------------------
print(history.history.keys())
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'validation'], loc='upper right')
plt.show()
workers=10)
#------------------------------------------------------保存模型---------------------------------------
model.summary()
#判断路径是否存在，不存在创建
if not os.path.isdir(save_dir):
os.makedirs(save_dir)
model_path = os.path.join(save_dir, model_name)
model.save(model_path) #保存模型
#------------------------------------------------------训练过程可视化-----------------------------------
#绘制训练与验证的准确率值
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('Model accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Valid'], loc='upper left')
plt.savefig('tradition_cnn_valid_acc.png')
plt.show()
#绘制训练与验证的损失
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Valid'], loc='upper left')
plt.savefig('tradition_cnn_valid_loss.png')
plt.show()