def binLocation(binNumber, productList):
if binNumber == 1:
bin1 = Final.Bin(productList)
return print(bin1)
if binNumber == 2:
bin2 = Final.Bin(productList)
return print(bin2)
if binNumber == 3:
bin3 = Final.Bin(productList)
return bin3
if binNumber == 4:
bin4 = Final.Bin(productList)
return bin4
if binNumber == 5:
bin5 = Final.Bin(productList)
return bin5
if binNumber == 6:
bin6 = Final.Bin(productList)
return bin6
if binNumber == 7:
bin7 = Final.Bin(productList)
return bin7
if binNumber == 8:
bin8 = Final.Bin(productList)
return bin8
if binNumber == 9:
bin9 = Final.Bin(productList)
return bin9
if binNumber == 10:
bin10 = Final.Bin(productList)
return bin10
def main():
try:
output_file = open('Final_output_result.txt', 'w')
print('start:\nlearning rate has been set to:{}\niteration criteria'
' has been set to:{}\n'.format(learning_rate, epoch))
print(
'error criteria has been set to:{}\nmomentum has been set to:{}\nbias has been set to:{}'.format(error_criteria,
momentum,
bias))
print(
'start:\nlearning rate has been set to:{}\niteration criteria has been set to:{}'.format(learning_rate, epoch),
file=output_file)
print(
'error criteria has been set to:{}\nmomentum has been set to:{}\nbias has been set to:{}'.format(error_criteria,
momentum,
bias),
file=output_file)
d = Dt.Data(train_file, test_file, output_file, epsilon)
##TODO training phase
d.arrange_train()
# d_final = d.split_desire(d.get_desire()) # a dictionary that contains all the desire output
d_final = d.get_desire()
d.arrange_test()
print("1 input layer, 1 hidden layer, 1 output layer\n")
print("1 input layer, 1 hidden layer, 1 output layer\n", file=output_file)
print("the number of input node is: {}, hidden node is: {}, output node is: {}\n".format(input_node, hidden_node,
output_node))
print("the number of input node is: {}, hidden node is: {}, output node is: {}\n".format(input_node, hidden_node,
output_node),
file=output_file)
print(" hidden node activation function is tanh function, output node activation function is sigmoid function")
print(" hidden node activation function is tanh function, output node activation function is sigmoid function",
file=output_file)
# set to 4,4,3 is the best for the assignment 1 data
# set to 11,58,3 is the best for 400 data assignment 2
print("Start the training phase\n")
print("Start the training phase\n", file=output_file)
b1 = Bp.Backpro(input_node, hidden_node, output_node, d_final, d.get_x(),
learning_rate, file=output_file) # first:weights,second:desire output
b1.run(epsilon, epoch, error_criteria, momentum)
print("Start the testing phase\n")
print("Start the testing phase\n", file=output_file)
true = b1.test(d.get_test_new(), epsilon)
desire = Fn.test(d.get_test_desire(), epsilon)
print('final Training epoch is: {}\n'.format(b1.get_epoch()))
print('final Training epoch is: {}\n'.format(b1.get_epoch()), file=output_file)
print('final Training Sum error is: {}\n'.format(b1.get_error()))
print('final Training Sum error is: {}\n'.format(b1.get_error()), file=output_file)
print('final Training Mean squared error is: {}\n'.format((1 / len(d_final)) * b1.get_error()))
print('final Training Mean squared error is: {}\n'.format((1 / len(d_final)) * b1.get_error()), file=output_file)
Fn.final(d.get_final_class(), desire, true, b1.get_error(), output_file, d_final)
print('final Training epoch is: {}\n'.format(b1.get_epoch()))
print('final Training epoch is: {}\n'.format(b1.get_epoch()), file=output_file)
except IOError:
print('File Error')
finally:
output_file.close()
def lose(self):
import Final
self.Form = Final.MyDialog()
self.fui = Final.Ui_Dialog()
self.fui.setupUi(self.Form)
self.fui.Exit.clicked.connect(self.out)
self.fui.Rematch.clicked.connect(self.rematch)
self.Form.exec()
def draw(self):
import Final
self.Form = Final.MyDialog()
self.fui = Final.Ui_Dialog()
self.fui.setupUi(self.Form)
self.fui.Exit.clicked.connect(self.out)
self.fui.label.setPixmap(QPixmap(".\\img/draw.png"))
self.fui.Rematch.clicked.connect(self.rematch)
self.Form.exec()
def cross_validate(n):
accuracy_list = []
df = tt.preProcess()
for i in range(n):
X_train, X_test = train_test_split(df, test_size=0.1)
dict, temp, classDict = tt.train_supervised(X_train)
accuracy = tt.predict_supervised(dict, X_test, classDict)
accuracy_list.append(accuracy)
mean_accuracy = np.mean(accuracy_list)
print("mean accuracy is: ", mean_accuracy)
return np.mean(accuracy_list)
def upload():
target = os.path.join(APP_ROOT, "static/")
print(target)
if not os.path.isdir(target):
os.mkdir(target)
for file in request.files.getlist("file"):
print(file)
filename = file.filename
destination = "".join([target, filename])
print(destination)
#os.remove(r".\static\segmented.jpg")
file.save(destination)
inferencecopy2.DeeplabSeg(Image.open(destination))
classpredic = Final.LdaAnalysis(Image.open(r'.\static\segmented.jpg'))
#os.remove("segmented.jpg")
return render_template("complete.html",
image_name1='segmented.jpg',
image_name2=filename,
value=classpredic)
def buttonClicked(self):
sender = self.sender()
if sender.text() == "Show Basic":
Final.show_regular(GenreList)
if sender.text() == "Show Google":
googlemap.show_google(GenreList)
if sender.text() == "Show Location":
if len(GenreList) == 1:
self.statusBar().showMessage('')
location.show_location(GenreList[0])
else:
self.statusBar().showMessage('Only Accept One Input!')
if sender.text() == "Show Density":
if len(GenreList) == 1:
self.statusBar().showMessage('')
density.show_density(GenreList[0])
else:
self.statusBar().showMessage('Only Accept One Input!')
def somefunc(link):
http=urllib3.PoolManager()
req=http.request('GET',link)
soup=BeautifulSoup(req.data,'html.parser')
#print("Step 1\n")
f=open('Review.txt','a')
global no
global r1
#print('number =')
#print(no)
r1.append(rank())
for e in soup.find_all('h1'):
h1=e.get('class')
if h1 is not None and 'heading_title' in h1:
f.writelines("******************************************")
f.writelines(e.text)
r1[no].name=e.text
f.writelines("******************************************")
f.writelines("\n\n")
e1=soup.find_all("div",{"class":"entry"})
sum=0
for e in e1[1:10]:
#if e.text is not None in e:
h=e.text
try:
f.writelines(e.text)
num=Final.rate(e.text)
f.writelines('\n\n')
print(e.text)
if num > 3:
f.writelines("Excellent Review: ")
print("Excellent Review: ")
elif num > 1:
f.writelines("Good Review: ")
print("Good Review: ")
elif num < 0:
f.writelines("Bad Review: ")
print("Bad Review:")
else:
f.writelines("Average Review: ")
print("Average Review: ")
f.writelines(str(num))
print(num)
sum=sum+num
f.writelines('\n\n\n')
except:
print('some Error')
#print(sum)
#print(no)
r1[no].rate=sum
f.close()
no=no+1
def predict():
clf = joblib.load('finalModel.pkl')
to_predict_list = request.form.to_dict()
card_id = request.form.getlist('card_id')
date = pd.to_datetime(request.form['firstactivemonth'], errors='coerce')
f1 = request.form.getlist('feature_1')
f2 = request.form.getlist('feature_2')
f3 = request.form.getlist('feature_3')
data = {
'card_id': card_id,
'first_active_month': date,
'feature_1': f1,
'feature_2': f2,
'feature_3': f3
}
data = pd.DataFrame(data)
prediction = final.final_fun_1(data)
print("Loyalty Score", prediction)
return jsonify({'prediction': str(prediction)})
def ShelfLocation(shelf):
shelf3 = Final.shelf()
shelf2 = Final.shelf()
shelf1 = Final.shelf()
import readFile
import Final
#Creates aisle
aisle1 = Final.Aisle()
aisle2 = Final.Aisle()
aisle3 = Final.Aisle()
aisle4 = Final.Aisle()
aisle5 = Final.Aisle()
aisle6 = Final.Aisle()
def ShelfLocation(shelf):
shelf3 = Final.shelf()
shelf2 = Final.shelf()
shelf1 = Final.shelf()
#b =binLocation(readFile.binNum[0],readFile.descript[0])
#
def binLocation(binNumber, productList):
if binNumber == 1:
bin1 = Final.Bin(productList)
return print(bin1)
if binNumber == 2:
bin2 = Final.Bin(productList)
return print(bin2)
if binNumber == 3:
bin3 = Final.Bin(productList)
return bin3
if binNumber == 4:
def make_grid(self, board_size):
return Final.make_grid(list(board_size))
def make_ants(self, ant_locations):
return Final.make_ants(tuple(map(tuple,ant_locations)))
import Final
import cv2
ls = {} # required dictionary
while (1):
val = Final.GetValues(ls)
print(ls)
if val == 27: #press esc to break the loop
break
cv2.destroyAllWindows()
def adding():
Final.add_person("face_recognition_system/people/", "rectangle",
person1.get())
def attendance():
Final.recognize_people("face_recognition_system/people/", "rectangle")
from Start import * from Final import * from Game import * a = Start() a.blank() b = Game() b.window(int(a.start_count), int(a.start_money)) c = Final() name = b.zn[0] money = b.mon_all[4] x = list(zip(name, money)) x.sort(key=lambda f: f[1]) x.reverse() name = [i[0] for i in x] #список имен с капиталом по убыванию money = [i[1] for i in x] #список капиталов по убыванию c.window(name, money, b.mon_all) print(c.mnoey)