def audio():
print "Loading audio Data"
if args['a']: #use the audio file or numpy file if it exists
return DataConverter.main(args['a'])
if args['v']: #extract audio from video data
return DataConverter.main(args['v'])
if args['b']:
npy = args['b'] + ".wav.npy"
if os.path.isfile(npy):
return DataConverter.main(npy)
wav = args['b'] + ".wav"
if os.path.isfile(wav):
return DataConverter.main(wav)
parser.epilog = "No audio file found."
parser.print_help()
exit()
def audio():
print "Loading audio Data"
if args['a']: #use the audio file or numpy file if it exists
return DataConverter.main(args['a'])
if args['v']: #extract audio from video data
return DataConverter.main(args['v'])
if args['b']:
npy = args['b'] + ".wav.npy"
if os.path.isfile(npy):
return DataConverter.main(npy)
wav = args['b'] + ".wav"
if os.path.isfile(wav):
return DataConverter.main(wav)
parser.epilog = "No audio file found."
parser.print_help()
exit()
def __init__(self):
self.world = tkinter.Tk()
self.world.title(u"Syokudou")
self.world.geometry("1280x720")
self.canvas = tkinter.Canvas(self.world,width = 1280,height=720)
self.canvas.create_rectangle(0,0,(gra_WIDTH),(gra_HEIGHT),fill = 'green')
#画像データ読込
self.Table_img = Image.open('img/objset.png')
self.RoundTable_img = Image.open('img/round.png')
self.RoundHalf_img = Image.open('img/round_half.png')
self.WindowTable_img = Image.open('img/windowtable.png')
self.Table_img = ImageTk.PhotoImage(self.Table_img)
self.RoundTable_img = ImageTk.PhotoImage(self.RoundTable_img)
self.RoundHalf_img = ImageTk.PhotoImage(self.RoundHalf_img)
self.WindowTable_img= ImageTk.PhotoImage(self.WindowTable_img)
self.canvas.place(x=100,y=100)
#Slip はマスの開始位置をずらす必要があるときに使う変数,Slipが表す長さ分だけ上に配置される。
self.Slip = 0
AbleStay = dc.data()
self.humans = []
for i in range(AbleStay.getLength()):
self.humans.append(human.human(1,AbleStay.getX(i),AbleStay.getY(i)))
self.world.after(10,self.update_humans)
def dataAq():
print "Loading Data Acquisition Input"
if args['d']: #use the audio file or numpy file if it exists
return DataConverter.main(args['d'])
if args['b']:
npy = args['b'] + ".dat.npy"
if os.path.isfile(npy):
return DataConverter.main(npy)
npy = args['b'] + ".npy"
if os.path.isfile(npy):
return DataConverter.main(npy)
dat = args['b'] + ".dat"
if os.path.isfile(dat):
return DataConverter.main(dat)
parser.epilog = "No data file found."
parser.print_help()
exit()
def main(_):
data_converter = dc.DataConverter(DATA_PATH)
with tf.Session() as sess:
network = nk.Network(sess, NAME, data_converter)
sess.run(tf.global_variables_initializer())
#saver = sv.Saver(NAME, sess)
network.Train(data_converter)
def dataAq():
print "Loading Data Aquisition Input"
if args['d']: #use the audio file or numpy file if it exists
return DataConverter.main(args['d'])
if args['b']:
npy = args['b'] + ".dat.npy"
if os.path.isfile(npy):
return DataConverter.main(npy)
npy = args['b'] + ".npy"
if os.path.isfile(npy):
return DataConverter.main(npy)
dat = args['b'] + ".dat"
if os.path.isfile(dat):
return DataConverter.main(dat)
parser.epilog = "No data file found."
parser.print_help()
exit()
def test_merge_lists_no_equal(self):
# Given
database_list = [
Bar.Bar('MSFT', 1, '2020-04-15 15:55:00', 171.92, 172.25, 171.79,
171.95, 534118),
Bar.Bar('MSFT', 1, '2020-04-15 15:56:00', 171.92, 172.25, 171.79,
171.95, 534118)
]
api_list = [
Bar.Bar('MSFT', 1, '2020-04-15 15:59:00', 171.92, 172.25, 171.79,
171.95, 534118),
Bar.Bar('MSFT', 1, '2020-04-15 16:00:00', 171.92, 172.25, 171.79,
171.95, 534118)
]
# When
merged_list, api_list_short = DataConverter.merge_lists(
database_list, api_list)
# Then
expected_api_list_short = [
Bar.Bar('MSFT', 1, '2020-04-15 15:59:00', 171.92, 172.25, 171.79,
171.95, 534118),
Bar.Bar('MSFT', 1, '2020-04-15 16:00:00', 171.92, 172.25, 171.79,
171.95, 534118)
]
expected_merged_list = [
Bar.Bar('MSFT', 1, '2020-04-15 15:55:00', 171.92, 172.25, 171.79,
171.95, 534118),
Bar.Bar('MSFT', 1, '2020-04-15 15:56:00', 171.92, 172.25, 171.79,
171.95, 534118),
Bar.Bar('MSFT', 1, '2020-04-15 15:59:00', 171.92, 172.25, 171.79,
171.95, 534118),
Bar.Bar('MSFT', 1, '2020-04-15 16:00:00', 171.92, 172.25, 171.79,
171.95, 534118)
]
self.assertEqual(len(expected_merged_list), len(merged_list))
for index in range(len(expected_merged_list)):
# print(expected_merged_list[index].time_stamp)
self.assertEqual(expected_merged_list[index].time_stamp,
merged_list[index].time_stamp)
self.assertEqual(len(expected_api_list_short), len(api_list_short))
for index in range(len(expected_api_list_short)):
self.assertEqual(expected_api_list_short[index].time_stamp,
api_list_short[index].time_stamp)
def printOutput(self):
return(sorted(set([DataConverter.sanitize(t) for t in self])))
import DataConverter
import FileManager
data = FileManager.getDictionaryData("data.txt")
print(data['name']+' data is',sorted(set([DataConverter.sanitize(each_t) for each_t in data['values']])))
import DataConverter
import FileManager
clean_data = []
unique_data = []
data = FileManager.getListData("temp.txt")
for each_t in data:
if each_t not in clean_data:
clean_data.append(DataConverter.sanitize(each_t))
for each_t in clean_data:
if each_t not in unique_data:
unique_data.append(each_t)
print(sorted(unique_data))
import DataConverter
import FileManager
data = FileManager.getListData("data.txt")
sandy_data = {}
sandy_data['name'] = data.pop(0)
sandy_data['dob'] = data.pop(0)
sandy_data['values'] = data
print(
sandy_data['name'] + ' data is',
sorted(
set([
DataConverter.sanitize(each_t) for each_t in sandy_data['values']
])))
import DataConverter
import FileManager
data = FileManager.getListData("temp.txt")
print(sorted(set([DataConverter.sanitize(each_t) for each_t in data])))
# print(sorted([set(DataConverter.sanitize(each_t)) for each_t in data]))
def main():
st.sidebar.header('Прогнозирование банкротства компаний')
page = st.sidebar.selectbox("Навигатор", ["Теория", "Практика","О данных", "Предобработка данных"])
data = load_data()
st.set_option('deprecation.showPyplotGlobalUse', False)
if page == "Теория":
st.header("Прогнозирование банкротства компаний")
st.write("Please select a page on the left.")
# st.image('DataAnal/диплом/pic/main.PNG')
st.header("О методах прогнозирования, используемых в программе")
aboutModels()
info()
elif page == "О данных":
AboutData(data)
Visualize(data)
elif page == "Предобработка данных":
st.title("Предобработка данных")
st.write(data.head())
dc.PrepFor()
elif page == "Практика":
st.title("Data Exploration")
st.write(data.head())
st.write("""# Прогноз финансовых бедствий различных компаний""")
method = st.selectbox("Выбор метода прогнозирования", ["Выбор модели",
"LightGBM",
"Stochastic Gradient Decent",
"Decision Tree",
"Naive Bayes",
"Support Vector Machines",
"KNN",
"Logistic Regression",
"Random Forest",
"Linear Regression",
"XGBoost",
"ANN",
"Вывод"])
if method == "Выбор модели":
st.write("Выбор метода")
elif method == "LightGBM":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "Stochastic Gradient Decent":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "Decision Tree":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "Naive Bayes":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "Support Vector Machines":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "KNN":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "Logistic Regression":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "Random Forest":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "Linear Regression":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "XGBoost":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "ANN":
params = add_parameter_ui(method)
get_classifier(method, params)
elif method == "Вывод":
st.title("Сравнение моделей")
st.image('DataAnal/диплом/pic/Итог.PNG')
skipSmallerThan = int(args.skipSmallerThan)
resampleTo = int(args.resampleTo)
csvSep = args.csvSep
addXYZAxes = args.addXYZAxes
tickDistance = args.tickDistance
addCustomAxes = args.addCustomAxes
# Case 1: Use the command line interface
loadFromCmd = tgmmPath != None or csvPath != None or biotracksPath != None or svfPath != None
loaderState2 = None
if loadFromCmd:
if csvPath is not None:
print("Load from CSV...")
loader = dc.CsvLoader(csvPath,
resampleTo=resampleTo,
minTrackLength=skipSmallerThan,
firstLineIsHeader=(csvNoHeader is None),
csvSeparator=csvSep)
if addState2 is not None:
loaderState2 = dc.CsvLoader(
addState2,
resampleTo=resampleTo,
minTrackLength=skipSmallerThan,
firstLineIsHeader=(csvNoHeader is None),
csvSeparator=csvSep)
if tgmmPath is not None:
print("Load from TGMM...")
loader = dc.TgmmLoader(
tgmmPath,
resampleTo=resampleTo,
minTrackLength=skipSmallerThan,
import DataConverter Data = DataConverter.data() print(Data.getX(0))
