2023-05-10 20:29:50 +02:00
|
|
|
import pandas
|
|
|
|
import os
|
|
|
|
|
|
|
|
from keras.applications.densenet import layers
|
|
|
|
|
|
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
import tensorflow
|
|
|
|
|
|
|
|
|
2023-05-10 20:22:22 +02:00
|
|
|
reloaded = tensorflow.keras.models.load_model('test')
|
|
|
|
|
|
|
|
x_to_test = pandas.read_csv('./X_test.csv')
|
|
|
|
y_to_test = pandas.read_csv('./Y_test.csv')
|
|
|
|
|
2023-05-10 20:32:32 +02:00
|
|
|
accu = reloaded.evaluate(x_to_test, y_to_test)
|
2023-05-10 20:22:22 +02:00
|
|
|
|
2023-05-10 20:41:43 +02:00
|
|
|
|
2023-05-10 20:32:32 +02:00
|
|
|
pre = reloaded.predict(x_to_test)
|
2023-05-10 20:41:43 +02:00
|
|
|
pre_array = [float(i)/sum(pre) for i in pre]
|
|
|
|
|
2023-05-10 20:44:28 +02:00
|
|
|
with open("prediction.txt", "w") as txt_file:
|
|
|
|
for line in pre_array:
|
|
|
|
txt_file.write(f"{line}")
|