2023-06-06 22:24:23 +02:00
|
|
|
import pickle
|
2023-06-08 11:25:04 +02:00
|
|
|
import os
|
2023-06-06 22:24:23 +02:00
|
|
|
import numpy as np
|
|
|
|
|
2023-06-08 11:25:04 +02:00
|
|
|
workspace_path = os.getenv('WORKSPACE')
|
|
|
|
pickle_path = os.path.join(workspace_path, 'model_with_data.pickle')
|
2023-06-06 22:24:23 +02:00
|
|
|
|
2023-06-08 11:25:04 +02:00
|
|
|
if os.path.exists(pickle_path):
|
|
|
|
with open(pickle_path, 'rb') as file:
|
|
|
|
loaded_data = pickle.load(file)
|
|
|
|
else:
|
|
|
|
## aby było mozna uruchomić lokalnie
|
|
|
|
with open('model_with_data.pickle', 'rb') as file:
|
|
|
|
loaded_data = pickle.load(file)
|
|
|
|
|
2023-06-06 22:24:23 +02:00
|
|
|
# Wczytanie modelu
|
|
|
|
model = loaded_data[0]
|
|
|
|
|
|
|
|
#Wczytanie danych testowych
|
|
|
|
X_test_scaled = loaded_data[3]
|
|
|
|
y_test_encoded = loaded_data[4]
|
|
|
|
|
|
|
|
# Predykcja
|
|
|
|
|
|
|
|
y_pred = model.predict(X_test_scaled)
|
|
|
|
y_pred_classess = np.argmax(y_pred, axis=1)
|
|
|
|
|
|
|
|
# Zapisanie wyników predykcji do pliku
|
|
|
|
|
|
|
|
np.savetxt('results_prediction.csv', y_pred, delimiter=',')
|