import pickle
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score

np.set_printoptions(threshold=20)

file_path = 'model.pkl'
with open(file_path, 'rb') as file:
    model = pickle.load(file)
print("Model został wczytany z pliku:", file_path)

test_df = pd.read_csv("datasets/docker_test_dataset.csv")

Y_test = test_df[['playlist_genre']]
X_test = test_df.drop(columns='playlist_genre')
Y_test = np.ravel(Y_test)

scaler = StandardScaler()
numeric_columns = X_test.select_dtypes(include=['int', 'float']).columns
X_test_scaled = scaler.fit_transform(X_test[numeric_columns])

Y_pred = model.predict(X_test_scaled)

with open('model_predictions.txt', 'w') as f:
    pass

with open('model_predictions.txt', 'a') as f:
    labels_dict = {0: 'edm', 1 : 'latin', 2 : 'pop',  3 : 'r&b', 4 : 'rap', 5 :'rock'}
    Y_test_labels = [labels_dict[number] for number in Y_test]
    Y_pred_labels = [labels_dict[number] for number in Y_pred]
    f.write("Real:" + str(Y_test_labels[:20])+ " \nPredicted: "+ str(Y_pred_labels[:20]))
    accuracy = accuracy_score(Y_test, Y_pred)
    f.write("\nAccuracy:" + str(accuracy))