import pickle
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score
from sacred import Experiment
from sacred.observers import FileStorageObserver, MongoObserver

ex = Experiment('464953_evaluation')

ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@tzietkiewicz.vm.wmi.amu.edu.pl:27017'))
ex.observers.append(FileStorageObserver('my_experiment_logs'))

@ex.config
def config():
    model_filename = 'model.pkl'
    test_dataset_filename = 'datasets/docker_test_dataset.csv'

@ex.main
def run_evaluation(_run ,model_filename, test_dataset_filename):
    with open(model_filename, 'rb') as file:
        model = pickle.load(file)
    print("Model został wczytany z pliku:", model_filename)
    
    with _run.open_resource(test_dataset_filename) as f:
        test_df = pd.read_csv(f)
    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)
    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]
    accuracy = accuracy_score(Y_test, Y_pred)
    ex.log_scalar('accuracy', accuracy)
    with open('model_predictions.txt', 'w') as f:
        f.write("Real:" + str(Y_test_labels[:20]) + " \nPredicted: " + str(Y_pred_labels[:20]))
        f.write("\nAccuracy:" + str(accuracy))
    ex.add_artifact('model_predictions.txt')
    ex.add_resource(__file__)
    print("Accuracy:", accuracy)
    return accuracy

if __name__ == '__main__':
    ex.run_commandline()