'''
Zadanie na dzień 09.05.2021 nie jest możliwe do skończenia bez dostępu do Jenkinsa!
'''




from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras.layers import Dense
from sklearn.metrics import accuracy_score, classification_report
import pandas as pd
from sklearn.model_selection import train_test_split
import wget
import numpy as np
from sacred.observers import MongoObserver
from sacred import Experiment
from datetime import datetime
import os

ex = Experiment("sacred_scopes", interactive=True)
ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@localhost:27017',
                                  db_name='sacred'))  # Tutaj podajemy dane uwierzytelniające i nazwę bazy skonfigurowane w pliku .env podczas uruchamiania bazy.
# W przypadku instancji na Jenkinsie url będzie wyglądał następująco: mongodb://mongo_user:mongo_password_IUM_2021@localhost:27017

@ex.config
def my_config():
    train_size_param = 0.8
    test_size_param = 0.2

@ex.capture
def prepare_model(train_size_param, test_size_param, _run):
    _run.info["prepare_model_ts"] = str(datetime.now())

    url = 'https://git.wmi.amu.edu.pl/s434788/ium_434788/raw/branch/master/winequality-red.csv'
    wget.download(url, out='Zajęcia7/winequality-red.csv', bar=None)

    wine=pd.read_csv('Zajęcia7/winequality-red.csv')
    wine

    y = wine.quality
    y.head()

    x = wine.drop(['quality'], axis= 1)
    x.head()

    x=((x-x.min())/(x.max()-x.min())) #Normalizacja

    x_train, x_test, y_train, y_test = train_test_split(x,y , test_size=test_size_param, train_size=train_size_param, random_state=21)

    def regression_model():
        model = Sequential()
        model.add(Dense(32,activation = "relu", input_shape = (x_train.shape[1],)))
        model.add(Dense(64,activation = "relu"))
        model.add(Dense(1,activation = "relu"))
        
        model.compile(optimizer = "adam", loss = "mean_squared_error")
        return model

    model = regression_model()
    model.fit(x_train, y_train, epochs = 600, verbose = 1)

    model.save('Zajęcia7/saved_model')

    y_pred = model.predict(x_test)

    y_pred[:5]

    y_pred = np.around(y_pred, decimals=0)

    y_pred[:5]

    print(accuracy_score(y_test, y_pred))

    _run.info["Final Results: "] = classification_report(y_test,y_pred)

    return(classification_report(y_test,y_pred))

@ex.main
def my_main(train_size_param, test_size_param):
    print(prepare_model()) ## Nie musimy przekazywać wartości


r = ex.run()
ex.add_artifact("Zajęcia7/saved_model/saved_model.pb")