#! /usr/bin/python3
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
import requests
from sacred.observers import FileStorageObserver
from sacred import Experiment
from datetime import datetime
import os
from sacred.observers import MongoObserver

ex = Experiment("ium_s434695", interactive=False)

ex.observers.append(MongoObserver(url='mongodb://mongo_user:mongo_password_IUM_2021@172.17.0.1:27017',
                                  db_name='sacred'))

@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/s434695/ium_434695/raw/commit/2301fb86e434734376f73503307a8f3255a75cc6/vgsales.csv'
    r = requests.get(url, allow_redirects=True)

    open('vgsales.csv', 'wb').write(r.content)
    df = pd.read_csv('vgsales.csv')



    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

    df['Nintendo'] = df['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
    df = df.drop(['Rank','Name','Platform','Year','Genre','Publisher'],axis = 1)
    df

    y = df.Nintendo

    df=((df-df.min())/(df.max()-df.min()))

    x = df.drop(['Nintendo'],axis = 1)

    x_train, x_test, y_train, y_test = train_test_split(x,y , test_size=0.2,train_size=0.8, random_state=21)

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

    y_pred = model.predict(x_test)

    y_pred[:5]

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

    y_pred[:5]

    return(classification_report(y_test,y_pred))

@ex.main
def my_main(train_size_param, test_size_param):
    print(prepare_model())


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