from Prediction import Prediction
import numpy as np
import pandas as pd
import random
from sklearn.metrics import mean_squared_error
from sklearn.metrics import mean_absolute_error
from sklearn.metrics import median_absolute_error
from math import sqrt

#Prediction of complexity level (the number of levels is variable)
#Each row is a complexity level, each pair [,] is the note and the time for a question (test with 3 levels)

dataI=pd.read_csv('dataInitial.csv', sep=' ', header=0)
data=pd.read_csv('data.csv', sep=' ', header=0)
v1=[]
v2=[]
n=0
#for name,dr in dataI.iterrows():
for i in range(1):

    #initialization of Beta distribution for all the complexity levels (test with 5 levels)
    betap=[[1,1],[1,2],[1,3],[1,4],[1,5]]

    #Parameters: previous grades and times, a-priori paameters for beta distribution in each complexity level, step for change beta parameters, value of penalization for time and value of limit between win and loss
    pred=Prediction(dataI.iloc[i,:], data.iloc[i,:], betap, 0.2, 1/16, 6)
    pred.CalculateGradePenalization()
    pred.Calculate()
    pred.CalculateSW()