hyp_test

import re
import math
from string import ascii_lowercase
import random
from scipy import stats

# Genera una stringa casuale di lunghezza fissata
def randomString(stringLength):
    letters = ascii_lowercase
    return ''.join(random.choice(letters) for i in range(stringLength))

# Effettua il preprocessing del testo
def preprocessing(text):
    text = text.lower()
    text = re.sub(r"['\",.;:_@#()”“’—?!&$\n]+\ *", " ", text) # conversione dei caratteri speciali in uno spazio
    text = text.replace("-", "") # conversione del carattere - in uno spazio
    text = text.replace(" ", "") # rimozione spazi
    return text

def meanLogLikelihoodRatio(string,p,q):
    length = len(string)
    value = 0
    div_p_q = stats.entropy(p, q, base=2)
    div_q_p = stats.entropy(q, p, base=2)

    for i in range(length):
        j = ascii_lowercase.index(string[i])
        a = p[j]/q[j]
        value += math.log(a,2)

    value = value / length

    x = math.fabs(value - div_p_q)
    y = math.fabs(value - (- div_q_p))

    print("x: " + str(x) + " y: " + str(y))

    if x < y:
        alpha = 2**(-length * div_q_p)
        return("Random String", value, alpha)
    elif x > y:
        beta =  2**(-length * div_p_q)
        return("English String", value, beta)
    else:
        return("I Don't Know", value, 1)

def main():
    # Distribuzione delle lettere casuali: viene presa come ipotesi nulla
    randomLettersProbs = [1 / 26 for letter in ascii_lowercase]

    # Frequenza delle lettere lingua inglese: viene presa come ipotesi alternativa
    englishLettersProbs = [0.08167, 0.01492, 0.02782, 0.04253, 0.12702,
                           0.02228, 0.02015, 0.06094, 0.06966, 0.00153,
                           0.00772, 0.04025, 0.02406, 0.06749, 0.07507,
                           0.01929, 0.00095, 0.05987, 0.06327, 0.09056,
                           0.02758, 0.00978, 0.02360, 0.00150, 0.01974,
                           0.00074]

    # generazione di stringhe random
    randomStrings = []
    stringLength = 25
    randomStringNumber = 50
    for i in range(randomStringNumber):
        string = randomString(stringLength)
        randomStrings.append(string)

    # lettura delle stringhe in lingua inglese
    f = open("text.txt", 'r')
    englishText = f.read()
    englishText = preprocessing(englishText)

    englishStrings = []
    while englishText != "":
        englishStrings.append(englishText[0:stringLength])
        englishText = englishText[stringLength:]

    print("We'll now test the random strings")
    randomErrorCounter = 0
    for string in randomStrings:
        result, value, errorProb = meanLogLikelihoodRatio(string, randomLettersProbs, englishLettersProbs)
        print(result, value, errorProb)
        if result != "Random String":
            randomErrorCounter += 1

    print(randomErrorCounter)

    print("We'll now test the english strings")
    englishErrorCounter = 0
    for string in englishStrings:
        result, value, error_prob = meanLogLikelihoodRatio(string, randomLettersProbs, englishLettersProbs)
        print(string)
        print(result, value, error_prob)
        if result != "English String":
            englishErrorCounter += 1

    print(englishErrorCounter)

if __name__ == '__main__':
    main()